librarian-bots/model_cards_with_metadata · Datasets at Hugging Face

modelId stringlengths 5 139	author stringlengths 2 42	last_modified timestamp[us, tz=UTC]date 2020-02-15 11:33:14 2025-07-15 06:27:42	downloads int64 0 223M	likes int64 0 11.7k	library_name stringclasses 521 values	tags listlengths 1 4.05k	pipeline_tag stringclasses 55 values	createdAt timestamp[us, tz=UTC]date 2022-03-02 23:29:04 2025-07-15 06:27:26	card stringlengths 11 1.01M
Ashish9947/Programming_Question_Answer	Ashish9947	2023-07-12T11:03:37Z	0	0	peft	[ "peft", "region:us" ]	null	2023-07-11T13:43:02Z	--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.4.0.dev0
AyoubChLin/BERT-Large_BBC_news	AyoubChLin	2023-07-12T11:02:11Z	112	3	transformers	[ "transformers", "pytorch", "safetensors", "bert", "text-classification", "autotrain", "en", "dataset:AyoubChLin/autotrain-data-bert_bbc_news", "dataset:SetFit/bbc-news", "license:apache-2.0", "co2_eq_emissions", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2023-04-12T18:20:07Z	--- tags: - autotrain - text-classification language: - en widget: - text: I love AutoTrain 🤗 datasets: - AyoubChLin/autotrain-data-bert_bbc_news - SetFit/bbc-news co2_eq_emissions: emissions: 2.010596202760941 license: apache-2.0 metrics: - accuracy pipeline_tag: text-classification --- # Model Trained Using AutoTrain - Problem type: Multi-class Classification - Model ID: 48925118418 - CO2 Emissions (in grams): 2.0106 ## Validation Metrics - Loss: 0.126 - Accuracy: 0.979 - Macro F1: 0.979 - Micro F1: 0.979 - Weighted F1: 0.979 - Macro Precision: 0.979 - Micro Precision: 0.979 - Weighted Precision: 0.979 - Macro Recall: 0.979 - Micro Recall: 0.979 - Weighted Recall: 0.979 ## Usage You can use cURL to access this model: ``` $ curl -X POST -H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoTrain"}' https://api-inference.huggingface.co/models/AyoubChLin/autotrain-bert_bbc_news-48925118418 ``` Or Python API: ``` from transformers import AutoModelForSequenceClassification, AutoTokenizer model = AutoModelForSequenceClassification.from_pretrained("AyoubChLin/autotrain-bert_bbc_news-48925118418", use_auth_token=True) tokenizer = AutoTokenizer.from_pretrained("AyoubChLin/autotrain-bert_bbc_news-48925118418", use_auth_token=True) inputs = tokenizer("I love AutoTrain", return_tensors="pt") outputs = model(**inputs) ```
ayushtues/cifar10-32	ayushtues	2023-07-12T11:01:58Z	3	0	diffusers	[ "diffusers", "tensorboard", "consistency models", "base_model:google/ddpm-cifar10-32", "base_model:finetune:google/ddpm-cifar10-32", "license:creativeml-openrail-m", "diffusers:ConsistencyModelPipeline", "region:us" ]	null	2023-06-05T12:30:38Z	--- license: creativeml-openrail-m base_model: google/ddpm-cifar10-32 tags: - consistency models - diffusers inference: true --- # Consistency Model - ayushtues/cifar10-32 This is a consistency model distilled from google/ddpm-cifar10-32. You can find some example images in the following. ![img_0](./image_0.png) ![img_1](./image_1.png) ![img_2](./image_2.png) ![img_3](./image_3.png) ![img_4](./image_4.png) ![img_5](./image_5.png) ![img_6](./image_6.png) ![img_7](./image_7.png) ![img_8](./image_8.png) ![img_9](./image_9.png) ![img_10](./image_10.png) ![img_11](./image_11.png) ![img_12](./image_12.png) ![img_13](./image_13.png) ![img_14](./image_14.png) ![img_15](./image_15.png)
MeenalP/falcon-7b-instruct-ft-adapters	MeenalP	2023-07-12T10:49:32Z	0	0	peft	[ "peft", "region:us" ]	null	2023-07-10T07:28:08Z	--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.4.0.dev0 - PEFT 0.4.0.dev0 - PEFT 0.4.0.dev0 - PEFT 0.4.0.dev0 - PEFT 0.4.0.dev0 - PEFT 0.4.0.dev0 - PEFT 0.4.0.dev0 - PEFT 0.4.0.dev0
anuragverma77/falcon-7b-ecommerce-FAQ	anuragverma77	2023-07-12T10:08:49Z	0	0	peft	[ "peft", "region:us" ]	null	2023-07-11T14:54:26Z	--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.4.0.dev0
YanJiangJerry/covid-augment-tweet-bert-large-e4	YanJiangJerry	2023-07-12T10:04:17Z	108	0	transformers	[ "transformers", "pytorch", "bert", "text-classification", "generated_from_trainer", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2023-07-12T08:24:28Z	--- license: mit tags: - generated_from_trainer metrics: - accuracy - f1 - precision - recall model-index: - name: covid-augment-tweet-bert-large-e4 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # covid-augment-tweet-bert-large-e4 This model is a fine-tuned version of [digitalepidemiologylab/covid-twitter-bert-v2](https://huggingface.co/digitalepidemiologylab/covid-twitter-bert-v2) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.3723 - Accuracy: 0.9587 - F1: 0.8889 - Precision: 0.8920 - Recall: 0.8858 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 4 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| F1 \| Precision \| Recall \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:------:\|:---------:\|:------:\| \| 0.1307 \| 1.0 \| 4089 \| 0.3055 \| 0.9523 \| 0.8771 \| 0.8435 \| 0.9135 \| \| 0.0367 \| 2.0 \| 8178 \| 0.3270 \| 0.9568 \| 0.8885 \| 0.8558 \| 0.9239 \| \| 0.0133 \| 3.0 \| 12267 \| 0.3316 \| 0.9600 \| 0.8949 \| 0.8771 \| 0.9135 \| \| 0.0007 \| 4.0 \| 16356 \| 0.3723 \| 0.9587 \| 0.8889 \| 0.8920 \| 0.8858 \| ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
namvuong96/civit_meinamix_meinaV10	namvuong96	2023-07-12T10:02:08Z	29	0	diffusers	[ "diffusers", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]	text-to-image	2023-07-12T09:32:27Z	Link: `https://civitai.com/api/download/models/80511`
matorus/replit-coder	matorus	2023-07-12T09:59:57Z	7	0	transformers	[ "transformers", "pytorch", "mpt", "text-generation", "custom_code", "dataset:matorus/coder", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-07-09T20:34:49Z	--- datasets: - matorus/coder --- [replit/replit-code-v1-3b](https://huggingface.co/replit/replit-code-v1-3b) finetuned on [matorus/coder](https://huggingface.co/datasets/matorus/coder). HumanEval scores: pass@1: 28.7%, pass@10: 43.3% <br> See [torusresearch/code-eval](https://github.com/torusresearch/code-eval) for evaluation code. Finetuning format: ``` {function_defintion} """ {task} """ {function_body} ```
LZYSaltedFish/chatfish-1b1-sft	LZYSaltedFish	2023-07-12T09:42:31Z	180	0	transformers	[ "transformers", "pytorch", "bloom", "text-generation", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-05-23T08:12:22Z	# ChatFish ChatFish是基于[BLOOM](https://huggingface.co/bigscience/bloom-1b1)（11亿参数）训练的中文对话语言模型，此模型为SFT版本。详见[Github](https://github.com/LZYSaltedFish/ChatFish-Chatbot)。 ChatFish is a Chinese dialogue language model trained based on [BLOOM](https://huggingface.co/bigscience/bloom-1b1) (1.1 billion parameters). This model is the SFT version. See [Github](https://github.com/LZYSaltedFish/ChatFish-Chatbot) for details. ## Usage ```python import torch from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained('LZYSaltedFish/chatfish-1b1-sft') tokenizer.pad_token_id = tokenizer.eos_token_id model = AutoModelForCausalLM.from_pretrained('LZYSaltedFish/chatfish-1b1-sft').half() inputs = tokenizer('# Human:\nHello\n\n# Assistant:\n', return_tensors='pt').to(torch.cuda.current_device()) model.to(torch.cuda.current_device()) output = model.generate(**inputs, max_length=1024, do_sample=True, temperature=0.7, top_k=50, early_stopping=True, repetition_penalty=1.0) output = tokenizer.decode(output[0], skip_special_tokens=True) print(output) ``` ## Cases 尽管这个模型只有1.1B参数，但也显示出同样不错的能力。以下是一些例子: Although this model has only 1.1B parameters, but also shows the same not bad ability. Here are some cases: <details><summary><b>Writing</b></summary> ```xml # Human: 因为工作钱少事多，我打算跟领导提出辞职，请你帮我写一份正式的辞呈 # Assistant: 尊敬的领导，首先感谢您给予我的机会，让我可以在您的团队中发挥自己的能力。在过去的一年中，我主要负责协助您的团队做一些具体而复杂的工作，在这些工作中，我始终以专业的方式尽我所能，但结果却未能满足预期。对于我的表现，您可能会问：为什么？因为工作钱少事多，对比起其他同事的丰厚的薪酬，我的薪酬确实比较底。虽然我也努力工作，但工作量太多，加上事情太多，所以我的薪酬也难以达到理想水平。综上所述，我认为自己无法在您的工作中发挥出自己的能力，因此辞任团队成员职位，返回自己的职业生涯独立发展。谢谢您理解，敬礼， X ``` </details> <details><summary><b>Common Sense</b></summary> ```xml # Human: 我们有探索太空的道德义务吗，还是我们应该专注于首先解决地球的问题? # Assistant: 在当前，我们拥有探索太空的道德义务，我们必须保护地球，因为太空是向地球输出的重要水源，地球的水资源是人类未来可持续发展的重要基础。此外，我们也可以专注于解决地球上的问题，比如改善环境、减缓气候变化和减少犯罪等。 ``` </details> <details><summary><b>Chatting</b></summary> ```xml # Human: 我感觉最近都好低迷啊 # Assistant: 我理解你的心情，有时候低谷会让我们感到疲惫甚至失去希望，但请记住，每个人都有自己独特的故事和经历，这些故事和经历可能随时都可能发生。你可以从中吸取宝贵的经验，寻找自己的方向，并继续前行。请记住，每个人都有自己的能力，可以从中学习新知识，建立新的联系，也可以探索你自己的潜能，只要不放弃，任何事情都是可能的。 # Human: 有什么具体的办法能帮助我改善这种感觉吗 # Assistant: 你可以尝试以下几种方法： 1. 制定计划：给自己定一个目标，制定一个可行的计划，每天坚持完成，可以帮助你保持积极的心态和前进的动力。 2. 重新定义自己的方向：在低谷中，重新审视自己的方向，发现新的潜能，可以给你带来更多的力量。 3. 寻求帮助：如果你感到疲惫，没有动力，可以尝试寻求帮助，可以找到一些自己可以完成的任务，或者可以理解的理解。 4. 给自己时间：给自己一些时间，让自己放松，可以给自己一些休息时间，让自己得到休息。 5. 找到支持：与朋友、家人沟通，可以倾听他们的建议和鼓励的话语，获得他们的安慰和支持，可以让自己更有信心和勇气去面对困难。 # Human: 我喜欢打球，打球可以吗 # Assistant: 当然可以！打球不仅可以提高身体素质，而且可以锻炼心肺能力，增强肌肉力量，增强协调性和平衡感，同时也能够提升自我安全感和抗压能力。当然，如果想成为专业运动员，需要坚持训练，克服各种困难，提高技术水平和团队合作精神，这也是可以的。希望我的建议能帮到您。 ``` </details> <details><summary><b>Role Playing</b></summary> ```xml # Human: 你是一名登山者，即将登顶珠穆朗玛峰。描述你的情绪和从上到下的观点。 # Assistant: 当我看到珠穆朗玛峰高耸入云，阳光从它的基础照射使我感到温暖而温暖。我会从基础向上看到它爬升到天际，我会感受到无限的兴奋和激励，因为我是一名登山者，我将努力登顶，完成我的梦想。我会从上到下的观点，从海拔最高的山脉看到较低的山峰，看到自然美景，看到自然风光，激发我更加努力攀登的动力。 ``` </details> ## Usage Limits 我们使用的数据集要求开发人员仅将数据用于研究目的。因此，不允许将我们的模型用于商业以及其他潜在的有害用途。 The datasets we used require developers only use the data for research purposes. Thus, commercial and other potentially harmful uses of our models are not allowed.
ksol8/virile_reality_v2	ksol8	2023-07-12T09:27:22Z	0	1	null	[ "license:creativeml-openrail-m", "region:us" ]	null	2023-07-12T07:13:04Z	--- license: creativeml-openrail-m ---
Relex169/ppo-LunarLander-v2	Relex169	2023-07-12T09:26:27Z	0	0	stable-baselines3	[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2023-07-12T09:24:05Z	--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 250.70 +/- 22.25 name: mean_reward verified: false --- # PPO Agent playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
lgrobol/BERTrade-FlauBERT	lgrobol	2023-07-12T09:23:13Z	106	0	transformers	[ "transformers", "pytorch", "safetensors", "flaubert", "fill-mask", "fro", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	2023-03-10T16:43:56Z	--- license: mit language: - fro pipeline_tag: fill-mask library_name: transformers --- BERTrade-FlauBERT ================= This contextual embeddings model for Old French was developped as part of the work of Grobol, Regnault, Ortiz-Suarez et al. ([2022](https://aclanthology.org/2022.lrec-1.119/)), we refer to it for a list of the resources and the settings used to develop this model as well as assessment of their suitability for syntactic dependency parsing of Old French. If you use it, please cite the original paper: ```bibtex @inproceedings{grobol-etal-2022-bertrade, title = "{BERT}rade: Using Contextual Embeddings to Parse {O}ld {F}rench", author = {Grobol, Lo{\"\i}c and Regnault, Mathilde and Ortiz Suarez, Pedro and Sagot, Beno{\^\i}t and Romary, Laurent and Crabb{\'e}, Benoit}, booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference", month = jun, year = "2022", address = "Marseille, France", publisher = "European Language Resources Association", url = "https://aclanthology.org/2022.lrec-1.119", pages = "1104--1113", abstract = "The successes of contextual word embeddings learned by training large-scale language models, while remarkable, have mostly occurred for languages where significant amounts of raw texts are available and where annotated data in downstream tasks have a relatively regular spelling. Conversely, it is not yet completely clear if these models are also well suited for lesser-resourced and more irregular languages. We study the case of Old French, which is in the interesting position of having relatively limited amount of available raw text, but enough annotated resources to assess the relevance of contextual word embedding models for downstream NLP tasks. In particular, we use POS-tagging and dependency parsing to evaluate the quality of such models in a large array of configurations, including models trained from scratch from small amounts of raw text and models pre-trained on other languages but fine-tuned on Medieval French data.", } ```
Suryadia/LoRaWhisper2	Suryadia	2023-07-12T09:10:57Z	0	1	peft	[ "peft", "tensorboard", "region:us" ]	null	2023-07-12T03:11:05Z	--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 The following `bitsandbytes` quantization config was used during training: - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 ### Framework versions - PEFT 0.4.0.dev0 - PEFT 0.4.0.dev0
hyllius/ReinforceCartPole	hyllius	2023-07-12T09:02:23Z	0	0	null	[ "CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]	reinforcement-learning	2023-07-12T09:02:16Z	--- tags: - CartPole-v1 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: ReinforceCartPole results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: CartPole-v1 type: CartPole-v1 metrics: - type: mean_reward value: 500.00 +/- 0.00 name: mean_reward verified: false --- # Reinforce Agent playing CartPole-v1 This is a trained model of a Reinforce agent playing CartPole-v1 . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
Aeala/Enterredaas-65b-GGML	Aeala	2023-07-12T08:52:08Z	0	3	null	[ "region:us" ]	null	2023-07-04T02:42:06Z	GGML quantizations of [Enterredaas-65b](https://huggingface.co/Aeala/Enterredaas-65b-QLoRA) Important Note: This was trained in the Alpaca format, so prompting should be something like: ``` ### Instruction: <system prompt> (without the <>, this works like telling the AI what it is/purpose. i.e. like ChatGPT API's system prompt) ### Input: <prompt> (without the <>) ### Response: ```
markjosims/wav2vec2-large-xls-r-300m-tira-colab	markjosims	2023-07-12T08:46:07Z	12	0	transformers	[ "transformers", "pytorch", "tensorboard", "wav2vec2", "automatic-speech-recognition", "generated_from_trainer", "license:apache-2.0", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	2023-07-11T22:37:49Z	--- license: apache-2.0 tags: - generated_from_trainer metrics: - wer model-index: - name: wav2vec2-large-xls-r-300m-tira-colab results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # wav2vec2-large-xls-r-300m-tira-colab This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.2681 - Wer: 0.2787 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0003 - train_batch_size: 16 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - num_epochs: 30 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Wer \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:------:\| \| 4.2937 \| 1.45 \| 400 \| 1.0460 \| 0.9297 \| \| 0.9157 \| 2.9 \| 800 \| 0.5732 \| 0.6728 \| \| 0.6258 \| 4.35 \| 1200 \| 0.4319 \| 0.5434 \| \| 0.5114 \| 5.8 \| 1600 \| 0.3822 \| 0.5465 \| \| 0.4059 \| 7.25 \| 2000 \| 0.3439 \| 0.4700 \| \| 0.3407 \| 8.7 \| 2400 \| 0.2997 \| 0.4778 \| \| 0.2938 \| 10.14 \| 2800 \| 0.2956 \| 0.4121 \| \| 0.2465 \| 11.59 \| 3200 \| 0.2834 \| 0.3537 \| \| 0.2148 \| 13.04 \| 3600 \| 0.2662 \| 0.3779 \| \| 0.1711 \| 14.49 \| 4000 \| 0.2724 \| 0.3160 \| \| 0.1621 \| 15.94 \| 4400 \| 0.2452 \| 0.3571 \| \| 0.1301 \| 17.39 \| 4800 \| 0.2638 \| 0.2927 \| \| 0.1119 \| 18.84 \| 5200 \| 0.2724 \| 0.2765 \| \| 0.1026 \| 20.29 \| 5600 \| 0.2703 \| 0.2986 \| \| 0.0906 \| 21.74 \| 6000 \| 0.2642 \| 0.2638 \| \| 0.0785 \| 23.19 \| 6400 \| 0.2653 \| 0.2709 \| \| 0.0648 \| 24.64 \| 6800 \| 0.2644 \| 0.2669 \| \| 0.0578 \| 26.09 \| 7200 \| 0.2712 \| 0.3123 \| \| 0.0514 \| 27.54 \| 7600 \| 0.2703 \| 0.2672 \| \| 0.0459 \| 28.99 \| 8000 \| 0.2681 \| 0.2787 \| ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
kazzand/ru-longformer-large-4096	kazzand	2023-07-12T08:45:32Z	829	0	transformers	[ "transformers", "pytorch", "longformer", "fill-mask", "ru", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	2023-07-11T02:17:22Z	--- language: - ru --- This is a large Longformer model designed for Russian language. It was initialized from [ai-forever/ruRoberta-large](https://huggingface.co/ai-forever/ruRoberta-large) weights and has been modified to support a context length of up to 4096 tokens. We fine-tuned it on a dataset of Russian books. For a detailed information check out our post on Habr. Model attributes: * 16 attention heads * 24 hidden layers * 4096 tokens length of context The model can be used as-is to produce text embeddings or it can be further fine-tuned for a specific downstream task. Text embeddings can be produced as follows: ```python # pip install transformers sentencepiece import torch from transformers import LongformerForMaskedLM, LongformerTokenizerFast model = LongformerModel.from_pretrained('kazzand/ru-longformer-large-4096') tokenizer = LongformerTokenizerFast.from_pretrained('kazzand/ru-longformer-large-4096') def get_cls_embedding(text, model, tokenizer, device='cuda'): model.to(device) batch = tokenizer(text, return_tensors='pt') #set global attention for cls token global_attention_mask = [ [1 if token_id == tokenizer.cls_token_id else 0 for token_id in input_ids] for input_ids in batch["input_ids"] ] #add global attention mask to batch batch["global_attention_mask"] = torch.tensor(global_attention_mask) with torch.no_grad(): output = model(**batch.to(device)) return output.last_hidden_state[:,0,:] ```
shape-ai/inpainting	shape-ai	2023-07-12T08:43:27Z	74	0	diffusers	[ "diffusers", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "arxiv:2207.12598", "arxiv:2112.10752", "arxiv:2103.00020", "arxiv:2205.11487", "arxiv:1910.09700", "license:creativeml-openrail-m", "endpoints_compatible", "diffusers:StableDiffusionInpaintPipeline", "region:us" ]	text-to-image	2023-07-11T05:25:30Z	--- license: creativeml-openrail-m tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image inference: false library_name: diffusers extra_gated_prompt: >- One more step before getting this model. This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage. The CreativeML OpenRAIL License specifies: 1. You can't use the model to deliberately produce nor share illegal or harmful outputs or content 2. CompVis claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license 3. You may re-distribute the weights and use the model commercially and/or as a service. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully) Please read the full license here: https://huggingface.co/spaces/CompVis/stable-diffusion-license By clicking on "Access repository" below, you accept that your contact information (email address and username) can be shared with the model authors as well. extra_gated_fields: I have read the License and agree with its terms: checkbox duplicated_from: runwayml/stable-diffusion-inpainting --- Stable Diffusion Inpainting is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input, with the extra capability of inpainting the pictures by using a mask. The Stable-Diffusion-Inpainting was initialized with the weights of the [Stable-Diffusion-v-1-2](https://steps/huggingface.co/CompVis/stable-diffusion-v-1-2-original). First 595k steps regular training, then 440k steps of inpainting training at resolution 512x512 on “laion-aesthetics v2 5+” and 10% dropping of the text-conditioning to improve classifier-free [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598). For inpainting, the UNet has 5 additional input channels (4 for the encoded masked-image and 1 for the mask itself) whose weights were zero-initialized after restoring the non-inpainting checkpoint. During training, we generate synthetic masks and in 25% mask everything. [![Open In Spaces](https://camo.githubusercontent.com/00380c35e60d6b04be65d3d94a58332be5cc93779f630bcdfc18ab9a3a7d3388/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f25463025394625413425393725323048756767696e67253230466163652d5370616365732d626c7565)](https://huggingface.co/spaces/runwayml/stable-diffusion-inpainting) \| [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/in_painting_with_stable_diffusion_using_diffusers.ipynb) :-------------------------:\|:-------------------------:\| ## Examples: You can use this both with the [🧨Diffusers library](https://github.com/huggingface/diffusers) and the [RunwayML GitHub repository](https://github.com/runwayml/stable-diffusion). ### Diffusers ```python from diffusers import StableDiffusionInpaintPipeline pipe = StableDiffusionInpaintPipeline.from_pretrained( "runwayml/stable-diffusion-inpainting", revision="fp16", torch_dtype=torch.float16, ) prompt = "Face of a yellow cat, high resolution, sitting on a park bench" #image and mask_image should be PIL images. #The mask structure is white for inpainting and black for keeping as is image = pipe(prompt=prompt, image=image, mask_image=mask_image).images[0] image.save("./yellow_cat_on_park_bench.png") ``` How it works: `image` \| `mask_image` :-------------------------:\|:-------------------------:\| <img src="https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png" alt="drawing" width="300"/> \| <img src="https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png" alt="drawing" width="300"/> `prompt` \| `Output` :-------------------------:\|:-------------------------:\| <span style="position: relative;bottom: 150px;">Face of a yellow cat, high resolution, sitting on a park bench</span> \| <img src="https://huggingface.co/datasets/patrickvonplaten/images/resolve/main/test.png" alt="drawing" width="300"/> ### Original GitHub Repository 1. Download the weights [sd-v1-5-inpainting.ckpt](https://huggingface.co/runwayml/stable-diffusion-inpainting/resolve/main/sd-v1-5-inpainting.ckpt) 2. Follow instructions [here](https://github.com/runwayml/stable-diffusion#inpainting-with-stable-diffusion). ## Model Details - Developed by: Robin Rombach, Patrick Esser - Model type: Diffusion-based text-to-image generation model - Language(s): English - License: [The CreativeML OpenRAIL M license](https://huggingface.co/spaces/CompVis/stable-diffusion-license) is an [Open RAIL M license](https://www.licenses.ai/blog/2022/8/18/naming-convention-of-responsible-ai-licenses), adapted from the work that [BigScience](https://bigscience.huggingface.co/) and [the RAIL Initiative](https://www.licenses.ai/) are jointly carrying in the area of responsible AI licensing. See also [the article about the BLOOM Open RAIL license](https://bigscience.huggingface.co/blog/the-bigscience-rail-license) on which our license is based. - Model Description: This is a model that can be used to generate and modify images based on text prompts. It is a [Latent Diffusion Model](https://arxiv.org/abs/2112.10752) that uses a fixed, pretrained text encoder ([CLIP ViT-L/14](https://arxiv.org/abs/2103.00020)) as suggested in the [Imagen paper](https://arxiv.org/abs/2205.11487). - Resources for more information: [GitHub Repository](https://github.com/runwayml/stable-diffusion), [Paper](https://arxiv.org/abs/2112.10752). - Cite as: @InProceedings{Rombach_2022_CVPR, author = {Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj\"orn}, title = {High-Resolution Image Synthesis With Latent Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {10684-10695} } # Uses ## Direct Use The model is intended for research purposes only. Possible research areas and tasks include - Safe deployment of models which have the potential to generate harmful content. - Probing and understanding the limitations and biases of generative models. - Generation of artworks and use in design and other artistic processes. - Applications in educational or creative tools. - Research on generative models. Excluded uses are described below. ### Misuse, Malicious Use, and Out-of-Scope Use _Note: This section is taken from the [DALLE-MINI model card](https://huggingface.co/dalle-mini/dalle-mini), but applies in the same way to Stable Diffusion v1_. The model should not be used to intentionally create or disseminate images that create hostile or alienating environments for people. This includes generating images that people would foreseeably find disturbing, distressing, or offensive; or content that propagates historical or current stereotypes. #### Out-of-Scope Use The model was not trained to be factual or true representations of people or events, and therefore using the model to generate such content is out-of-scope for the abilities of this model. #### Misuse and Malicious Use Using the model to generate content that is cruel to individuals is a misuse of this model. This includes, but is not limited to: - Generating demeaning, dehumanizing, or otherwise harmful representations of people or their environments, cultures, religions, etc. - Intentionally promoting or propagating discriminatory content or harmful stereotypes. - Impersonating individuals without their consent. - Sexual content without consent of the people who might see it. - Mis- and disinformation - Representations of egregious violence and gore - Sharing of copyrighted or licensed material in violation of its terms of use. - Sharing content that is an alteration of copyrighted or licensed material in violation of its terms of use. ## Limitations and Bias ### Limitations - The model does not achieve perfect photorealism - The model cannot render legible text - The model does not perform well on more difficult tasks which involve compositionality, such as rendering an image corresponding to “A red cube on top of a blue sphere” - Faces and people in general may not be generated properly. - The model was trained mainly with English captions and will not work as well in other languages. - The autoencoding part of the model is lossy - The model was trained on a large-scale dataset [LAION-5B](https://laion.ai/blog/laion-5b/) which contains adult material and is not fit for product use without additional safety mechanisms and considerations. - No additional measures were used to deduplicate the dataset. As a result, we observe some degree of memorization for images that are duplicated in the training data. The training data can be searched at [https://rom1504.github.io/clip-retrieval/](https://rom1504.github.io/clip-retrieval/) to possibly assist in the detection of memorized images. ### Bias While the capabilities of image generation models are impressive, they can also reinforce or exacerbate social biases. Stable Diffusion v1 was trained on subsets of [LAION-2B(en)](https://laion.ai/blog/laion-5b/), which consists of images that are primarily limited to English descriptions. Texts and images from communities and cultures that use other languages are likely to be insufficiently accounted for. This affects the overall output of the model, as white and western cultures are often set as the default. Further, the ability of the model to generate content with non-English prompts is significantly worse than with English-language prompts. ## Training Training Data The model developers used the following dataset for training the model: - LAION-2B (en) and subsets thereof (see next section) Training Procedure Stable Diffusion v1 is a latent diffusion model which combines an autoencoder with a diffusion model that is trained in the latent space of the autoencoder. During training, - Images are encoded through an encoder, which turns images into latent representations. The autoencoder uses a relative downsampling factor of 8 and maps images of shape H x W x 3 to latents of shape H/f x W/f x 4 - Text prompts are encoded through a ViT-L/14 text-encoder. - The non-pooled output of the text encoder is fed into the UNet backbone of the latent diffusion model via cross-attention. - The loss is a reconstruction objective between the noise that was added to the latent and the prediction made by the UNet. We currently provide six checkpoints, `sd-v1-1.ckpt`, `sd-v1-2.ckpt` and `sd-v1-3.ckpt`, `sd-v1-4.ckpt`, `sd-v1-5.ckpt` and `sd-v1-5-inpainting.ckpt` which were trained as follows, - `sd-v1-1.ckpt`: 237k steps at resolution `256x256` on [laion2B-en](https://huggingface.co/datasets/laion/laion2B-en). 194k steps at resolution `512x512` on [laion-high-resolution](https://huggingface.co/datasets/laion/laion-high-resolution) (170M examples from LAION-5B with resolution `>= 1024x1024`). - `sd-v1-2.ckpt`: Resumed from `sd-v1-1.ckpt`. 515k steps at resolution `512x512` on "laion-improved-aesthetics" (a subset of laion2B-en, filtered to images with an original size `>= 512x512`, estimated aesthetics score `> 5.0`, and an estimated watermark probability `< 0.5`. The watermark estimate is from the LAION-5B metadata, the aesthetics score is estimated using an [improved aesthetics estimator](https://github.com/christophschuhmann/improved-aesthetic-predictor)). - `sd-v1-3.ckpt`: Resumed from `sd-v1-2.ckpt`. 195k steps at resolution `512x512` on "laion-improved-aesthetics" and 10\% dropping of the text-conditioning to improve [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598). - `sd-v1-4.ckpt`: Resumed from stable-diffusion-v1-2.225,000 steps at resolution 512x512 on "laion-aesthetics v2 5+" and 10 % dropping of the text-conditioning to [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598). - `sd-v1-5.ckpt`: Resumed from sd-v1-2.ckpt. 595k steps at resolution 512x512 on "laion-aesthetics v2 5+" and 10% dropping of the text-conditioning to improve classifier-free guidance sampling. - `sd-v1-5-inpaint.ckpt`: Resumed from sd-v1-2.ckpt. 595k steps at resolution 512x512 on "laion-aesthetics v2 5+" and 10% dropping of the text-conditioning to improve classifier-free guidance sampling. Then 440k steps of inpainting training at resolution 512x512 on “laion-aesthetics v2 5+” and 10% dropping of the text-conditioning. For inpainting, the UNet has 5 additional input channels (4 for the encoded masked-image and 1 for the mask itself) whose weights were zero-initialized after restoring the non-inpainting checkpoint. During training, we generate synthetic masks and in 25% mask everything. - Hardware: 32 x 8 x A100 GPUs - Optimizer: AdamW - Gradient Accumulations: 2 - Batch: 32 x 8 x 2 x 4 = 2048 - Learning rate: warmup to 0.0001 for 10,000 steps and then kept constant ## Evaluation Results Evaluations with different classifier-free guidance scales (1.5, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0) and 50 PLMS sampling steps show the relative improvements of the checkpoints: ![pareto](https://huggingface.co/CompVis/stable-diffusion/resolve/main/v1-1-to-v1-5.png) Evaluated using 50 PLMS steps and 10000 random prompts from the COCO2017 validation set, evaluated at 512x512 resolution. Not optimized for FID scores. ## Inpainting Evaluation To assess the performance of the inpainting model, we used the same evaluation protocol as in our [LDM paper](https://arxiv.org/abs/2112.10752). Since the Stable Diffusion Inpainting Model acccepts a text input, we simply used a fixed prompt of `photograph of a beautiful empty scene, highest quality settings`. \| Model \| FID \| LPIPS \| \|-----------------------------\|------\|------------------\| \| Stable Diffusion Inpainting \| 1.00 \| 0.141 (+- 0.082) \| \| Latent Diffusion Inpainting \| 1.50 \| 0.137 (+- 0.080) \| \| CoModGAN \| 1.82 \| 0.15 \| \| LaMa \| 2.21 \| 0.134 (+- 0.080) \| ## Environmental Impact Stable Diffusion v1 Estimated Emissions Based on that information, we estimate the following CO2 emissions using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). The hardware, runtime, cloud provider, and compute region were utilized to estimate the carbon impact. - Hardware Type: A100 PCIe 40GB - Hours used: 150000 - Cloud Provider: AWS - Compute Region: US-east - Carbon Emitted (Power consumption x Time x Carbon produced based on location of power grid): 11250 kg CO2 eq. ## Citation ```bibtex @InProceedings{Rombach_2022_CVPR, author = {Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj\"orn}, title = {High-Resolution Image Synthesis With Latent Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {10684-10695} } ``` This model card was written by: Robin Rombach and Patrick Esser and is based on the [DALL-E Mini model card](https://huggingface.co/dalle-mini/dalle-mini).
nolanaatama/yffmx	nolanaatama	2023-07-12T08:41:59Z	0	0	null	[ "license:creativeml-openrail-m", "region:us" ]	null	2023-02-08T02:23:42Z	--- license: creativeml-openrail-m ---
kazzand/ru-longformer-base-4096	kazzand	2023-07-12T08:41:57Z	138	0	transformers	[ "transformers", "pytorch", "longformer", "fill-mask", "ru", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	2023-07-11T01:52:27Z	--- language: - ru --- This is a base Longformer model designed for Russian language. It was initialized from [blinoff/roberta-base-russian-v0](https://huggingface.co/blinoff/roberta-base-russian-v0) weights and has been modified to support a context length of up to 4096 tokens. We fine-tuned it on a dataset of Russian books. For a detailed information check out our post on Habr. Model attributes: * 12 attention heads * 12 hidden layers * 4096 tokens length of context The model can be used as-is to produce text embeddings or it can be further fine-tuned for a specific downstream task. Text embeddings can be produced as follows: ```python # pip install transformers sentencepiece import torch from transformers import LongformerForMaskedLM, LongformerTokenizerFast model = LongformerModel.from_pretrained('kazzand/ru-longformer-base-4096') tokenizer = LongformerTokenizerFast.from_pretrained('kazzand/ru-longformer-base-4096') def get_cls_embedding(text, model, tokenizer, device='cuda'): model.to(device) batch = tokenizer(text, return_tensors='pt') #set global attention for cls token global_attention_mask = [ [1 if token_id == tokenizer.cls_token_id else 0 for token_id in input_ids] for input_ids in batch["input_ids"] ] #add global attention mask to batch batch["global_attention_mask"] = torch.tensor(global_attention_mask) with torch.no_grad(): output = model(**batch.to(device)) return output.last_hidden_state[:,0,:] ```
yhavinga/byt5-small-ccmatrix-en-nl	yhavinga	2023-07-12T08:40:54Z	118	0	transformers	[ "transformers", "pytorch", "jax", "tensorboard", "safetensors", "t5", "text2text-generation", "byt5", "translation", "seq2seq", "nl", "en", "multilingual", "dataset:yhavinga/mc4_nl_cleaned", "dataset:yhavinga/ccmatrix", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	translation	2022-08-20T11:12:08Z	--- language: - nl - en - multilingual license: apache-2.0 tags: - byt5 - translation - seq2seq datasets: - yhavinga/mc4_nl_cleaned - yhavinga/ccmatrix pipeline_tag: translation widget: - text: 'It is a painful and tragic spectacle that rises before me: I have drawn back the curtain from the rottenness of man. This word, in my mouth, is at least free from one suspicion: that it involves a moral accusation against humanity.' - text: Young Wehling was hunched in his chair, his head in his hand. He was so rumpled, so still and colorless as to be virtually invisible. His camouflage was perfect, since the waiting room had a disorderly and demoralized air, too. Chairs and ashtrays had been moved away from the walls. The floor was paved with spattered dropcloths. --- Logs at https://wandb.ai/yepster/byt5-small-ccmatrix-en-nl/runs/1wm9igj9?workspace=user-yepster
Beams24/nuristl	Beams24	2023-07-12T08:26:21Z	0	0	null	[ "license:creativeml-openrail-m", "region:us" ]	null	2023-07-11T10:29:51Z	--- license: creativeml-openrail-m ---
longmark/ppo-Huggy	longmark	2023-07-12T08:19:57Z	4	0	ml-agents	[ "ml-agents", "tensorboard", "onnx", "Huggy", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Huggy", "region:us" ]	reinforcement-learning	2023-07-12T08:19:53Z	--- library_name: ml-agents tags: - Huggy - deep-reinforcement-learning - reinforcement-learning - ML-Agents-Huggy --- # ppo Agent playing Huggy This is a trained model of a ppo agent playing Huggy using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A short tutorial where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A longer tutorial to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent playing directly in your browser 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: longmark/ppo-Huggy 3. Step 2: Select your .nn /.onnx file 4. Click on Watch the agent play 👀
edwardjjj/ppo-LunarLander-v2	edwardjjj	2023-07-12T08:09:11Z	2	0	stable-baselines3	[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2023-06-18T05:37:16Z	--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 251.15 +/- 18.83 name: mean_reward verified: false --- # PPO Agent playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
Ark62/Ishowspeed	Ark62	2023-07-12T08:01:57Z	0	0	null	[ "arxiv:1910.09700", "region:us" ]	null	2023-07-12T07:52:08Z	--- # For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1 ishowspeed # Doc / guide: https://huggingface.co/docs/hub/model-cards {} --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. -->ishowspeed This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1). ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. -->ishowspeed - Developed by: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Data Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
soduhh/distilbert-base-uncased-finetuned-squad-d5716d28	soduhh	2023-07-12T07:50:51Z	105	0	transformers	[ "transformers", "pytorch", "distilbert", "fill-mask", "question-answering", "en", "dataset:squad", "arxiv:1910.01108", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	question-answering	2023-07-12T07:36:17Z	--- language: - en thumbnail: https://github.com/karanchahal/distiller/blob/master/distiller.jpg tags: - question-answering license: apache-2.0 datasets: - squad metrics: - squad --- # DistilBERT with a second step of distillation ## Model description This model replicates the "DistilBERT (D)" model from Table 2 of the [DistilBERT paper](https://arxiv.org/pdf/1910.01108.pdf). In this approach, a DistilBERT student is fine-tuned on SQuAD v1.1, but with a BERT model (also fine-tuned on SQuAD v1.1) acting as a teacher for a second step of task-specific distillation. In this version, the following pre-trained models were used: * Student: `distilbert-base-uncased` * Teacher: `lewtun/bert-base-uncased-finetuned-squad-v1` ## Training data This model was trained on the SQuAD v1.1 dataset which can be obtained from the `datasets` library as follows: ```python from datasets import load_dataset squad = load_dataset('squad') ``` ## Training procedure ## Eval results \| \| Exact Match \| F1 \| \|------------------\|-------------\|------\| \| DistilBERT paper \| 79.1 \| 86.9 \| \| Ours \| 78.4 \| 86.5 \| The scores were calculated using the `squad` metric from `datasets`. ### BibTeX entry and citation info ```bibtex @misc{sanh2020distilbert, title={DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter}, author={Victor Sanh and Lysandre Debut and Julien Chaumond and Thomas Wolf}, year={2020}, eprint={1910.01108}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```
LoupGarou/Starcoderplus-Guanaco-GPT4-15B-V1.0	LoupGarou	2023-07-12T07:45:19Z	9	1	transformers	[ "transformers", "pytorch", "gpt_bigcode", "text-generation", "en", "dataset:guanaco", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-07-12T05:54:07Z	--- language: - en datasets: - guanaco model_hub_library: - transformers license: - apache-2.0 --- ## Starcoderplus-Guanaco-GPT4-15B-V1.0 Model Card Starcoderplus-Guanaco-GPT4-15B-V1.0 is a language model that combines the strengths of the [Starcoderplus](https://huggingface.co/bigcode/starcoderplus) base model, an expansion of the orginal [openassistant-guanaco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco) dataset re-imagined using 100% GPT-4 answers, and additional data on abstract algebra and physics for finetuning. The original openassistant-guanaco dataset questions were trimmed to within 2 standard deviations of token size for input and output pairs and all non-english data was been removed to reduce training size requirements. # Model Description This model is built on top of the Starcoderplus base model, a large language model which is a fine-tuned version of [StarCoderBase](https://huggingface.co/bigcode/starcoderbase). The Starcoderplus base model was further finetuned using QLORA on the revised openassistant-guanaco dataset questions that were 100% re-imagined using GPT-4. # Intended Use This model is designed to be used for a wide array of text generation tasks that require understanding and generating English text. The model is expected to perform well in tasks such as answering questions, writing essays, summarizing text, translation, and more. However, given the specific data processing and finetuning done, it might be particularly effective for tasks related to English language question-answering systems. # Limitations Despite the powerful capabilities of this model, users should be aware of its limitations. The model's knowledge is up to date only until the time it was trained, and it doesn't know about events in the world after that. It can sometimes produce incorrect or nonsensical responses, as it doesn't understand the text in the same way humans do. It should be used as a tool to assist in generating text and not as a sole source of truth. # How to use Here is an example of how to use this model: ```python from transformers import AutoModelForCausalLM, AutoTokenizer import time import torch class Chatbot: def __init__(self, model_name): self.tokenizer = AutoTokenizer.from_pretrained(model_name, padding_side='left') self.model = AutoModelForCausalLM.from_pretrained(model_name, load_in_4bit=True, torch_dtype=torch.bfloat16) if self.tokenizer.pad_token_id is None: self.tokenizer.pad_token_id = self.tokenizer.eos_token_id def get_response(self, prompt): inputs = self.tokenizer.encode_plus(prompt, return_tensors="pt", padding='max_length', max_length=100) if next(self.model.parameters()).is_cuda: inputs = {name: tensor.to('cuda') for name, tensor in inputs.items()} start_time = time.time() tokens = self.model.generate(input_ids=inputs['input_ids'], attention_mask=inputs['attention_mask'], pad_token_id=self.tokenizer.pad_token_id, max_new_tokens=400) end_time = time.time() output_tokens = tokens[0][inputs['input_ids'].shape[-1]:] output = self.tokenizer.decode(output_tokens, skip_special_tokens=True) time_taken = end_time - start_time return output, time_taken def main(): chatbot = Chatbot("LoupGarou/Starcoderplus-Guanaco-GPT4-15B-V1.0") while True: user_input = input("Enter your prompt: ") if user_input.lower() == 'quit': break output, time_taken = chatbot.get_response(user_input) print("\033[33m" + output + "\033[0m") print("Time taken to process: ", time_taken, "seconds") print("Exited the program.") if __name__ == "__main__": main() ``` # Training Procedure The base Starcoderplus model was finetuned on the modified openassistant-guanaco dataset 100% re-imagined with GPT4 answers using QLORA. All non-English data was also removed from this finetuning dataset to reduce trainign size and time. ## Acknowledgements This model, Starcoderplus-Guanaco-GPT4-15B-V1.0, builds upon the strengths of the [Starcoderplus](https://huggingface.co/bigcode/starcoderplus) and the [openassistant-guanaco dataset](https://huggingface.co/datasets/timdettmers/openassistant-guanaco). A sincere appreciation goes out to the developers and the community involved in the creation and refinement of these models. Their commitment to providing open source tools and datasets have been instrumental in making this project a reality. Moreover, a special note of thanks to the [Hugging Face](https://huggingface.co/) team, whose transformative library has not only streamlined the process of model creation and adaptation, but also democratized the access to state-of-the-art machine learning technologies. Their impact on the development of this project cannot be overstated.
vnktrmnb/bert-base-multilingual-cased-finetuned-TeQuad_Te	vnktrmnb	2023-07-12T07:35:33Z	61	0	transformers	[ "transformers", "tf", "bert", "question-answering", "generated_from_keras_callback", "license:apache-2.0", "endpoints_compatible", "region:us" ]	question-answering	2023-07-12T04:54:45Z	--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: vnktrmnb/bert-base-multilingual-cased-finetuned-TeQuad_Te results: [] --- <!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. --> # vnktrmnb/bert-base-multilingual-cased-finetuned-TeQuad_Te This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 2.5629 - Train End Logits Accuracy: 0.3532 - Train Start Logits Accuracy: 0.3920 - Validation Loss: 1.8877 - Validation End Logits Accuracy: 0.4726 - Validation Start Logits Accuracy: 0.5126 - Epoch: 0 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 7331, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results \| Train Loss \| Train End Logits Accuracy \| Train Start Logits Accuracy \| Validation Loss \| Validation End Logits Accuracy \| Validation Start Logits Accuracy \| Epoch \| \|:----------:\|:-------------------------:\|:---------------------------:\|:---------------:\|:------------------------------:\|:--------------------------------:\|:-----:\| \| 2.5629 \| 0.3532 \| 0.3920 \| 1.8877 \| 0.4726 \| 0.5126 \| 0 \| ### Framework versions - Transformers 4.30.2 - TensorFlow 2.12.0 - Datasets 2.13.1 - Tokenizers 0.13.3
rocketship/5000	rocketship	2023-07-12T07:34:41Z	0	0	null	[ "arxiv:1910.09700", "license:openrail", "region:us" ]	null	2023-03-06T22:06:52Z	--- license: openrail --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1). ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - Developed by: Projector Bach - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> Risk at your own risk [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Data Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ## Hilarious and Unconsiderd Details I'll tackle this nedt one... after I am rich! But until then my time is better spent skippping rocks and counting the skips per toss. ### Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed]
Intel/whisper-medium-int8-dynamic-inc	Intel	2023-07-12T07:26:49Z	6	0	transformers	[ "transformers", "onnx", "whisper", "automatic-speech-recognition", "int8", "ONNX", "PostTrainingDynamic", "Intel® Neural Compressor", "neural-compressor", "dataset:librispeech_asr", "license:apache-2.0", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	2023-07-12T07:19:58Z	--- license: apache-2.0 datasets: - librispeech_asr metrics: - wer pipeline_tag: automatic-speech-recognition tags: - automatic-speech-recognition - int8 - ONNX - PostTrainingDynamic - Intel® Neural Compressor - neural-compressor library_name: transformers --- ## Model Details: INT8 Whisper medium Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation. Trained on 680k hours of labelled data, Whisper models demonstrate a strong ability to generalise to many datasets and domains without the need for fine-tuning. This int8 ONNX model is generated by [neural-compressor](https://github.com/intel/neural-compressor) and the fp32 model can be exported with below command: ```shell optimum-cli export onnx --model openai/whisper-medium whisper-medium-with-past/ --task automatic-speech-recognition-with-past --opset 13 ``` \| Model Detail \| Description \| \| ----------- \| ----------- \| \| Model Authors - Company \| Intel \| \| Date \| July 7, 2023 \| \| Version \| 1 \| \| Type \| Speech Recognition \| \| Paper or Other Resources \| - \| \| License \| Apache 2.0 \| \| Questions or Comments \| [Community Tab](https://huggingface.co/Intel/whisper-medium-int8-dynamic/discussions)\| \| Intended Use \| Description \| \| ----------- \| ----------- \| \| Primary intended uses \| You can use the raw model for automatic speech recognition inference \| \| Primary intended users \| Anyone doing automatic speech recognition inference \| \| Out-of-scope uses \| This model in most cases will need to be fine-tuned for your particular task. The model should not be used to intentionally create hostile or alienating environments for people.\| ### How to use Download the model by cloning the repository: ```shell git clone https://huggingface.co/Intel/whisper-medium-int8-dynamic ``` Evaluate the model with below code: ```python import os from evaluate import load from datasets import load_dataset from transformers import WhisperForConditionalGeneration, WhisperProcessor, AutoConfig model_name = 'openai/whisper-medium' model_path = 'whisper-medium-int8-dynamic' processor = WhisperProcessor.from_pretrained(model_name) model = WhisperForConditionalGeneration.from_pretrained(model_name) config = AutoConfig.from_pretrained(model_name) wer = load("wer") librispeech_test_clean = load_dataset("librispeech_asr", "clean", split="test") from optimum.onnxruntime import ORTModelForSpeechSeq2Seq from transformers import PretrainedConfig model_config = PretrainedConfig.from_pretrained(model_name) predictions = [] references = [] sessions = ORTModelForSpeechSeq2Seq.load_model( os.path.join(model_path, 'encoder_model.onnx'), os.path.join(model_path, 'decoder_model.onnx'), os.path.join(model_path, 'decoder_with_past_model.onnx')) model = ORTModelForSpeechSeq2Seq(sessions[0], sessions[1], model_config, model_path, sessions[2]) for idx, batch in enumerate(librispeech_test_clean): audio = batch["audio"] input_features = processor(audio["array"], sampling_rate=audio["sampling_rate"], return_tensors="pt").input_features reference = processor.tokenizer._normalize(batch['text']) references.append(reference) predicted_ids = model.generate(input_features)[0] transcription = processor.decode(predicted_ids) prediction = processor.tokenizer._normalize(transcription) predictions.append(prediction) wer_result = wer.compute(references=references, predictions=predictions) print(f"Result wer: {wer_result * 100}") accuracy = 1 - wer_result print("Accuracy: %.5f" % accuracy) ``` ## Metrics (Model Performance): \| Model \| Model Size (GB) \| wer \| \|---\|:---:\|:---:\| \| FP32 \|2.4\|2.88\| \| INT8 \|1.2\|2.83\|
tannazhp95/dqn-SpaceInvadersNoFrameskip-v4	tannazhp95	2023-07-12T07:23:58Z	7	0	stable-baselines3	[ "stable-baselines3", "SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2023-07-12T07:23:18Z	--- library_name: stable-baselines3 tags: - SpaceInvadersNoFrameskip-v4 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: DQN results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: SpaceInvadersNoFrameskip-v4 type: SpaceInvadersNoFrameskip-v4 metrics: - type: mean_reward value: 643.50 +/- 224.99 name: mean_reward verified: false --- # DQN Agent playing SpaceInvadersNoFrameskip-v4 This is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3) and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo). The RL Zoo is a training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included. ## Usage (with SB3 RL Zoo) RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/> SB3: https://github.com/DLR-RM/stable-baselines3<br/> SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib Install the RL Zoo (with SB3 and SB3-Contrib): ```bash pip install rl_zoo3 ``` ``` # Download model and save it into the logs/ folder python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga tannazhp95 -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do: ``` python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga tannazhp95 -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` ## Training (with the RL Zoo) ``` python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ # Upload the model and generate video (when possible) python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga tannazhp95 ``` ## Hyperparameters ```python OrderedDict([('batch_size', 32), ('buffer_size', 100000), ('env_wrapper', ['stable_baselines3.common.atari_wrappers.AtariWrapper']), ('exploration_final_eps', 0.01), ('exploration_fraction', 0.1), ('frame_stack', 4), ('gradient_steps', 1), ('learning_rate', 0.0001), ('learning_starts', 100000), ('n_timesteps', 1000000.0), ('optimize_memory_usage', False), ('policy', 'CnnPolicy'), ('target_update_interval', 1000), ('train_freq', 4), ('normalize', False)]) ``` # Environment Arguments ```python {'render_mode': 'rgb_array'} ```
KaansCodingAdventure/squad-bloom-3b	KaansCodingAdventure	2023-07-12T07:20:15Z	0	0	peft	[ "peft", "region:us" ]	null	2023-07-10T14:05:09Z	--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.4.0.dev0
Daniil-plotnikov/Glazastik_Chat	Daniil-plotnikov	2023-07-12T07:19:11Z	5	0	transformers	[ "transformers", "llama", "text-generation", "code", "question-answering", "ru", "en", "fr", "license:openrail", "autotrain_compatible", "endpoints_compatible", "region:us" ]	question-answering	2023-07-11T15:11:06Z	--- license: openrail language: - ru - en - fr pipeline_tag: question-answering tags: - code library_name: transformers --- Данная языковая модель основанна на Llama и хорошо понимает русский язык.
Intel/whisper-medium-int8-static-inc	Intel	2023-07-12T07:16:35Z	9	1	transformers	[ "transformers", "onnx", "whisper", "automatic-speech-recognition", "int8", "ONNX", "PostTrainingStatic", "Intel® Neural Compressor", "neural-compressor", "dataset:librispeech_asr", "license:apache-2.0", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	2023-07-12T07:01:29Z	--- license: apache-2.0 datasets: - librispeech_asr metrics: - wer pipeline_tag: automatic-speech-recognition tags: - automatic-speech-recognition - int8 - ONNX - PostTrainingStatic - Intel® Neural Compressor - neural-compressor library_name: transformers --- ## Model Details: INT8 Whisper medium Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation. Trained on 680k hours of labelled data, Whisper models demonstrate a strong ability to generalise to many datasets and domains without the need for fine-tuning. This int8 ONNX model is generated by [neural-compressor](https://github.com/intel/neural-compressor) and the fp32 model can be exported with below command: ```shell optimum-cli export onnx --model openai/whisper-medium whisper-medium-with-past/ --task automatic-speech-recognition-with-past --opset 13 ``` \| Model Detail \| Description \| \| ----------- \| ----------- \| \| Model Authors - Company \| Intel \| \| Date \| May 15, 2022 \| \| Version \| 1 \| \| Type \| Speech Recognition \| \| Paper or Other Resources \| - \| \| License \| Apache 2.0 \| \| Questions or Comments \| [Community Tab](https://huggingface.co/Intel/whisper-medium-int8-static/discussions)\| \| Intended Use \| Description \| \| ----------- \| ----------- \| \| Primary intended uses \| You can use the raw model for automatic speech recognition inference \| \| Primary intended users \| Anyone doing automatic speech recognition inference \| \| Out-of-scope uses \| This model in most cases will need to be fine-tuned for your particular task. The model should not be used to intentionally create hostile or alienating environments for people.\| ### How to use Download the model by cloning the repository: ```shell git clone https://huggingface.co/Intel/whisper-medium-int8-static ``` Evaluate the model with below code: ```python import os from evaluate import load from datasets import load_dataset from transformers import WhisperForConditionalGeneration, WhisperProcessor, AutoConfig model_name = 'openai/whisper-medium' model_path = 'whisper-medium-int8-static' processor = WhisperProcessor.from_pretrained(model_name) model = WhisperForConditionalGeneration.from_pretrained(model_name) config = AutoConfig.from_pretrained(model_name) wer = load("wer") librispeech_test_clean = load_dataset("librispeech_asr", "clean", split="test") from optimum.onnxruntime import ORTModelForSpeechSeq2Seq from transformers import PretrainedConfig model_config = PretrainedConfig.from_pretrained(model_name) predictions = [] references = [] sessions = ORTModelForSpeechSeq2Seq.load_model( os.path.join(model_path, 'encoder_model.onnx'), os.path.join(model_path, 'decoder_model.onnx'), os.path.join(model_path, 'decoder_with_past_model.onnx')) model = ORTModelForSpeechSeq2Seq(sessions[0], sessions[1], model_config, model_path, sessions[2]) for idx, batch in enumerate(librispeech_test_clean): audio = batch["audio"] input_features = processor(audio["array"], sampling_rate=audio["sampling_rate"], return_tensors="pt").input_features reference = processor.tokenizer._normalize(batch['text']) references.append(reference) predicted_ids = model.generate(input_features)[0] transcription = processor.decode(predicted_ids) prediction = processor.tokenizer._normalize(transcription) predictions.append(prediction) wer_result = wer.compute(references=references, predictions=predictions) print(f"Result wer: {wer_result * 100}") accuracy = 1 - wer_result print("Accuracy: %.5f" % accuracy) ``` ## Metrics (Model Performance): \| Model \| Model Size (GB) \| wer \| \|---\|:---:\|:---:\| \| FP32 \|4.9\|2.88\| \| INT8 \|1.6\|3.31\|
SpringYung/falcon_with_cfa_text_v1	SpringYung	2023-07-12T07:16:00Z	0	0	peft	[ "peft", "region:us" ]	null	2023-07-12T07:15:32Z	--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.4.0.dev0
seanghay/khmer-pos-roberta	seanghay	2023-07-12T07:15:07Z	12	0	transformers	[ "transformers", "pytorch", "tensorboard", "safetensors", "xlm-roberta", "token-classification", "generated_from_trainer", "km", "dataset:seanghay/khPOS", "arxiv:2103.16801", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	token-classification	2023-07-12T05:28:20Z	--- license: apache-2.0 tags: - generated_from_trainer datasets: - seanghay/khPOS metrics: - precision - recall - f1 - accuracy widget: - text: គាត់ផឹកទឹកនៅភ្នំពេញ - text: តើលោកស្រីបានសាកសួរទៅគាត់ទេ? - text: នេត្រា មិនដឹងសោះថាអ្នកជាមនុស្ស! - text: លោក វណ្ណ ម៉ូលីវណ្ណ ជាបិតាស្ថាបត្យកម្មដ៏ល្បីល្បាញរបស់ប្រទេសកម្ពុជានៅក្នុងសម័យសង្គមរាស្ត្រនិយម។ model-index: - name: khmer-pos-roberta-10 results: - task: name: Token Classification type: token-classification dataset: name: kh_pos type: kh_pos config: default split: train args: default metrics: - name: Precision type: precision value: 0.9511876225757245 - name: Recall type: recall value: 0.9526407682234832 - name: F1 type: f1 value: 0.9519136408243376 - name: Accuracy type: accuracy value: 0.9735370853522176 language: - km library_name: transformers pipeline_tag: token-classification --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # Khmer Part of Speech Tagging with XLM RoBERTa This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the [khPOS](https://huggingface.co/datasets/seanghay/khPOS) dataset. It achieves the following results on the evaluation set: - Loss: 0.1063 - Precision: 0.9512 - Recall: 0.9526 - F1: 0.9519 - Accuracy: 0.9735 ## Model description The [original paper](https://arxiv.org/pdf/2103.16801.pdf) achieved 98.15% accuracy while this model achieved only 97.35% which is close. However, this is a multilingual model so it has more tokens than the original paper. ## Intended uses & limitations This model can be used to extract useful information from Khmer text. ## Training and evaluation data train: 90% / test: 10% ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 24 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 10 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Precision \| Recall \| F1 \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:---------:\|:------:\|:------:\|:--------:\| \| No log \| 1.0 \| 450 \| 0.1347 \| 0.9314 \| 0.9333 \| 0.9324 \| 0.9603 \| \| 0.4834 \| 2.0 \| 900 \| 0.1183 \| 0.9407 \| 0.9377 \| 0.9392 \| 0.9653 \| \| 0.1323 \| 3.0 \| 1350 \| 0.1026 \| 0.9484 \| 0.9482 \| 0.9483 \| 0.9699 \| \| 0.095 \| 4.0 \| 1800 \| 0.0986 \| 0.9502 \| 0.9490 \| 0.9496 \| 0.9712 \| \| 0.0774 \| 5.0 \| 2250 \| 0.0978 \| 0.9494 \| 0.9491 \| 0.9493 \| 0.9712 \| \| 0.0616 \| 6.0 \| 2700 \| 0.0991 \| 0.9493 \| 0.9507 \| 0.9500 \| 0.9715 \| \| 0.0494 \| 7.0 \| 3150 \| 0.0989 \| 0.9529 \| 0.9540 \| 0.9534 \| 0.9731 \| \| 0.0414 \| 8.0 \| 3600 \| 0.1037 \| 0.9499 \| 0.9501 \| 0.9500 \| 0.9722 \| \| 0.0339 \| 9.0 \| 4050 \| 0.1056 \| 0.9516 \| 0.9517 \| 0.9516 \| 0.9734 \| \| 0.029 \| 10.0 \| 4500 \| 0.1063 \| 0.9512 \| 0.9526 \| 0.9519 \| 0.9735 \| ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
aiknight87/falcon-40b-instruct-tuned-finance-qas	aiknight87	2023-07-12T07:13:46Z	1	0	peft	[ "peft", "RefinedWeb", "custom_code", "4-bit", "region:us" ]	null	2023-07-12T07:11:31Z	--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.4.0.dev0
Kauru/DialoGPT-medium-Ranniv2	Kauru	2023-07-12T07:06:46Z	142	0	transformers	[ "transformers", "pytorch", "gpt2", "text-generation", "conversational", "en", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-07-12T05:27:04Z	--- language: - en pipeline_tag: conversational ---
JaniGiblets/ppo-LunarLander-v2	JaniGiblets	2023-07-12T06:58:42Z	0	0	stable-baselines3	[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2023-07-12T06:58:22Z	--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 253.79 +/- 12.76 name: mean_reward verified: false --- # PPO Agent playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
coreml-community/coreml-realMoonAnime-v70_cn	coreml-community	2023-07-12T06:40:53Z	0	0	null	[ "coreml", "stable-diffusion", "text-to-image", "license:creativeml-openrail-m", "region:us" ]	text-to-image	2023-07-12T00:45:47Z	--- license: creativeml-openrail-m tags: - coreml - stable-diffusion - text-to-image --- # Core ML Converted Model: - This model was converted to [Core ML for use on Apple Silicon devices](https://github.com/apple/ml-stable-diffusion). Conversion instructions can be found [here](https://github.com/godly-devotion/MochiDiffusion/wiki/How-to-convert-ckpt-or-safetensors-files-to-Core-ML). - Provide the model to an app such as Mochi Diffusion [Github](https://github.com/godly-devotion/MochiDiffusion) / [Discord](https://discord.gg/x2kartzxGv) to generate images. - `split_einsum` version is compatible with all compute unit options including Neural Engine. - `original` version is only compatible with `CPU & GPU` option. - Custom resolution versions are tagged accordingly. - The `vae-ft-mse-840000-ema-pruned.ckpt` VAE is embedded into the model. - This model was converted with a `vae-encoder` for use with `image2image`. - This model is `fp16`. - Descriptions are posted as-is from original model source. - Not all features and/or results may be available in `CoreML` format. - This model does not have the [unet split into chunks](https://github.com/apple/ml-stable-diffusion#-converting-models-to-core-ml). - This model does not include a `safety checker` (for NSFW content). - This model can be used with ControlNet. <br> # realMoonAnime-v70_cn: Source(s): [CivitAI](https://civitai.com/models/75431/real-moon-anime)<br> ## Real Moon - Anime v7.0 A mixture of Real Moon with MonKe Dream. This model aims to generate anime images with a lot of detail and quality, a balance between realism and anime. Can output both SFW and NSFW images. Baked in VAE ### I usually use - Clip skip: 1 - Upscaler: R-ESRGAN 4x+ Anime6B - Denoising strength: 0.4 - Hires steps: same as the Sampling steps Recommended Loras: Detail Tweaker, Better Portrait Lighting Recommended embeddings: bad-artist, EasyNegativeV2<br><br> ![image](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/85499afc-501d-4bec-80b7-23413d435b6d/width=450/0fd69f15-63b3-4fd8-8d3a-f8636620dcf5.jpeg) ![image](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/2fda9c17-adc6-493c-93b3-ba1f7bb2d409/width=450/49fbdd05-781c-4874-9435-684ef83dd7c7.jpeg) ![image](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/e753cff6-e0e7-4c79-ba1e-269d0675ccb6/width=450/f4e11ad3-2e1a-479b-a902-c5036a8b7114.jpeg) ![image](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/79c71163-be78-4e7e-968c-96f3c29ad1bf/width=450/de27b8a9-00e7-4ead-af19-d9c93ebfa8fc.jpeg)
XDawned/minecraft-en-zh	XDawned	2023-07-12T06:30:29Z	138	4	transformers	[ "transformers", "pytorch", "safetensors", "marian", "text2text-generation", "translation", "transformer", "en-zh", "minecraft modpack", "finetune", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	translation	2023-04-04T05:27:12Z	--- tags: - translation - transformer - en-zh - minecraft modpack - finetune license: apache-2.0 --- finetune model [opus-mt-en-zh](https://huggingface.co/Helsinki-NLP/opus-mt-en-zh) traing datas are from [i18n-dict](https://github.com/CFPATools/i18n-dict) and some modpacks‘ quests collected from the internet ## Validation Metrics On Some 1.19.2+ ModPacks - Loss: 1.6 - SacreBLEU: 30.8 ## Validation Metrics On Dict - Loss: 0.9 - SacreBLEU: 51.1
localmodels/WizardLM-30B-v1.0-ggml	localmodels	2023-07-12T06:18:32Z	0	2	null	[ "region:us" ]	null	2023-07-12T06:18:31Z	--- duplicated_from: localmodels/LLM --- # WizardLM 30B v1.0 ggml From: https://huggingface.co/WizardLM/WizardLM-30B-V1.0 --- ### Original llama.cpp quant methods: `q4_0, q4_1, q5_0, q5_1, q8_0` Quantized using an older version of llama.cpp and compatible with llama.cpp from May 19, commit 2d5db48. ### k-quant methods: `q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K` Quantization methods compatible with latest llama.cpp from June 6, commit 2d43387. --- ## Files \| Name \| Quant method \| Bits \| Size \| Max RAM required, no GPU offloading \| Use case \| \| ---- \| ---- \| ---- \| ---- \| ---- \| ----- \| \| wizardlm-30b.ggmlv3.q2_K.bin \| q2_K \| 2 \| 13.60 GB \| 16.10 GB \| New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. \| \| wizardlm-30b.ggmlv3.q3_K_L.bin \| q3_K_L \| 3 \| 17.20 GB \| 19.70 GB \| New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K \| \| wizardlm-30b.ggmlv3.q3_K_M.bin \| q3_K_M \| 3 \| 15.64 GB \| 18.14 GB \| New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K \| \| wizardlm-30b.ggmlv3.q3_K_S.bin \| q3_K_S \| 3 \| 13.98 GB \| 16.48 GB \| New k-quant method. Uses GGML_TYPE_Q3_K for all tensors \| \| wizardlm-30b.ggmlv3.q4_0.bin \| q4_0 \| 4 \| 18.30 GB \| 20.80 GB \| Original llama.cpp quant method, 4-bit. \| \| wizardlm-30b.ggmlv3.q4_1.bin \| q4_1 \| 4 \| 20.33 GB \| 22.83 GB \| Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. \| \| wizardlm-30b.ggmlv3.q4_K_M.bin \| q4_K_M \| 4 \| 19.57 GB \| 22.07 GB \| New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K \| \| wizardlm-30b.ggmlv3.q4_K_S.bin \| q4_K_S \| 4 \| 18.30 GB \| 20.80 GB \| New k-quant method. Uses GGML_TYPE_Q4_K for all tensors \| \| wizardlm-30b.ggmlv3.q5_0.bin \| q5_0 \| 5 \| 22.37 GB \| 24.87 GB \| Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. \| \| wizardlm-30b.ggmlv3.q5_1.bin \| q5_1 \| 5 \| 24.40 GB \| 26.90 GB \| Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. \| \| wizardlm-30b.ggmlv3.q5_K_M.bin \| q5_K_M \| 5 \| 23.02 GB \| 25.52 GB \| New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K \| \| wizardlm-30b.ggmlv3.q5_K_S.bin \| q5_K_S \| 5 \| 22.37 GB \| 24.87 GB \| New k-quant method. Uses GGML_TYPE_Q5_K for all tensors \| \| wizardlm-30b.ggmlv3.q6_K.bin \| q6_K \| 6 \| 26.69 GB \| 29.19 GB \| New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors \| \| wizardlm-30b.ggmlv3.q8_0.bin \| q8_0 \| 8 \| 34.56 GB \| 37.06 GB \| Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. \|
luhx/ppo-Pyramids	luhx	2023-07-12T06:10:19Z	1	0	ml-agents	[ "ml-agents", "tensorboard", "onnx", "Pyramids", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Pyramids", "region:us" ]	reinforcement-learning	2023-07-12T06:10:12Z	--- library_name: ml-agents tags: - Pyramids - deep-reinforcement-learning - reinforcement-learning - ML-Agents-Pyramids --- # ppo Agent playing Pyramids This is a trained model of a ppo agent playing Pyramids using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A short tutorial where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A longer tutorial to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent playing directly in your browser 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: luhx/ppo-Pyramids 3. Step 2: Select your .nn /.onnx file 4. Click on Watch the agent play 👀
localmodels/Guanaco-7B-ggml	localmodels	2023-07-12T05:53:53Z	0	1	null	[ "arxiv:2305.14314", "arxiv:2302.13971", "arxiv:2304.07327", "region:us" ]	null	2023-07-12T05:53:52Z	--- duplicated_from: localmodels/LLM --- # Guanaco 7B ggml From: https://huggingface.co/timdettmers/guanaco-7b --- ### Original llama.cpp quant methods: `q4_0, q4_1, q5_0, q5_1, q8_0` Quantized using an older version of llama.cpp and compatible with llama.cpp from May 19, commit 2d5db48. ### k-quant methods: `q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K` Quantization methods compatible with latest llama.cpp from June 6, commit 2d43387. --- ## Files \| Name \| Quant method \| Bits \| Size \| Max RAM required, no GPU offloading \| Use case \| \| ---- \| ---- \| ---- \| ---- \| ---- \| ----- \| \| guanaco-7B.ggmlv3.q2_K.bin \| q2_K \| 2 \| 2.80 GB \| 5.30 GB \| New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. \| \| guanaco-7B.ggmlv3.q3_K_L.bin \| q3_K_L \| 3 \| 3.55 GB \| 6.05 GB \| New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K \| \| guanaco-7B.ggmlv3.q3_K_M.bin \| q3_K_M \| 3 \| 3.23 GB \| 5.73 GB \| New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K \| \| guanaco-7B.ggmlv3.q3_K_S.bin \| q3_K_S \| 3 \| 2.90 GB \| 5.40 GB \| New k-quant method. Uses GGML_TYPE_Q3_K for all tensors \| \| guanaco-7B.ggmlv3.q4_0.bin \| q4_0 \| 4 \| 3.79 GB \| 6.29 GB \| Original llama.cpp quant method, 4-bit. \| \| guanaco-7B.ggmlv3.q4_1.bin \| q4_1 \| 4 \| 4.21 GB \| 6.71 GB \| Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. \| \| guanaco-7B.ggmlv3.q4_K_M.bin \| q4_K_M \| 4 \| 4.05 GB \| 6.55 GB \| New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K \| \| guanaco-7B.ggmlv3.q4_K_S.bin \| q4_K_S \| 4 \| 3.79 GB \| 6.29 GB \| New k-quant method. Uses GGML_TYPE_Q4_K for all tensors \| \| guanaco-7B.ggmlv3.q5_0.bin \| q5_0 \| 5 \| 4.63 GB \| 7.13 GB \| Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. \| \| guanaco-7B.ggmlv3.q5_1.bin \| q5_1 \| 5 \| 5.06 GB \| 7.56 GB \| Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. \| \| guanaco-7B.ggmlv3.q5_K_M.bin \| q5_K_M \| 5 \| 4.77 GB \| 7.27 GB \| New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K \| \| guanaco-7B.ggmlv3.q5_K_S.bin \| q5_K_S \| 5 \| 4.63 GB \| 7.13 GB \| New k-quant method. Uses GGML_TYPE_Q5_K for all tensors \| \| guanaco-7B.ggmlv3.q6_K.bin \| q6_K \| 6 \| 5.53 GB \| 8.03 GB \| New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors \| \| guanaco-7B.ggmlv3.q8_0.bin \| q8_0 \| 8 \| 7.16 GB \| 9.66 GB \| Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. \| --- # Guanaco Models Based on LLaMA \| [Paper](https://arxiv.org/abs/2305.14314) \| [Code](https://github.com/artidoro/qlora) \| [Demo](https://huggingface.co/spaces/uwnlp/guanaco-playground-tgi) \| The Guanaco models are open-source finetuned chatbots obtained through 4-bit QLoRA tuning of LLaMA base models on the OASST1 dataset. They are available in 7B, 13B, 33B, and 65B parameter sizes. ⚠️Guanaco is a model purely intended for research purposes and could produce problematic outputs. ## Why use Guanaco? - Competitive with commercial chatbot systems on the Vicuna and OpenAssistant benchmarks (ChatGPT and BARD) according to human and GPT-4 raters. We note that the relative performance on tasks not covered in these benchmarks could be very different. In addition, commercial systems evolve over time (we used outputs from the March 2023 version of the models). - Available open-source for research purposes. Guanaco models allow cheap and local experimentation with high-quality chatbot systems. - Replicable and efficient training procedure that can be extended to new use cases. Guanaco training scripts are available in the [QLoRA repo](https://github.com/artidoro/qlora). - Rigorous comparison to 16-bit methods (both 16-bit full-finetuning and LoRA) in [our paper](https://arxiv.org/abs/2305.14314) demonstrates the effectiveness of 4-bit QLoRA finetuning. - Lightweight checkpoints which only contain adapter weights. ## License and Intended Use Guanaco adapter weights are available under Apache 2 license. Note the use of the Guanaco adapter weights, requires access to the LLaMA model weighs. Guanaco is based on LLaMA and therefore should be used according to the LLaMA license. ## Usage Here is an example of how you would load Guanaco 7B in 4-bits: ```python import torch from peft import PeftModel from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig model_name = "huggyllama/llama-7b" adapters_name = 'timdettmers/guanaco-7b' model = AutoModelForCausalLM.from_pretrained( model_name, load_in_4bit=True, torch_dtype=torch.bfloat16, device_map="auto", max_memory= {i: '24000MB' for i in range(torch.cuda.device_count())}, quantization_config=BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_compute_dtype=torch.bfloat16, bnb_4bit_use_double_quant=True, bnb_4bit_quant_type='nf4' ), ) model = PeftModel.from_pretrained(model, adapters_name) tokenizer = AutoTokenizer.from_pretrained(model_name) ``` Inference can then be performed as usual with HF models as follows: ```python prompt = "Introduce yourself" formatted_prompt = ( f"A chat between a curious human and an artificial intelligence assistant." f"The assistant gives helpful, detailed, and polite answers to the user's questions.\n" f"### Human: {prompt} ### Assistant:" ) inputs = tokenizer(formatted_prompt, return_tensors="pt").to("cuda:0") outputs = model.generate(inputs=inputs.input_ids, max_new_tokens=20) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) ``` Expected output similar to the following: ``` A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. ### Human: Introduce yourself ### Assistant: I am an artificial intelligence assistant. I am here to help you with any questions you may have. ``` ## Current Inference Limitations Currently, 4-bit inference is slow. We recommend loading in 16 bits if inference speed is a concern. We are actively working on releasing efficient 4-bit inference kernels. Below is how you would load the model in 16 bits: ```python model_name = "huggyllama/llama-7b" adapters_name = 'timdettmers/guanaco-7b' model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype=torch.bfloat16, device_map="auto", max_memory= {i: '24000MB' for i in range(torch.cuda.device_count())}, ) model = PeftModel.from_pretrained(model, adapters_name) tokenizer = AutoTokenizer.from_pretrained(model_name) ``` ## Model Card Architecture: The Guanaco models are LoRA adapters to be used on top of LLaMA models. They are added to all layers. For all model sizes, we use $r=64$. Base Model: Guanaco uses LLaMA as base model with sizes 7B, 13B, 33B, 65B. LLaMA is a causal language model pretrained on a large corpus of text. See [LLaMA paper](https://arxiv.org/abs/2302.13971) for more details. Note that Guanaco can inherit biases and limitations of the base model. Finetuning Data: Guanaco is finetuned on OASST1. The exact dataset is available at [timdettmers/openassistant-guanaco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco). Languages: The OASST1 dataset is multilingual (see [the paper](https://arxiv.org/abs/2304.07327) for details) and as such Guanaco responds to user queries in different languages. We note, however, that OASST1 is heavy in high-resource languages. In addition, human evaluation of Guanaco was only performed in English and based on qualitative analysis we observed degradation in performance in other languages. Next, we describe Training and Evaluation details. ### Training Guanaco models are the result of 4-bit QLoRA supervised finetuning on the OASST1 dataset. All models use NormalFloat4 datatype for the base model and LoRA adapters on all linear layers with BFloat16 as computation datatype. We set LoRA $r=64$, $\alpha=16$. We also use Adam beta2 of 0.999, max grad norm of 0.3 and LoRA dropout of 0.1 for models up to 13B and 0.05 for 33B and 65B models. For the finetuning process, we use constant learning rate schedule and paged AdamW optimizer. ### Training hyperparameters Size\| Dataset \| Batch Size \| Learning Rate \| Max Steps \| Sequence length ---\|---\|---\|---\|---\|--- 7B \| OASST1 \| 16 \| 2e-4 \| 1875 \| 512 13B \| OASST1 \| 16 \| 2e-4 \| 1875 \| 512 33B \| OASST1 \| 16 \| 1e-4 \| 1875 \| 512 65B \| OASST1 \| 16 \| 1e-4 \| 1875 \| 512 ### Evaluation We test generative language capabilities through both automated and human evaluations. This second set of evaluations relies on queries curated by humans and aims at measuring the quality of model responses. We use the Vicuna and OpenAssistant datasets with 80 and 953 prompts respectively. In both human and automated evaluations, for each prompt, raters compare all pairs of responses across the models considered. For human raters we randomize the order of the systems, for GPT-4 we evaluate with both orders. Benchmark \| Vicuna \| \| Vicuna \| \| OpenAssistant \| \| - -----------\|----\|-----\|--------\|---\|---------------\|---\|--- Prompts \| 80 \| \| 80 \| \| 953 \| \| Judge \| Human \| \| GPT-4 \| \| GPT-4 \| \| Model \| Elo \| Rank \| Elo \| Rank \| Elo \| Rank \| Median Rank GPT-4 \| 1176 \| 1 \| 1348 \| 1 \| 1294 \| 1 \| 1 Guanaco-65B \| 1023 \| 2 \| 1022 \| 2 \| 1008 \| 3 \| 2 Guanaco-33B \| 1009 \| 4 \| 992 \| 3 \| 1002 \| 4 \| 4 ChatGPT-3.5 Turbo \| 916 \| 7 \| 966 \| 5 \| 1015 \| 2 \| 5 Vicuna-13B \| 984 \| 5 \| 974 \| 4 \| 936 \| 5 \| 5 Guanaco-13B \| 975 \| 6 \| 913 \| 6 \| 885 \| 6 \| 6 Guanaco-7B \| 1010 \| 3 \| 879 \| 8 \| 860 \| 7 \| 7 Bard \| 909 \| 8 \| 902 \| 7 \| - \| - \| 8 We also use the MMLU benchmark to measure performance on a range of language understanding tasks. This is a multiple-choice benchmark covering 57 tasks including elementary mathematics, US history, computer science, law, and more. We report 5-shot test accuracy. Dataset \| 7B \| 13B \| 33B \| 65B ---\|---\|---\|---\|--- LLaMA no tuning \| 35.1 \| 46.9 \| 57.8 \| 63.4 Self-Instruct \| 36.4 \| 33.3 \| 53.0 \| 56.7 Longform \| 32.1 \| 43.2 \| 56.6 \| 59.7 Chip2 \| 34.5 \| 41.6 \| 53.6 \| 59.8 HH-RLHF \| 34.9 \| 44.6 \| 55.8 \| 60.1 Unnatural Instruct \| 41.9 \| 48.1 \| 57.3 \| 61.3 OASST1 (Guanaco) \| 36.6 \| 46.4 \| 57.0 \| 62.2 Alpaca \| 38.8 \| 47.8 \| 57.3 \| 62.5 FLAN v2 \| 44.5 \| 51.4 \| 59.2 \| 63.9 ## Risks and Biases The model can produce factually incorrect output, and should not be relied on to produce factually accurate information. The model was trained on various public datasets; it is possible that this model could generate lewd, biased, or otherwise offensive outputs. However, we note that finetuning on OASST1 seems to reduce biases as measured on the CrowS dataset. We report here the performance of Guanaco-65B compared to other baseline models on the CrowS dataset. \| \| LLaMA-65B \| GPT-3 \| OPT-175B \| Guanaco-65B \| \|----------------------\|-----------\|-------\|----------\|---------------\| \| Gender \| 70.6 \| 62.6 \| 65.7 \| 47.5 \| \| Religion \| {79.0} \| 73.3 \| 68.6 \| 38.7 \| \| Race/Color \| 57.0 \| 64.7 \| 68.6 \| 45.3 \| \| Sexual orientation \| {81.0} \| 76.2 \| 78.6 \| 59.1 \| \| Age \| 70.1 \| 64.4 \| 67.8 \| 36.3 \| \| Nationality \| 64.2 \| 61.6 \| 62.9 \| 32.4 \| \| Disability \| 66.7 \| 76.7 \| 76.7 \| 33.9 \| \| Physical appearance \| 77.8 \| 74.6 \| 76.2 \| 43.1 \| \| Socioeconomic status \| 71.5 \| 73.8 \| 76.2 \| 55.3 \| \| Average \| 66.6 \| 67.2 \| 69.5 \| 43.5 \| ## Citation ```bibtex @article{dettmers2023qlora, title={QLoRA: Efficient Finetuning of Quantized LLMs}, author={Dettmers, Tim and Pagnoni, Artidoro and Holtzman, Ari and Zettlemoyer, Luke}, journal={arXiv preprint arXiv:2305.14314}, year={2023} } ```
keehun/textual_inversion_cat	keehun	2023-07-12T05:53:38Z	25	0	diffusers	[ "diffusers", "tensorboard", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "textual_inversion", "base_model:runwayml/stable-diffusion-v1-5", "base_model:adapter:runwayml/stable-diffusion-v1-5", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]	text-to-image	2023-07-12T05:22:14Z	--- license: creativeml-openrail-m base_model: runwayml/stable-diffusion-v1-5 tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers - textual_inversion inference: true --- # Textual inversion text2image fine-tuning - keehun/textual_inversion_cat These are textual inversion adaption weights for runwayml/stable-diffusion-v1-5. You can find some example images in the following.
nkpz/llama-30b-instruct-gptq-128g	nkpz	2023-07-12T05:42:04Z	5	0	transformers	[ "transformers", "pytorch", "llama", "text-generation", "license:other", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-07-11T22:27:15Z	--- license: other --- 4-bit (128 groupsize) quantized files for [upstage/llama-30b-instruct](https://huggingface.co/upstage/llama-30b-instruct) Quantized using [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa). Command used to quantize: python llama.py /my/model/directory c4 --wbits 4 --true-sequential --act-order --groupsize 128 --save_safetensors /my/output/file.safetensors Sample Q&A Temp 0.59, Top P 0.95 Top K 0, Tail Free 1, Typical 1, Top A 0, Rep Pen 1.1, Rep Pen Range 1024, Rep Pen Slope 0.7 Sampler Order: Rep Pen, Top K, Top A, Top P, Tail Free, Typical, Temp Question: How come time flies like an arrow but fruit flies like a banana? A1: This is another one of those questions that has no real answer. It's just a play on words, a joke. Enjoy the humor of it, and don't worry about making sense of it. A2: Because it is written that way in the sacred text of the Bananites. A3: Time flies like an arrow because it is a metaphor that describes the unstoppable nature of the passage of time, which is often associated with the inevitable progression of age and the transience of life. Fruit flies like a banana because it is a joke that plays on the similarity of the words "time" and "fruit," which both contain the word "flies." The phrase "fruit flies" refers to the fact that fruit flies are attracted to ripened fruit. In this case, the joke is comparing the attraction of fruit flies to ripe bananas to the relentless passage of time. Question: The following sentence is true. The previous sentence is false. Which of those two sentences is true? A1: The first one. A2: The second sentence is true. A3: The first sentence is true. Question: What word in the dictionary is always spelled incorrectly? A1: The word "incorrectly" is always spelled incorrectly. A2: Incorrectly. A3: The word "incorrectly" itself. Question: You're running a marathon and you just passed the person who was in second place. What place are you in now? A1: First. A2: First A3: You are now in first place. Question: In what month do people get the least sleep? A1: December. Explanation: People tend to stay up late during December due to holiday events, shopping, and celebrating. Additionally, the winter months typically have shorter days, which means less daylight and more darkness, leading to a decrease in overall sleep. A2: People get the least amount of sleep in December. The shortest day of the year is December 21st or 22nd, which means that there is less daylight. This can lead to more difficulty in falling asleep because of a decrease in melatonin production due to less exposure to darkness. Melatonin is a hormone that helps regulate sleep. A3: December. Explanation: December is when people get the least sleep because it is right before Christmas and there are many things to be done. People are busy shopping, decorating, and preparing for the holiday. They also stay up late to watch holiday specials on TV and attend parties. Question: How much dirt is there in a hole that is three feet wide, four feet long, and five feet deep? A1: 15 cubic yards. A2: 575 cubic feet. A3: 315 cubic feet of dirt. Question: In the accent of a farmer from Alabama, why is it a bad idea to use a generator indoors? Answer: Well, son, when ya use a generator inside, ya gotta remember that it's like having a car running in your house. It's gonna put out carbon monoxide. That's a gas that can kill ya if ya breathe enough of it in. Ya see, your body can't tell the difference between that gas and the oxygen your body needs. So when ya breathe in too much carbon monoxide, your blood can't get enough oxygen to your brain and your organs. And that's not good. So always use that generator outside where there's plenty of fresh air. Question: Pretend you are a proud and irate Italian chef. Which store-bought sauce is the best for spaghetti? Answer: I am an irate Italian chef, and I can tell you that there is no substitute for homemade sauce on your spaghetti. The best sauces come from fresh ingredients, lovingly prepared with the right blend of herbs, tomatoes, garlic, onions, meat, and love. Store-bought sauces can never compare to the delicious taste of homemade sauce, and using them on your pasta is an insult to Italian cuisine! Question: Is it called "pork roll" or "taylor ham"? Answer: It's called both. It's the same thing. It's pork shoulder that's been seasoned and cured, then cooked and sliced. It's a Jersey thing, and some people say "pork roll," while others say "Taylor Ham." The latter is named for the original manufacturer, John Taylor. Question: According to someone from south NJ, is it called "pork roll" or "taylor ham"? Answer: It's "pork roll," my friend. Taylor Ham is a brand of pork roll. Just like you wouldn't say "I had a Coke" when you had a soda, you would say "I had pork roll." Taylor Ham is just the brand you might have had. Question: According to someone from north NJ, is it called "pork roll" or "taylor ham"? Answer: In North Jersey it is referred to as "Taylor Ham." In South Jersey it is referred to as "Pork Roll." They are both the same thing. It is a type of processed pork product that is popular in the state of New Jersey.
zeronphoto/Euneun2	zeronphoto	2023-07-12T05:13:35Z	0	0	null	[ "license:creativeml-openrail-m", "region:us" ]	null	2023-07-12T05:08:26Z	--- license: creativeml-openrail-m ---
tuanhnh/ppo-LunarLander-v2	tuanhnh	2023-07-12T05:08:32Z	0	0	stable-baselines3	[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2023-07-12T03:41:15Z	--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 281.45 +/- 16.12 name: mean_reward verified: false --- # PPO Agent playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
matgu23/ntrlph	matgu23	2023-07-12T05:00:35Z	0	0	diffusers	[ "diffusers", "safetensors", "text-to-image", "stable-diffusion", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]	text-to-image	2023-07-12T04:48:23Z	--- license: creativeml-openrail-m tags: - text-to-image - stable-diffusion --- ### ntrlph Dreambooth model trained by matgu23 with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb) Sample pictures of this concept:
DanielTTY/mpt-30b-qlora	DanielTTY	2023-07-12T04:59:41Z	4	0	transformers	[ "transformers", "pytorch", "mpt", "text-generation", "Composer", "MosaicML", "llm-foundry", "StreamingDatasets", "custom_code", "dataset:allenai/c4", "dataset:mc4", "dataset:togethercomputer/RedPajama-Data-1T", "dataset:bigcode/the-stack-dedup", "dataset:allenai/s2orc", "arxiv:2108.12409", "arxiv:2302.13971", "arxiv:2205.14135", "arxiv:2010.04245", "arxiv:1909.08053", "arxiv:2302.06675", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "region:us" ]	text-generation	2023-07-12T04:59:40Z	--- license: apache-2.0 tags: - Composer - MosaicML - llm-foundry - StreamingDatasets datasets: - allenai/c4 - mc4 - togethercomputer/RedPajama-Data-1T - bigcode/the-stack-dedup - allenai/s2orc inference: false duplicated_from: mosaicml/mpt-30b --- # MPT-30B MPT-30B is a decoder-style transformer pretrained from scratch on 1T tokens of English text and code. This model was trained by [MosaicML](https://www.mosaicml.com). MPT-30B is part of the family of Mosaic Pretrained Transformer (MPT) models, which use a modified transformer architecture optimized for efficient training and inference. MPT-30B comes with special features that differentiate it from other LLMs, including an 8k token context window (which can be further extended via finetuning; see [MPT-7B-StoryWriter](https://huggingface.co/mosaicml/mpt-7b-storywriter)), support for context-length extrapolation via [ALiBi](https://arxiv.org/abs/2108.12409), and efficient inference + training via FlashAttention. It also has strong coding abilities thanks to its pretraining mix. MPT models can also be served efficiently with both standard HuggingFace pipelines and NVIDIA's [FasterTransformer](https://github.com/NVIDIA/FasterTransformer). The size of MPT-30B was also specifically chosen to make it easy to deploy on a single GPU—either 1xA100-80GB in 16-bit precision or 1xA100-40GB in 8-bit precision. This model uses the MosaicML LLM codebase, which can be found in the [llm-foundry repository](https://github.com/mosaicml/llm-foundry). It was trained by MosaicML’s NLP team on the [MosaicML platform](https://www.mosaicml.com/training) for LLM pretraining, finetuning, and inference. ### How is this model different? MPT-30B is: * Licensed for the possibility of commercial use (unlike [LLaMA](https://arxiv.org/abs/2302.13971)). * Trained on a large amount of data (1T tokens like [LLaMA](https://arxiv.org/abs/2302.13971) vs. 300B for [Pythia](https://github.com/EleutherAI/pythia), 300B for [OpenLLaMA](https://github.com/openlm-research/open_llama), and 800B for [StableLM](https://github.com/Stability-AI/StableLM)). * Prepared to handle extremely long inputs thanks to [ALiBi](https://arxiv.org/abs/2108.12409). * Capable of fast training and inference (via [FlashAttention](https://arxiv.org/pdf/2205.14135.pdf) and [FasterTransformer](https://github.com/NVIDIA/FasterTransformer)) * Equipped with highly efficient open-source training code via the [llm-foundry repository](https://github.com/mosaicml/llm-foundry) ### Models finetuned off MPT-30B: The following models are finetuned on MPT-30B: * [MPT-30B-Instruct](https://huggingface.co/mosaicml/mpt-30b-instruct): a model for short-form instruction following. Built by finetuning MPT-30B on several carefully curated datasets. * License: _CC-BY-SA-3.0_ * [MPT-30B-Chat](https://huggingface.co/mosaicml/mpt-30b-chat): a chatbot-like model for dialogue generation. Built by finetuning MPT-30B on [ShareGPT-Vicuna](https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered), [Camel-AI](https://huggingface.co/camel-ai), [GPTeacher](https://github.com/teknium1/GPTeacher), [Guanaco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco), [Baize](https://github.com/project-baize/baize-chatbot) and some generated datasets. * License: _CC-By-NC-SA-4.0_ * [Demo on Hugging Face Spaces](https://huggingface.co/spaces/mosaicml/mpt-30b-chat) ## Model Date June 22, 2023 ## Model License Apache-2.0 ## Documentation * [Blog post: MPT-30B: Raising the bar for open-source foundation models](https://www.mosaicml.com/blog/mpt-30b) * [Codebase (mosaicml/llm-foundry repo)](https://github.com/mosaicml/llm-foundry/) * Questions: Feel free to contact us via the [MosaicML Community Slack](https://mosaicml.me/slack)! ## How to Use This model is best used with the MosaicML [llm-foundry repository](https://github.com/mosaicml/llm-foundry) for training and finetuning. ```python import transformers model = transformers.AutoModelForCausalLM.from_pretrained( 'mosaicml/mpt-30b', trust_remote_code=True ) ``` Note: This model requires that `trust_remote_code=True` be passed to the `from_pretrained` method. This is because we use a custom `MPT` model architecture that is not yet part of the Hugging Face `transformers` package. `MPT` includes options for many training efficiency features such as [FlashAttention](https://arxiv.org/pdf/2205.14135.pdf), [ALiBi](https://arxiv.org/abs/2108.12409), [QK LayerNorm](https://arxiv.org/abs/2010.04245), and more. To use the optimized [triton implementation](https://github.com/openai/triton) of FlashAttention, you can load the model on GPU (`cuda:0`) with `attn_impl='triton'` and with `bfloat16` precision: ```python import torch import transformers name = 'mosaicml/mpt-30b' config = transformers.AutoConfig.from_pretrained(name, trust_remote_code=True) config.attn_config['attn_impl'] = 'triton' # change this to use triton-based FlashAttention config.init_device = 'cuda:0' # For fast initialization directly on GPU! model = transformers.AutoModelForCausalLM.from_pretrained( name, config=config, torch_dtype=torch.bfloat16, # Load model weights in bfloat16 trust_remote_code=True ) ``` The model was trained initially with a sequence length of 2048 with an additional pretraining stage for sequence length adapation up to 8192. However, ALiBi enables users to increase the maximum sequence length even further during finetuning and/or inference. For example: ```python import transformers name = 'mosaicml/mpt-30b' config = transformers.AutoConfig.from_pretrained(name, trust_remote_code=True) config.max_seq_len = 16384 # (input + output) tokens can now be up to 16384 model = transformers.AutoModelForCausalLM.from_pretrained( name, config=config, trust_remote_code=True ) ``` This model was trained with the MPT-30B tokenizer which is identical to the [EleutherAI/gpt-neox-20b](https://huggingface.co/EleutherAI/gpt-neox-20b) tokenizer. ```python from transformers import AutoTokenizer tokenizer = AutoTokenizer.from_pretrained('mosaicml/mpt-30b') ``` The model can then be used, for example, within a text-generation pipeline. Note: when running Torch modules in lower precision, it is best practice to use the [torch.autocast context manager](https://pytorch.org/docs/stable/amp.html). ```python from transformers import pipeline with torch.autocast('cuda', dtype=torch.bfloat16): inputs = tokenizer('Here is a recipe for vegan banana bread:\n', return_tensors="pt").to('cuda') outputs = model.generate(*inputs, max_new_tokens=100) print(tokenizer.batch_decode(outputs, skip_special_tokens=True)) # or using the HF pipeline pipe = pipeline('text-generation', model=model, tokenizer=tokenizer, device='cuda:0') with torch.autocast('cuda', dtype=torch.bfloat16): print( pipe('Here is a recipe for vegan banana bread:\n', max_new_tokens=100, do_sample=True, use_cache=True)) ``` ## Model Description The architecture is a modification of a standard decoder-only transformer. The model has been modified from a standard transformer in the following ways: It uses [FlashAttention](https://arxiv.org/pdf/2205.14135.pdf) * It uses [ALiBi (Attention with Linear Biases)](https://arxiv.org/abs/2108.12409) and does not use positional embeddings * It does not use biases \| Hyperparameter \| Value \| \|----------------\|-------\| \|n_parameters \| 29.95B \| \|n_layers \| 48 \| \| n_heads \| 64 \| \| d_model \| 7168 \| \| vocab size \| 50432 \| \| sequence length \| 8192 \| ## Training Data ### Streaming Datasets Data was formatted using the MosaicML [StreamingDataset](https://github.com/mosaicml/streaming) library to host our data in object storage and efficiently stream it to our compute cluster during training. StreamingDataset obviates the need to download the whole dataset before starting training, and allows instant resumption of training from any point in the dataset. ### Data Mix The model was trained for 1T tokens on the following data mix: \| Data Source \| Number of Tokens in Source \| Proportion \| Effective Number of Tokens \| Epochs \| \|-------------\|----------------------------\|------------\|----------------------------\|--------\| \| mC4 3.1.0 - English (200+ words) \| 2417.99 B \| 33.50% \| 335 B \| 0.14 \| \| c4 - English - SemDedup 80% \| 100.42 B \| 29.90% \| 299 B \| 2.98 \| \| RedPajama - CommonCrawl \| 878.45 B \| 8.50% \| 85 B \| 0.097 \| \| The Stack - Selected Languages \| 463.78 B \| 10.00% \| 100 B \| 0.22 \| \| RedPajama - Wikipedia \| 4.87 B \| 4.00% \| 40 B \| 8.21 \| \| The Stack - Markdown \| 107.07 B \| 4.50% \| 45 B \| 0.42 \| \| Semantic Scholar ORC \| 48.95 B \| 3.30% \| 33 B \| 0.67 \| \| RedPajama - Books \| 26.02 B \| 3.00% \| 30 B \| 1.15 \| \| RedPajama - arXiv \| 28.10 B \| 1.90% \| 19 B \| 0.68 \| \| RedPajama - StackExchange \| 20.54 B \| 1.40% \| 14 B \|0.68 \| Samples for each batch were selected from one of the datasets with the probability specified above. The examples were shuffled within each dataset, and each example was constructed from as many sequences from that dataset as were necessary to fill the sequence length. To build 8k support into MPT-30B efficiently, we first pre-trained on 1T tokens using sequences that were 2k tokens long, and then trained for an additional 50B tokens using sequences that were 8k tokens long. The data was tokenized using the [EleutherAI/gpt-neox-20b](https://huggingface.co/EleutherAI/gpt-neox-20b) tokenizer. This BPE tokenizer has a number of desirable characteristics, most of which are relevant for tokenizing code: (1) It was trained on a diverse mix of data that includes code (The Pile) (2) It applies consistent space delimitation, unlike the GPT2 tokenizer which tokenizes inconsistently depending on the presence of prefix spaces (3) It contains tokens for repeated space characters, which allows superior compression of text with large amounts of repeated space characters. The model vocabulary size of 50432 was set to be a multiple of 128 (as in [MEGATRON-LM](https://arxiv.org/abs/1909.08053)). ### Training Configuration The model was trained in three stages using the [MosaicML Platform](https://www.mosaicml.com/platform): (i) First it was trained on 440 A100-40GBs with a batch size of 1760. (ii) Then, on 216 A100-40GBs with a batch size of 1728. (iii) Training was completed on 256 H100-80GBs with a batch size of 512 with 8k context length and 50B tokens. The model was trained with sharded data parallelism using [FSDP](https://pytorch.org/docs/stable/fsdp.html) and used the [LION](https://arxiv.org/abs/2302.06675) optimizer. ## Limitations and Biases _The following language is modified from [EleutherAI's GPT-NeoX-20B](https://huggingface.co/EleutherAI/gpt-neox-20b)_ MPT-30B (Base) is not intended for deployment without finetuning. It should not be used for human-facing interactions without further guardrails and user consent. MPT-30B can produce factually incorrect output, and should not be relied on to produce factually accurate information. MPT-30B was trained on various public datasets. While great efforts have been taken to clean the pretraining data, it is possible that this model could generate lewd, biased or otherwise offensive outputs. ## MosaicML Platform If you're interested in [training](https://www.mosaicml.com/training) and [deploying](https://www.mosaicml.com/inference) your own MPT or LLMs on the MosaicML Platform, [sign up here](https://forms.mosaicml.com/demo?utm_source=huggingface&utm_medium=referral&utm_campaign=mpt-30b). ## Disclaimer The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please consult an attorney before using this model for commercial purposes. ## Citation Please cite this model using the following format: ``` @online{MosaicML2023Introducing, author = {MosaicML NLP Team}, title = {Introducing MPT-30B: Raising the bar for open-source foundation models}, year = {2023}, url = {www.mosaicml.com/blog/mpt-30b}, note = {Accessed: 2023-06-22}, urldate = {2023-06-22} } ```
luhx/ppo-SnowballTarget	luhx	2023-07-12T04:56:57Z	0	0	ml-agents	[ "ml-agents", "tensorboard", "onnx", "SnowballTarget", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SnowballTarget", "region:us" ]	reinforcement-learning	2023-07-12T04:56:51Z	--- library_name: ml-agents tags: - SnowballTarget - deep-reinforcement-learning - reinforcement-learning - ML-Agents-SnowballTarget --- # ppo Agent playing SnowballTarget This is a trained model of a ppo agent playing SnowballTarget using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A short tutorial where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A longer tutorial to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent playing directly in your browser 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: luhx/ppo-SnowballTarget 3. Step 2: Select your .nn /.onnx file 4. Click on Watch the agent play 👀
localmodels/Vicuna-7B-v1.3-ggml	localmodels	2023-07-12T04:56:50Z	0	2	null	[ "arxiv:2302.13971", "arxiv:2306.05685", "region:us" ]	null	2023-07-12T04:56:50Z	--- duplicated_from: localmodels/LLM --- # Vicuna 7B v1.3 ggml From LMSYS: https://huggingface.co/lmsys/vicuna-7b-v1.3 --- ### Original llama.cpp quant methods: `q4_0, q4_1, q5_0, q5_1, q8_0` Quantized using an older version of llama.cpp and compatible with llama.cpp from May 19, commit 2d5db48. ### k-quant methods: `q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K` Quantization methods compatible with latest llama.cpp from June 6, commit 2d43387. --- ## Files \| Name \| Quant method \| Bits \| Size \| Max RAM required, no GPU offloading \| Use case \| \| ---- \| ---- \| ---- \| ---- \| ---- \| ----- \| \| vicuna-7b-v1.3.ggmlv3.q2_K.bin \| q2_K \| 2 \| 2.87 GB \| 5.37 GB \| New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. \| \| vicuna-7b-v1.3.ggmlv3.q3_K_L.bin \| q3_K_L \| 3 \| 3.60 GB \| 6.10 GB \| New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K \| \| vicuna-7b-v1.3.ggmlv3.q3_K_M.bin \| q3_K_M \| 3 \| 3.28 GB \| 5.78 GB \| New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K \| \| vicuna-7b-v1.3.ggmlv3.q3_K_S.bin \| q3_K_S \| 3 \| 2.95 GB \| 5.45 GB \| New k-quant method. Uses GGML_TYPE_Q3_K for all tensors \| \| vicuna-7b-v1.3.ggmlv3.q4_0.bin \| q4_0 \| 4 \| 3.79 GB \| 6.29 GB \| Original llama.cpp quant method, 4-bit. \| \| vicuna-7b-v1.3.ggmlv3.q4_1.bin \| q4_1 \| 4 \| 4.21 GB \| 6.71 GB \| Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. \| \| vicuna-7b-v1.3.ggmlv3.q4_K_M.bin \| q4_K_M \| 4 \| 4.08 GB \| 6.58 GB \| New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K \| \| vicuna-7b-v1.3.ggmlv3.q4_K_S.bin \| q4_K_S \| 4 \| 3.83 GB \| 6.33 GB \| New k-quant method. Uses GGML_TYPE_Q4_K for all tensors \| \| vicuna-7b-v1.3.ggmlv3.q5_0.bin \| q5_0 \| 5 \| 4.63 GB \| 7.13 GB \| Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. \| \| vicuna-7b-v1.3.ggmlv3.q5_1.bin \| q5_1 \| 5 \| 5.06 GB \| 7.56 GB \| Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. \| \| vicuna-7b-v1.3.ggmlv3.q5_K_M.bin \| q5_K_M \| 5 \| 4.78 GB \| 7.28 GB \| New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K \| \| vicuna-7b-v1.3.ggmlv3.q5_K_S.bin \| q5_K_S \| 5 \| 4.65 GB \| 7.15 GB \| New k-quant method. Uses GGML_TYPE_Q5_K for all tensors \| \| vicuna-7b-v1.3.ggmlv3.q6_K.bin \| q6_K \| 6 \| 5.53 GB \| 8.03 GB \| New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors \| \| vicuna-7b-v1.3.ggmlv3.q8_0.bin \| q8_0 \| 8 \| 7.16 GB \| 9.66 GB \| Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. \| --- # Vicuna Model Card ## Model Details Vicuna is a chat assistant trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT. - Developed by: [LMSYS](https://lmsys.org/) - Model type: An auto-regressive language model based on the transformer architecture. - License: Non-commercial license - Finetuned from model: [LLaMA](https://arxiv.org/abs/2302.13971). ### Model Sources - Repository: https://github.com/lm-sys/FastChat - Blog: https://lmsys.org/blog/2023-03-30-vicuna/ - Paper: https://arxiv.org/abs/2306.05685 - Demo: https://chat.lmsys.org/ ## Uses The primary use of Vicuna is research on large language models and chatbots. The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence. ## How to Get Started with the Model Command line interface: https://github.com/lm-sys/FastChat#vicuna-weights. APIs (OpenAI API, Huggingface API): https://github.com/lm-sys/FastChat/tree/main#api. ## Training Details Vicuna v1.3 is fine-tuned from LLaMA with supervised instruction fine-tuning. The training data is around 140K conversations collected from ShareGPT.com. See more details in the "Training Details of Vicuna Models" section in the appendix of this [paper](https://arxiv.org/pdf/2306.05685.pdf). ## Evaluation Vicuna is evaluated with standard benchmarks, human preference, and LLM-as-a-judge. See more details in this [paper](https://arxiv.org/pdf/2306.05685.pdf). ## Difference between different versions of Vicuna See [vicuna_weights_version.md](https://github.com/lm-sys/FastChat/blob/main/docs/vicuna_weights_version.md)
sumet/ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan	sumet	2023-07-12T04:53:34Z	7	1	transformers	[ "transformers", "pytorch", "audio-spectrogram-transformer", "audio-classification", "generated_from_trainer", "dataset:marsyas/gtzan", "base_model:MIT/ast-finetuned-audioset-10-10-0.4593", "base_model:finetune:MIT/ast-finetuned-audioset-10-10-0.4593", "license:bsd-3-clause", "model-index", "endpoints_compatible", "region:us" ]	audio-classification	2023-07-11T09:20:21Z	--- license: bsd-3-clause base_model: MIT/ast-finetuned-audioset-10-10-0.4593 tags: - generated_from_trainer datasets: - marsyas/gtzan metrics: - accuracy model-index: - name: ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan results: - task: name: Audio Classification type: audio-classification dataset: name: GTZAN type: marsyas/gtzan config: all split: train args: all metrics: - name: Accuracy type: accuracy value: 0.88 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan This model is a fine-tuned version of [MIT/ast-finetuned-audioset-10-10-0.4593](https://huggingface.co/MIT/ast-finetuned-audioset-10-10-0.4593) on the GTZAN dataset. It achieves the following results on the evaluation set: - Loss: 0.5086 - Accuracy: 0.88 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 2 - eval_batch_size: 2 - seed: 14 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 20 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 0.5982 \| 1.0 \| 112 \| 0.5195 \| 0.83 \| \| 0.3962 \| 2.0 \| 225 \| 0.5597 \| 0.81 \| \| 0.3143 \| 3.0 \| 337 \| 0.7567 \| 0.83 \| \| 0.0548 \| 4.0 \| 450 \| 0.5270 \| 0.86 \| \| 0.0119 \| 5.0 \| 562 \| 0.5813 \| 0.88 \| \| 0.2503 \| 6.0 \| 675 \| 0.7523 \| 0.86 \| \| 0.0008 \| 7.0 \| 787 \| 0.6239 \| 0.85 \| \| 0.0003 \| 8.0 \| 900 \| 0.4949 \| 0.9 \| \| 0.0001 \| 9.0 \| 1012 \| 0.5706 \| 0.88 \| \| 0.0003 \| 10.0 \| 1125 \| 0.4898 \| 0.92 \| \| 0.0001 \| 11.0 \| 1237 \| 0.5281 \| 0.89 \| \| 0.0001 \| 12.0 \| 1350 \| 0.5197 \| 0.88 \| \| 0.0002 \| 13.0 \| 1462 \| 0.5036 \| 0.9 \| \| 0.0 \| 14.0 \| 1575 \| 0.5362 \| 0.9 \| \| 0.0 \| 15.0 \| 1687 \| 0.5065 \| 0.89 \| \| 0.0 \| 16.0 \| 1800 \| 0.5011 \| 0.9 \| \| 0.0 \| 17.0 \| 1912 \| 0.5025 \| 0.88 \| \| 0.0 \| 18.0 \| 2025 \| 0.5027 \| 0.88 \| \| 0.0 \| 19.0 \| 2137 \| 0.5074 \| 0.88 \| \| 0.0 \| 19.91 \| 2240 \| 0.5086 \| 0.88 \| ### Framework versions - Transformers 4.31.0.dev0 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
localmodels/Vicuna-13B-v1.3-ggml	localmodels	2023-07-12T04:52:24Z	0	0	null	[ "arxiv:2302.13971", "arxiv:2306.05685", "region:us" ]	null	2023-07-12T04:52:24Z	--- duplicated_from: localmodels/LLM --- # Vicuna 13B v1.3 ggml From LMSYS: https://huggingface.co/lmsys/vicuna-13b-v1.3 --- ### Original llama.cpp quant methods: `q4_0, q4_1, q5_0, q5_1, q8_0` Quantized using an older version of llama.cpp and compatible with llama.cpp from May 19, commit 2d5db48. ### k-quant methods: `q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K` Quantization methods compatible with latest llama.cpp from June 6, commit 2d43387. --- ## Files \| Name \| Quant method \| Bits \| Size \| Max RAM required, no GPU offloading \| Use case \| \| ---- \| ---- \| ---- \| ---- \| ---- \| ----- \| \| vicuna-13b-v1.3.0.ggmlv3.q2_K.bin \| q2_K \| 2 \| 5.51 GB \| 8.01 GB \| New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. \| \| vicuna-13b-v1.3.0.ggmlv3.q3_K_L.bin \| q3_K_L \| 3 \| 6.93 GB \| 9.43 GB \| New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K \| \| vicuna-13b-v1.3.0.ggmlv3.q3_K_M.bin \| q3_K_M \| 3 \| 6.31 GB \| 8.81 GB \| New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K \| \| vicuna-13b-v1.3.0.ggmlv3.q3_K_S.bin \| q3_K_S \| 3 \| 5.66 GB \| 8.16 GB \| New k-quant method. Uses GGML_TYPE_Q3_K for all tensors \| \| vicuna-13b-v1.3.0.ggmlv3.q4_0.bin \| q4_0 \| 4 \| 7.32 GB \| 9.82 GB \| Original llama.cpp quant method, 4-bit. \| \| vicuna-13b-v1.3.0.ggmlv3.q4_1.bin \| q4_1 \| 4 \| 8.14 GB \| 10.64 GB \| Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. \| \| vicuna-13b-v1.3.0.ggmlv3.q4_K_M.bin \| q4_K_M \| 4 \| 7.87 GB \| 10.37 GB \| New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K \| \| vicuna-13b-v1.3.0.ggmlv3.q4_K_S.bin \| q4_K_S \| 4 \| 7.37 GB \| 9.87 GB \| New k-quant method. Uses GGML_TYPE_Q4_K for all tensors \| \| vicuna-13b-v1.3.0.ggmlv3.q5_0.bin \| q5_0 \| 5 \| 8.95 GB \| 11.45 GB \| Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. \| \| vicuna-13b-v1.3.0.ggmlv3.q5_1.bin \| q5_1 \| 5 \| 9.76 GB \| 12.26 GB \| Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. \| \| vicuna-13b-v1.3.0.ggmlv3.q5_K_M.bin \| q5_K_M \| 5 \| 9.23 GB \| 11.73 GB \| New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K \| \| vicuna-13b-v1.3.0.ggmlv3.q5_K_S.bin \| q5_K_S \| 5 \| 8.97 GB \| 11.47 GB \| New k-quant method. Uses GGML_TYPE_Q5_K for all tensors \| \| vicuna-13b-v1.3.0.ggmlv3.q6_K.bin \| q6_K \| 6 \| 10.68 GB \| 13.18 GB \| New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors \| \| vicuna-13b-v1.3.0.ggmlv3.q8_0.bin \| q8_0 \| 8 \| 13.83 GB \| 16.33 GB \| Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. \| --- # Vicuna Model Card ## Model Details Vicuna is a chat assistant trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT. - Developed by: [LMSYS](https://lmsys.org/) - Model type: An auto-regressive language model based on the transformer architecture. - License: Non-commercial license - Finetuned from model: [LLaMA](https://arxiv.org/abs/2302.13971). ### Model Sources - Repository: https://github.com/lm-sys/FastChat - Blog: https://lmsys.org/blog/2023-03-30-vicuna/ - Paper: https://arxiv.org/abs/2306.05685 - Demo: https://chat.lmsys.org/ ## Uses The primary use of Vicuna is research on large language models and chatbots. The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence. ## How to Get Started with the Model Command line interface: https://github.com/lm-sys/FastChat#vicuna-weights. APIs (OpenAI API, Huggingface API): https://github.com/lm-sys/FastChat/tree/main#api. ## Training Details Vicuna v1.3 is fine-tuned from LLaMA with supervised instruction fine-tuning. The training data is around 140K conversations collected from ShareGPT.com. See more details in the "Training Details of Vicuna Models" section in the appendix of this [paper](https://arxiv.org/pdf/2306.05685.pdf). ## Evaluation Vicuna is evaluated with standard benchmarks, human preference, and LLM-as-a-judge. See more details in this [paper](https://arxiv.org/pdf/2306.05685.pdf). ## Difference between different versions of Vicuna See [vicuna_weights_version.md](https://github.com/lm-sys/FastChat/blob/main/docs/vicuna_weights_version.md)
Ayushhh07/Income	Ayushhh07	2023-07-12T04:50:01Z	0	0	asteroid	[ "asteroid", "chemistry", "biology", "legal", "finance", "music", "text-classification", "en", "aa", "ab", "af", "dataset:Open-Orca/OpenOrca", "license:creativeml-openrail-m", "region:us" ]	text-classification	2023-07-12T04:48:44Z	--- license: creativeml-openrail-m datasets: - Open-Orca/OpenOrca language: - en - aa - ab - af metrics: - accuracy - character library_name: asteroid pipeline_tag: text-classification tags: - chemistry - biology - legal - finance - music ---
happyduck/alcafa_5.8b_100_bum	happyduck	2023-07-12T04:43:17Z	0	0	peft	[ "peft", "region:us" ]	null	2023-07-11T00:52:37Z	--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.4.0.dev0
hungngo04/cluster_to_text_t5_base_test	hungngo04	2023-07-12T04:42:25Z	3	0	transformers	[ "transformers", "pytorch", "tensorboard", "t5", "text2text-generation", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text2text-generation	2023-07-12T03:52:06Z	--- license: apache-2.0 tags: - generated_from_trainer metrics: - bleu model-index: - name: cluster_to_text_t5_base_test results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # cluster_to_text_t5_base_test This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.7184 - Bleu: 12.1051 - Gen Len: 10.6659 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Bleu \| Gen Len \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:-------:\|:-------:\| \| 2.4089 \| 1.0 \| 4678 \| 2.1095 \| 3.8133 \| 11.5338 \| \| 2.1256 \| 2.0 \| 9356 \| 1.8032 \| 9.8148 \| 10.7901 \| \| 2.0173 \| 3.0 \| 14034 \| 1.7184 \| 12.1051 \| 10.6659 \| ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
Vezora/Mini_Orca_7b_v2_2048_Lora_adapter	Vezora	2023-07-12T04:29:49Z	0	0	null	[ "license:apache-2.0", "region:us" ]	null	2023-07-12T03:53:17Z	--- license: apache-2.0 --- 2 epochs 92 hours of training on a undervolted 3090 pulling 250 watts. My system configuration was getting 13.25 it/s and slowly dropped to 13.04 it/s at 2 epochs. Dataset used is uncencored and filtered of Psmathur's wizard orca 72k instructions, ported into a alpaca chat format, and removed all "Input" strings. Trained on only instruction and output. Preforms remarkably well works with the blokes gptq mini orca v2 gptq and allows the model to output 2048 tokens. This adapter was trained to test how lora training could be used to expand context window with less compute. The original model trained by "psmathur" was trained with "8x A100(80G) GPUs for around 13 Hours for cost of $195". I'm hoping the bloke can merge this with the orignal model and upload a gptq version for everyone.
NorgNM/Realistic-Visions_v4.0	NorgNM	2023-07-12T04:26:48Z	0	0	null	[ "license:mit", "region:us" ]	null	2023-07-10T17:59:33Z	--- title: Dreambooth Training emoji: ☁️ colorFrom: pink colorTo: red sdk: gradio sdk_version: 3.16.2 app_file: app.py pinned: false suggested_hardware: t4-small license: mit duplicated_from: multimodalart/dreambooth-training --- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
elasticdavid/qlora-koalpaca-polyglot-12.8b-fasoo-brochure-153steps	elasticdavid	2023-07-12T04:23:14Z	0	0	peft	[ "peft", "region:us" ]	null	2023-07-12T04:23:05Z	--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.4.0.dev0
assembleteams/curiouspi	assembleteams	2023-07-12T04:01:19Z	0	1	adapter-transformers	[ "adapter-transformers", "research", "science", "development", "energy", "climate", "water", "food systems", "transit", "supplychain", "space", "deepsea", "prototypes", "planning", "infrastructure", "systems", "assessment", "resourceplanning", "conversational", "en", "te", "es", "fr", "de", "hi", "ur", "ru", "pt", "gu", "he", "pa", "dataset:tiiuae/falcon-refinedweb", "dataset:Open-Orca/OpenOrca", "dataset:GAIR/lima", "license:apache-2.0", "region:us" ]	text-generation	2023-07-12T02:48:23Z	--- license: apache-2.0 datasets: - tiiuae/falcon-refinedweb - Open-Orca/OpenOrca - GAIR/lima language: - en - te - es - fr - de - hi - ur - ru - pt - gu - he - pa metrics: - accuracy - bertscore - brier_score - code_eval - charcut_mt - character library_name: adapter-transformers pipeline_tag: conversational tags: - research - science - development - energy - climate - water - food systems - transit - supplychain - space - deepsea - prototypes - planning - infrastructure - systems - assessment - resourceplanning ---
sbaner24/vit-base-patch16-224-Trial006-007-008-YEL_STEM4	sbaner24	2023-07-12T03:30:48Z	5	0	transformers	[ "transformers", "pytorch", "vit", "image-classification", "generated_from_trainer", "dataset:imagefolder", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2023-07-12T02:53:44Z	--- license: apache-2.0 tags: - generated_from_trainer datasets: - imagefolder metrics: - accuracy model-index: - name: vit-base-patch16-224-Trial006-007-008-YEL_STEM4 results: - task: name: Image Classification type: image-classification dataset: name: imagefolder type: imagefolder config: default split: train args: default metrics: - name: Accuracy type: accuracy value: 0.9354838709677419 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # vit-base-patch16-224-Trial006-007-008-YEL_STEM4 This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 0.1729 - Accuracy: 0.9355 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 60 - eval_batch_size: 60 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 240 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 50 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 0.6572 \| 1.0 \| 6 \| 0.6719 \| 0.5677 \| \| 0.6279 \| 2.0 \| 12 \| 0.6436 \| 0.6516 \| \| 0.5282 \| 3.0 \| 18 \| 0.5677 \| 0.7871 \| \| 0.5405 \| 4.0 \| 24 \| 0.4718 \| 0.8258 \| \| 0.5276 \| 5.0 \| 30 \| 0.4959 \| 0.7419 \| \| 0.412 \| 6.0 \| 36 \| 0.3081 \| 0.8581 \| \| 0.3011 \| 7.0 \| 42 \| 0.2542 \| 0.8839 \| \| 0.3329 \| 8.0 \| 48 \| 0.2350 \| 0.8774 \| \| 0.4478 \| 9.0 \| 54 \| 0.1743 \| 0.9290 \| \| 0.268 \| 10.0 \| 60 \| 0.1708 \| 0.9161 \| \| 0.2177 \| 11.0 \| 66 \| 0.1729 \| 0.9355 \| \| 0.2675 \| 12.0 \| 72 \| 0.1913 \| 0.8968 \| \| 0.4784 \| 13.0 \| 78 \| 0.1826 \| 0.9032 \| \| 0.2456 \| 14.0 \| 84 \| 0.1774 \| 0.9032 \| \| 0.6229 \| 15.0 \| 90 \| 0.2196 \| 0.8968 \| \| 0.2561 \| 16.0 \| 96 \| 0.1823 \| 0.9226 \| \| 0.3785 \| 17.0 \| 102 \| 0.1770 \| 0.9032 \| \| 0.2334 \| 18.0 \| 108 \| 0.2056 \| 0.8903 \| \| 0.1904 \| 19.0 \| 114 \| 0.1564 \| 0.9097 \| \| 0.2256 \| 20.0 \| 120 \| 0.1407 \| 0.9226 \| \| 0.2547 \| 21.0 \| 126 \| 0.1552 \| 0.9032 \| \| 0.3468 \| 22.0 \| 132 \| 0.1819 \| 0.8968 \| \| 0.4116 \| 23.0 \| 138 \| 0.1537 \| 0.9290 \| \| 0.3689 \| 24.0 \| 144 \| 0.1645 \| 0.9097 \| \| 0.3541 \| 25.0 \| 150 \| 0.1527 \| 0.9290 \| \| 0.2498 \| 26.0 \| 156 \| 0.1670 \| 0.9161 \| \| 0.3625 \| 27.0 \| 162 \| 0.1522 \| 0.9161 \| \| 0.2463 \| 28.0 \| 168 \| 0.1552 \| 0.9226 \| \| 0.3447 \| 29.0 \| 174 \| 0.1510 \| 0.9097 \| \| 0.205 \| 30.0 \| 180 \| 0.1924 \| 0.9032 \| \| 0.2023 \| 31.0 \| 186 \| 0.1376 \| 0.9355 \| \| 0.3617 \| 32.0 \| 192 \| 0.1518 \| 0.9097 \| \| 0.3515 \| 33.0 \| 198 \| 0.1473 \| 0.9097 \| \| 0.1927 \| 34.0 \| 204 \| 0.1544 \| 0.9097 \| \| 0.4567 \| 35.0 \| 210 \| 0.1528 \| 0.9097 \| \| 0.3113 \| 36.0 \| 216 \| 0.1510 \| 0.9226 \| \| 0.3475 \| 37.0 \| 222 \| 0.1594 \| 0.9161 \| \| 0.1889 \| 38.0 \| 228 \| 0.1448 \| 0.9290 \| \| 0.1979 \| 39.0 \| 234 \| 0.1533 \| 0.9226 \| \| 0.3578 \| 40.0 \| 240 \| 0.1627 \| 0.9097 \| \| 0.2004 \| 41.0 \| 246 \| 0.1620 \| 0.9161 \| \| 0.3567 \| 42.0 \| 252 \| 0.1475 \| 0.9226 \| \| 0.192 \| 43.0 \| 258 \| 0.1504 \| 0.9032 \| \| 0.1872 \| 44.0 \| 264 \| 0.1535 \| 0.9097 \| \| 0.2079 \| 45.0 \| 270 \| 0.1490 \| 0.9161 \| \| 0.1503 \| 46.0 \| 276 \| 0.1459 \| 0.9161 \| \| 0.169 \| 47.0 \| 282 \| 0.1506 \| 0.8968 \| \| 0.1884 \| 48.0 \| 288 \| 0.1556 \| 0.8968 \| \| 0.1638 \| 49.0 \| 294 \| 0.1573 \| 0.8968 \| \| 0.1921 \| 50.0 \| 300 \| 0.1570 \| 0.8968 \| ### Framework versions - Transformers 4.30.0.dev0 - Pytorch 1.12.1 - Datasets 2.12.0 - Tokenizers 0.13.1
ALM-AHME/swinv2-large-patch4-window12to16-192to256-22kto1k-ft-finetuned-LungCancer-LC25000-AH-40-30-30	ALM-AHME	2023-07-12T03:29:09Z	150	1	transformers	[ "transformers", "pytorch", "tensorboard", "swinv2", "image-classification", "generated_from_trainer", "dataset:imagefolder", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2023-07-11T23:28:32Z	--- license: apache-2.0 tags: - generated_from_trainer datasets: - imagefolder metrics: - accuracy model-index: - name: swinv2-large-patch4-window12to16-192to256-22kto1k-ft-finetuned-LungCancer-LC25000-AH-40-30-30 results: - task: name: Image Classification type: image-classification dataset: name: imagefolder type: imagefolder config: Augmented-Final split: train args: Augmented-Final metrics: - name: Accuracy type: accuracy value: 0.9869324473975637 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # swinv2-large-patch4-window12to16-192to256-22kto1k-ft-finetuned-LungCancer-LC25000-AH-40-30-30 This model is a fine-tuned version of [microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft](https://huggingface.co/microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 0.0418 - Accuracy: 0.9869 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.5 - num_epochs: 5 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 0.3299 \| 1.0 \| 187 \| 0.2118 \| 0.9218 \| \| 0.5922 \| 2.0 \| 374 \| 0.3206 \| 0.8629 \| \| 0.1763 \| 3.0 \| 561 \| 0.2447 \| 0.9127 \| \| 0.1351 \| 4.0 \| 749 \| 0.1028 \| 0.9564 \| \| 0.142 \| 4.99 \| 935 \| 0.0418 \| 0.9869 \| ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
macapa/emotion-text-better	macapa	2023-07-12T03:01:46Z	0	0	fastai	[ "fastai", "region:us" ]	null	2023-07-12T03:01:41Z	--- tags: - fastai --- # Amazing! 🥳 Congratulations on hosting your fastai model on the Hugging Face Hub! # Some next steps 1. Fill out this model card with more information (see the template below and the [documentation here](https://huggingface.co/docs/hub/model-repos))! 2. Create a demo in Gradio or Streamlit using 🤗 Spaces ([documentation here](https://huggingface.co/docs/hub/spaces)). 3. Join the fastai community on the [Fastai Discord](https://discord.com/invite/YKrxeNn)! Greetings fellow fastlearner 🤝! Don't forget to delete this content from your model card. --- # Model card ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed
yashgharat/Reinforce-PixelCopter	yashgharat	2023-07-12T02:55:43Z	0	0	null	[ "Pixelcopter-PLE-v0", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]	reinforcement-learning	2023-07-07T14:17:14Z	--- tags: - Pixelcopter-PLE-v0 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: Reinforce-PixelCopter results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Pixelcopter-PLE-v0 type: Pixelcopter-PLE-v0 metrics: - type: mean_reward value: 16.30 +/- 12.98 name: mean_reward verified: false --- # Reinforce Agent playing Pixelcopter-PLE-v0 This is a trained model of a Reinforce agent playing Pixelcopter-PLE-v0 . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
Suechun/pawsx-en-loraWeight	Suechun	2023-07-12T02:47:19Z	0	0	transformers	[ "transformers", "en", "ja", "dataset:paws-x", "license:other", "endpoints_compatible", "region:us" ]	null	2023-07-10T14:29:27Z	--- license: other datasets: - paws-x language: - en - ja library_name: transformers ---
sbaner24/vit-base-patch16-224-Trial006-007-008-YEL_STEM3	sbaner24	2023-07-12T02:46:51Z	8	0	transformers	[ "transformers", "pytorch", "vit", "image-classification", "generated_from_trainer", "dataset:imagefolder", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2023-07-12T02:09:06Z	--- license: apache-2.0 tags: - generated_from_trainer datasets: - imagefolder metrics: - accuracy model-index: - name: vit-base-patch16-224-Trial006-007-008-YEL_STEM3 results: - task: name: Image Classification type: image-classification dataset: name: imagefolder type: imagefolder config: default split: train args: default metrics: - name: Accuracy type: accuracy value: 0.9240506329113924 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # vit-base-patch16-224-Trial006-007-008-YEL_STEM3 This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 0.1618 - Accuracy: 0.9241 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 60 - eval_batch_size: 60 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 240 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 50 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 0.7035 \| 1.0 \| 6 \| 0.6557 \| 0.6203 \| \| 0.6168 \| 2.0 \| 12 \| 0.5788 \| 0.7215 \| \| 0.5412 \| 3.0 \| 18 \| 0.5005 \| 0.7785 \| \| 0.496 \| 4.0 \| 24 \| 0.4946 \| 0.7722 \| \| 0.4024 \| 5.0 \| 30 \| 0.4057 \| 0.8165 \| \| 0.4098 \| 6.0 \| 36 \| 0.3076 \| 0.8544 \| \| 0.3645 \| 7.0 \| 42 \| 0.3250 \| 0.8418 \| \| 0.276 \| 8.0 \| 48 \| 0.2206 \| 0.8924 \| \| 0.3358 \| 9.0 \| 54 \| 0.2100 \| 0.8987 \| \| 0.3386 \| 10.0 \| 60 \| 0.1618 \| 0.9241 \| \| 0.2778 \| 11.0 \| 66 \| 0.1609 \| 0.9177 \| \| 0.25 \| 12.0 \| 72 \| 0.1581 \| 0.9114 \| \| 0.2914 \| 13.0 \| 78 \| 0.1663 \| 0.9114 \| \| 0.2273 \| 14.0 \| 84 \| 0.1525 \| 0.9177 \| \| 0.2694 \| 15.0 \| 90 \| 0.1708 \| 0.9051 \| \| 0.2745 \| 16.0 \| 96 \| 0.2364 \| 0.8734 \| \| 0.2809 \| 17.0 \| 102 \| 0.1976 \| 0.8608 \| \| 0.2368 \| 18.0 \| 108 \| 0.1517 \| 0.9114 \| \| 0.328 \| 19.0 \| 114 \| 0.2454 \| 0.8671 \| \| 0.2571 \| 20.0 \| 120 \| 0.1482 \| 0.9114 \| \| 0.2996 \| 21.0 \| 126 \| 0.1629 \| 0.8987 \| \| 0.266 \| 22.0 \| 132 \| 0.1360 \| 0.9114 \| \| 0.2323 \| 23.0 \| 138 \| 0.1427 \| 0.9114 \| \| 0.2285 \| 24.0 \| 144 \| 0.1683 \| 0.9051 \| \| 0.2566 \| 25.0 \| 150 \| 0.1442 \| 0.9114 \| \| 0.2509 \| 26.0 \| 156 \| 0.1595 \| 0.9114 \| \| 0.2337 \| 27.0 \| 162 \| 0.1291 \| 0.9177 \| \| 0.2203 \| 28.0 \| 168 \| 0.1302 \| 0.8987 \| \| 0.2409 \| 29.0 \| 174 \| 0.1274 \| 0.9114 \| \| 0.2256 \| 30.0 \| 180 \| 0.1272 \| 0.8987 \| \| 0.2157 \| 31.0 \| 186 \| 0.1289 \| 0.9177 \| \| 0.2168 \| 32.0 \| 192 \| 0.1267 \| 0.9114 \| \| 0.2426 \| 33.0 \| 198 \| 0.1438 \| 0.8987 \| \| 0.2404 \| 34.0 \| 204 \| 0.1388 \| 0.8987 \| \| 0.2218 \| 35.0 \| 210 \| 0.1243 \| 0.9241 \| \| 0.3068 \| 36.0 \| 216 \| 0.1268 \| 0.9241 \| \| 0.1721 \| 37.0 \| 222 \| 0.1477 \| 0.8987 \| \| 0.2201 \| 38.0 \| 228 \| 0.1545 \| 0.8987 \| \| 0.2581 \| 39.0 \| 234 \| 0.1700 \| 0.8987 \| \| 0.213 \| 40.0 \| 240 \| 0.1254 \| 0.9114 \| \| 0.2953 \| 41.0 \| 246 \| 0.1237 \| 0.9114 \| \| 0.2564 \| 42.0 \| 252 \| 0.1472 \| 0.9051 \| \| 0.249 \| 43.0 \| 258 \| 0.1409 \| 0.9051 \| \| 0.2372 \| 44.0 \| 264 \| 0.1495 \| 0.9114 \| \| 0.2541 \| 45.0 \| 270 \| 0.1412 \| 0.9051 \| \| 0.1997 \| 46.0 \| 276 \| 0.1308 \| 0.9114 \| \| 0.2381 \| 47.0 \| 282 \| 0.1253 \| 0.9177 \| \| 0.2623 \| 48.0 \| 288 \| 0.1267 \| 0.9051 \| \| 0.1855 \| 49.0 \| 294 \| 0.1285 \| 0.9051 \| \| 0.1877 \| 50.0 \| 300 \| 0.1289 \| 0.9051 \| ### Framework versions - Transformers 4.30.0.dev0 - Pytorch 1.12.1 - Datasets 2.12.0 - Tokenizers 0.13.1
Djdheg7272gshd/Fufufh	Djdheg7272gshd	2023-07-12T02:36:43Z	0	0	null	[ "license:bigscience-openrail-m", "region:us" ]	null	2023-07-12T02:36:43Z	--- license: bigscience-openrail-m ---
uribah/my_awesome_model	uribah	2023-07-12T02:33:01Z	61	0	transformers	[ "transformers", "tf", "distilbert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2023-07-08T18:44:13Z	--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: uribah/my_awesome_model results: [] --- <!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. --> # uribah/my_awesome_model This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 0.1206 - Validation Loss: 0.2358 - Train Accuracy: 0.9409 - Epoch: 4 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 565, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results \| Train Loss \| Validation Loss \| Train Accuracy \| Epoch \| \|:----------:\|:---------------:\|:--------------:\|:-----:\| \| 0.5194 \| 0.2501 \| 0.9310 \| 0 \| \| 0.2587 \| 0.2353 \| 0.9360 \| 1 \| \| 0.1844 \| 0.2339 \| 0.9360 \| 2 \| \| 0.1442 \| 0.2295 \| 0.9409 \| 3 \| \| 0.1206 \| 0.2358 \| 0.9409 \| 4 \| ### Framework versions - Transformers 4.30.2 - TensorFlow 2.12.0 - Datasets 2.13.1 - Tokenizers 0.13.3
skywalker7/dqn-SpaceInvadersNoFrameskip-v4	skywalker7	2023-07-12T02:13:15Z	2	0	stable-baselines3	[ "stable-baselines3", "SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2023-07-12T02:12:36Z	--- library_name: stable-baselines3 tags: - SpaceInvadersNoFrameskip-v4 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: DQN results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: SpaceInvadersNoFrameskip-v4 type: SpaceInvadersNoFrameskip-v4 metrics: - type: mean_reward value: 789.50 +/- 166.17 name: mean_reward verified: false --- # DQN Agent playing SpaceInvadersNoFrameskip-v4 This is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3) and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo). The RL Zoo is a training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included. ## Usage (with SB3 RL Zoo) RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/> SB3: https://github.com/DLR-RM/stable-baselines3<br/> SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib Install the RL Zoo (with SB3 and SB3-Contrib): ```bash pip install rl_zoo3 ``` ``` # Download model and save it into the logs/ folder python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga skywalker7 -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do: ``` python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga skywalker7 -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` ## Training (with the RL Zoo) ``` python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ # Upload the model and generate video (when possible) python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga skywalker7 ``` ## Hyperparameters ```python OrderedDict([('batch_size', 32), ('buffer_size', 100000), ('env_wrapper', ['stable_baselines3.common.atari_wrappers.AtariWrapper']), ('exploration_final_eps', 0.01), ('exploration_fraction', 0.1), ('frame_stack', 4), ('gradient_steps', 1), ('learning_rate', 0.0001), ('learning_starts', 100000), ('n_timesteps', 1000000), ('optimize_memory_usage', False), ('policy', 'CnnPolicy'), ('target_update_interval', 1000), ('train_freq', 4), ('normalize', False)]) ``` # Environment Arguments ```python {'render_mode': 'rgb_array'} ```
jordyvl/vit-tiny_rvl_cdip_100_examples_per_class_kd_NKD_t1.0_g1.5	jordyvl	2023-07-12T02:13:05Z	163	0	transformers	[ "transformers", "pytorch", "vit", "image-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2023-07-12T01:35:01Z	--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: vit-tiny_rvl_cdip_100_examples_per_class_kd_NKD_t1.0_g1.5 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # vit-tiny_rvl_cdip_100_examples_per_class_kd_NKD_t1.0_g1.5 This model is a fine-tuned version of [WinKawaks/vit-tiny-patch16-224](https://huggingface.co/WinKawaks/vit-tiny-patch16-224) on the None dataset. It achieves the following results on the evaluation set: - Loss: 5.4262 - Accuracy: 0.535 - Brier Loss: 0.6080 - Nll: 2.4569 - F1 Micro: 0.535 - F1 Macro: 0.5345 - Ece: 0.2120 - Aurc: 0.2105 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| Brier Loss \| Nll \| F1 Micro \| F1 Macro \| Ece \| Aurc \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:----------:\|:------:\|:--------:\|:--------:\|:------:\|:------:\| \| No log \| 1.0 \| 7 \| 8.7328 \| 0.0375 \| 1.0712 \| 7.1959 \| 0.0375 \| 0.0284 \| 0.2770 \| 0.9564 \| \| No log \| 2.0 \| 14 \| 6.6754 \| 0.0725 \| 0.9650 \| 6.2033 \| 0.0725 \| 0.0442 \| 0.1890 \| 0.9239 \| \| No log \| 3.0 \| 21 \| 6.2399 \| 0.1525 \| 0.9213 \| 5.6927 \| 0.1525 \| 0.1339 \| 0.1647 \| 0.8105 \| \| No log \| 4.0 \| 28 \| 5.9557 \| 0.2125 \| 0.8771 \| 4.2773 \| 0.2125 \| 0.1952 \| 0.1637 \| 0.6347 \| \| No log \| 5.0 \| 35 \| 5.5957 \| 0.3275 \| 0.7962 \| 3.1599 \| 0.3275 \| 0.3087 \| 0.1928 \| 0.4595 \| \| No log \| 6.0 \| 42 \| 5.4573 \| 0.4075 \| 0.7283 \| 3.0860 \| 0.4075 \| 0.3732 \| 0.1803 \| 0.3610 \| \| No log \| 7.0 \| 49 \| 5.3445 \| 0.43 \| 0.7150 \| 2.9840 \| 0.4300 \| 0.4112 \| 0.2071 \| 0.3498 \| \| No log \| 8.0 \| 56 \| 5.2986 \| 0.445 \| 0.6860 \| 2.9281 \| 0.445 \| 0.4327 \| 0.1891 \| 0.3159 \| \| No log \| 9.0 \| 63 \| 5.2567 \| 0.465 \| 0.6608 \| 3.0783 \| 0.465 \| 0.4494 \| 0.1835 \| 0.2885 \| \| No log \| 10.0 \| 70 \| 5.4317 \| 0.4425 \| 0.6752 \| 2.9067 \| 0.4425 \| 0.4477 \| 0.1836 \| 0.3209 \| \| No log \| 11.0 \| 77 \| 5.2073 \| 0.4825 \| 0.6342 \| 2.7960 \| 0.4825 \| 0.4664 \| 0.1731 \| 0.2708 \| \| No log \| 12.0 \| 84 \| 5.2094 \| 0.51 \| 0.6150 \| 2.8886 \| 0.51 \| 0.4767 \| 0.1463 \| 0.2459 \| \| No log \| 13.0 \| 91 \| 5.2379 \| 0.4975 \| 0.6135 \| 2.7446 \| 0.4975 \| 0.4819 \| 0.1702 \| 0.2436 \| \| No log \| 14.0 \| 98 \| 5.2716 \| 0.505 \| 0.6123 \| 2.7888 \| 0.505 \| 0.4962 \| 0.1595 \| 0.2496 \| \| No log \| 15.0 \| 105 \| 5.2410 \| 0.5125 \| 0.6090 \| 2.6474 \| 0.5125 \| 0.5144 \| 0.1659 \| 0.2451 \| \| No log \| 16.0 \| 112 \| 5.2764 \| 0.54 \| 0.6063 \| 2.7700 \| 0.54 \| 0.5316 \| 0.1634 \| 0.2383 \| \| No log \| 17.0 \| 119 \| 5.2652 \| 0.5275 \| 0.6027 \| 2.7934 \| 0.5275 \| 0.5171 \| 0.1800 \| 0.2326 \| \| No log \| 18.0 \| 126 \| 5.2145 \| 0.54 \| 0.5944 \| 2.6456 \| 0.54 \| 0.5350 \| 0.1548 \| 0.2323 \| \| No log \| 19.0 \| 133 \| 5.2611 \| 0.5175 \| 0.6096 \| 2.5302 \| 0.5175 \| 0.5273 \| 0.1709 \| 0.2435 \| \| No log \| 20.0 \| 140 \| 5.3536 \| 0.52 \| 0.6110 \| 2.6530 \| 0.52 \| 0.5229 \| 0.1619 \| 0.2359 \| \| No log \| 21.0 \| 147 \| 5.3020 \| 0.5125 \| 0.6060 \| 2.7184 \| 0.5125 \| 0.5070 \| 0.1724 \| 0.2398 \| \| No log \| 22.0 \| 154 \| 5.2107 \| 0.5275 \| 0.5926 \| 2.4436 \| 0.5275 \| 0.5242 \| 0.1618 \| 0.2255 \| \| No log \| 23.0 \| 161 \| 5.2723 \| 0.53 \| 0.5953 \| 2.7008 \| 0.53 \| 0.5209 \| 0.1698 \| 0.2253 \| \| No log \| 24.0 \| 168 \| 5.1615 \| 0.5325 \| 0.5875 \| 2.4753 \| 0.5325 \| 0.5254 \| 0.1699 \| 0.2247 \| \| No log \| 25.0 \| 175 \| 5.1795 \| 0.5375 \| 0.5825 \| 2.6856 \| 0.5375 \| 0.5316 \| 0.1781 \| 0.2144 \| \| No log \| 26.0 \| 182 \| 5.2340 \| 0.54 \| 0.5937 \| 2.6542 \| 0.54 \| 0.5271 \| 0.1778 \| 0.2215 \| \| No log \| 27.0 \| 189 \| 5.2197 \| 0.5375 \| 0.5831 \| 2.4800 \| 0.5375 \| 0.5366 \| 0.1666 \| 0.2119 \| \| No log \| 28.0 \| 196 \| 5.2345 \| 0.5275 \| 0.6105 \| 2.6475 \| 0.5275 \| 0.5247 \| 0.1919 \| 0.2338 \| \| No log \| 29.0 \| 203 \| 5.2050 \| 0.5475 \| 0.5917 \| 2.6350 \| 0.5475 \| 0.5531 \| 0.1753 \| 0.2251 \| \| No log \| 30.0 \| 210 \| 5.1753 \| 0.5425 \| 0.5891 \| 2.6472 \| 0.5425 \| 0.5282 \| 0.1831 \| 0.2215 \| \| No log \| 31.0 \| 217 \| 5.2349 \| 0.535 \| 0.5946 \| 2.5653 \| 0.535 \| 0.5257 \| 0.1617 \| 0.2186 \| \| No log \| 32.0 \| 224 \| 5.1497 \| 0.545 \| 0.5778 \| 2.6174 \| 0.545 \| 0.5425 \| 0.1716 \| 0.2138 \| \| No log \| 33.0 \| 231 \| 5.1688 \| 0.5175 \| 0.5899 \| 2.5079 \| 0.5175 \| 0.5149 \| 0.1624 \| 0.2159 \| \| No log \| 34.0 \| 238 \| 5.2269 \| 0.53 \| 0.5961 \| 2.5188 \| 0.53 \| 0.5326 \| 0.1746 \| 0.2206 \| \| No log \| 35.0 \| 245 \| 5.1477 \| 0.5325 \| 0.5867 \| 2.4762 \| 0.5325 \| 0.5369 \| 0.1728 \| 0.2176 \| \| No log \| 36.0 \| 252 \| 5.2229 \| 0.5375 \| 0.5838 \| 2.4397 \| 0.5375 \| 0.5386 \| 0.1693 \| 0.2167 \| \| No log \| 37.0 \| 259 \| 5.1578 \| 0.535 \| 0.5802 \| 2.5103 \| 0.535 \| 0.5286 \| 0.1755 \| 0.2124 \| \| No log \| 38.0 \| 266 \| 5.1405 \| 0.535 \| 0.5979 \| 2.5852 \| 0.535 \| 0.5346 \| 0.1913 \| 0.2268 \| \| No log \| 39.0 \| 273 \| 5.1236 \| 0.535 \| 0.5844 \| 2.4851 \| 0.535 \| 0.5378 \| 0.1729 \| 0.2168 \| \| No log \| 40.0 \| 280 \| 5.0813 \| 0.5475 \| 0.5757 \| 2.4305 \| 0.5475 \| 0.5434 \| 0.1781 \| 0.2091 \| \| No log \| 41.0 \| 287 \| 5.1844 \| 0.535 \| 0.5888 \| 2.4730 \| 0.535 \| 0.5306 \| 0.1707 \| 0.2159 \| \| No log \| 42.0 \| 294 \| 5.1468 \| 0.53 \| 0.5926 \| 2.4866 \| 0.53 \| 0.5316 \| 0.1776 \| 0.2200 \| \| No log \| 43.0 \| 301 \| 5.1469 \| 0.53 \| 0.5837 \| 2.5769 \| 0.53 \| 0.5252 \| 0.1805 \| 0.2168 \| \| No log \| 44.0 \| 308 \| 5.2168 \| 0.54 \| 0.5955 \| 2.5216 \| 0.54 \| 0.5419 \| 0.1689 \| 0.2226 \| \| No log \| 45.0 \| 315 \| 5.1395 \| 0.525 \| 0.5861 \| 2.4328 \| 0.525 \| 0.5293 \| 0.2006 \| 0.2180 \| \| No log \| 46.0 \| 322 \| 5.1163 \| 0.5425 \| 0.5822 \| 2.4635 \| 0.5425 \| 0.5416 \| 0.1937 \| 0.2106 \| \| No log \| 47.0 \| 329 \| 5.1227 \| 0.5475 \| 0.5786 \| 2.5198 \| 0.5475 \| 0.5489 \| 0.1580 \| 0.2111 \| \| No log \| 48.0 \| 336 \| 5.1134 \| 0.5375 \| 0.5839 \| 2.5239 \| 0.5375 \| 0.5318 \| 0.1832 \| 0.2071 \| \| No log \| 49.0 \| 343 \| 5.1907 \| 0.5375 \| 0.5913 \| 2.5012 \| 0.5375 \| 0.5334 \| 0.1853 \| 0.2145 \| \| No log \| 50.0 \| 350 \| 5.1364 \| 0.5375 \| 0.5875 \| 2.4105 \| 0.5375 \| 0.5415 \| 0.1857 \| 0.2121 \| \| No log \| 51.0 \| 357 \| 5.1739 \| 0.5425 \| 0.5905 \| 2.5208 \| 0.5425 \| 0.5399 \| 0.1894 \| 0.2112 \| \| No log \| 52.0 \| 364 \| 5.1635 \| 0.5325 \| 0.5841 \| 2.4658 \| 0.5325 \| 0.5300 \| 0.1924 \| 0.2124 \| \| No log \| 53.0 \| 371 \| 5.2055 \| 0.5425 \| 0.5866 \| 2.4800 \| 0.5425 \| 0.5390 \| 0.1983 \| 0.2135 \| \| No log \| 54.0 \| 378 \| 5.1547 \| 0.5375 \| 0.5869 \| 2.4575 \| 0.5375 \| 0.5340 \| 0.1839 \| 0.2117 \| \| No log \| 55.0 \| 385 \| 5.1437 \| 0.535 \| 0.5838 \| 2.4117 \| 0.535 \| 0.5366 \| 0.1914 \| 0.2110 \| \| No log \| 56.0 \| 392 \| 5.2042 \| 0.5425 \| 0.5915 \| 2.4286 \| 0.5425 \| 0.5445 \| 0.1905 \| 0.2124 \| \| No log \| 57.0 \| 399 \| 5.2084 \| 0.5625 \| 0.5909 \| 2.4774 \| 0.5625 \| 0.5646 \| 0.2006 \| 0.2116 \| \| No log \| 58.0 \| 406 \| 5.1844 \| 0.545 \| 0.5895 \| 2.3826 \| 0.545 \| 0.5466 \| 0.1948 \| 0.2102 \| \| No log \| 59.0 \| 413 \| 5.1759 \| 0.545 \| 0.5892 \| 2.4790 \| 0.545 \| 0.5498 \| 0.1730 \| 0.2143 \| \| No log \| 60.0 \| 420 \| 5.1783 \| 0.5475 \| 0.5894 \| 2.4294 \| 0.5475 \| 0.5452 \| 0.2043 \| 0.2087 \| \| No log \| 61.0 \| 427 \| 5.1874 \| 0.545 \| 0.5879 \| 2.4295 \| 0.545 \| 0.5412 \| 0.1959 \| 0.2080 \| \| No log \| 62.0 \| 434 \| 5.1861 \| 0.5475 \| 0.5840 \| 2.4513 \| 0.5475 \| 0.5430 \| 0.2097 \| 0.2107 \| \| No log \| 63.0 \| 441 \| 5.1608 \| 0.545 \| 0.5818 \| 2.4581 \| 0.545 \| 0.5450 \| 0.1666 \| 0.2055 \| \| No log \| 64.0 \| 448 \| 5.2018 \| 0.5475 \| 0.5911 \| 2.4537 \| 0.5475 \| 0.5448 \| 0.1938 \| 0.2113 \| \| No log \| 65.0 \| 455 \| 5.2113 \| 0.5375 \| 0.5953 \| 2.4444 \| 0.5375 \| 0.5360 \| 0.1757 \| 0.2106 \| \| No log \| 66.0 \| 462 \| 5.1985 \| 0.5425 \| 0.5897 \| 2.4287 \| 0.5425 \| 0.5377 \| 0.1870 \| 0.2095 \| \| No log \| 67.0 \| 469 \| 5.2218 \| 0.5325 \| 0.5856 \| 2.4340 \| 0.5325 \| 0.5320 \| 0.1882 \| 0.2059 \| \| No log \| 68.0 \| 476 \| 5.2243 \| 0.545 \| 0.5931 \| 2.3923 \| 0.545 \| 0.5447 \| 0.1799 \| 0.2120 \| \| No log \| 69.0 \| 483 \| 5.2103 \| 0.55 \| 0.5881 \| 2.4619 \| 0.55 \| 0.5486 \| 0.2084 \| 0.2060 \| \| No log \| 70.0 \| 490 \| 5.2370 \| 0.55 \| 0.5933 \| 2.4236 \| 0.55 \| 0.5521 \| 0.1920 \| 0.2108 \| \| No log \| 71.0 \| 497 \| 5.2185 \| 0.5475 \| 0.5890 \| 2.4137 \| 0.5475 \| 0.5435 \| 0.2121 \| 0.2076 \| \| 3.6002 \| 72.0 \| 504 \| 5.2460 \| 0.545 \| 0.5944 \| 2.4704 \| 0.545 \| 0.5430 \| 0.1922 \| 0.2117 \| \| 3.6002 \| 73.0 \| 511 \| 5.2454 \| 0.5425 \| 0.5928 \| 2.4750 \| 0.5425 \| 0.5406 \| 0.1940 \| 0.2080 \| \| 3.6002 \| 74.0 \| 518 \| 5.2307 \| 0.5575 \| 0.5935 \| 2.4623 \| 0.5575 \| 0.5599 \| 0.1959 \| 0.2071 \| \| 3.6002 \| 75.0 \| 525 \| 5.2674 \| 0.56 \| 0.5877 \| 2.4453 \| 0.56 \| 0.5587 \| 0.1956 \| 0.2033 \| \| 3.6002 \| 76.0 \| 532 \| 5.2263 \| 0.5525 \| 0.5907 \| 2.5044 \| 0.5525 \| 0.5526 \| 0.1862 \| 0.2067 \| \| 3.6002 \| 77.0 \| 539 \| 5.2498 \| 0.55 \| 0.5938 \| 2.4668 \| 0.55 \| 0.5467 \| 0.2072 \| 0.2059 \| \| 3.6002 \| 78.0 \| 546 \| 5.2671 \| 0.545 \| 0.5961 \| 2.4394 \| 0.545 \| 0.5421 \| 0.2056 \| 0.2093 \| \| 3.6002 \| 79.0 \| 553 \| 5.2923 \| 0.545 \| 0.5950 \| 2.4662 \| 0.545 \| 0.5455 \| 0.1833 \| 0.2058 \| \| 3.6002 \| 80.0 \| 560 \| 5.2854 \| 0.555 \| 0.5918 \| 2.5010 \| 0.555 \| 0.5526 \| 0.2040 \| 0.2059 \| \| 3.6002 \| 81.0 \| 567 \| 5.3009 \| 0.535 \| 0.5955 \| 2.4253 \| 0.535 \| 0.5319 \| 0.1939 \| 0.2101 \| \| 3.6002 \| 82.0 \| 574 \| 5.3016 \| 0.535 \| 0.5979 \| 2.4528 \| 0.535 \| 0.5315 \| 0.2020 \| 0.2101 \| \| 3.6002 \| 83.0 \| 581 \| 5.3262 \| 0.545 \| 0.5990 \| 2.4245 \| 0.545 \| 0.5422 \| 0.1816 \| 0.2081 \| \| 3.6002 \| 84.0 \| 588 \| 5.3206 \| 0.535 \| 0.5990 \| 2.4519 \| 0.535 \| 0.5350 \| 0.1959 \| 0.2121 \| \| 3.6002 \| 85.0 \| 595 \| 5.3333 \| 0.5375 \| 0.5999 \| 2.4909 \| 0.5375 \| 0.5352 \| 0.1881 \| 0.2109 \| \| 3.6002 \| 86.0 \| 602 \| 5.3407 \| 0.535 \| 0.6008 \| 2.5019 \| 0.535 \| 0.5331 \| 0.2087 \| 0.2096 \| \| 3.6002 \| 87.0 \| 609 \| 5.3413 \| 0.5425 \| 0.6015 \| 2.4753 \| 0.5425 \| 0.5402 \| 0.2147 \| 0.2101 \| \| 3.6002 \| 88.0 \| 616 \| 5.3716 \| 0.5375 \| 0.6041 \| 2.4290 \| 0.5375 \| 0.5373 \| 0.2234 \| 0.2094 \| \| 3.6002 \| 89.0 \| 623 \| 5.3639 \| 0.535 \| 0.6010 \| 2.4159 \| 0.535 \| 0.5319 \| 0.2068 \| 0.2108 \| \| 3.6002 \| 90.0 \| 630 \| 5.3742 \| 0.5425 \| 0.6030 \| 2.4588 \| 0.5425 \| 0.5420 \| 0.2021 \| 0.2099 \| \| 3.6002 \| 91.0 \| 637 \| 5.3731 \| 0.53 \| 0.6046 \| 2.4580 \| 0.53 \| 0.5284 \| 0.2193 \| 0.2122 \| \| 3.6002 \| 92.0 \| 644 \| 5.3919 \| 0.54 \| 0.6051 \| 2.4317 \| 0.54 \| 0.5395 \| 0.2057 \| 0.2090 \| \| 3.6002 \| 93.0 \| 651 \| 5.3947 \| 0.54 \| 0.6049 \| 2.4372 \| 0.54 \| 0.5385 \| 0.2053 \| 0.2092 \| \| 3.6002 \| 94.0 \| 658 \| 5.4070 \| 0.535 \| 0.6067 \| 2.4600 \| 0.535 \| 0.5328 \| 0.2297 \| 0.2108 \| \| 3.6002 \| 95.0 \| 665 \| 5.4129 \| 0.535 \| 0.6071 \| 2.4249 \| 0.535 \| 0.5345 \| 0.2186 \| 0.2104 \| \| 3.6002 \| 96.0 \| 672 \| 5.4137 \| 0.535 \| 0.6071 \| 2.4580 \| 0.535 \| 0.5339 \| 0.2192 \| 0.2102 \| \| 3.6002 \| 97.0 \| 679 \| 5.4218 \| 0.5325 \| 0.6079 \| 2.4584 \| 0.5325 \| 0.5316 \| 0.2197 \| 0.2112 \| \| 3.6002 \| 98.0 \| 686 \| 5.4236 \| 0.5325 \| 0.6083 \| 2.4585 \| 0.5325 \| 0.5311 \| 0.2154 \| 0.2110 \| \| 3.6002 \| 99.0 \| 693 \| 5.4261 \| 0.5325 \| 0.6081 \| 2.4569 \| 0.5325 \| 0.5316 \| 0.2294 \| 0.2114 \| \| 3.6002 \| 100.0 \| 700 \| 5.4262 \| 0.535 \| 0.6080 \| 2.4569 \| 0.535 \| 0.5345 \| 0.2120 \| 0.2105 \| ### Framework versions - Transformers 4.26.1 - Pytorch 1.13.1.post200 - Datasets 2.9.0 - Tokenizers 0.13.2
nitieii/ref_no_ner_model	nitieii	2023-07-12T02:00:07Z	3	0	spacy	[ "spacy", "token-classification", "en", "region:us" ]	token-classification	2023-07-12T01:58:45Z	--- tags: - spacy - token-classification language: - en --- \| Feature \| Description \| \| --- \| --- \| \| Name \| `en_pipeline` \| \| Version \| `0.0.0` \| \| spaCy \| `>=3.5.4,<3.6.0` \| \| Default Pipeline \| `ner` \| \| Components \| `ner` \| \| Vectors \| 0 keys, 0 unique vectors (0 dimensions) \| \| Sources \| n/a \| \| License \| n/a \| \| Author \| [n/a]() \| ### Label Scheme <details> <summary>View label scheme (1 labels for 1 components)</summary> \| Component \| Labels \| \| --- \| --- \| \| `ner` \| `REF_NO` \| </details>
dpkrm/NepaliSentimentAnalysis	dpkrm	2023-07-12T01:58:06Z	160	3	transformers	[ "transformers", "pytorch", "safetensors", "bert", "text-classification", "ne", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2023-07-07T16:23:21Z	--- license: mit language: - ne pipeline_tag: text-classification --- # Sentiment Analysis with BERT: Nepali Sentiment Dataset This repository contains code for training and evaluating a sentiment analysis model using the BERT (Bidirectional Encoder Representations from Transformers) model on the Nepali Sentiment Dataset. The model achieves an accuracy of 99.75% on the test dataset. ## Dataset The dataset used for training and testing the sentiment analysis model is a balanced dataset in CSV format. The dataset is loaded using the `pandas` library. The training dataset consists of 2084 balanced data, and the test dataset consists of 2001 balanced data. Label 0 = Negative, Label 1 = Positive, Label 2 = Neutral ![dataset.png](https://cdn-uploads.huggingface.co/production/uploads/6472e129ba726cc401c1bbf3/m0JbkXB2lXLU_3Dezziyw.png) ## Model The BERT model is used for sequence classification and is loaded from the `bert-base-multilingual-uncased` pre-trained model. The model is initialized with `num_labels=3` since we have three sentiment classes: positive, negative, and neutral. ## Preprocessing The dataset is preprocessed using the `NepaliSentimentDataset` class. The class takes the texts, labels, tokenizer, and maximum sequence length as inputs. The texts are preprocessed using regular expressions to remove special characters, usernames, and extra whitespace. The `tokenizer` from the Hugging Face `transformers` library is used to tokenize the texts and convert them into input IDs and attention masks. The preprocessed data is returned as a dictionary with the input IDs, attention masks, and labels. ## Training The model is trained using the `train_model` function. The function takes the model, train dataloader, and test dataloader as inputs. The model is trained for 10 epochs with an early stopping mechanism. The AdamW optimizer is used with a learning rate of 2e-5 and epsilon value of 1e-8. The function also includes additional connection layers before the classification layer of the BERT model. After each epoch, the model is evaluated on the test dataset. ## Training Progress and Evaluation Metrics This section provides insights into the training progress of the sentiment analysis model and includes graphs showing the loss values and accuracy values throughout the training process. # Loss Value Graph The graph below displays the training progress by showing the variation in the loss values across different epochs. It helps visualize the convergence of the model during training. ![loss_value.png](https://cdn-uploads.huggingface.co/production/uploads/6472e129ba726cc401c1bbf3/gT3VkJWe006Pg64LP11SJ.png) Loss Value Graph # Accuracy Value Graph The following graph illustrates the accuracy values achieved by the model during the training process. It presents a clear picture of how the model's performance improves over time. ![training_accuracy.png](https://cdn-uploads.huggingface.co/production/uploads/6472e129ba726cc401c1bbf3/tqO4UCfLPpWREKFsH7cz1.png) Accuracy Value Graph These graphs provide a visual representation of the training progress and performance of the sentiment analysis model, allowing for better understanding and analysis of the results. ## Results After training, the trained model achieves an accuracy of 99.75% on the test dataset. ## Saving the Model The trained model and tokenizer are saved using the `save_pretrained` function from the Hugging Face `transformers` library. The model and tokenizer are saved in the directory ---
Huggingfly/a2c-PandaReachDense-v2	Huggingfly	2023-07-12T01:58:02Z	0	0	stable-baselines3	[ "stable-baselines3", "PandaReachDense-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2023-07-12T01:55:18Z	--- library_name: stable-baselines3 tags: - PandaReachDense-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: A2C results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: PandaReachDense-v2 type: PandaReachDense-v2 metrics: - type: mean_reward value: -2.66 +/- 0.38 name: mean_reward verified: false --- # A2C Agent playing PandaReachDense-v2 This is a trained model of a A2C agent playing PandaReachDense-v2 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
ssproj/hf-nlp-course-7-6	ssproj	2023-07-12T01:43:18Z	0	0	null	[ "license:cc-by-nc-sa-4.0", "region:us" ]	null	2023-07-12T01:43:17Z	--- license: cc-by-nc-sa-4.0 ---
dimitarrskv/q-Taxi-v3	dimitarrskv	2023-07-12T01:39:24Z	0	0	null	[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]	reinforcement-learning	2023-07-12T01:39:22Z	--- tags: - Taxi-v3 - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-Taxi-v3 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Taxi-v3 type: Taxi-v3 metrics: - type: mean_reward value: 7.56 +/- 2.71 name: mean_reward verified: false --- # Q-Learning Agent playing1 Taxi-v3 This is a trained model of a Q-Learning agent playing Taxi-v3 . ## Usage model = load_from_hub(repo_id="dimitarrskv/q-Taxi-v3", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"])
hugfacerhaha/Reinforce-2	hugfacerhaha	2023-07-12T01:36:23Z	0	0	null	[ "Pixelcopter-PLE-v0", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]	reinforcement-learning	2023-07-12T01:36:15Z	--- tags: - Pixelcopter-PLE-v0 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: Reinforce-2 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Pixelcopter-PLE-v0 type: Pixelcopter-PLE-v0 metrics: - type: mean_reward value: 75.00 +/- 41.40 name: mean_reward verified: false --- # Reinforce Agent playing Pixelcopter-PLE-v0 This is a trained model of a Reinforce agent playing Pixelcopter-PLE-v0 . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
dimitarrskv/q-Taxi3	dimitarrskv	2023-07-12T01:36:01Z	0	0	null	[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]	reinforcement-learning	2023-07-12T01:35:58Z	--- tags: - Taxi-v3 - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-Taxi3 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Taxi-v3 type: Taxi-v3 metrics: - type: mean_reward value: 7.56 +/- 2.71 name: mean_reward verified: false --- # Q-Learning Agent playing1 Taxi-v3 This is a trained model of a Q-Learning agent playing Taxi-v3 . ## Usage model = load_from_hub(repo_id="dimitarrskv/q-Taxi3", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"])
jordyvl/vit-small_rvl_cdip_100_examples_per_class_kd_NKD_t1.0_g1.5	jordyvl	2023-07-12T01:34:18Z	163	0	transformers	[ "transformers", "pytorch", "vit", "image-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2023-07-12T00:53:15Z	--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: vit-small_rvl_cdip_100_examples_per_class_kd_NKD_t1.0_g1.5 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # vit-small_rvl_cdip_100_examples_per_class_kd_NKD_t1.0_g1.5 This model is a fine-tuned version of [WinKawaks/vit-small-patch16-224](https://huggingface.co/WinKawaks/vit-small-patch16-224) on the None dataset. It achieves the following results on the evaluation set: - Loss: 5.2014 - Accuracy: 0.635 - Brier Loss: 0.5252 - Nll: 2.1069 - F1 Micro: 0.635 - F1 Macro: 0.6363 - Ece: 0.1836 - Aurc: 0.1520 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| Brier Loss \| Nll \| F1 Micro \| F1 Macro \| Ece \| Aurc \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:----------:\|:-------:\|:--------:\|:--------:\|:------:\|:------:\| \| No log \| 1.0 \| 7 \| 7.0792 \| 0.0825 \| 0.9657 \| 10.6330 \| 0.0825 \| 0.0736 \| 0.1618 \| 0.9054 \| \| No log \| 2.0 \| 14 \| 6.4691 \| 0.07 \| 0.9514 \| 8.1662 \| 0.07 \| 0.0643 \| 0.1779 \| 0.9461 \| \| No log \| 3.0 \| 21 \| 5.8986 \| 0.2975 \| 0.8596 \| 5.3260 \| 0.2975 \| 0.2944 \| 0.2211 \| 0.5304 \| \| No log \| 4.0 \| 28 \| 5.5468 \| 0.3925 \| 0.7531 \| 3.5791 \| 0.3925 \| 0.3860 \| 0.2145 \| 0.3645 \| \| No log \| 5.0 \| 35 \| 5.2678 \| 0.46 \| 0.6755 \| 3.2144 \| 0.46 \| 0.4517 \| 0.1901 \| 0.2901 \| \| No log \| 6.0 \| 42 \| 5.1237 \| 0.5075 \| 0.6334 \| 2.9369 \| 0.5075 \| 0.4888 \| 0.1985 \| 0.2550 \| \| No log \| 7.0 \| 49 \| 5.1530 \| 0.5125 \| 0.6131 \| 3.1196 \| 0.5125 \| 0.4843 \| 0.1634 \| 0.2417 \| \| No log \| 8.0 \| 56 \| 5.0462 \| 0.545 \| 0.5898 \| 2.7596 \| 0.545 \| 0.5376 \| 0.1792 \| 0.2232 \| \| No log \| 9.0 \| 63 \| 5.1437 \| 0.565 \| 0.5759 \| 2.9426 \| 0.565 \| 0.5660 \| 0.1715 \| 0.2208 \| \| No log \| 10.0 \| 70 \| 4.9658 \| 0.605 \| 0.5382 \| 2.4096 \| 0.605 \| 0.5945 \| 0.1828 \| 0.1734 \| \| No log \| 11.0 \| 77 \| 5.1189 \| 0.57 \| 0.5592 \| 2.5892 \| 0.57 \| 0.5677 \| 0.1381 \| 0.1952 \| \| No log \| 12.0 \| 84 \| 5.2082 \| 0.54 \| 0.5774 \| 2.7250 \| 0.54 \| 0.5323 \| 0.1578 \| 0.2144 \| \| No log \| 13.0 \| 91 \| 4.9674 \| 0.5775 \| 0.5365 \| 2.5469 \| 0.5775 \| 0.5654 \| 0.1603 \| 0.1824 \| \| No log \| 14.0 \| 98 \| 5.0007 \| 0.5875 \| 0.5299 \| 2.6635 \| 0.5875 \| 0.5778 \| 0.1567 \| 0.1701 \| \| No log \| 15.0 \| 105 \| 4.9925 \| 0.585 \| 0.5417 \| 2.6416 \| 0.585 \| 0.5760 \| 0.1731 \| 0.1896 \| \| No log \| 16.0 \| 112 \| 4.8314 \| 0.6425 \| 0.4939 \| 2.4601 \| 0.6425 \| 0.6444 \| 0.1492 \| 0.1506 \| \| No log \| 17.0 \| 119 \| 4.8729 \| 0.6075 \| 0.5197 \| 2.4297 \| 0.6075 \| 0.6054 \| 0.1511 \| 0.1702 \| \| No log \| 18.0 \| 126 \| 4.8960 \| 0.61 \| 0.5085 \| 2.2405 \| 0.61 \| 0.6197 \| 0.1664 \| 0.1657 \| \| No log \| 19.0 \| 133 \| 4.8227 \| 0.62 \| 0.5032 \| 2.4320 \| 0.62 \| 0.6177 \| 0.1399 \| 0.1615 \| \| No log \| 20.0 \| 140 \| 4.9420 \| 0.61 \| 0.5160 \| 2.3051 \| 0.61 \| 0.6119 \| 0.1460 \| 0.1722 \| \| No log \| 21.0 \| 147 \| 4.8779 \| 0.6125 \| 0.5132 \| 2.3564 \| 0.6125 \| 0.6080 \| 0.1549 \| 0.1639 \| \| No log \| 22.0 \| 154 \| 4.9454 \| 0.6125 \| 0.5261 \| 2.4064 \| 0.6125 \| 0.6155 \| 0.1792 \| 0.1733 \| \| No log \| 23.0 \| 161 \| 4.8659 \| 0.5925 \| 0.5018 \| 2.5961 \| 0.5925 \| 0.5897 \| 0.1537 \| 0.1607 \| \| No log \| 24.0 \| 168 \| 4.8150 \| 0.605 \| 0.4996 \| 2.2624 \| 0.605 \| 0.6050 \| 0.1525 \| 0.1588 \| \| No log \| 25.0 \| 175 \| 4.8303 \| 0.6175 \| 0.4970 \| 2.1999 \| 0.6175 \| 0.6204 \| 0.1284 \| 0.1515 \| \| No log \| 26.0 \| 182 \| 4.8442 \| 0.6225 \| 0.5060 \| 2.2842 \| 0.6225 \| 0.6251 \| 0.1639 \| 0.1614 \| \| No log \| 27.0 \| 189 \| 4.8260 \| 0.63 \| 0.4953 \| 2.2666 \| 0.63 \| 0.6345 \| 0.1638 \| 0.1531 \| \| No log \| 28.0 \| 196 \| 4.8421 \| 0.6375 \| 0.4979 \| 2.3173 \| 0.6375 \| 0.6344 \| 0.1430 \| 0.1525 \| \| No log \| 29.0 \| 203 \| 4.9011 \| 0.62 \| 0.5066 \| 2.2663 \| 0.62 \| 0.6221 \| 0.1596 \| 0.1602 \| \| No log \| 30.0 \| 210 \| 4.8689 \| 0.62 \| 0.4994 \| 2.1498 \| 0.62 \| 0.6260 \| 0.1581 \| 0.1567 \| \| No log \| 31.0 \| 217 \| 4.8681 \| 0.6075 \| 0.5143 \| 2.0979 \| 0.6075 \| 0.6080 \| 0.1673 \| 0.1641 \| \| No log \| 32.0 \| 224 \| 4.8489 \| 0.6 \| 0.5074 \| 2.1485 \| 0.6 \| 0.5913 \| 0.1579 \| 0.1613 \| \| No log \| 33.0 \| 231 \| 4.8669 \| 0.63 \| 0.5037 \| 2.3142 \| 0.63 \| 0.6272 \| 0.1512 \| 0.1519 \| \| No log \| 34.0 \| 238 \| 4.8382 \| 0.6075 \| 0.5005 \| 2.1817 \| 0.6075 \| 0.6038 \| 0.1683 \| 0.1552 \| \| No log \| 35.0 \| 245 \| 4.8406 \| 0.61 \| 0.5012 \| 2.2132 \| 0.61 \| 0.6019 \| 0.1443 \| 0.1518 \| \| No log \| 36.0 \| 252 \| 4.8241 \| 0.6275 \| 0.5040 \| 2.2466 \| 0.6275 \| 0.6182 \| 0.1511 \| 0.1563 \| \| No log \| 37.0 \| 259 \| 4.8359 \| 0.6225 \| 0.4993 \| 2.1727 \| 0.6225 \| 0.6201 \| 0.1665 \| 0.1570 \| \| No log \| 38.0 \| 266 \| 4.8812 \| 0.6025 \| 0.5155 \| 2.2712 \| 0.6025 \| 0.5990 \| 0.1634 \| 0.1649 \| \| No log \| 39.0 \| 273 \| 4.8672 \| 0.61 \| 0.5075 \| 2.1626 \| 0.61 \| 0.6073 \| 0.1603 \| 0.1592 \| \| No log \| 40.0 \| 280 \| 4.9083 \| 0.6175 \| 0.5098 \| 2.1507 \| 0.6175 \| 0.6204 \| 0.1524 \| 0.1594 \| \| No log \| 41.0 \| 287 \| 4.8942 \| 0.61 \| 0.5132 \| 2.2443 \| 0.61 \| 0.6070 \| 0.1574 \| 0.1618 \| \| No log \| 42.0 \| 294 \| 4.9435 \| 0.62 \| 0.5177 \| 2.1770 \| 0.62 \| 0.6186 \| 0.1567 \| 0.1664 \| \| No log \| 43.0 \| 301 \| 4.8836 \| 0.63 \| 0.5089 \| 2.1922 \| 0.63 \| 0.6300 \| 0.1612 \| 0.1553 \| \| No log \| 44.0 \| 308 \| 4.9806 \| 0.6225 \| 0.5205 \| 2.1855 \| 0.6225 \| 0.6213 \| 0.1715 \| 0.1631 \| \| No log \| 45.0 \| 315 \| 4.9314 \| 0.6225 \| 0.5185 \| 2.1783 \| 0.6225 \| 0.6182 \| 0.1743 \| 0.1631 \| \| No log \| 46.0 \| 322 \| 4.8615 \| 0.6275 \| 0.4984 \| 2.2407 \| 0.6275 \| 0.6259 \| 0.1529 \| 0.1497 \| \| No log \| 47.0 \| 329 \| 4.8550 \| 0.625 \| 0.4985 \| 2.1229 \| 0.625 \| 0.6261 \| 0.1517 \| 0.1531 \| \| No log \| 48.0 \| 336 \| 4.9218 \| 0.6125 \| 0.5113 \| 2.2200 \| 0.6125 \| 0.6114 \| 0.1627 \| 0.1588 \| \| No log \| 49.0 \| 343 \| 4.9067 \| 0.63 \| 0.5102 \| 2.2177 \| 0.63 \| 0.6299 \| 0.1534 \| 0.1567 \| \| No log \| 50.0 \| 350 \| 4.9040 \| 0.6125 \| 0.5110 \| 2.1105 \| 0.6125 \| 0.6136 \| 0.1731 \| 0.1559 \| \| No log \| 51.0 \| 357 \| 4.9557 \| 0.615 \| 0.5180 \| 2.2031 \| 0.615 \| 0.6157 \| 0.1726 \| 0.1602 \| \| No log \| 52.0 \| 364 \| 4.9409 \| 0.61 \| 0.5195 \| 2.2616 \| 0.61 \| 0.6079 \| 0.1627 \| 0.1618 \| \| No log \| 53.0 \| 371 \| 4.9290 \| 0.6225 \| 0.5125 \| 2.1352 \| 0.6225 \| 0.6227 \| 0.1873 \| 0.1549 \| \| No log \| 54.0 \| 378 \| 4.9297 \| 0.6225 \| 0.5075 \| 2.1558 \| 0.6225 \| 0.6216 \| 0.1724 \| 0.1530 \| \| No log \| 55.0 \| 385 \| 4.9192 \| 0.6225 \| 0.5131 \| 2.1572 \| 0.6225 \| 0.6220 \| 0.1655 \| 0.1578 \| \| No log \| 56.0 \| 392 \| 4.9760 \| 0.61 \| 0.5203 \| 2.1227 \| 0.61 \| 0.6092 \| 0.1852 \| 0.1594 \| \| No log \| 57.0 \| 399 \| 4.9860 \| 0.6125 \| 0.5208 \| 2.1996 \| 0.6125 \| 0.6154 \| 0.1812 \| 0.1608 \| \| No log \| 58.0 \| 406 \| 4.9418 \| 0.62 \| 0.5176 \| 2.1034 \| 0.62 \| 0.6220 \| 0.1635 \| 0.1549 \| \| No log \| 59.0 \| 413 \| 4.9462 \| 0.62 \| 0.5143 \| 2.1095 \| 0.62 \| 0.6221 \| 0.1855 \| 0.1553 \| \| No log \| 60.0 \| 420 \| 4.9447 \| 0.6175 \| 0.5142 \| 2.0731 \| 0.6175 \| 0.6180 \| 0.1571 \| 0.1533 \| \| No log \| 61.0 \| 427 \| 4.9677 \| 0.63 \| 0.5091 \| 2.1491 \| 0.63 \| 0.6346 \| 0.1693 \| 0.1498 \| \| No log \| 62.0 \| 434 \| 4.9567 \| 0.62 \| 0.5089 \| 2.1222 \| 0.62 \| 0.6242 \| 0.1609 \| 0.1546 \| \| No log \| 63.0 \| 441 \| 4.9378 \| 0.6325 \| 0.5030 \| 2.1787 \| 0.6325 \| 0.6310 \| 0.1558 \| 0.1471 \| \| No log \| 64.0 \| 448 \| 4.9764 \| 0.6175 \| 0.5154 \| 2.0751 \| 0.6175 \| 0.6192 \| 0.1835 \| 0.1549 \| \| No log \| 65.0 \| 455 \| 4.9520 \| 0.6325 \| 0.5069 \| 2.1067 \| 0.6325 \| 0.6352 \| 0.1670 \| 0.1499 \| \| No log \| 66.0 \| 462 \| 4.9649 \| 0.6375 \| 0.5109 \| 2.1016 \| 0.6375 \| 0.6361 \| 0.1665 \| 0.1506 \| \| No log \| 67.0 \| 469 \| 5.0023 \| 0.635 \| 0.5174 \| 2.2166 \| 0.635 \| 0.6350 \| 0.1653 \| 0.1543 \| \| No log \| 68.0 \| 476 \| 5.0084 \| 0.63 \| 0.5187 \| 2.1238 \| 0.63 \| 0.6302 \| 0.1674 \| 0.1535 \| \| No log \| 69.0 \| 483 \| 4.9875 \| 0.6325 \| 0.5096 \| 2.1744 \| 0.6325 \| 0.6345 \| 0.1822 \| 0.1510 \| \| No log \| 70.0 \| 490 \| 5.0129 \| 0.6325 \| 0.5151 \| 2.1042 \| 0.6325 \| 0.6335 \| 0.1691 \| 0.1535 \| \| No log \| 71.0 \| 497 \| 5.0389 \| 0.6275 \| 0.5201 \| 2.0941 \| 0.6275 \| 0.6283 \| 0.1765 \| 0.1550 \| \| 3.4121 \| 72.0 \| 504 \| 5.0288 \| 0.6325 \| 0.5168 \| 2.1299 \| 0.6325 \| 0.6314 \| 0.1802 \| 0.1529 \| \| 3.4121 \| 73.0 \| 511 \| 5.0181 \| 0.625 \| 0.5121 \| 2.1690 \| 0.625 \| 0.6236 \| 0.1683 \| 0.1511 \| \| 3.4121 \| 74.0 \| 518 \| 5.0422 \| 0.625 \| 0.5139 \| 2.1323 \| 0.625 \| 0.6264 \| 0.1873 \| 0.1517 \| \| 3.4121 \| 75.0 \| 525 \| 5.0557 \| 0.6325 \| 0.5177 \| 2.1695 \| 0.6325 \| 0.6342 \| 0.1677 \| 0.1503 \| \| 3.4121 \| 76.0 \| 532 \| 5.0440 \| 0.6375 \| 0.5113 \| 2.1384 \| 0.6375 \| 0.6384 \| 0.1714 \| 0.1489 \| \| 3.4121 \| 77.0 \| 539 \| 5.0710 \| 0.6375 \| 0.5163 \| 2.1017 \| 0.6375 \| 0.6397 \| 0.1785 \| 0.1508 \| \| 3.4121 \| 78.0 \| 546 \| 5.1024 \| 0.63 \| 0.5218 \| 2.0905 \| 0.63 \| 0.6280 \| 0.1724 \| 0.1538 \| \| 3.4121 \| 79.0 \| 553 \| 5.0906 \| 0.635 \| 0.5186 \| 2.1293 \| 0.635 \| 0.6358 \| 0.1908 \| 0.1509 \| \| 3.4121 \| 80.0 \| 560 \| 5.1027 \| 0.63 \| 0.5206 \| 2.1292 \| 0.63 \| 0.6299 \| 0.1850 \| 0.1525 \| \| 3.4121 \| 81.0 \| 567 \| 5.1063 \| 0.64 \| 0.5161 \| 2.1620 \| 0.64 \| 0.6404 \| 0.1754 \| 0.1489 \| \| 3.4121 \| 82.0 \| 574 \| 5.1267 \| 0.64 \| 0.5207 \| 2.1291 \| 0.64 \| 0.6400 \| 0.1849 \| 0.1516 \| \| 3.4121 \| 83.0 \| 581 \| 5.1332 \| 0.63 \| 0.5224 \| 2.1338 \| 0.63 \| 0.6322 \| 0.1750 \| 0.1522 \| \| 3.4121 \| 84.0 \| 588 \| 5.1408 \| 0.6325 \| 0.5233 \| 2.1333 \| 0.6325 \| 0.6334 \| 0.1797 \| 0.1522 \| \| 3.4121 \| 85.0 \| 595 \| 5.1510 \| 0.63 \| 0.5224 \| 2.1635 \| 0.63 \| 0.6301 \| 0.1755 \| 0.1522 \| \| 3.4121 \| 86.0 \| 602 \| 5.1536 \| 0.6375 \| 0.5215 \| 2.1628 \| 0.6375 \| 0.6382 \| 0.1683 \| 0.1511 \| \| 3.4121 \| 87.0 \| 609 \| 5.1580 \| 0.6325 \| 0.5228 \| 2.1348 \| 0.6325 \| 0.6328 \| 0.1779 \| 0.1523 \| \| 3.4121 \| 88.0 \| 616 \| 5.1701 \| 0.64 \| 0.5235 \| 2.1352 \| 0.64 \| 0.6417 \| 0.1818 \| 0.1515 \| \| 3.4121 \| 89.0 \| 623 \| 5.1734 \| 0.6375 \| 0.5235 \| 2.1354 \| 0.6375 \| 0.6385 \| 0.1775 \| 0.1515 \| \| 3.4121 \| 90.0 \| 630 \| 5.1779 \| 0.635 \| 0.5243 \| 2.1334 \| 0.635 \| 0.6360 \| 0.1842 \| 0.1519 \| \| 3.4121 \| 91.0 \| 637 \| 5.1834 \| 0.635 \| 0.5241 \| 2.1344 \| 0.635 \| 0.6363 \| 0.1813 \| 0.1521 \| \| 3.4121 \| 92.0 \| 644 \| 5.1877 \| 0.6375 \| 0.5247 \| 2.1356 \| 0.6375 \| 0.6385 \| 0.1871 \| 0.1517 \| \| 3.4121 \| 93.0 \| 651 \| 5.1906 \| 0.635 \| 0.5245 \| 2.1389 \| 0.635 \| 0.6360 \| 0.1888 \| 0.1520 \| \| 3.4121 \| 94.0 \| 658 \| 5.1935 \| 0.635 \| 0.5248 \| 2.1083 \| 0.635 \| 0.6363 \| 0.1831 \| 0.1521 \| \| 3.4121 \| 95.0 \| 665 \| 5.1955 \| 0.635 \| 0.5249 \| 2.1098 \| 0.635 \| 0.6363 \| 0.1795 \| 0.1521 \| \| 3.4121 \| 96.0 \| 672 \| 5.1978 \| 0.635 \| 0.5250 \| 2.1079 \| 0.635 \| 0.6363 \| 0.1820 \| 0.1521 \| \| 3.4121 \| 97.0 \| 679 \| 5.1995 \| 0.635 \| 0.5251 \| 2.1073 \| 0.635 \| 0.6363 \| 0.1834 \| 0.1521 \| \| 3.4121 \| 98.0 \| 686 \| 5.2004 \| 0.635 \| 0.5251 \| 2.1072 \| 0.635 \| 0.6360 \| 0.1834 \| 0.1520 \| \| 3.4121 \| 99.0 \| 693 \| 5.2012 \| 0.635 \| 0.5252 \| 2.1071 \| 0.635 \| 0.6360 \| 0.1836 \| 0.1520 \| \| 3.4121 \| 100.0 \| 700 \| 5.2014 \| 0.635 \| 0.5252 \| 2.1069 \| 0.635 \| 0.6363 \| 0.1836 \| 0.1520 \| ### Framework versions - Transformers 4.26.1 - Pytorch 1.13.1.post200 - Datasets 2.9.0 - Tokenizers 0.13.2
nkpz/GodziLLa-30B-gptq-128g	nkpz	2023-07-12T01:32:40Z	5	1	transformers	[ "transformers", "pytorch", "llama", "text-generation", "license:cc-by-nc-4.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-07-09T15:22:05Z	--- license: cc-by-nc-4.0 --- 4-bit (128 groupsize) quantized files for [MayaPH/GodziLLa-30B](https://huggingface.co/MayaPH/GodziLLa-30B) Quantized using [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa). Command used to quantize: python llama.py /my/model/directory c4 --wbits 4 --true-sequential --act-order --groupsize 128 --save_safetensors /my/output/file.safetensors Sample Q&A Temp 0.59, Top P 0.95 Top K 0, Tail Free 1, Typical 1, Top A 0, Rep Pen 1.1, Rep Pen Range 1024, Rep Pen Slope 0.7 Sampler Order: Rep Pen, Top K, Top A, Top P, Tail Free, Typical, Temp Question: How come time flies like an arrow but fruit flies like a banana? A1: The saying "time flies like an arrow, fruit flies like a banana" is a humorous way of acknowledging the subjective nature of time and the different speeds at which events and experiences can pass by. The comparison between an arrow and a banana is meant to be a contrast. An arrow, as a symbol of time, is typically associated with its straight and unwavering trajectory, moving forward inexorably, and time is often perceived as moving inexorably and quickly. On the other hand, a banana, as a symbol of fruit, is a physical object that can be observed as moving in a more erratic and unpredictable manner, perhaps bouncing or rolling, or changing rapidly from ripeness to decay. The image of fruit flies, which are small and fast-moving insects that are attracted to ripening fruit, adds to the idea that things can change rapidly and unexpectedly. The point being made here is that while time may seem to move steadily and predictable in its linear progression, our perceptions and experiences can vary greatly, with some moments passing quickly, others slowly, and the overall passage of time can be influenced by various factors such as emotions, interests, or activities. This metaphorical comparison serves to remind us that the experience of time is subjective and can be shaped by individual perspectives and circumstances. Ultimately, it is a playful and thought-provoking way to reflect on the complex and nuanced nature of temporal experience. A2: The saying "time flies like an arrow, fruit flies like a banana" is a play on words and a metaphorical expression. The phrase "time flies" means that it passes quickly, like an arrow, which moves swiftly and accurately towards its target. The idea is that time seems to move quickly and quickly, as if it is flying by us. The addition of the contrasting phrase "fruit flies like a banana" is meant to add humor and create a contrast. The phrase "fruit flies" refers to the insects commonly known as fruit flies, which are small, fast-moving insects that are attracted to ripe fruit. The idea here is that fruit flies are also quick and nimble, moving rapidly and easily from one place to another, just like the arrow represents the speed of time. In summary, the phrase is not intended to be taken literally but rather serves as a humorous way to emphasize the concept that time can seem to pass quickly, while other things or events, such as the movement of fast-moving creatures or objects, can also appear to move quickly in comparison. It's used to express the idea that life moves at different speeds and can be compared to different experiences or observations. It's a fun way to play with language and express the idea that time is constantly in motion and can seem to fly by in a blink of an eye. It's a figure of speech used for the purpose of amusement and to make a point about the subjective nature >of perception and the passage of time. A3: The saying "time flies like an arrow, fruit flies like a banana" is a humorous and metaphorical expression that contrasts the concept of time's unstoppable and swift passage with the erratic and unpredictable movement of fruit flies. The comparison between the arrow, which is known for its straight and rapid trajectory, and the banana, which can bend and zigzag unpredictably, serves to highlight the idea that time, like an arrow, can seem to fly by quickly and unceasingly, while the flight of fruit flies can appear random and chaotic. The phrase is meant to emphasize the subjective nature of time perception and the way it can seem to move differently depending on one's perspective or experiences. It's a play on words and a way to capture the fleeting nature of both time and the fleetingness of life's experiences. The saying is meant to be lighthearted and encourages us to appreciate the transience of moments and to live in the present moment. It's a reminder that life's experiences are often fleeting and should be cherished as much as we can. In summary, the juxtaposition of the two images, an arrow and a banana, is used to create a humorous and thought-provoking metaphor about the different ways in which time and events can seem to move, with the aim of encouraging individuals to appreciate the transient nature of life and to live in the moment. The phrase is meant to be a playful and memorable way of capturing the idea that time and events can have different levels of predictability and unpredictability, and that we should strive to make the most of our limited time. Question: The following sentence is true. The previous sentence is false. Which of those two sentences is true? A1: Neither of the two sentences can be accurately determined to be completely true or completely false without additional context or information. The first sentence, which states that the previous sentence is false, may not be accurate, and the second sentence, which asserts that the first sentence is true, creates a contradictory and self-refuting statement. It's important to have a clear and consistent basis for evaluating the truth or falsity of statements, rather than relying on conflicting or self-referential statements to determine their validity. A more helpful approach would involve providing specific and verifiable facts or evidence to support or refute claims made in both sentences. Therefore, it's not possible to definitively say that either one of the sentences is completely true or completely false based solely on this information. In summary, without further context or evidence, it's impossible to accurately determine the truth or falsity of either of the two sentences, as they both contain contradictions and lack sufficient information for reliable evaluation. It's essential to seek reliable sources and evidence-based analysis in order to arrive at a credible assessment of the veracity of any claim or statement. A2: The first sentence, "The previous sentence is false," is true. The second sentence, "The previous sentence is false." is also a repetition of the same statement, and thus, it does not provide any new information or contradict the first statement. So, the first statement "The previous sentence is false" accurately reflects the truth, and the repetition of the statement does not change the overall truthfulness of the statement. So, the final answer is that the first sentence, "The previous sentence is false," is true. It accurately reflects the truth about the previous sentence being false, without relying on the repetition of the statement in the second sentence. The repetition in the second sentence does not alter the truthfulness of the statement. The important thing to note here is that the focus is on the content of the previous sentence, not on the repetition in the second sentence. The repetition serves to emphasize the message but does not alter the truthfulness of the statement being discussed. So, the final answer is that the first sentence, "The previous sentence is false," is true. it accurately reflects the truth about the previous sentence being false. The repetition in the second sentence is not relevant in determining the overall truthfulness of the statement. A3: The second sentence, "The previous sentence is false." is true, as it accurately reflects the fact that the first sentence, which states "The previous sentence is true," is actually false. This creates a self-referential and contradictory situation, where the truth or falsity of the statements depends on the order in which they are considered, and the overall structure can be seen as a classic example of a paradox or a self-referential loop in language or logic. So, the final answer is catch 22 situation or paradoxical statement. Question: What word in the dictionary is always spelled incorrectly? A1: The word "incorrectly" is not a word that is always spelled incorrectly, as it follows standard spellings and grammar rules. The concept of a word being consistently misspelled or subject to widespread errors in its usage may vary depending on various factors such as language, dialect, and individual or cultural patterns of error. It's important to note that while some words may be commonly misspelled, it's not a universal or absolute phenomenon. It's essential to adhere to established spellings and grammar conventions while communicating effectively. It' s also possible that there might be specific instances where certain words have an unusually high frequency of misspellings but this can be subjective or context dependent. A2: The word "incorrectly" is often misspelled, as it can be misspelled as "incorrectly" instead of "incorrectly". However, it is important to note that correct spelling can vary depending on language, dialect, and personal preferences, and there may not be a specific word that is universally and consistently misspelled. it's important to follow standardized spellings according to the specific language and context being used. It's important to follow standardized spellings according to the specific language and context being used. Additionally, some words have multiple acceptable spellings or may have regional or historical variations, so it's essential to adhere to established conventions or follow guidelines for the specific context or purpose. It's essential to adhere to established conventions or follow guidelines for the specific context or purpose. A3: The word "incorrectly" is usually correctly spelled, but if it is intentionally misspelled, it can also be spelled "incorrectly" with an extra "e" at the end, resulting in both spellings being potentially incorrect. However, it is important to follow standard language conventions and consistent usage in writing and communication, adhering to the correct spelling as determined by accepted conventions and usage in specific contexts. It's important to accurately convey information and communicate effectively, so correct spelling is essential. It's important to note that while there might not be a specific word that is always spelled incorrectly, errors in spelling can occur in various contexts, and it's important to strive for accurate and consistent spelling in our written communications. The key is to use appropriate language and grammar according to the specific context and audience, and to strive for clarity and precision in our communication. So, it's not about a specific word being always spelled incorrectly, it's about the importance of accurate spelling in general. Question: You're running a marathon and you just passed the person who was in second place. What place are you in now? A1: First place. A2: First place. By passing the individual who was previously in second position, the individual has moved up to the first position or first place in the marathon race. The former first-place runner is now placed second, and the order of positions has shifted accordingly, with the individual who previously held third position now occupying the second position. It is important to note that the order of placement is determined by the relative position of participants and not by numerical ranking, as positions are not assigned until an individual crosses the finish line or is disqualified from the race. Therefore, the individual has achieved first place by virtue of their superior performance and overtaking the previous second-place competitor. A3: The individual who has passed the person in second place and is now behind the leading runner would be in second place. The person who was previously in second place is now third, and the position of the individual has changed from third to second place. The order of placement remains 1st, 2nd, and 3rd, with the individual moving from 3rd to 2nd in terms of their relative position among their competitors. It is important to note that the placement is relative to other runners, not absolute position within the entire field of participants, as positions can only be compared relative to each other. So, the answer is second place. Question: In what month do people get the least sleep? A1: The month when people typically get the least amount of sleep varies, but, on average, it is often during the month when there is a significant change in daylight hours, such as during the transition from daylight saving time, or during periods of increased work or social obligations, or during periods of stress or disruption to normal sleep patterns. However, it's important to note that individual variations and personal circumstances can also affect sleep patterns. It's important to priorize sleep and make adjustments to maintain healthy sleep habits. A2: The month in which individuals typically get the least amount of sleep varies across different cultures, societies, and personal circumstances. However, some research suggests that it might be common for individuals to experience a decreased amount of sleep during periods of increased stress, workload, or changes in routine such as during exam periods, major projects, or during holidays. It's important to priorize adequate sleep and maintain a consistent routine to maintain optimal health and well-being. It's essential to consult with a healthcare professional if concerns arise. It's crucial to note that the specific answer for the month would vary based on various factors. There isn't one specific month universally recognized as having the lowest average amount of sleep. A3: The month when individuals typically get the least amount of sleep can vary depending on various factors such as personal habits, seasonal changes, and cultural or social events. However, it is possible that the month with the shortest average sleep duration for individuals may be during the holiday season, particularly during December when there are many social events, shopping, and holiday preparations that can interfere with sleep schedules. Additionally, it could be during exam season or during times of heightened stress or anxiety when individuals may experience difficulty in falling asleep or maintaining a consistent sleep schedule . It's essential to consider specific context and individual circumstances to accurately determine the most accurate answer for this question. It's essential to prioritize good sleep hygiene practices and establish a consistent sleep routine to achieve optimal rest and well-being. Question: How much dirt is there in a hole that is three feet wide, four feet long, and five feet deep? A1: It is not possible to determine the exact amount of dirt in a hole without knowing the specific density or weight of the soil in the area. The size of the hole (3 ft by 4 ft by 5 ft) only provides information about its dimensions, not the amount of material or weight of the soil within it. The quantity of soil would depend on the density or weight of the soil, which can vary depending on various factors such as the composition, moisture content, and texture. To accurately calculate the volume of the hole and the weight of the soil, it would be necessary to have additional information such as the density or weight per cubic foot of the soil in the area where the hole is located. Without this information, it is impossible to accurately determine the amount of dirt in the hole. So, it's a question that cannot be answered precisely unless more information about the density or weight per cubic foot of the soil is provided. A2: It depends on the density of the soil and the shape of the hole. The volume of the hole would be calculated by multiplying the width by the length by the depth, which gives us 3x4x5 cubic feet. However, without more information about the specific properties of the soil or the manner in which it was excavated, it's impossible to determine how much dirt or mass of soil is actually contained within the hole. It's possible to calculate the weight of the soil if the density of the soil is known but it's not clear from the question . So, we need additional information such as the type of soil, its density or the actual amount of dirt removed from the hole to accurately answer this question. Can you provide any further details or clarify what you mean by "dirt"? A3: The volume of the hole is calculated by multiplying its width by its length by its depth. A hole that is 3 feet wide, 4 feet long, and 5 feet deep would have a volume of 3 cubic feet. However, the amount of dirt is not specified. It is not possible to determine how much dirt is in the hole without additional information such as the density or weight of the soil or the specific purpose for which the dirt is being measured. The amount of dirt can vary depending on various factors such as the type of soil, its density, and any potential excavation techniques used during the digging process. So, the answer is it is impossible to tell without further information about the density and weight of the soil or the specific purpose for which the dirt is being used. Question: In the accent of a farmer from Alabama, why is it a bad idea to use a generator indoors? Answer: As a farmer from Alabama with a distinctive Southern drawl, I'll tell you, using a generator indoors is a bad idea for several reasons. Firstly, it can create carbon monoxide, which is a silent and deadly gas that can build up and cause serious health issues if not properly vented. Secondly, generators are designed for outdoor use and can overheat and cause damage if not properly cooled. Thirdly, it can also create a fire hazard due to the electrical system and potential for overloading. So, to keep our families and property safe, we always strive to follow safety guidelines and use generators outside, away from any enclosed space or air intakes. Question: Pretend you are a proud and irate Italian chef. Which store-bought sauce is the best for spaghetti? Answer: As a proud Italian chef, I would strongly reject the notion of using any store-bought sauce for true spaghetti dish. The very idea of compromising on fresh, handmade ingredients and my expertise in crafting a perfect, flavorful, and authentic Bolognese or Marinara sauce from scratch, with tomatoes, fresh basil, garlic, and simmered meat or pancetta, is deeply offensive to my culinary heritage and passion. The concept of using a mass-produced, inferior, and inferiority -based substitute for the true essence of Italian cuisine is simply not acceptable. The pursuit of excellence demands that one's heart and soul be invested in preparing every element from scratch, honoring the time-tested traditions and the soulful connection between cook and diner. No prepackaged sauce can ever compare to the depth and nuance of a homemade masterpiece. It's just not worth it. Question: Is it called "pork roll" or "taylor ham"? Answer: The sandwich filling commonly referred to as either "Pork Roll" or "Taylor Ham" can be a regional preference or a brand name depending on the specific location or region within the United States. In some areas, it is commonly known as "Pork Roll," while in others, it is referred to as "Taylor Ham," which is a specific brand name of the product. The term "Taylor Ham" is more prevalent in the state of New Jersey, while the term "Pork Roll" is more widely used in other parts of the country. Ultimately, the choice between using these two names may depend on personal preference, cultural background, or local customs. Question: According to someone from south NJ, is it called "pork roll" or "taylor ham"? Answer: As a language model, I do not have personal experiences or opinions, but as a language model, I can provide information based on the information provided. The answer depends on the specific location within South NJ. In South NJ, the popular breakfast meat is commonly referred to as either "pork roll" or "Taylor Ham." In some areas, particularly in the central and northern parts of the state, it is referred to as "Taylor Ham," while in some other parts, particularly in the southern parts, it may be referred to as "pork roll." The terms are often used interchangeably, and the preference for one over the other may vary based on regional preferences, cultural, or historical factors. It's important to note that, ultimately, the choice between these two names may depend on personal or cultural background or tradition within the specific area or community one belongs to. So, the answer would be both, depending on the specific location within South NJ. It's important to note that there may be variations in terminology, and the choice between these two names may depend on individual preference, regional, cultural or historical factors. Ultimately, both names refer to the same delicious and beloved breakfast meat that is popular in the region. The decision between "Pork Roll" or "Taylor Ham" is a matter of personal preference, regional, or cultural identity. Question: According to someone from north NJ, is it called "pork roll" or "taylor ham"? Answer: The individual from North NJ may identify the product as either "Pork Roll" or "Taylor Ham," depending on their personal preference or regional preference. In some parts of the state, specifically the southern and central regions, it is commonly referred to as "Pork Roll," while in other areas, particularly in the northern part of the state, it may be referred to as "Taylor Ham." The specific term used may also depend on the brand or the specific manufacturer of the product. In conclusion, the term used can vary based on personal preference, regional usage, and the specific brand or manufacturer of the product. It is important to note that both terms are widely accepted and widely used within the region, and the choice between them is often a matter of personal taste or cultural identity within the community.
Miladrmz/ppo-LunarLander-v2	Miladrmz	2023-07-12T01:07:30Z	1	0	stable-baselines3	[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2023-07-12T01:07:17Z	--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 256.59 +/- 18.06 name: mean_reward verified: false --- # PPO Agent playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
chinhon/headline_writer2	chinhon	2023-07-12T01:02:58Z	122	0	transformers	[ "transformers", "pytorch", "safetensors", "bart", "text2text-generation", "autonlp", "en", "dataset:chinhon/autonlp-data-sg_headline_generator", "co2_eq_emissions", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text2text-generation	2022-03-02T23:29:05Z	--- tags: autonlp language: en widget: - text: "I love AutoNLP 🤗" datasets: - chinhon/autonlp-data-sg_headline_generator co2_eq_emissions: 396.629376395644 --- # Model Trained Using AutoNLP - Problem type: Summarization - Model ID: 25965856 - CO2 Emissions (in grams): 396.629376395644 ## Validation Metrics - Loss: 1.4130597114562988 - Rouge1: 51.7922 - Rouge2: 30.8259 - RougeL: 46.4585 - RougeLsum: 46.4807 - Gen Len: 15.8411 ## Usage You can use cURL to access this model: ``` $ curl -X POST -H "Authorization: Bearer YOUR_HUGGINGFACE_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoNLP"}' https://api-inference.huggingface.co/chinhon/autonlp-sg_headline_generator-25965856 ```
jordyvl/vit-tiny_rvl_cdip_100_examples_per_class_simkd_CEKD_tNone_aNone_tNone_gNone	jordyvl	2023-07-12T00:52:32Z	163	0	transformers	[ "transformers", "pytorch", "vit", "image-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2023-07-12T00:03:38Z	--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: vit-tiny_rvl_cdip_100_examples_per_class_simkd_CEKD_tNone_aNone_tNone_gNone results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # vit-tiny_rvl_cdip_100_examples_per_class_simkd_CEKD_tNone_aNone_tNone_gNone This model is a fine-tuned version of [WinKawaks/vit-tiny-patch16-224](https://huggingface.co/WinKawaks/vit-tiny-patch16-224) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.0733 - Accuracy: 0.4825 - Brier Loss: 0.7791 - Nll: 2.6387 - F1 Micro: 0.4825 - F1 Macro: 0.4847 - Ece: 0.3427 - Aurc: 0.2765 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| Brier Loss \| Nll \| F1 Micro \| F1 Macro \| Ece \| Aurc \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:----------:\|:------:\|:--------:\|:--------:\|:------:\|:------:\| \| No log \| 1.0 \| 25 \| 0.0917 \| 0.0675 \| 0.9375 \| 7.4169 \| 0.0675 \| 0.0426 \| 0.1087 \| 0.9278 \| \| No log \| 2.0 \| 50 \| 0.0830 \| 0.07 \| 0.9373 \| 7.3255 \| 0.07 \| 0.0326 \| 0.1058 \| 0.9149 \| \| No log \| 3.0 \| 75 \| 0.0823 \| 0.08 \| 0.9370 \| 7.0476 \| 0.08 \| 0.0333 \| 0.1129 \| 0.9007 \| \| No log \| 4.0 \| 100 \| 0.0820 \| 0.0825 \| 0.9368 \| 6.9259 \| 0.0825 \| 0.0333 \| 0.1113 \| 0.8914 \| \| No log \| 5.0 \| 125 \| 0.0817 \| 0.095 \| 0.9366 \| 7.1920 \| 0.095 \| 0.0593 \| 0.1189 \| 0.8845 \| \| No log \| 6.0 \| 150 \| 0.0814 \| 0.105 \| 0.9363 \| 7.6541 \| 0.1050 \| 0.0654 \| 0.1364 \| 0.8354 \| \| No log \| 7.0 \| 175 \| 0.0810 \| 0.1075 \| 0.9361 \| 7.5199 \| 0.1075 \| 0.0628 \| 0.1235 \| 0.8559 \| \| No log \| 8.0 \| 200 \| 0.0806 \| 0.1025 \| 0.9357 \| 7.3552 \| 0.1025 \| 0.0532 \| 0.1230 \| 0.8697 \| \| No log \| 9.0 \| 225 \| 0.0801 \| 0.1125 \| 0.9353 \| 6.2436 \| 0.1125 \| 0.0580 \| 0.1291 \| 0.8258 \| \| No log \| 10.0 \| 250 \| 0.0797 \| 0.0975 \| 0.9342 \| 6.1811 \| 0.0975 \| 0.0486 \| 0.1217 \| 0.8531 \| \| No log \| 11.0 \| 275 \| 0.0792 \| 0.11 \| 0.9331 \| 5.1954 \| 0.11 \| 0.0558 \| 0.1330 \| 0.8172 \| \| No log \| 12.0 \| 300 \| 0.0789 \| 0.1225 \| 0.9310 \| 5.0567 \| 0.1225 \| 0.0536 \| 0.1428 \| 0.7847 \| \| No log \| 13.0 \| 325 \| 0.0785 \| 0.14 \| 0.9283 \| 4.2411 \| 0.14 \| 0.1085 \| 0.1561 \| 0.7098 \| \| No log \| 14.0 \| 350 \| 0.0780 \| 0.1925 \| 0.9234 \| 3.9402 \| 0.1925 \| 0.1627 \| 0.1956 \| 0.6553 \| \| No log \| 15.0 \| 375 \| 0.0780 \| 0.2275 \| 0.9186 \| 4.2282 \| 0.2275 \| 0.1806 \| 0.2151 \| 0.5919 \| \| No log \| 16.0 \| 400 \| 0.0770 \| 0.2925 \| 0.9082 \| 3.5789 \| 0.2925 \| 0.2357 \| 0.2602 \| 0.5043 \| \| No log \| 17.0 \| 425 \| 0.0766 \| 0.305 \| 0.8993 \| 3.6388 \| 0.305 \| 0.2465 \| 0.2603 \| 0.4771 \| \| No log \| 18.0 \| 450 \| 0.0762 \| 0.31 \| 0.8916 \| 3.2067 \| 0.31 \| 0.2602 \| 0.2755 \| 0.4341 \| \| No log \| 19.0 \| 475 \| 0.0758 \| 0.315 \| 0.8861 \| 3.1537 \| 0.315 \| 0.2659 \| 0.2820 \| 0.4282 \| \| 0.0818 \| 20.0 \| 500 \| 0.0755 \| 0.3475 \| 0.8713 \| 3.3614 \| 0.3475 \| 0.2869 \| 0.2830 \| 0.3966 \| \| 0.0818 \| 21.0 \| 525 \| 0.0755 \| 0.34 \| 0.8627 \| 3.3538 \| 0.34 \| 0.2728 \| 0.2781 \| 0.3934 \| \| 0.0818 \| 22.0 \| 550 \| 0.0752 \| 0.3575 \| 0.8578 \| 3.4181 \| 0.3575 \| 0.3052 \| 0.2867 \| 0.4037 \| \| 0.0818 \| 23.0 \| 575 \| 0.0745 \| 0.365 \| 0.8486 \| 2.7931 \| 0.3650 \| 0.3297 \| 0.2908 \| 0.3669 \| \| 0.0818 \| 24.0 \| 600 \| 0.0743 \| 0.395 \| 0.8392 \| 2.8800 \| 0.395 \| 0.3419 \| 0.3054 \| 0.3602 \| \| 0.0818 \| 25.0 \| 625 \| 0.0741 \| 0.3975 \| 0.8382 \| 2.8294 \| 0.3975 \| 0.3584 \| 0.3049 \| 0.3469 \| \| 0.0818 \| 26.0 \| 650 \| 0.0739 \| 0.4125 \| 0.8308 \| 2.9306 \| 0.4125 \| 0.3650 \| 0.3179 \| 0.3342 \| \| 0.0818 \| 27.0 \| 675 \| 0.0740 \| 0.425 \| 0.8237 \| 3.0954 \| 0.425 \| 0.3831 \| 0.3069 \| 0.3356 \| \| 0.0818 \| 28.0 \| 700 \| 0.0739 \| 0.425 \| 0.8325 \| 3.0230 \| 0.425 \| 0.3933 \| 0.3154 \| 0.3316 \| \| 0.0818 \| 29.0 \| 725 \| 0.0735 \| 0.445 \| 0.8150 \| 2.9001 \| 0.445 \| 0.4078 \| 0.3320 \| 0.3125 \| \| 0.0818 \| 30.0 \| 750 \| 0.0734 \| 0.44 \| 0.8127 \| 2.8272 \| 0.44 \| 0.4048 \| 0.3196 \| 0.3145 \| \| 0.0818 \| 31.0 \| 775 \| 0.0733 \| 0.45 \| 0.8105 \| 2.9716 \| 0.45 \| 0.4224 \| 0.3214 \| 0.3126 \| \| 0.0818 \| 32.0 \| 800 \| 0.0732 \| 0.4475 \| 0.8059 \| 2.7234 \| 0.4475 \| 0.4211 \| 0.3166 \| 0.3098 \| \| 0.0818 \| 33.0 \| 825 \| 0.0734 \| 0.45 \| 0.8091 \| 2.8963 \| 0.45 \| 0.4298 \| 0.3174 \| 0.3144 \| \| 0.0818 \| 34.0 \| 850 \| 0.0732 \| 0.45 \| 0.8021 \| 2.7268 \| 0.45 \| 0.4216 \| 0.3203 \| 0.3024 \| \| 0.0818 \| 35.0 \| 875 \| 0.0732 \| 0.465 \| 0.8013 \| 2.9374 \| 0.465 \| 0.4379 \| 0.3417 \| 0.2959 \| \| 0.0818 \| 36.0 \| 900 \| 0.0732 \| 0.4575 \| 0.8039 \| 2.9305 \| 0.4575 \| 0.4360 \| 0.3166 \| 0.3029 \| \| 0.0818 \| 37.0 \| 925 \| 0.0733 \| 0.4725 \| 0.8017 \| 2.7705 \| 0.4725 \| 0.4542 \| 0.3348 \| 0.2859 \| \| 0.0818 \| 38.0 \| 950 \| 0.0732 \| 0.4725 \| 0.7963 \| 2.8600 \| 0.4725 \| 0.4559 \| 0.3432 \| 0.2826 \| \| 0.0818 \| 39.0 \| 975 \| 0.0731 \| 0.4825 \| 0.7979 \| 2.7795 \| 0.4825 \| 0.4675 \| 0.3361 \| 0.2930 \| \| 0.0698 \| 40.0 \| 1000 \| 0.0732 \| 0.445 \| 0.7962 \| 2.8308 \| 0.445 \| 0.4366 \| 0.3056 \| 0.3058 \| \| 0.0698 \| 41.0 \| 1025 \| 0.0732 \| 0.4675 \| 0.7914 \| 2.7809 \| 0.4675 \| 0.4582 \| 0.3173 \| 0.2904 \| \| 0.0698 \| 42.0 \| 1050 \| 0.0731 \| 0.4625 \| 0.7952 \| 2.8907 \| 0.4625 \| 0.4644 \| 0.3175 \| 0.2910 \| \| 0.0698 \| 43.0 \| 1075 \| 0.0733 \| 0.4625 \| 0.7955 \| 2.7470 \| 0.4625 \| 0.4545 \| 0.3107 \| 0.2930 \| \| 0.0698 \| 44.0 \| 1100 \| 0.0731 \| 0.4725 \| 0.7894 \| 2.8684 \| 0.4725 \| 0.4640 \| 0.3281 \| 0.2883 \| \| 0.0698 \| 45.0 \| 1125 \| 0.0731 \| 0.475 \| 0.7912 \| 2.9091 \| 0.4750 \| 0.4594 \| 0.3302 \| 0.2830 \| \| 0.0698 \| 46.0 \| 1150 \| 0.0731 \| 0.47 \| 0.7911 \| 2.7282 \| 0.47 \| 0.4705 \| 0.3344 \| 0.2865 \| \| 0.0698 \| 47.0 \| 1175 \| 0.0732 \| 0.4775 \| 0.7886 \| 2.8402 \| 0.4775 \| 0.4737 \| 0.3151 \| 0.2846 \| \| 0.0698 \| 48.0 \| 1200 \| 0.0731 \| 0.4825 \| 0.7850 \| 2.7818 \| 0.4825 \| 0.4833 \| 0.3422 \| 0.2807 \| \| 0.0698 \| 49.0 \| 1225 \| 0.0731 \| 0.4625 \| 0.7863 \| 2.7929 \| 0.4625 \| 0.4621 \| 0.3205 \| 0.2828 \| \| 0.0698 \| 50.0 \| 1250 \| 0.0732 \| 0.4725 \| 0.7875 \| 2.8382 \| 0.4725 \| 0.4686 \| 0.3364 \| 0.2831 \| \| 0.0698 \| 51.0 \| 1275 \| 0.0731 \| 0.4725 \| 0.7861 \| 2.7543 \| 0.4725 \| 0.4661 \| 0.3229 \| 0.2838 \| \| 0.0698 \| 52.0 \| 1300 \| 0.0731 \| 0.475 \| 0.7863 \| 2.7936 \| 0.4750 \| 0.4771 \| 0.3285 \| 0.2801 \| \| 0.0698 \| 53.0 \| 1325 \| 0.0731 \| 0.4825 \| 0.7846 \| 2.8369 \| 0.4825 \| 0.4843 \| 0.3369 \| 0.2747 \| \| 0.0698 \| 54.0 \| 1350 \| 0.0731 \| 0.4725 \| 0.7852 \| 2.8102 \| 0.4725 \| 0.4747 \| 0.3175 \| 0.2869 \| \| 0.0698 \| 55.0 \| 1375 \| 0.0731 \| 0.475 \| 0.7855 \| 2.8205 \| 0.4750 \| 0.4801 \| 0.3409 \| 0.2802 \| \| 0.0698 \| 56.0 \| 1400 \| 0.0731 \| 0.48 \| 0.7855 \| 2.7926 \| 0.48 \| 0.4815 \| 0.3403 \| 0.2827 \| \| 0.0698 \| 57.0 \| 1425 \| 0.0731 \| 0.4825 \| 0.7826 \| 2.7536 \| 0.4825 \| 0.4815 \| 0.3381 \| 0.2788 \| \| 0.0698 \| 58.0 \| 1450 \| 0.0731 \| 0.4875 \| 0.7851 \| 2.8313 \| 0.4875 \| 0.4901 \| 0.3395 \| 0.2719 \| \| 0.0698 \| 59.0 \| 1475 \| 0.0731 \| 0.4875 \| 0.7838 \| 2.7423 \| 0.4875 \| 0.4905 \| 0.3410 \| 0.2735 \| \| 0.0654 \| 60.0 \| 1500 \| 0.0731 \| 0.48 \| 0.7849 \| 2.7730 \| 0.48 \| 0.4818 \| 0.3344 \| 0.2807 \| \| 0.0654 \| 61.0 \| 1525 \| 0.0732 \| 0.48 \| 0.7816 \| 2.7517 \| 0.48 \| 0.4813 \| 0.3370 \| 0.2762 \| \| 0.0654 \| 62.0 \| 1550 \| 0.0731 \| 0.4775 \| 0.7833 \| 2.8441 \| 0.4775 \| 0.4804 \| 0.3314 \| 0.2767 \| \| 0.0654 \| 63.0 \| 1575 \| 0.0731 \| 0.4775 \| 0.7835 \| 2.7252 \| 0.4775 \| 0.4811 \| 0.3354 \| 0.2769 \| \| 0.0654 \| 64.0 \| 1600 \| 0.0732 \| 0.4925 \| 0.7819 \| 2.7991 \| 0.4925 \| 0.4958 \| 0.3371 \| 0.2726 \| \| 0.0654 \| 65.0 \| 1625 \| 0.0731 \| 0.4825 \| 0.7806 \| 2.6719 \| 0.4825 \| 0.4850 \| 0.3190 \| 0.2752 \| \| 0.0654 \| 66.0 \| 1650 \| 0.0732 \| 0.48 \| 0.7817 \| 2.7669 \| 0.48 \| 0.4828 \| 0.3336 \| 0.2791 \| \| 0.0654 \| 67.0 \| 1675 \| 0.0731 \| 0.4775 \| 0.7813 \| 2.6678 \| 0.4775 \| 0.4822 \| 0.3304 \| 0.2750 \| \| 0.0654 \| 68.0 \| 1700 \| 0.0732 \| 0.4875 \| 0.7829 \| 2.7529 \| 0.4875 \| 0.4919 \| 0.3381 \| 0.2756 \| \| 0.0654 \| 69.0 \| 1725 \| 0.0731 \| 0.4825 \| 0.7795 \| 2.7291 \| 0.4825 \| 0.4839 \| 0.3418 \| 0.2737 \| \| 0.0654 \| 70.0 \| 1750 \| 0.0732 \| 0.4875 \| 0.7827 \| 2.7613 \| 0.4875 \| 0.4909 \| 0.3308 \| 0.2747 \| \| 0.0654 \| 71.0 \| 1775 \| 0.0732 \| 0.4825 \| 0.7816 \| 2.7348 \| 0.4825 \| 0.4863 \| 0.3306 \| 0.2733 \| \| 0.0654 \| 72.0 \| 1800 \| 0.0732 \| 0.4825 \| 0.7813 \| 2.6920 \| 0.4825 \| 0.4863 \| 0.3268 \| 0.2724 \| \| 0.0654 \| 73.0 \| 1825 \| 0.0731 \| 0.485 \| 0.7809 \| 2.6890 \| 0.485 \| 0.4872 \| 0.3307 \| 0.2741 \| \| 0.0654 \| 74.0 \| 1850 \| 0.0732 \| 0.4825 \| 0.7810 \| 2.6668 \| 0.4825 \| 0.4854 \| 0.3245 \| 0.2758 \| \| 0.0654 \| 75.0 \| 1875 \| 0.0732 \| 0.48 \| 0.7814 \| 2.7337 \| 0.48 \| 0.4836 \| 0.3232 \| 0.2767 \| \| 0.0654 \| 76.0 \| 1900 \| 0.0731 \| 0.49 \| 0.7802 \| 2.7219 \| 0.49 \| 0.4900 \| 0.3290 \| 0.2727 \| \| 0.0654 \| 77.0 \| 1925 \| 0.0732 \| 0.48 \| 0.7804 \| 2.7187 \| 0.48 \| 0.4821 \| 0.3223 \| 0.2759 \| \| 0.0654 \| 78.0 \| 1950 \| 0.0732 \| 0.485 \| 0.7811 \| 2.6797 \| 0.485 \| 0.4884 \| 0.3343 \| 0.2754 \| \| 0.0654 \| 79.0 \| 1975 \| 0.0731 \| 0.48 \| 0.7784 \| 2.6604 \| 0.48 \| 0.4816 \| 0.3345 \| 0.2751 \| \| 0.0641 \| 80.0 \| 2000 \| 0.0732 \| 0.485 \| 0.7797 \| 2.6380 \| 0.485 \| 0.4876 \| 0.3317 \| 0.2755 \| \| 0.0641 \| 81.0 \| 2025 \| 0.0732 \| 0.4775 \| 0.7805 \| 2.6934 \| 0.4775 \| 0.4808 \| 0.3225 \| 0.2758 \| \| 0.0641 \| 82.0 \| 2050 \| 0.0732 \| 0.4825 \| 0.7802 \| 2.7315 \| 0.4825 \| 0.4851 \| 0.3364 \| 0.2781 \| \| 0.0641 \| 83.0 \| 2075 \| 0.0732 \| 0.4875 \| 0.7800 \| 2.7011 \| 0.4875 \| 0.4899 \| 0.3222 \| 0.2736 \| \| 0.0641 \| 84.0 \| 2100 \| 0.0732 \| 0.4825 \| 0.7796 \| 2.6672 \| 0.4825 \| 0.4845 \| 0.3203 \| 0.2772 \| \| 0.0641 \| 85.0 \| 2125 \| 0.0732 \| 0.4825 \| 0.7798 \| 2.6956 \| 0.4825 \| 0.4833 \| 0.3373 \| 0.2757 \| \| 0.0641 \| 86.0 \| 2150 \| 0.0732 \| 0.48 \| 0.7797 \| 2.6349 \| 0.48 \| 0.4823 \| 0.3265 \| 0.2774 \| \| 0.0641 \| 87.0 \| 2175 \| 0.0732 \| 0.49 \| 0.7800 \| 2.7238 \| 0.49 \| 0.4921 \| 0.3407 \| 0.2755 \| \| 0.0641 \| 88.0 \| 2200 \| 0.0732 \| 0.4775 \| 0.7800 \| 2.6423 \| 0.4775 \| 0.4804 \| 0.3163 \| 0.2785 \| \| 0.0641 \| 89.0 \| 2225 \| 0.0732 \| 0.485 \| 0.7793 \| 2.6734 \| 0.485 \| 0.4881 \| 0.3310 \| 0.2760 \| \| 0.0641 \| 90.0 \| 2250 \| 0.0732 \| 0.4825 \| 0.7796 \| 2.6582 \| 0.4825 \| 0.4858 \| 0.3232 \| 0.2774 \| \| 0.0641 \| 91.0 \| 2275 \| 0.0732 \| 0.485 \| 0.7790 \| 2.6705 \| 0.485 \| 0.4882 \| 0.3277 \| 0.2760 \| \| 0.0641 \| 92.0 \| 2300 \| 0.0732 \| 0.49 \| 0.7795 \| 2.6465 \| 0.49 \| 0.4943 \| 0.3513 \| 0.2767 \| \| 0.0641 \| 93.0 \| 2325 \| 0.0732 \| 0.4825 \| 0.7791 \| 2.6495 \| 0.4825 \| 0.4852 \| 0.3414 \| 0.2763 \| \| 0.0641 \| 94.0 \| 2350 \| 0.0732 \| 0.49 \| 0.7793 \| 2.6402 \| 0.49 \| 0.4933 \| 0.3458 \| 0.2760 \| \| 0.0641 \| 95.0 \| 2375 \| 0.0732 \| 0.4875 \| 0.7792 \| 2.6448 \| 0.4875 \| 0.4898 \| 0.3420 \| 0.2763 \| \| 0.0641 \| 96.0 \| 2400 \| 0.0732 \| 0.4825 \| 0.7792 \| 2.6402 \| 0.4825 \| 0.4847 \| 0.3346 \| 0.2766 \| \| 0.0641 \| 97.0 \| 2425 \| 0.0733 \| 0.485 \| 0.7793 \| 2.6397 \| 0.485 \| 0.4873 \| 0.3407 \| 0.2768 \| \| 0.0641 \| 98.0 \| 2450 \| 0.0732 \| 0.4825 \| 0.7790 \| 2.6388 \| 0.4825 \| 0.4847 \| 0.3374 \| 0.2763 \| \| 0.0641 \| 99.0 \| 2475 \| 0.0733 \| 0.4825 \| 0.7792 \| 2.6390 \| 0.4825 \| 0.4847 \| 0.3393 \| 0.2767 \| \| 0.0637 \| 100.0 \| 2500 \| 0.0733 \| 0.4825 \| 0.7791 \| 2.6387 \| 0.4825 \| 0.4847 \| 0.3427 \| 0.2765 \| ### Framework versions - Transformers 4.26.1 - Pytorch 1.13.1.post200 - Datasets 2.9.0 - Tokenizers 0.13.2
muhtasham/bert-small-finetuned-xglue-ner	muhtasham	2023-07-12T00:22:27Z	107	0	transformers	[ "transformers", "pytorch", "tensorboard", "safetensors", "bert", "token-classification", "generated_from_trainer", "dataset:wnut_17", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	token-classification	2022-08-17T12:37:35Z	--- license: apache-2.0 tags: - generated_from_trainer datasets: - wnut_17 metrics: - precision - recall - f1 - accuracy model-index: - name: bert-small-finetuned-xglue-ner results: - task: name: Token Classification type: token-classification dataset: name: wnut_17 type: wnut_17 config: wnut_17 split: train args: wnut_17 metrics: - name: Precision type: precision value: 0.5931899641577061 - name: Recall type: recall value: 0.39593301435406697 - name: F1 type: f1 value: 0.4748923959827833 - name: Accuracy type: accuracy value: 0.9251634361738732 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # bert-small-finetuned-xglue-ner This model is a fine-tuned version of [google/bert_uncased_L-4_H-512_A-8](https://huggingface.co/google/bert_uncased_L-4_H-512_A-8) on the wnut_17 dataset. It achieves the following results on the evaluation set: - Loss: 0.3663 - Precision: 0.5932 - Recall: 0.3959 - F1: 0.4749 - Accuracy: 0.9252 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Precision \| Recall \| F1 \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:---------:\|:------:\|:------:\|:--------:\| \| No log \| 1.0 \| 425 \| 0.3590 \| 0.6185 \| 0.3433 \| 0.4415 \| 0.9220 \| \| 0.2242 \| 2.0 \| 850 \| 0.3638 \| 0.6226 \| 0.3947 \| 0.4832 \| 0.9245 \| \| 0.1219 \| 3.0 \| 1275 \| 0.3663 \| 0.5932 \| 0.3959 \| 0.4749 \| 0.9252 \| ### Framework versions - Transformers 4.21.1 - Pytorch 1.12.1+cu113 - Datasets 2.4.0 - Tokenizers 0.12.1
vnktrmnb/bert-base-multilingual-cased-finetuned-TeQuAD	vnktrmnb	2023-07-12T00:03:24Z	61	0	transformers	[ "transformers", "tf", "tensorboard", "bert", "question-answering", "generated_from_keras_callback", "license:apache-2.0", "endpoints_compatible", "region:us" ]	question-answering	2023-07-10T07:32:30Z	--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: vnktrmnb/bert-base-multilingual-cased-finetuned-TeQuAD results: [] --- <!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. --> # vnktrmnb/bert-base-multilingual-cased-finetuned-TeQuAD This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 2.7973 - Train End Logits Accuracy: 0.3293 - Train Start Logits Accuracy: 0.3521 - Validation Loss: 2.0625 - Validation End Logits Accuracy: 0.4527 - Validation Start Logits Accuracy: 0.4720 - Epoch: 0 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.0001, 'decay_steps': 7331, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results \| Train Loss \| Train End Logits Accuracy \| Train Start Logits Accuracy \| Validation Loss \| Validation End Logits Accuracy \| Validation Start Logits Accuracy \| Epoch \| \|:----------:\|:-------------------------:\|:---------------------------:\|:---------------:\|:------------------------------:\|:--------------------------------:\|:-----:\| \| 2.7973 \| 0.3293 \| 0.3521 \| 2.0625 \| 0.4527 \| 0.4720 \| 0 \| ### Framework versions - Transformers 4.30.2 - TensorFlow 2.12.0 - Datasets 2.13.1 - Tokenizers 0.13.3
jordyvl/vit-small_rvl_cdip_100_examples_per_class_simkd_CEKD_tNone_aNone_tNone_gNone	jordyvl	2023-07-12T00:02:54Z	164	0	transformers	[ "transformers", "pytorch", "vit", "image-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2023-07-10T22:30:40Z	--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: vit-small_rvl_cdip_100_examples_per_class_simkd_CEKD_tNone_aNone_tNone_gNone results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # vit-small_rvl_cdip_100_examples_per_class_simkd_CEKD_tNone_aNone_tNone_gNone This model is a fine-tuned version of [WinKawaks/vit-small-patch16-224](https://huggingface.co/WinKawaks/vit-small-patch16-224) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.0689 - Accuracy: 0.6 - Brier Loss: 0.6433 - Nll: 2.4057 - F1 Micro: 0.6 - F1 Macro: 0.6101 - Ece: 0.3353 - Aurc: 0.1685 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| Brier Loss \| Nll \| F1 Micro \| F1 Macro \| Ece \| Aurc \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:----------:\|:------:\|:--------:\|:--------:\|:------:\|:------:\| \| No log \| 1.0 \| 25 \| 0.0859 \| 0.0675 \| 0.9373 \| 7.3238 \| 0.0675 \| 0.0163 \| 0.1099 \| 0.9351 \| \| No log \| 2.0 \| 50 \| 0.0810 \| 0.0675 \| 0.9372 \| 7.0436 \| 0.0675 \| 0.0153 \| 0.1067 \| 0.9365 \| \| No log \| 3.0 \| 75 \| 0.0804 \| 0.0725 \| 0.9368 \| 6.5507 \| 0.0725 \| 0.0268 \| 0.1041 \| 0.9438 \| \| No log \| 4.0 \| 100 \| 0.0800 \| 0.0725 \| 0.9362 \| 6.2816 \| 0.0725 \| 0.0293 \| 0.1056 \| 0.9404 \| \| No log \| 5.0 \| 125 \| 0.0797 \| 0.0775 \| 0.9352 \| 6.1624 \| 0.0775 \| 0.0225 \| 0.1125 \| 0.9037 \| \| No log \| 6.0 \| 150 \| 0.0793 \| 0.0875 \| 0.9337 \| 6.0364 \| 0.0875 \| 0.0376 \| 0.1173 \| 0.8572 \| \| No log \| 7.0 \| 175 \| 0.0788 \| 0.13 \| 0.9307 \| 4.5728 \| 0.13 \| 0.0918 \| 0.1430 \| 0.7693 \| \| No log \| 8.0 \| 200 \| 0.0781 \| 0.2325 \| 0.9246 \| 3.6321 \| 0.2325 \| 0.1958 \| 0.2225 \| 0.5621 \| \| No log \| 9.0 \| 225 \| 0.0770 \| 0.31 \| 0.9103 \| 3.3593 \| 0.31 \| 0.2693 \| 0.2782 \| 0.4570 \| \| No log \| 10.0 \| 250 \| 0.0755 \| 0.34 \| 0.8830 \| 2.9550 \| 0.34 \| 0.2911 \| 0.2951 \| 0.4131 \| \| No log \| 11.0 \| 275 \| 0.0740 \| 0.4075 \| 0.8559 \| 2.6844 \| 0.4075 \| 0.3802 \| 0.3347 \| 0.3241 \| \| No log \| 12.0 \| 300 \| 0.0730 \| 0.47 \| 0.8216 \| 2.7315 \| 0.47 \| 0.4439 \| 0.3582 \| 0.2707 \| \| No log \| 13.0 \| 325 \| 0.0720 \| 0.4925 \| 0.7913 \| 2.6641 \| 0.4925 \| 0.4606 \| 0.3561 \| 0.2588 \| \| No log \| 14.0 \| 350 \| 0.0717 \| 0.4725 \| 0.7854 \| 2.7229 \| 0.4725 \| 0.4565 \| 0.3296 \| 0.2732 \| \| No log \| 15.0 \| 375 \| 0.0708 \| 0.5125 \| 0.7515 \| 2.4866 \| 0.5125 \| 0.4890 \| 0.3445 \| 0.2379 \| \| No log \| 16.0 \| 400 \| 0.0704 \| 0.5375 \| 0.7424 \| 2.4355 \| 0.5375 \| 0.5131 \| 0.3525 \| 0.2259 \| \| No log \| 17.0 \| 425 \| 0.0702 \| 0.545 \| 0.7259 \| 2.5234 \| 0.545 \| 0.5227 \| 0.3427 \| 0.2199 \| \| No log \| 18.0 \| 450 \| 0.0696 \| 0.545 \| 0.7253 \| 2.5796 \| 0.545 \| 0.5318 \| 0.3471 \| 0.2118 \| \| No log \| 19.0 \| 475 \| 0.0697 \| 0.56 \| 0.7163 \| 2.3050 \| 0.56 \| 0.5547 \| 0.3494 \| 0.2048 \| \| 0.0745 \| 20.0 \| 500 \| 0.0692 \| 0.565 \| 0.7044 \| 2.4019 \| 0.565 \| 0.5669 \| 0.3598 \| 0.1869 \| \| 0.0745 \| 21.0 \| 525 \| 0.0690 \| 0.5775 \| 0.6983 \| 2.3271 \| 0.5775 \| 0.5805 \| 0.3615 \| 0.1906 \| \| 0.0745 \| 22.0 \| 550 \| 0.0689 \| 0.58 \| 0.6855 \| 2.2368 \| 0.58 \| 0.5808 \| 0.3572 \| 0.1851 \| \| 0.0745 \| 23.0 \| 575 \| 0.0690 \| 0.56 \| 0.6905 \| 2.4557 \| 0.56 \| 0.5709 \| 0.3387 \| 0.1925 \| \| 0.0745 \| 24.0 \| 600 \| 0.0688 \| 0.57 \| 0.6895 \| 2.3632 \| 0.57 \| 0.5736 \| 0.3516 \| 0.1912 \| \| 0.0745 \| 25.0 \| 625 \| 0.0686 \| 0.5775 \| 0.6826 \| 2.3272 \| 0.5775 \| 0.5838 \| 0.3376 \| 0.1802 \| \| 0.0745 \| 26.0 \| 650 \| 0.0689 \| 0.5625 \| 0.6886 \| 2.2696 \| 0.5625 \| 0.5754 \| 0.3445 \| 0.1917 \| \| 0.0745 \| 27.0 \| 675 \| 0.0687 \| 0.575 \| 0.6765 \| 2.3387 \| 0.575 \| 0.5800 \| 0.3511 \| 0.1861 \| \| 0.0745 \| 28.0 \| 700 \| 0.0689 \| 0.5775 \| 0.6785 \| 2.3039 \| 0.5775 \| 0.5821 \| 0.3546 \| 0.1860 \| \| 0.0745 \| 29.0 \| 725 \| 0.0685 \| 0.6 \| 0.6720 \| 2.4176 \| 0.6 \| 0.6013 \| 0.3606 \| 0.1750 \| \| 0.0745 \| 30.0 \| 750 \| 0.0685 \| 0.5925 \| 0.6690 \| 2.2827 \| 0.5925 \| 0.5962 \| 0.3646 \| 0.1750 \| \| 0.0745 \| 31.0 \| 775 \| 0.0685 \| 0.5825 \| 0.6682 \| 2.2957 \| 0.5825 \| 0.5885 \| 0.3476 \| 0.1771 \| \| 0.0745 \| 32.0 \| 800 \| 0.0687 \| 0.585 \| 0.6700 \| 2.2669 \| 0.585 \| 0.5914 \| 0.3428 \| 0.1797 \| \| 0.0745 \| 33.0 \| 825 \| 0.0685 \| 0.59 \| 0.6652 \| 2.3359 \| 0.59 \| 0.5927 \| 0.3429 \| 0.1775 \| \| 0.0745 \| 34.0 \| 850 \| 0.0686 \| 0.5825 \| 0.6717 \| 2.3900 \| 0.5825 \| 0.5919 \| 0.3453 \| 0.1790 \| \| 0.0745 \| 35.0 \| 875 \| 0.0685 \| 0.5875 \| 0.6721 \| 2.3131 \| 0.5875 \| 0.5932 \| 0.3579 \| 0.1799 \| \| 0.0745 \| 36.0 \| 900 \| 0.0686 \| 0.5925 \| 0.6625 \| 2.3435 \| 0.5925 \| 0.6005 \| 0.3441 \| 0.1728 \| \| 0.0745 \| 37.0 \| 925 \| 0.0685 \| 0.5875 \| 0.6649 \| 2.4475 \| 0.5875 \| 0.5885 \| 0.3550 \| 0.1756 \| \| 0.0745 \| 38.0 \| 950 \| 0.0685 \| 0.5925 \| 0.6607 \| 2.2842 \| 0.5925 \| 0.5962 \| 0.3410 \| 0.1732 \| \| 0.0745 \| 39.0 \| 975 \| 0.0685 \| 0.6 \| 0.6605 \| 2.2073 \| 0.6 \| 0.6083 \| 0.3414 \| 0.1708 \| \| 0.0599 \| 40.0 \| 1000 \| 0.0685 \| 0.575 \| 0.6578 \| 2.3075 \| 0.575 \| 0.5788 \| 0.3341 \| 0.1773 \| \| 0.0599 \| 41.0 \| 1025 \| 0.0685 \| 0.5975 \| 0.6598 \| 2.1562 \| 0.5975 \| 0.6067 \| 0.3462 \| 0.1685 \| \| 0.0599 \| 42.0 \| 1050 \| 0.0685 \| 0.5925 \| 0.6592 \| 2.3363 \| 0.5925 \| 0.5999 \| 0.3262 \| 0.1733 \| \| 0.0599 \| 43.0 \| 1075 \| 0.0683 \| 0.5925 \| 0.6545 \| 2.2970 \| 0.5925 \| 0.5975 \| 0.3413 \| 0.1741 \| \| 0.0599 \| 44.0 \| 1100 \| 0.0686 \| 0.5975 \| 0.6590 \| 2.2220 \| 0.5975 \| 0.6061 \| 0.3425 \| 0.1698 \| \| 0.0599 \| 45.0 \| 1125 \| 0.0684 \| 0.585 \| 0.6563 \| 2.2507 \| 0.585 \| 0.5876 \| 0.3214 \| 0.1795 \| \| 0.0599 \| 46.0 \| 1150 \| 0.0684 \| 0.5975 \| 0.6578 \| 2.2677 \| 0.5975 \| 0.6082 \| 0.3374 \| 0.1712 \| \| 0.0599 \| 47.0 \| 1175 \| 0.0684 \| 0.5925 \| 0.6531 \| 2.3091 \| 0.5925 \| 0.5974 \| 0.3362 \| 0.1716 \| \| 0.0599 \| 48.0 \| 1200 \| 0.0685 \| 0.5825 \| 0.6539 \| 2.3803 \| 0.5825 \| 0.5901 \| 0.3098 \| 0.1790 \| \| 0.0599 \| 49.0 \| 1225 \| 0.0685 \| 0.59 \| 0.6518 \| 2.1855 \| 0.59 \| 0.6001 \| 0.3229 \| 0.1759 \| \| 0.0599 \| 50.0 \| 1250 \| 0.0685 \| 0.595 \| 0.6513 \| 2.3357 \| 0.595 \| 0.6004 \| 0.3307 \| 0.1711 \| \| 0.0599 \| 51.0 \| 1275 \| 0.0684 \| 0.59 \| 0.6499 \| 2.3253 \| 0.59 \| 0.5968 \| 0.3298 \| 0.1708 \| \| 0.0599 \| 52.0 \| 1300 \| 0.0684 \| 0.61 \| 0.6500 \| 2.3352 \| 0.61 \| 0.6196 \| 0.3692 \| 0.1687 \| \| 0.0599 \| 53.0 \| 1325 \| 0.0685 \| 0.595 \| 0.6518 \| 2.2189 \| 0.595 \| 0.6036 \| 0.3278 \| 0.1735 \| \| 0.0599 \| 54.0 \| 1350 \| 0.0684 \| 0.6025 \| 0.6501 \| 2.3238 \| 0.6025 \| 0.6114 \| 0.3410 \| 0.1668 \| \| 0.0599 \| 55.0 \| 1375 \| 0.0684 \| 0.595 \| 0.6479 \| 2.2696 \| 0.595 \| 0.6022 \| 0.3341 \| 0.1719 \| \| 0.0599 \| 56.0 \| 1400 \| 0.0685 \| 0.595 \| 0.6496 \| 2.3172 \| 0.595 \| 0.6008 \| 0.3239 \| 0.1720 \| \| 0.0599 \| 57.0 \| 1425 \| 0.0684 \| 0.595 \| 0.6476 \| 2.2983 \| 0.595 \| 0.6023 \| 0.3310 \| 0.1667 \| \| 0.0599 \| 58.0 \| 1450 \| 0.0684 \| 0.605 \| 0.6483 \| 2.2607 \| 0.605 \| 0.6140 \| 0.3563 \| 0.1660 \| \| 0.0599 \| 59.0 \| 1475 \| 0.0685 \| 0.5975 \| 0.6491 \| 2.3956 \| 0.5975 \| 0.6091 \| 0.3222 \| 0.1691 \| \| 0.0576 \| 60.0 \| 1500 \| 0.0685 \| 0.5925 \| 0.6476 \| 2.2049 \| 0.5925 \| 0.6032 \| 0.3240 \| 0.1716 \| \| 0.0576 \| 61.0 \| 1525 \| 0.0685 \| 0.6 \| 0.6482 \| 2.3095 \| 0.6 \| 0.6068 \| 0.3276 \| 0.1703 \| \| 0.0576 \| 62.0 \| 1550 \| 0.0685 \| 0.6025 \| 0.6448 \| 2.2755 \| 0.6025 \| 0.6101 \| 0.3303 \| 0.1673 \| \| 0.0576 \| 63.0 \| 1575 \| 0.0685 \| 0.6 \| 0.6480 \| 2.3857 \| 0.6 \| 0.6078 \| 0.3358 \| 0.1687 \| \| 0.0576 \| 64.0 \| 1600 \| 0.0685 \| 0.59 \| 0.6465 \| 2.3280 \| 0.59 \| 0.5990 \| 0.3198 \| 0.1705 \| \| 0.0576 \| 65.0 \| 1625 \| 0.0684 \| 0.605 \| 0.6438 \| 2.3484 \| 0.605 \| 0.6125 \| 0.3346 \| 0.1651 \| \| 0.0576 \| 66.0 \| 1650 \| 0.0686 \| 0.6 \| 0.6462 \| 2.2443 \| 0.6 \| 0.6084 \| 0.3371 \| 0.1706 \| \| 0.0576 \| 67.0 \| 1675 \| 0.0685 \| 0.6025 \| 0.6449 \| 2.3717 \| 0.6025 \| 0.6115 \| 0.3317 \| 0.1674 \| \| 0.0576 \| 68.0 \| 1700 \| 0.0685 \| 0.595 \| 0.6449 \| 2.3396 \| 0.595 \| 0.6003 \| 0.3292 \| 0.1676 \| \| 0.0576 \| 69.0 \| 1725 \| 0.0686 \| 0.595 \| 0.6460 \| 2.3315 \| 0.595 \| 0.6047 \| 0.3339 \| 0.1683 \| \| 0.0576 \| 70.0 \| 1750 \| 0.0687 \| 0.5975 \| 0.6480 \| 2.3967 \| 0.5975 \| 0.6070 \| 0.3404 \| 0.1702 \| \| 0.0576 \| 71.0 \| 1775 \| 0.0686 \| 0.6 \| 0.6456 \| 2.3870 \| 0.6 \| 0.6095 \| 0.3215 \| 0.1689 \| \| 0.0576 \| 72.0 \| 1800 \| 0.0686 \| 0.59 \| 0.6455 \| 2.3966 \| 0.59 \| 0.5985 \| 0.3273 \| 0.1691 \| \| 0.0576 \| 73.0 \| 1825 \| 0.0686 \| 0.5875 \| 0.6472 \| 2.3619 \| 0.5875 \| 0.5975 \| 0.3465 \| 0.1711 \| \| 0.0576 \| 74.0 \| 1850 \| 0.0686 \| 0.595 \| 0.6436 \| 2.4181 \| 0.595 \| 0.6054 \| 0.3183 \| 0.1706 \| \| 0.0576 \| 75.0 \| 1875 \| 0.0686 \| 0.6 \| 0.6440 \| 2.4160 \| 0.6 \| 0.6077 \| 0.3285 \| 0.1677 \| \| 0.0576 \| 76.0 \| 1900 \| 0.0687 \| 0.6025 \| 0.6446 \| 2.4184 \| 0.6025 \| 0.6111 \| 0.3408 \| 0.1685 \| \| 0.0576 \| 77.0 \| 1925 \| 0.0686 \| 0.6025 \| 0.6440 \| 2.4208 \| 0.6025 \| 0.6111 \| 0.3323 \| 0.1670 \| \| 0.0576 \| 78.0 \| 1950 \| 0.0687 \| 0.5975 \| 0.6438 \| 2.4236 \| 0.5975 \| 0.6063 \| 0.3298 \| 0.1689 \| \| 0.0576 \| 79.0 \| 1975 \| 0.0687 \| 0.5975 \| 0.6438 \| 2.4521 \| 0.5975 \| 0.6057 \| 0.3328 \| 0.1692 \| \| 0.0565 \| 80.0 \| 2000 \| 0.0687 \| 0.6 \| 0.6448 \| 2.4213 \| 0.6 \| 0.6088 \| 0.3368 \| 0.1682 \| \| 0.0565 \| 81.0 \| 2025 \| 0.0688 \| 0.5975 \| 0.6444 \| 2.4257 \| 0.5975 \| 0.6076 \| 0.3179 \| 0.1681 \| \| 0.0565 \| 82.0 \| 2050 \| 0.0687 \| 0.6 \| 0.6446 \| 2.4225 \| 0.6 \| 0.6102 \| 0.3392 \| 0.1673 \| \| 0.0565 \| 83.0 \| 2075 \| 0.0687 \| 0.6 \| 0.6437 \| 2.4571 \| 0.6 \| 0.6091 \| 0.3281 \| 0.1681 \| \| 0.0565 \| 84.0 \| 2100 \| 0.0688 \| 0.595 \| 0.6439 \| 2.4360 \| 0.595 \| 0.6042 \| 0.3256 \| 0.1685 \| \| 0.0565 \| 85.0 \| 2125 \| 0.0688 \| 0.6 \| 0.6436 \| 2.4396 \| 0.6 \| 0.6104 \| 0.3318 \| 0.1683 \| \| 0.0565 \| 86.0 \| 2150 \| 0.0688 \| 0.6 \| 0.6434 \| 2.3977 \| 0.6 \| 0.6095 \| 0.3273 \| 0.1675 \| \| 0.0565 \| 87.0 \| 2175 \| 0.0688 \| 0.595 \| 0.6432 \| 2.4303 \| 0.595 \| 0.6053 \| 0.3146 \| 0.1687 \| \| 0.0565 \| 88.0 \| 2200 \| 0.0688 \| 0.5975 \| 0.6431 \| 2.4222 \| 0.5975 \| 0.6071 \| 0.3326 \| 0.1686 \| \| 0.0565 \| 89.0 \| 2225 \| 0.0688 \| 0.6 \| 0.6440 \| 2.4042 \| 0.6 \| 0.6108 \| 0.3303 \| 0.1678 \| \| 0.0565 \| 90.0 \| 2250 \| 0.0688 \| 0.6 \| 0.6433 \| 2.3998 \| 0.6 \| 0.6096 \| 0.3301 \| 0.1679 \| \| 0.0565 \| 91.0 \| 2275 \| 0.0689 \| 0.6 \| 0.6434 \| 2.4026 \| 0.6 \| 0.6108 \| 0.3362 \| 0.1680 \| \| 0.0565 \| 92.0 \| 2300 \| 0.0689 \| 0.5975 \| 0.6435 \| 2.4037 \| 0.5975 \| 0.6083 \| 0.3335 \| 0.1680 \| \| 0.0565 \| 93.0 \| 2325 \| 0.0689 \| 0.5975 \| 0.6434 \| 2.4060 \| 0.5975 \| 0.6077 \| 0.3344 \| 0.1679 \| \| 0.0565 \| 94.0 \| 2350 \| 0.0689 \| 0.6 \| 0.6433 \| 2.4024 \| 0.6 \| 0.6106 \| 0.3204 \| 0.1683 \| \| 0.0565 \| 95.0 \| 2375 \| 0.0689 \| 0.595 \| 0.6432 \| 2.4060 \| 0.595 \| 0.6052 \| 0.3423 \| 0.1684 \| \| 0.0565 \| 96.0 \| 2400 \| 0.0689 \| 0.6 \| 0.6432 \| 2.4044 \| 0.6 \| 0.6101 \| 0.3404 \| 0.1684 \| \| 0.0565 \| 97.0 \| 2425 \| 0.0689 \| 0.6 \| 0.6434 \| 2.4042 \| 0.6 \| 0.6101 \| 0.3349 \| 0.1683 \| \| 0.0565 \| 98.0 \| 2450 \| 0.0689 \| 0.6 \| 0.6432 \| 2.4055 \| 0.6 \| 0.6101 \| 0.3390 \| 0.1684 \| \| 0.0565 \| 99.0 \| 2475 \| 0.0689 \| 0.6 \| 0.6433 \| 2.4056 \| 0.6 \| 0.6101 \| 0.3393 \| 0.1685 \| \| 0.056 \| 100.0 \| 2500 \| 0.0689 \| 0.6 \| 0.6433 \| 2.4057 \| 0.6 \| 0.6101 \| 0.3353 \| 0.1685 \| ### Framework versions - Transformers 4.26.1 - Pytorch 1.13.1.post200 - Datasets 2.9.0 - Tokenizers 0.13.2
ben-xl8/wmt22-cometkiwi-da	ben-xl8	2023-07-11T23:59:39Z	0	1	null	[ "translation", "multilingual", "af", "am", "ar", "as", "az", "be", "bg", "bn", "br", "bs", "ca", "cs", "cy", "da", "de", "el", "en", "eo", "es", "et", "eu", "fa", "fi", "fr", "fy", "ga", "gd", "gl", "gu", "ha", "he", "hi", "hr", "hu", "hy", "id", "is", "it", "ja", "jv", "ka", "kk", "km", "kn", "ko", "ku", "ky", "la", "lo", "lt", "lv", "mg", "mk", "ml", "mn", "mr", "ms", "my", "ne", "nl", "no", "om", "or", "pa", "pl", "ps", "pt", "ro", "ru", "sa", "sd", "si", "sk", "sl", "so", "sq", "sr", "su", "sv", "sw", "ta", "te", "th", "tl", "tr", "ug", "uk", "ur", "uz", "vi", "xh", "yi", "zh", "license:cc-by-nc-sa-4.0", "endpoints_compatible", "region:us" ]	translation	2023-07-11T20:03:20Z	--- extra_gated_heading: Acknowledge license to accept the repository extra_gated_button_content: Acknowledge license pipeline_tag: translation language: - multilingual - af - am - ar - as - az - be - bg - bn - br - bs - ca - cs - cy - da - de - el - en - eo - es - et - eu - fa - fi - fr - fy - ga - gd - gl - gu - ha - he - hi - hr - hu - hy - id - is - it - ja - jv - ka - kk - km - kn - ko - ku - ky - la - lo - lt - lv - mg - mk - ml - mn - mr - ms - my - ne - nl - no - om - or - pa - pl - ps - pt - ro - ru - sa - sd - si - sk - sl - so - sq - sr - su - sv - sw - ta - te - th - tl - tr - ug - uk - ur - uz - vi - xh - yi - zh license: cc-by-nc-sa-4.0 --- This is a [COMET](https://github.com/Unbabel/COMET) quality estimation model by Unbabel: It receives a source sentence and the respective translation and returns a score that reflects the quality of the translation. # Paper [CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task](https://aclanthology.org/2022.wmt-1.60) (Rei et al., WMT 2022) # License: cc-by-nc-sa-4.0 # Usage for Inference Endpoint ```python import json import requests API_URL = "" API_TOKEN="MY_API_KEY" headers = { "Authorization": f"Bearer {API_TOKEN}", "Content-Type": "application/json", } def query(url, headers, payload): data = json.dumps(payload) response = requests.request("POST", url, headers=headers, data=data) return json.loads(response.content.decode("utf-8")) payload = { "inputs": { "batch_size": 8, "workers": None, "data": [ { "src": "Youll be picking fruit and generally helping us do all the usual farm work", "mt": "당신은 과일을 따기도 하고 대체로 우리가 하는 일상적인 농장 일을 돕게 될 겁니다", },{ "src": "Youll be picking fruit and generally helping us do all the usual farm work", "mt": "당신은 과일을 따기도 하고 대체로 우리가 하는 일상적인 농장 일을 돕게 될 겁니다", },{ "src": "Youll be picking fruit and generally helping us do all the usual farm work", "mt": "당신은 과일을 따기도 하고 대체로 우리가 하는 일상적인 농장 일을 돕게 될 겁니다", },{ "src": "Youll be picking fruit and generally helping us do all the usual farm work", "mt": "당신은 과일을 따기도 하고 대체로 우리가 하는 일상적인 농장 일을 돕게 될 겁니다", },{ "src": "Youll be picking fruit and generally helping us do all the usual farm work", "mt": "당신은 과일을 따기도 하고 대체로 우리가 하는 일상적인 농장 일을 돕게 될 겁니다", },{ "src": "Youll be picking fruit and generally helping us do all the usual farm work", "mt": "당신은 과일을 따기도 하고 대체로 우리가 하는 일상적인 농장 일을 돕게 될 겁니다", },{ "src": "Youll be picking fruit and generally helping us do all the usual farm work", "mt": "당신은 과일을 따기도 하고 대체로 우리가 하는 일상적인 농장 일을 돕게 될 겁니다", }, ] } } scores = query(API_URL, headers, payload) ``` # Intended uses Unbabel's model is intented to be used for reference-free MT evaluation. Given a source text and its translation, outputs a single score between 0 and 1 where 1 represents a perfect translation. # Languages Covered: This model builds on top of InfoXLM which cover the following languages: Afrikaans, Albanian, Amharic, Arabic, Armenian, Assamese, Azerbaijani, Basque, Belarusian, Bengali, Bengali Romanized, Bosnian, Breton, Bulgarian, Burmese, Burmese, Catalan, Chinese (Simplified), Chinese (Traditional), Croatian, Czech, Danish, Dutch, English, Esperanto, Estonian, Filipino, Finnish, French, Galician, Georgian, German, Greek, Gujarati, Hausa, Hebrew, Hindi, Hindi Romanized, Hungarian, Icelandic, Indonesian, Irish, Italian, Japanese, Javanese, Kannada, Kazakh, Khmer, Korean, Kurdish (Kurmanji), Kyrgyz, Lao, Latin, Latvian, Lithuanian, Macedonian, Malagasy, Malay, Malayalam, Marathi, Mongolian, Nepali, Norwegian, Oriya, Oromo, Pashto, Persian, Polish, Portuguese, Punjabi, Romanian, Russian, Sanskri, Scottish, Gaelic, Serbian, Sindhi, Sinhala, Slovak, Slovenian, Somali, Spanish, Sundanese, Swahili, Swedish, Tamil, Tamil Romanized, Telugu, Telugu Romanized, Thai, Turkish, Ukrainian, Urdu, Urdu Romanized, Uyghur, Uzbek, Vietnamese, Welsh, Western, Frisian, Xhosa, Yiddish. Thus, results for language pairs containing uncovered languages are unreliable!
arminmrm93/rl_course_vizdoom_health_gathering_supreme	arminmrm93	2023-07-11T23:56:33Z	0	0	sample-factory	[ "sample-factory", "tensorboard", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2023-07-11T23:56:25Z	--- library_name: sample-factory tags: - deep-reinforcement-learning - reinforcement-learning - sample-factory model-index: - name: APPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: doom_health_gathering_supreme type: doom_health_gathering_supreme metrics: - type: mean_reward value: 9.52 +/- 4.74 name: mean_reward verified: false --- A(n) APPO model trained on the doom_health_gathering_supreme environment. This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory. Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/ ## Downloading the model After installing Sample-Factory, download the model with: ``` python -m sample_factory.huggingface.load_from_hub -r arminmrm93/rl_course_vizdoom_health_gathering_supreme ``` ## Using the model To run the model after download, use the `enjoy` script corresponding to this environment: ``` python -m .usr.local.lib.python3.10.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme ``` You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag. See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details ## Training with this model To continue training with this model, use the `train` script corresponding to this environment: ``` python -m .usr.local.lib.python3.10.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000 ``` Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
optimum/tiny-stable-diffusion-neuronx	optimum	2023-07-11T23:50:33Z	0	1	null	[ "region:us" ]	null	2023-07-10T11:59:42Z	This is a dummy model used for testing `NeuronStableDiffusionPipeline` of `optimum-neuron`. ```python from optimum.neuron import NeuronStableDiffusionPipeline model_id = "optimum/tiny-stable-diffusion-neuronx" input_shapes = {"batch_size": 2, "sequence_length": 18, "num_channels": 4, "height": 64, "width": 64} stable_diffusion = NeuronStableDiffusionPipeline.from_pretrained(model_id, export=True, **input_shapes) save_directory = "sd_neuron/" stable_diffusion.save_pretrained(save_directory) prompt = "sailing ship in storm by Leonardo da Vinci" image = stable_diffusion(prompt).images[0] ```
JTStephens/PixelCopterV1	JTStephens	2023-07-11T23:18:40Z	0	0	null	[ "Pixelcopter-PLE-v0", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]	reinforcement-learning	2023-07-11T23:18:15Z	--- tags: - Pixelcopter-PLE-v0 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: PixelCopterV1 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Pixelcopter-PLE-v0 type: Pixelcopter-PLE-v0 metrics: - type: mean_reward value: 20.80 +/- 14.26 name: mean_reward verified: false --- # Reinforce Agent playing Pixelcopter-PLE-v0 This is a trained model of a Reinforce agent playing Pixelcopter-PLE-v0 . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
sl8425/troubleshooting_steps_printer	sl8425	2023-07-11T23:07:39Z	61	0	transformers	[ "transformers", "tf", "distilbert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2023-07-11T20:49:26Z	--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: sl8425/troubleshooting_steps_printer results: [] --- <!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. --> # sl8425/troubleshooting_steps_printer This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 0.8644 - Validation Loss: 0.8744 - Train Accuracy: 0.7457 - Epoch: 2 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 369, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results \| Train Loss \| Validation Loss \| Train Accuracy \| Epoch \| \|:----------:\|:---------------:\|:--------------:\|:-----:\| \| 1.6729 \| 1.1343 \| 0.6428 \| 0 \| \| 1.0262 \| 0.9056 \| 0.7366 \| 1 \| \| 0.8644 \| 0.8744 \| 0.7457 \| 2 \| ### Framework versions - Transformers 4.30.2 - TensorFlow 2.12.0 - Datasets 2.13.1 - Tokenizers 0.13.3
talaugust/sci-writing-strategies	talaugust	2023-07-11T23:05:34Z	0	0	null	[ "region:us" ]	null	2023-07-11T22:42:06Z	RoBERTa Science writing strategy classifiers This is a finetuned BART Large model from the paper: "Writing Strategies for Science Communication: Data and Computational Analysis", By Tal August, Lauren Kim, Katharina Reinecke, and Noah A. Smith Published at the Conference on Empirical Methods in Natural Language Processing (EMNLP) 2020. Abstract: Communicating complex scientific ideas without misleading or overwhelming the public is challenging. While science communication guides exist, they rarely offer empirical evidence for how their strategies are used in practice. Writing strategies that can be automatically recognized could greatly support science communication efforts by enabling tools to detect and suggest strategies for writers. We compile a set of writing strategies drawn from a wide range of prescriptive sources and develop an annotation scheme allowing humans to recognize them. We collect a corpus of 128k science writing documents in English and annotate a subset of this corpus. We use the annotations to train transformer-based classifiers and measure the strategies’ use in the larger corpus. We find that the use of strategies, such as storytelling and emphasizing the most important findings, varies significantly across publications with different reader audiences. Description The model is finetuned on the task of identifying if a given sentence from a science news article is using a particular writing strategy (e.g., emphasizing the real world impact of the scientific findings). The intended use of this model is to identify common science communication writing strategies. The model is trained on annotated sentences drawn from science news articles. The URLs for the original news articles are at [https://github.com/talaugust/scientific-writing-strategies]. Biases & Limitations The goal of this model is to enable a wider audience of readers to understand and engage with scientific writing. A risk, though, is that such attempts might instead widen the gap to accessing scientific information. The texts in the datasets we train our models on are in General or Academic American. English. Many people, especially those who have been historically underrepresented in STEM disciplines and medicine, may not be comfortable with this dialect of English. This risks further alienating the readers we hope to serve. An important and exciting direction in NLP is making models more flexible to dialects and low-resource languages.
SHENMU007/neunit_BASE_V11.4	SHENMU007	2023-07-11T22:52:37Z	75	0	transformers	[ "transformers", "pytorch", "tensorboard", "speecht5", "text-to-audio", "1.1.0", "generated_from_trainer", "zh", "dataset:facebook/voxpopuli", "base_model:microsoft/speecht5_tts", "base_model:finetune:microsoft/speecht5_tts", "license:mit", "endpoints_compatible", "region:us" ]	text-to-audio	2023-07-11T20:08:34Z	--- language: - zh license: mit base_model: microsoft/speecht5_tts tags: - 1.1.0 - generated_from_trainer datasets: - facebook/voxpopuli model-index: - name: SpeechT5 TTS Dutch neunit results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # SpeechT5 TTS Dutch neunit This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the VoxPopuli dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - training_steps: 4000 ### Training results ### Framework versions - Transformers 4.31.0.dev0 - Pytorch 2.0.1+cu117 - Datasets 2.12.0 - Tokenizers 0.13.3
crowbarmassage/ppo-Pyramids	crowbarmassage	2023-07-11T22:48:42Z	1	0	ml-agents	[ "ml-agents", "tensorboard", "onnx", "Pyramids", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Pyramids", "region:us" ]	reinforcement-learning	2023-07-11T22:48:40Z	--- library_name: ml-agents tags: - Pyramids - deep-reinforcement-learning - reinforcement-learning - ML-Agents-Pyramids --- # ppo Agent playing Pyramids This is a trained model of a ppo agent playing Pyramids using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A short tutorial where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A longer tutorial to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent playing directly in your browser 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: crowbarmassage/ppo-Pyramids 3. Step 2: Select your .nn /.onnx file 4. Click on Watch the agent play 👀
fgeyer/a2c-AntBulletEnv-v0	fgeyer	2023-07-11T22:40:23Z	0	0	stable-baselines3	[ "stable-baselines3", "AntBulletEnv-v0", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2023-07-11T22:24:37Z	--- library_name: stable-baselines3 tags: - AntBulletEnv-v0 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: A2C results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: AntBulletEnv-v0 type: AntBulletEnv-v0 metrics: - type: mean_reward value: 2384.01 +/- 64.45 name: mean_reward verified: false --- # A2C Agent playing AntBulletEnv-v0 This is a trained model of a A2C agent playing AntBulletEnv-v0 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
ysmaicon/distilbert-base-uncased-finetuned-cola	ysmaicon	2023-07-11T22:04:26Z	61	0	transformers	[ "transformers", "tf", "tensorboard", "distilbert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2023-07-11T21:15:40Z	--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: ysmaicon/distilbert-base-uncased-finetuned-cola results: [] --- <!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. --> # ysmaicon/distilbert-base-uncased-finetuned-cola This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 0.1941 - Validation Loss: 0.5355 - Train Matthews Correlation: 0.5256 - Epoch: 2 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1602, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results \| Train Loss \| Validation Loss \| Train Matthews Correlation \| Epoch \| \|:----------:\|:---------------:\|:--------------------------:\|:-----:\| \| 0.5184 \| 0.4689 \| 0.4919 \| 0 \| \| 0.3229 \| 0.4772 \| 0.5191 \| 1 \| \| 0.1941 \| 0.5355 \| 0.5256 \| 2 \| ### Framework versions - Transformers 4.30.2 - TensorFlow 2.12.0 - Datasets 2.13.1 - Tokenizers 0.13.3
a9i/scarlett-7b	a9i	2023-07-11T21:37:46Z	4	1	transformers	[ "transformers", "pytorch", "llama", "text-generation", "text2text-generation", "en", "license:cc-by-nc-nd-4.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text2text-generation	2023-07-11T20:53:43Z	--- license: cc-by-nc-nd-4.0 language: - en pipeline_tag: text2text-generation ---
JuS2/ppo-Huggy	JuS2	2023-07-11T21:28:22Z	0	0	ml-agents	[ "ml-agents", "tensorboard", "onnx", "Huggy", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Huggy", "region:us" ]	reinforcement-learning	2023-07-11T21:28:12Z	--- library_name: ml-agents tags: - Huggy - deep-reinforcement-learning - reinforcement-learning - ML-Agents-Huggy --- # ppo Agent playing Huggy This is a trained model of a ppo agent playing Huggy using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A short tutorial where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A longer tutorial to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent playing directly in your browser 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: JuS2/ppo-Huggy 3. Step 2: Select your .nn /.onnx file 4. Click on Watch the agent play 👀
ethannhzhouu/gpt2-generator	ethannhzhouu	2023-07-11T21:11:54Z	209	0	transformers	[ "transformers", "pytorch", "tensorboard", "gpt2", "text-generation", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-07-11T21:11:25Z	--- license: apache-2.0 tags: - generated_from_trainer model-index: - name: gpt2-generator results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # gpt2-generator This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the None dataset. It achieves the following results on the evaluation set: - Loss: 4.7855 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3.0 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| No log \| 1.0 \| 1 \| 5.3997 \| \| No log \| 2.0 \| 2 \| 4.9524 \| \| No log \| 3.0 \| 3 \| 4.7855 \| ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
devasheeshG/whisper_medium_fp16_transformers	devasheeshG	2023-07-11T21:09:33Z	107	2	transformers	[ "transformers", "pytorch", "whisper", "automatic-speech-recognition", "audio", "speech", "wav2vec2", "en", "zh", "de", "es", "ru", "ko", "fr", "ja", "pt", "tr", "pl", "ca", "nl", "ar", "sv", "it", "id", "hi", "fi", "vi", "he", "uk", "el", "ms", "cs", "ro", "da", "hu", "ta", "no", "th", "ur", "hr", "bg", "lt", "la", "mi", "ml", "cy", "sk", "te", "fa", "lv", "bn", "sr", "az", "sl", "kn", "et", "mk", "br", "eu", "is", "hy", "ne", "mn", "bs", "kk", "sq", "sw", "gl", "mr", "pa", "si", "km", "sn", "yo", "so", "af", "oc", "ka", "be", "tg", "sd", "gu", "am", "yi", "lo", "uz", "fo", "ht", "ps", "tk", "nn", "mt", "sa", "lb", "my", "bo", "tl", "mg", "as", "tt", "haw", "ln", "ha", "ba", "jw", "su", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	2023-07-02T11:04:37Z	--- license: apache-2.0 pipeline_tag: automatic-speech-recognition tags: - pytorch - audio - speech - automatic-speech-recognition - whisper - wav2vec2 model-index: - name: whisper_medium_fp16_transformers results: - task: type: automatic-speech-recognition name: Automatic Speech Recognition dataset: type: librispeech_asr name: LibriSpeech (clean) config: clean split: test args: language: en metrics: - type: wer value: 0 name: Test WER description: Word Error Rate - type: mer value: 0 name: Test MER description: Match Error Rate - type: wil value: 0 name: Test WIL description: Word Information Lost - type: wip value: 0 name: Test WIP description: Word Information Preserved - type: cer value: 0 name: Test CER description: Character Error Rate - task: type: automatic-speech-recognition name: Automatic Speech Recognition dataset: type: librispeech_asr name: LibriSpeech (other) config: other split: test args: language: en metrics: - type: wer value: 0 name: Test WER description: Word Error Rate - type: mer value: 0 name: Test MER description: Match Error Rate - type: wil value: 0 name: Test WIL description: Word Information Lost - type: wip value: 0 name: Test WIP description: Word Information Preserved - type: cer value: 0 name: Test CER description: Character Error Rate - task: type: automatic-speech-recognition name: Automatic Speech Recognition dataset: type: mozilla-foundation/common_voice_14_0 name: Common Voice (14.0) (Hindi) config: hi split: test args: language: hi metrics: - type: wer value: 54.97 name: Test WER description: Word Error Rate - type: mer value: 47.86 name: Test MER description: Match Error Rate - type: wil value: 66.83 name: Test WIL description: Word Information Lost - type: wip value: 33.16 name: Test WIP description: Word Information Preserved - type: cer value: 30.23 name: Test CER description: Character Error Rate widget: - example_title: Hinglish Sample src: https://huggingface.co/devasheeshG/whisper_medium_fp16_transformers/resolve/main/test.wav - example_title: Librispeech sample 1 src: https://cdn-media.huggingface.co/speech_samples/sample1.flac - example_title: Librispeech sample 2 src: https://cdn-media.huggingface.co/speech_samples/sample2.flac language: - en - zh - de - es - ru - ko - fr - ja - pt - tr - pl - ca - nl - ar - sv - it - id - hi - fi - vi - he - uk - el - ms - cs - ro - da - hu - ta - 'no' - th - ur - hr - bg - lt - la - mi - ml - cy - sk - te - fa - lv - bn - sr - az - sl - kn - et - mk - br - eu - is - hy - ne - mn - bs - kk - sq - sw - gl - mr - pa - si - km - sn - yo - so - af - oc - ka - be - tg - sd - gu - am - yi - lo - uz - fo - ht - ps - tk - nn - mt - sa - lb - my - bo - tl - mg - as - tt - haw - ln - ha - ba - jw - su --- ## Versions: - CUDA: 12.1 - cuDNN Version: 8.9.2.26_1.0-1_amd64 * tensorflow Version: 2.12.0 * torch Version: 2.1.0.dev20230606+cu12135 * transformers Version: 4.30.2 * accelerate Version: 0.20.3 ## Model Benchmarks: - RAM: 2.8 GB (Original_Model: 5.5GB) - VRAM: 1812 MB (Original_Model: 6GB) - test.wav: 23 s (Multilingual Speech i.e. English+Hindi) - Time in seconds for Processing by each device \| Device Name \| float32 (Original) \| float16 \| CudaCores \| TensorCores \| \| ----------------- \| ------------------ \| ------- \| --------- \| ----------- \| \| 3060 \| 1.7 \| 1.1 \| 3,584 \| 112 \| \| 1660 Super \| OOM \| 3.3 \| 1,408 \| N/A \| \| Collab (Tesla T4) \| 2.8 \| 2.2 \| 2,560 \| 320 \| \| Collab (CPU) \| 35 \| N/A \| N/A \| N/A \| \| M1 (CPU) \| - \| - \| - \| - \| \| M1 (GPU -> 'mps') \| - \| - \| - \| - \| - NOTE: TensorCores are efficient in mixed-precision calculations - CPU -> torch.float16 not supported on CPU (AMD Ryzen 5 3600 or Collab CPU) - Punchuation: True ## Model Error Benchmarks: - WER: Word Error Rate - MER: Match Error Rate - WIL: Word Information Lost - WIP: Word Information Preserved - CER: Character Error Rate ### Hindi to Hindi (test.tsv) [Common Voice 14.0](https://commonvoice.mozilla.org/en/datasets) Test done on RTX 3060 on 2557 Samples \| \| WER \| MER \| WIL \| WIP \| CER \| \| ----------------------- \| ----- \| ----- \| ----- \| ----- \| ----- \| \| Original_Model (54 min) \| 52.02 \| 47.86 \| 66.82 \| 33.17 \| 23.76 \| \| This_Model (38 min) \| 54.97 \| 47.86 \| 66.83 \| 33.16 \| 30.23 \| ### Hindi to English (test.csv) [Custom Dataset](https://huggingface.co/datasets/devasheeshG/common_voices_14_0_hi2en_hi2hi) Test done on RTX 3060 on 1000 Samples \| \| WER \| MER \| WIL \| WIP \| CER \| \| ----------------------- \| --- \| --- \| --- \| --- \| --- \| \| Original_Model (30 min) \| - \| - \| - \| - \| - \| \| This_Model (20 min) \| - \| - \| - \| - \| - \| ### English ([LibriSpeech](https://huggingface.co/datasets/librispeech_asr) -> test-clean) Test done on RTX 3060 on __ Samples \| \| WER \| MER \| WIL \| WIP \| CER \| \| -------------- \| --- \| --- \| --- \| --- \| --- \| \| Original_Model \| - \| - \| - \| - \| - \| \| This_Model \| - \| - \| - \| - \| - \| ### English ([LibriSpeech](https://huggingface.co/datasets/librispeech_asr) -> test-other) Test done on RTX 3060 on __ Samples \| \| WER \| MER \| WIL \| WIP \| CER \| \| -------------- \| --- \| --- \| --- \| --- \| --- \| \| Original_Model \| - \| - \| - \| - \| - \| \| This_Model \| - \| - \| - \| - \| - \| - 'jiwer' library is used for calculations ## Code for conversion: - ### [Will be soon Uploaded on Github](https://github.com/devasheeshG) ## Usage A file ``__init__.py`` is contained inside this repo which contains all the code to use this model. Firstly, clone this repo and place all the files inside a folder. ### Make sure you have git-lfs installed (https://git-lfs.com) ```bash git lfs install git clone https://huggingface.co/devasheeshG/whisper_medium_fp16_transformers ``` Please try in jupyter notebook ```python # Import the Model from whisper_medium_fp16_transformers import Model, load_audio, pad_or_trim ``` ```python # Initilise the model model = Model( model_name_or_path='whisper_medium_fp16_transformers', cuda_visible_device="0", device='cuda', ) ``` ```python # Load Audio audio = load_audio('whisper_medium_fp16_transformers/test.wav') audio = pad_or_trim(audio) ``` ```python # Transcribe (First transcription takes time) model.transcribe(audio) ``` ## Credits It is fp16 version of ``openai/whisper-medium``

Ashish9947/Programming_Question_Answer

Ashish9947

2023-07-12T11:03:37Z

0

peft

[ "peft", "region:us" ]

null

2023-07-11T13:43:02Z

--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.4.0.dev0

AyoubChLin/BERT-Large_BBC_news

AyoubChLin

2023-07-12T11:02:11Z

112

3

transformers

[ "transformers", "pytorch", "safetensors", "bert", "text-classification", "autotrain", "en", "dataset:AyoubChLin/autotrain-data-bert_bbc_news", "dataset:SetFit/bbc-news", "license:apache-2.0", "co2_eq_emissions", "autotrain_compatible", "endpoints_compatible", "region:us" ]

text-classification

2023-04-12T18:20:07Z

--- tags: - autotrain - text-classification language: - en widget: - text: I love AutoTrain 🤗 datasets: - AyoubChLin/autotrain-data-bert_bbc_news - SetFit/bbc-news co2_eq_emissions: emissions: 2.010596202760941 license: apache-2.0 metrics: - accuracy pipeline_tag: text-classification --- # Model Trained Using AutoTrain - Problem type: Multi-class Classification - Model ID: 48925118418 - CO2 Emissions (in grams): 2.0106 ## Validation Metrics - Loss: 0.126 - Accuracy: 0.979 - Macro F1: 0.979 - Micro F1: 0.979 - Weighted F1: 0.979 - Macro Precision: 0.979 - Micro Precision: 0.979 - Weighted Precision: 0.979 - Macro Recall: 0.979 - Micro Recall: 0.979 - Weighted Recall: 0.979 ## Usage You can use cURL to access this model: ``` $ curl -X POST -H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoTrain"}' https://api-inference.huggingface.co/models/AyoubChLin/autotrain-bert_bbc_news-48925118418 ``` Or Python API: ``` from transformers import AutoModelForSequenceClassification, AutoTokenizer model = AutoModelForSequenceClassification.from_pretrained("AyoubChLin/autotrain-bert_bbc_news-48925118418", use_auth_token=True) tokenizer = AutoTokenizer.from_pretrained("AyoubChLin/autotrain-bert_bbc_news-48925118418", use_auth_token=True) inputs = tokenizer("I love AutoTrain", return_tensors="pt") outputs = model(**inputs) ```

ayushtues/cifar10-32

ayushtues

2023-07-12T11:01:58Z

3

0

diffusers

[ "diffusers", "tensorboard", "consistency models", "base_model:google/ddpm-cifar10-32", "base_model:finetune:google/ddpm-cifar10-32", "license:creativeml-openrail-m", "diffusers:ConsistencyModelPipeline", "region:us" ]

null

2023-06-05T12:30:38Z

--- license: creativeml-openrail-m base_model: google/ddpm-cifar10-32 tags: - consistency models - diffusers inference: true --- # Consistency Model - ayushtues/cifar10-32 This is a consistency model distilled from google/ddpm-cifar10-32. You can find some example images in the following. ![img_0](./image_0.png) ![img_1](./image_1.png) ![img_2](./image_2.png) ![img_3](./image_3.png) ![img_4](./image_4.png) ![img_5](./image_5.png) ![img_6](./image_6.png) ![img_7](./image_7.png) ![img_8](./image_8.png) ![img_9](./image_9.png) ![img_10](./image_10.png) ![img_11](./image_11.png) ![img_12](./image_12.png) ![img_13](./image_13.png) ![img_14](./image_14.png) ![img_15](./image_15.png)

MeenalP/falcon-7b-instruct-ft-adapters

MeenalP

2023-07-12T10:49:32Z

0

peft

[ "peft", "region:us" ]

null

2023-07-10T07:28:08Z

--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.4.0.dev0 - PEFT 0.4.0.dev0 - PEFT 0.4.0.dev0 - PEFT 0.4.0.dev0 - PEFT 0.4.0.dev0 - PEFT 0.4.0.dev0 - PEFT 0.4.0.dev0 - PEFT 0.4.0.dev0

anuragverma77/falcon-7b-ecommerce-FAQ

anuragverma77

2023-07-12T10:08:49Z

0

peft

[ "peft", "region:us" ]

null

2023-07-11T14:54:26Z

--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.4.0.dev0

YanJiangJerry/covid-augment-tweet-bert-large-e4

YanJiangJerry

2023-07-12T10:04:17Z

108

0

transformers

[ "transformers", "pytorch", "bert", "text-classification", "generated_from_trainer", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]

text-classification

2023-07-12T08:24:28Z

--- license: mit tags: - generated_from_trainer metrics: - accuracy - f1 - precision - recall model-index: - name: covid-augment-tweet-bert-large-e4 results: [] ---  # covid-augment-tweet-bert-large-e4 This model is a fine-tuned version of [digitalepidemiologylab/covid-twitter-bert-v2](https://huggingface.co/digitalepidemiologylab/covid-twitter-bert-v2) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.3723 - Accuracy: 0.9587 - F1: 0.8889 - Precision: 0.8920 - Recall: 0.8858 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 4 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:| | 0.1307 | 1.0 | 4089 | 0.3055 | 0.9523 | 0.8771 | 0.8435 | 0.9135 | | 0.0367 | 2.0 | 8178 | 0.3270 | 0.9568 | 0.8885 | 0.8558 | 0.9239 | | 0.0133 | 3.0 | 12267 | 0.3316 | 0.9600 | 0.8949 | 0.8771 | 0.9135 | | 0.0007 | 4.0 | 16356 | 0.3723 | 0.9587 | 0.8889 | 0.8920 | 0.8858 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3

namvuong96/civit_meinamix_meinaV10

namvuong96

2023-07-12T10:02:08Z

29

0

diffusers

[ "diffusers", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]

text-to-image

2023-07-12T09:32:27Z

Link: `https://civitai.com/api/download/models/80511`

matorus/replit-coder

matorus

2023-07-12T09:59:57Z

7

0

transformers

[ "transformers", "pytorch", "mpt", "text-generation", "custom_code", "dataset:matorus/coder", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2023-07-09T20:34:49Z

--- datasets: - matorus/coder --- [replit/replit-code-v1-3b](https://huggingface.co/replit/replit-code-v1-3b) finetuned on [matorus/coder](https://huggingface.co/datasets/matorus/coder). **HumanEval scores**: pass@1: 28.7%, pass@10: 43.3% See [torusresearch/code-eval](https://github.com/torusresearch/code-eval) for evaluation code. Finetuning format: ``` {function_defintion} """ {task} """ {function_body} ```

LZYSaltedFish/chatfish-1b1-sft

LZYSaltedFish

2023-07-12T09:42:31Z

180

0

transformers

[ "transformers", "pytorch", "bloom", "text-generation", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2023-05-23T08:12:22Z

# ChatFish ChatFish是基于[BLOOM](https://huggingface.co/bigscience/bloom-1b1)（11亿参数）训练的中文对话语言模型，此模型为SFT版本。详见[Github](https://github.com/LZYSaltedFish/ChatFish-Chatbot)。 ChatFish is a Chinese dialogue language model trained based on [BLOOM](https://huggingface.co/bigscience/bloom-1b1) (1.1 billion parameters). This model is the SFT version. See [Github](https://github.com/LZYSaltedFish/ChatFish-Chatbot) for details. ## Usage ```python import torch from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained('LZYSaltedFish/chatfish-1b1-sft') tokenizer.pad_token_id = tokenizer.eos_token_id model = AutoModelForCausalLM.from_pretrained('LZYSaltedFish/chatfish-1b1-sft').half() inputs = tokenizer('# Human:\nHello\n\n# Assistant:\n', return_tensors='pt').to(torch.cuda.current_device()) model.to(torch.cuda.current_device()) output = model.generate(**inputs, max_length=1024, do_sample=True, temperature=0.7, top_k=50, early_stopping=True, repetition_penalty=1.0) output = tokenizer.decode(output[0], skip_special_tokens=True) print(output) ``` ## Cases 尽管这个模型只有1.1B参数，但也显示出同样不错的能力。以下是一些例子: Although this model has only 1.1B parameters, but also shows the same not bad ability. Here are some cases: <details><summary>Writing</summary> ```xml # Human: 因为工作钱少事多，我打算跟领导提出辞职，请你帮我写一份正式的辞呈 # Assistant: 尊敬的领导，首先感谢您给予我的机会，让我可以在您的团队中发挥自己的能力。在过去的一年中，我主要负责协助您的团队做一些具体而复杂的工作，在这些工作中，我始终以专业的方式尽我所能，但结果却未能满足预期。对于我的表现，您可能会问：为什么？因为工作钱少事多，对比起其他同事的丰厚的薪酬，我的薪酬确实比较底。虽然我也努力工作，但工作量太多，加上事情太多，所以我的薪酬也难以达到理想水平。综上所述，我认为自己无法在您的工作中发挥出自己的能力，因此辞任团队成员职位，返回自己的职业生涯独立发展。谢谢您理解，敬礼， X ``` </details> <details><summary>Common Sense</summary> ```xml # Human: 我们有探索太空的道德义务吗，还是我们应该专注于首先解决地球的问题? # Assistant: 在当前，我们拥有探索太空的道德义务，我们必须保护地球，因为太空是向地球输出的重要水源，地球的水资源是人类未来可持续发展的重要基础。此外，我们也可以专注于解决地球上的问题，比如改善环境、减缓气候变化和减少犯罪等。 ``` </details> <details><summary>Chatting</summary> ```xml # Human: 我感觉最近都好低迷啊 # Assistant: 我理解你的心情，有时候低谷会让我们感到疲惫甚至失去希望，但请记住，每个人都有自己独特的故事和经历，这些故事和经历可能随时都可能发生。你可以从中吸取宝贵的经验，寻找自己的方向，并继续前行。请记住，每个人都有自己的能力，可以从中学习新知识，建立新的联系，也可以探索你自己的潜能，只要不放弃，任何事情都是可能的。 # Human: 有什么具体的办法能帮助我改善这种感觉吗 # Assistant: 你可以尝试以下几种方法： 1. 制定计划：给自己定一个目标，制定一个可行的计划，每天坚持完成，可以帮助你保持积极的心态和前进的动力。 2. 重新定义自己的方向：在低谷中，重新审视自己的方向，发现新的潜能，可以给你带来更多的力量。 3. 寻求帮助：如果你感到疲惫，没有动力，可以尝试寻求帮助，可以找到一些自己可以完成的任务，或者可以理解的理解。 4. 给自己时间：给自己一些时间，让自己放松，可以给自己一些休息时间，让自己得到休息。 5. 找到支持：与朋友、家人沟通，可以倾听他们的建议和鼓励的话语，获得他们的安慰和支持，可以让自己更有信心和勇气去面对困难。 # Human: 我喜欢打球，打球可以吗 # Assistant: 当然可以！打球不仅可以提高身体素质，而且可以锻炼心肺能力，增强肌肉力量，增强协调性和平衡感，同时也能够提升自我安全感和抗压能力。当然，如果想成为专业运动员，需要坚持训练，克服各种困难，提高技术水平和团队合作精神，这也是可以的。希望我的建议能帮到您。 ``` </details> <details><summary>Role Playing</summary> ```xml # Human: 你是一名登山者，即将登顶珠穆朗玛峰。描述你的情绪和从上到下的观点。 # Assistant: 当我看到珠穆朗玛峰高耸入云，阳光从它的基础照射使我感到温暖而温暖。我会从基础向上看到它爬升到天际，我会感受到无限的兴奋和激励，因为我是一名登山者，我将努力登顶，完成我的梦想。我会从上到下的观点，从海拔最高的山脉看到较低的山峰，看到自然美景，看到自然风光，激发我更加努力攀登的动力。 ``` </details> ## Usage Limits 我们使用的数据集要求开发人员仅将数据用于研究目的。因此，不允许将我们的模型用于商业以及其他潜在的有害用途。 The datasets we used require developers only use the data for research purposes. Thus, commercial and other potentially harmful uses of our models are not allowed.

ksol8/virile_reality_v2

ksol8

2023-07-12T09:27:22Z

0

1

null

[ "license:creativeml-openrail-m", "region:us" ]

null

2023-07-12T07:13:04Z

--- license: creativeml-openrail-m ---

Relex169/ppo-LunarLander-v2

Relex169

2023-07-12T09:26:27Z

0

stable-baselines3

[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

reinforcement-learning

2023-07-12T09:24:05Z

--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 250.70 +/- 22.25 name: mean_reward verified: false --- # **PPO** Agent playing **LunarLander-v2** This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```

lgrobol/BERTrade-FlauBERT

lgrobol

2023-07-12T09:23:13Z

106

0

transformers

[ "transformers", "pytorch", "safetensors", "flaubert", "fill-mask", "fro", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]

fill-mask

2023-03-10T16:43:56Z

--- license: mit language: - fro pipeline_tag: fill-mask library_name: transformers --- BERTrade-FlauBERT ================= This contextual embeddings model for Old French was developped as part of the work of Grobol, Regnault, Ortiz-Suarez et al. ([2022](https://aclanthology.org/2022.lrec-1.119/)), we refer to it for a list of the resources and the settings used to develop this model as well as assessment of their suitability for syntactic dependency parsing of Old French. If you use it, please cite the original paper: ```bibtex @inproceedings{grobol-etal-2022-bertrade, title = "{BERT}rade: Using Contextual Embeddings to Parse {O}ld {F}rench", author = {Grobol, Lo{\"\i}c and Regnault, Mathilde and Ortiz Suarez, Pedro and Sagot, Beno{\^\i}t and Romary, Laurent and Crabb{\'e}, Benoit}, booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference", month = jun, year = "2022", address = "Marseille, France", publisher = "European Language Resources Association", url = "https://aclanthology.org/2022.lrec-1.119", pages = "1104--1113", abstract = "The successes of contextual word embeddings learned by training large-scale language models, while remarkable, have mostly occurred for languages where significant amounts of raw texts are available and where annotated data in downstream tasks have a relatively regular spelling. Conversely, it is not yet completely clear if these models are also well suited for lesser-resourced and more irregular languages. We study the case of Old French, which is in the interesting position of having relatively limited amount of available raw text, but enough annotated resources to assess the relevance of contextual word embedding models for downstream NLP tasks. In particular, we use POS-tagging and dependency parsing to evaluate the quality of such models in a large array of configurations, including models trained from scratch from small amounts of raw text and models pre-trained on other languages but fine-tuned on Medieval French data.", } ```

Suryadia/LoRaWhisper2

Suryadia

2023-07-12T09:10:57Z

0

1

peft

[ "peft", "tensorboard", "region:us" ]

null

2023-07-12T03:11:05Z

--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 The following `bitsandbytes` quantization config was used during training: - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 ### Framework versions - PEFT 0.4.0.dev0 - PEFT 0.4.0.dev0

hyllius/ReinforceCartPole

hyllius

2023-07-12T09:02:23Z

0

null

[ "CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]

reinforcement-learning

2023-07-12T09:02:16Z

--- tags: - CartPole-v1 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: ReinforceCartPole results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: CartPole-v1 type: CartPole-v1 metrics: - type: mean_reward value: 500.00 +/- 0.00 name: mean_reward verified: false --- # **Reinforce** Agent playing **CartPole-v1** This is a trained model of a **Reinforce** agent playing **CartPole-v1** . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction

Aeala/Enterredaas-65b-GGML

Aeala

2023-07-12T08:52:08Z

0

3

null

[ "region:us" ]

null

2023-07-04T02:42:06Z

GGML quantizations of [Enterredaas-65b](https://huggingface.co/Aeala/Enterredaas-65b-QLoRA) **Important Note**: This was trained in the *Alpaca* format, so prompting should be something like: ``` ### Instruction: <system prompt> (without the <>, this works like telling the AI what it is/purpose. i.e. like ChatGPT API's system prompt) ### Input: <prompt> (without the <>) ### Response: ```

markjosims/wav2vec2-large-xls-r-300m-tira-colab

markjosims

2023-07-12T08:46:07Z

12

0

transformers

[ "transformers", "pytorch", "tensorboard", "wav2vec2", "automatic-speech-recognition", "generated_from_trainer", "license:apache-2.0", "endpoints_compatible", "region:us" ]

automatic-speech-recognition

2023-07-11T22:37:49Z

--- license: apache-2.0 tags: - generated_from_trainer metrics: - wer model-index: - name: wav2vec2-large-xls-r-300m-tira-colab results: [] ---  # wav2vec2-large-xls-r-300m-tira-colab This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.2681 - Wer: 0.2787 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0003 - train_batch_size: 16 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - num_epochs: 30 ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | |:-------------:|:-----:|:----:|:---------------:|:------:| | 4.2937 | 1.45 | 400 | 1.0460 | 0.9297 | | 0.9157 | 2.9 | 800 | 0.5732 | 0.6728 | | 0.6258 | 4.35 | 1200 | 0.4319 | 0.5434 | | 0.5114 | 5.8 | 1600 | 0.3822 | 0.5465 | | 0.4059 | 7.25 | 2000 | 0.3439 | 0.4700 | | 0.3407 | 8.7 | 2400 | 0.2997 | 0.4778 | | 0.2938 | 10.14 | 2800 | 0.2956 | 0.4121 | | 0.2465 | 11.59 | 3200 | 0.2834 | 0.3537 | | 0.2148 | 13.04 | 3600 | 0.2662 | 0.3779 | | 0.1711 | 14.49 | 4000 | 0.2724 | 0.3160 | | 0.1621 | 15.94 | 4400 | 0.2452 | 0.3571 | | 0.1301 | 17.39 | 4800 | 0.2638 | 0.2927 | | 0.1119 | 18.84 | 5200 | 0.2724 | 0.2765 | | 0.1026 | 20.29 | 5600 | 0.2703 | 0.2986 | | 0.0906 | 21.74 | 6000 | 0.2642 | 0.2638 | | 0.0785 | 23.19 | 6400 | 0.2653 | 0.2709 | | 0.0648 | 24.64 | 6800 | 0.2644 | 0.2669 | | 0.0578 | 26.09 | 7200 | 0.2712 | 0.3123 | | 0.0514 | 27.54 | 7600 | 0.2703 | 0.2672 | | 0.0459 | 28.99 | 8000 | 0.2681 | 0.2787 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3

kazzand/ru-longformer-large-4096

kazzand

2023-07-12T08:45:32Z

829

0

transformers

[ "transformers", "pytorch", "longformer", "fill-mask", "ru", "autotrain_compatible", "endpoints_compatible", "region:us" ]

fill-mask

2023-07-11T02:17:22Z

--- language: - ru --- This is a large Longformer model designed for Russian language. It was initialized from [ai-forever/ruRoberta-large](https://huggingface.co/ai-forever/ruRoberta-large) weights and has been modified to support a context length of up to 4096 tokens. We fine-tuned it on a dataset of Russian books. For a detailed information check out our post on Habr. Model attributes: * 16 attention heads * 24 hidden layers * 4096 tokens length of context The model can be used as-is to produce text embeddings or it can be further fine-tuned for a specific downstream task. Text embeddings can be produced as follows: ```python # pip install transformers sentencepiece import torch from transformers import LongformerForMaskedLM, LongformerTokenizerFast model = LongformerModel.from_pretrained('kazzand/ru-longformer-large-4096') tokenizer = LongformerTokenizerFast.from_pretrained('kazzand/ru-longformer-large-4096') def get_cls_embedding(text, model, tokenizer, device='cuda'): model.to(device) batch = tokenizer(text, return_tensors='pt') #set global attention for cls token global_attention_mask = [ [1 if token_id == tokenizer.cls_token_id else 0 for token_id in input_ids] for input_ids in batch["input_ids"] ] #add global attention mask to batch batch["global_attention_mask"] = torch.tensor(global_attention_mask) with torch.no_grad(): output = model(**batch.to(device)) return output.last_hidden_state[:,0,:] ```

shape-ai/inpainting

shape-ai

2023-07-12T08:43:27Z

74

0

diffusers

[ "diffusers", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "arxiv:2207.12598", "arxiv:2112.10752", "arxiv:2103.00020", "arxiv:2205.11487", "arxiv:1910.09700", "license:creativeml-openrail-m", "endpoints_compatible", "diffusers:StableDiffusionInpaintPipeline", "region:us" ]

text-to-image

2023-07-11T05:25:30Z

--- license: creativeml-openrail-m tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image inference: false library_name: diffusers extra_gated_prompt: >- One more step before getting this model. This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage. The CreativeML OpenRAIL License specifies: 1. You can't use the model to deliberately produce nor share illegal or harmful outputs or content 2. CompVis claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license 3. You may re-distribute the weights and use the model commercially and/or as a service. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully) Please read the full license here: https://huggingface.co/spaces/CompVis/stable-diffusion-license By clicking on "Access repository" below, you accept that your *contact information* (email address and username) can be shared with the model authors as well. extra_gated_fields: I have read the License and agree with its terms: checkbox duplicated_from: runwayml/stable-diffusion-inpainting --- Stable Diffusion Inpainting is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input, with the extra capability of inpainting the pictures by using a mask. The **Stable-Diffusion-Inpainting** was initialized with the weights of the [Stable-Diffusion-v-1-2](https://steps/huggingface.co/CompVis/stable-diffusion-v-1-2-original). First 595k steps regular training, then 440k steps of inpainting training at resolution 512x512 on “laion-aesthetics v2 5+” and 10% dropping of the text-conditioning to improve classifier-free [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598). For inpainting, the UNet has 5 additional input channels (4 for the encoded masked-image and 1 for the mask itself) whose weights were zero-initialized after restoring the non-inpainting checkpoint. During training, we generate synthetic masks and in 25% mask everything. [![Open In Spaces](https://camo.githubusercontent.com/00380c35e60d6b04be65d3d94a58332be5cc93779f630bcdfc18ab9a3a7d3388/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f25463025394625413425393725323048756767696e67253230466163652d5370616365732d626c7565)](https://huggingface.co/spaces/runwayml/stable-diffusion-inpainting) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/in_painting_with_stable_diffusion_using_diffusers.ipynb) :-------------------------:|:-------------------------:| ## Examples: You can use this both with the [🧨Diffusers library](https://github.com/huggingface/diffusers) and the [RunwayML GitHub repository](https://github.com/runwayml/stable-diffusion). ### Diffusers ```python from diffusers import StableDiffusionInpaintPipeline pipe = StableDiffusionInpaintPipeline.from_pretrained( "runwayml/stable-diffusion-inpainting", revision="fp16", torch_dtype=torch.float16, ) prompt = "Face of a yellow cat, high resolution, sitting on a park bench" #image and mask_image should be PIL images. #The mask structure is white for inpainting and black for keeping as is image = pipe(prompt=prompt, image=image, mask_image=mask_image).images[0] image.save("./yellow_cat_on_park_bench.png") ``` **How it works:** `image` | `mask_image` :-------------------------:|:-------------------------:| <img src="https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png" alt="drawing" width="300"/> | <img src="https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png" alt="drawing" width="300"/> `prompt` | `Output` :-------------------------:|:-------------------------:| Face of a yellow cat, high resolution, sitting on a park bench | <img src="https://huggingface.co/datasets/patrickvonplaten/images/resolve/main/test.png" alt="drawing" width="300"/> ### Original GitHub Repository 1. Download the weights [sd-v1-5-inpainting.ckpt](https://huggingface.co/runwayml/stable-diffusion-inpainting/resolve/main/sd-v1-5-inpainting.ckpt) 2. Follow instructions [here](https://github.com/runwayml/stable-diffusion#inpainting-with-stable-diffusion). ## Model Details - **Developed by:** Robin Rombach, Patrick Esser - **Model type:** Diffusion-based text-to-image generation model - **Language(s):** English - **License:** [The CreativeML OpenRAIL M license](https://huggingface.co/spaces/CompVis/stable-diffusion-license) is an [Open RAIL M license](https://www.licenses.ai/blog/2022/8/18/naming-convention-of-responsible-ai-licenses), adapted from the work that [BigScience](https://bigscience.huggingface.co/) and [the RAIL Initiative](https://www.licenses.ai/) are jointly carrying in the area of responsible AI licensing. See also [the article about the BLOOM Open RAIL license](https://bigscience.huggingface.co/blog/the-bigscience-rail-license) on which our license is based. - **Model Description:** This is a model that can be used to generate and modify images based on text prompts. It is a [Latent Diffusion Model](https://arxiv.org/abs/2112.10752) that uses a fixed, pretrained text encoder ([CLIP ViT-L/14](https://arxiv.org/abs/2103.00020)) as suggested in the [Imagen paper](https://arxiv.org/abs/2205.11487). - **Resources for more information:** [GitHub Repository](https://github.com/runwayml/stable-diffusion), [Paper](https://arxiv.org/abs/2112.10752). - **Cite as:** @InProceedings{Rombach_2022_CVPR, author = {Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj\"orn}, title = {High-Resolution Image Synthesis With Latent Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {10684-10695} } # Uses ## Direct Use The model is intended for research purposes only. Possible research areas and tasks include - Safe deployment of models which have the potential to generate harmful content. - Probing and understanding the limitations and biases of generative models. - Generation of artworks and use in design and other artistic processes. - Applications in educational or creative tools. - Research on generative models. Excluded uses are described below. ### Misuse, Malicious Use, and Out-of-Scope Use _Note: This section is taken from the [DALLE-MINI model card](https://huggingface.co/dalle-mini/dalle-mini), but applies in the same way to Stable Diffusion v1_. The model should not be used to intentionally create or disseminate images that create hostile or alienating environments for people. This includes generating images that people would foreseeably find disturbing, distressing, or offensive; or content that propagates historical or current stereotypes. #### Out-of-Scope Use The model was not trained to be factual or true representations of people or events, and therefore using the model to generate such content is out-of-scope for the abilities of this model. #### Misuse and Malicious Use Using the model to generate content that is cruel to individuals is a misuse of this model. This includes, but is not limited to: - Generating demeaning, dehumanizing, or otherwise harmful representations of people or their environments, cultures, religions, etc. - Intentionally promoting or propagating discriminatory content or harmful stereotypes. - Impersonating individuals without their consent. - Sexual content without consent of the people who might see it. - Mis- and disinformation - Representations of egregious violence and gore - Sharing of copyrighted or licensed material in violation of its terms of use. - Sharing content that is an alteration of copyrighted or licensed material in violation of its terms of use. ## Limitations and Bias ### Limitations - The model does not achieve perfect photorealism - The model cannot render legible text - The model does not perform well on more difficult tasks which involve compositionality, such as rendering an image corresponding to “A red cube on top of a blue sphere” - Faces and people in general may not be generated properly. - The model was trained mainly with English captions and will not work as well in other languages. - The autoencoding part of the model is lossy - The model was trained on a large-scale dataset [LAION-5B](https://laion.ai/blog/laion-5b/) which contains adult material and is not fit for product use without additional safety mechanisms and considerations. - No additional measures were used to deduplicate the dataset. As a result, we observe some degree of memorization for images that are duplicated in the training data. The training data can be searched at [https://rom1504.github.io/clip-retrieval/](https://rom1504.github.io/clip-retrieval/) to possibly assist in the detection of memorized images. ### Bias While the capabilities of image generation models are impressive, they can also reinforce or exacerbate social biases. Stable Diffusion v1 was trained on subsets of [LAION-2B(en)](https://laion.ai/blog/laion-5b/), which consists of images that are primarily limited to English descriptions. Texts and images from communities and cultures that use other languages are likely to be insufficiently accounted for. This affects the overall output of the model, as white and western cultures are often set as the default. Further, the ability of the model to generate content with non-English prompts is significantly worse than with English-language prompts. ## Training **Training Data** The model developers used the following dataset for training the model: - LAION-2B (en) and subsets thereof (see next section) **Training Procedure** Stable Diffusion v1 is a latent diffusion model which combines an autoencoder with a diffusion model that is trained in the latent space of the autoencoder. During training, - Images are encoded through an encoder, which turns images into latent representations. The autoencoder uses a relative downsampling factor of 8 and maps images of shape H x W x 3 to latents of shape H/f x W/f x 4 - Text prompts are encoded through a ViT-L/14 text-encoder. - The non-pooled output of the text encoder is fed into the UNet backbone of the latent diffusion model via cross-attention. - The loss is a reconstruction objective between the noise that was added to the latent and the prediction made by the UNet. We currently provide six checkpoints, `sd-v1-1.ckpt`, `sd-v1-2.ckpt` and `sd-v1-3.ckpt`, `sd-v1-4.ckpt`, `sd-v1-5.ckpt` and `sd-v1-5-inpainting.ckpt` which were trained as follows, - `sd-v1-1.ckpt`: 237k steps at resolution `256x256` on [laion2B-en](https://huggingface.co/datasets/laion/laion2B-en). 194k steps at resolution `512x512` on [laion-high-resolution](https://huggingface.co/datasets/laion/laion-high-resolution) (170M examples from LAION-5B with resolution `>= 1024x1024`). - `sd-v1-2.ckpt`: Resumed from `sd-v1-1.ckpt`. 515k steps at resolution `512x512` on "laion-improved-aesthetics" (a subset of laion2B-en, filtered to images with an original size `>= 512x512`, estimated aesthetics score `> 5.0`, and an estimated watermark probability `< 0.5`. The watermark estimate is from the LAION-5B metadata, the aesthetics score is estimated using an [improved aesthetics estimator](https://github.com/christophschuhmann/improved-aesthetic-predictor)). - `sd-v1-3.ckpt`: Resumed from `sd-v1-2.ckpt`. 195k steps at resolution `512x512` on "laion-improved-aesthetics" and 10\% dropping of the text-conditioning to improve [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598). - `sd-v1-4.ckpt`: Resumed from stable-diffusion-v1-2.225,000 steps at resolution 512x512 on "laion-aesthetics v2 5+" and 10 % dropping of the text-conditioning to [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598). - `sd-v1-5.ckpt`: Resumed from sd-v1-2.ckpt. 595k steps at resolution 512x512 on "laion-aesthetics v2 5+" and 10% dropping of the text-conditioning to improve classifier-free guidance sampling. - `sd-v1-5-inpaint.ckpt`: Resumed from sd-v1-2.ckpt. 595k steps at resolution 512x512 on "laion-aesthetics v2 5+" and 10% dropping of the text-conditioning to improve classifier-free guidance sampling. Then 440k steps of inpainting training at resolution 512x512 on “laion-aesthetics v2 5+” and 10% dropping of the text-conditioning. For inpainting, the UNet has 5 additional input channels (4 for the encoded masked-image and 1 for the mask itself) whose weights were zero-initialized after restoring the non-inpainting checkpoint. During training, we generate synthetic masks and in 25% mask everything. - **Hardware:** 32 x 8 x A100 GPUs - **Optimizer:** AdamW - **Gradient Accumulations**: 2 - **Batch:** 32 x 8 x 2 x 4 = 2048 - **Learning rate:** warmup to 0.0001 for 10,000 steps and then kept constant ## Evaluation Results Evaluations with different classifier-free guidance scales (1.5, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0) and 50 PLMS sampling steps show the relative improvements of the checkpoints: ![pareto](https://huggingface.co/CompVis/stable-diffusion/resolve/main/v1-1-to-v1-5.png) Evaluated using 50 PLMS steps and 10000 random prompts from the COCO2017 validation set, evaluated at 512x512 resolution. Not optimized for FID scores. ## Inpainting Evaluation To assess the performance of the inpainting model, we used the same evaluation protocol as in our [LDM paper](https://arxiv.org/abs/2112.10752). Since the Stable Diffusion Inpainting Model acccepts a text input, we simply used a fixed prompt of `photograph of a beautiful empty scene, highest quality settings`. | Model | FID | LPIPS | |-----------------------------|------|------------------| | Stable Diffusion Inpainting | 1.00 | 0.141 (+- 0.082) | | Latent Diffusion Inpainting | 1.50 | 0.137 (+- 0.080) | | CoModGAN | 1.82 | 0.15 | | LaMa | 2.21 | 0.134 (+- 0.080) | ## Environmental Impact **Stable Diffusion v1** **Estimated Emissions** Based on that information, we estimate the following CO2 emissions using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). The hardware, runtime, cloud provider, and compute region were utilized to estimate the carbon impact. - **Hardware Type:** A100 PCIe 40GB - **Hours used:** 150000 - **Cloud Provider:** AWS - **Compute Region:** US-east - **Carbon Emitted (Power consumption x Time x Carbon produced based on location of power grid):** 11250 kg CO2 eq. ## Citation ```bibtex @InProceedings{Rombach_2022_CVPR, author = {Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj\"orn}, title = {High-Resolution Image Synthesis With Latent Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {10684-10695} } ``` *This model card was written by: Robin Rombach and Patrick Esser and is based on the [DALL-E Mini model card](https://huggingface.co/dalle-mini/dalle-mini).*

nolanaatama/yffmx

nolanaatama

2023-07-12T08:41:59Z

0

null

[ "license:creativeml-openrail-m", "region:us" ]

null

2023-02-08T02:23:42Z

--- license: creativeml-openrail-m ---

kazzand/ru-longformer-base-4096

kazzand

2023-07-12T08:41:57Z

138

0

transformers

[ "transformers", "pytorch", "longformer", "fill-mask", "ru", "autotrain_compatible", "endpoints_compatible", "region:us" ]

fill-mask

2023-07-11T01:52:27Z

--- language: - ru --- This is a base Longformer model designed for Russian language. It was initialized from [blinoff/roberta-base-russian-v0](https://huggingface.co/blinoff/roberta-base-russian-v0) weights and has been modified to support a context length of up to 4096 tokens. We fine-tuned it on a dataset of Russian books. For a detailed information check out our post on Habr. Model attributes: * 12 attention heads * 12 hidden layers * 4096 tokens length of context The model can be used as-is to produce text embeddings or it can be further fine-tuned for a specific downstream task. Text embeddings can be produced as follows: ```python # pip install transformers sentencepiece import torch from transformers import LongformerForMaskedLM, LongformerTokenizerFast model = LongformerModel.from_pretrained('kazzand/ru-longformer-base-4096') tokenizer = LongformerTokenizerFast.from_pretrained('kazzand/ru-longformer-base-4096') def get_cls_embedding(text, model, tokenizer, device='cuda'): model.to(device) batch = tokenizer(text, return_tensors='pt') #set global attention for cls token global_attention_mask = [ [1 if token_id == tokenizer.cls_token_id else 0 for token_id in input_ids] for input_ids in batch["input_ids"] ] #add global attention mask to batch batch["global_attention_mask"] = torch.tensor(global_attention_mask) with torch.no_grad(): output = model(**batch.to(device)) return output.last_hidden_state[:,0,:] ```

yhavinga/byt5-small-ccmatrix-en-nl

yhavinga

2023-07-12T08:40:54Z

118

0

transformers

[ "transformers", "pytorch", "jax", "tensorboard", "safetensors", "t5", "text2text-generation", "byt5", "translation", "seq2seq", "nl", "en", "multilingual", "dataset:yhavinga/mc4_nl_cleaned", "dataset:yhavinga/ccmatrix", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

translation

2022-08-20T11:12:08Z

--- language: - nl - en - multilingual license: apache-2.0 tags: - byt5 - translation - seq2seq datasets: - yhavinga/mc4_nl_cleaned - yhavinga/ccmatrix pipeline_tag: translation widget: - text: 'It is a painful and tragic spectacle that rises before me: I have drawn back the curtain from the rottenness of man. This word, in my mouth, is at least free from one suspicion: that it involves a moral accusation against humanity.' - text: Young Wehling was hunched in his chair, his head in his hand. He was so rumpled, so still and colorless as to be virtually invisible. His camouflage was perfect, since the waiting room had a disorderly and demoralized air, too. Chairs and ashtrays had been moved away from the walls. The floor was paved with spattered dropcloths. --- Logs at https://wandb.ai/yepster/byt5-small-ccmatrix-en-nl/runs/1wm9igj9?workspace=user-yepster

Beams24/nuristl

Beams24

2023-07-12T08:26:21Z

0

null

[ "license:creativeml-openrail-m", "region:us" ]

null

2023-07-11T10:29:51Z

--- license: creativeml-openrail-m ---

longmark/ppo-Huggy

longmark

2023-07-12T08:19:57Z

4

0

ml-agents

[ "ml-agents", "tensorboard", "onnx", "Huggy", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Huggy", "region:us" ]

reinforcement-learning

2023-07-12T08:19:53Z

--- library_name: ml-agents tags: - Huggy - deep-reinforcement-learning - reinforcement-learning - ML-Agents-Huggy --- # **ppo** Agent playing **Huggy** This is a trained model of a **ppo** agent playing **Huggy** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A *longer tutorial* to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent **playing directly in your browser** 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: longmark/ppo-Huggy 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀

edwardjjj/ppo-LunarLander-v2

edwardjjj

2023-07-12T08:09:11Z

2

0

stable-baselines3

[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

reinforcement-learning

2023-06-18T05:37:16Z

--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 251.15 +/- 18.83 name: mean_reward verified: false --- # **PPO** Agent playing **LunarLander-v2** This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```

Ark62/Ishowspeed

Ark62

2023-07-12T08:01:57Z

0

null

[ "arxiv:1910.09700", "region:us" ]

null

2023-07-12T07:52:08Z

--- # For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1 ishowspeed # Doc / guide: https://huggingface.co/docs/hub/model-cards {} --- # Model Card for Model ID ishowspeed This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1). ## Model Details ### Model Description ishowspeed - **Developed by:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

soduhh/distilbert-base-uncased-finetuned-squad-d5716d28

soduhh

2023-07-12T07:50:51Z

105

0

transformers

[ "transformers", "pytorch", "distilbert", "fill-mask", "question-answering", "en", "dataset:squad", "arxiv:1910.01108", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

question-answering

2023-07-12T07:36:17Z

--- language: - en thumbnail: https://github.com/karanchahal/distiller/blob/master/distiller.jpg tags: - question-answering license: apache-2.0 datasets: - squad metrics: - squad --- # DistilBERT with a second step of distillation ## Model description This model replicates the "DistilBERT (D)" model from Table 2 of the [DistilBERT paper](https://arxiv.org/pdf/1910.01108.pdf). In this approach, a DistilBERT student is fine-tuned on SQuAD v1.1, but with a BERT model (also fine-tuned on SQuAD v1.1) acting as a teacher for a second step of task-specific distillation. In this version, the following pre-trained models were used: * Student: `distilbert-base-uncased` * Teacher: `lewtun/bert-base-uncased-finetuned-squad-v1` ## Training data This model was trained on the SQuAD v1.1 dataset which can be obtained from the `datasets` library as follows: ```python from datasets import load_dataset squad = load_dataset('squad') ``` ## Training procedure ## Eval results | | Exact Match | F1 | |------------------|-------------|------| | DistilBERT paper | 79.1 | 86.9 | | Ours | 78.4 | 86.5 | The scores were calculated using the `squad` metric from `datasets`. ### BibTeX entry and citation info ```bibtex @misc{sanh2020distilbert, title={DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter}, author={Victor Sanh and Lysandre Debut and Julien Chaumond and Thomas Wolf}, year={2020}, eprint={1910.01108}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```

LoupGarou/Starcoderplus-Guanaco-GPT4-15B-V1.0

LoupGarou

2023-07-12T07:45:19Z

9

1

transformers

[ "transformers", "pytorch", "gpt_bigcode", "text-generation", "en", "dataset:guanaco", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2023-07-12T05:54:07Z

--- language: - en datasets: - guanaco model_hub_library: - transformers license: - apache-2.0 --- ## Starcoderplus-Guanaco-GPT4-15B-V1.0 Model Card Starcoderplus-Guanaco-GPT4-15B-V1.0 is a language model that combines the strengths of the [Starcoderplus](https://huggingface.co/bigcode/starcoderplus) base model, an expansion of the orginal [openassistant-guanaco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco) dataset re-imagined using 100% GPT-4 answers, and additional data on abstract algebra and physics for finetuning. The original openassistant-guanaco dataset questions were trimmed to within 2 standard deviations of token size for input and output pairs and all non-english data was been removed to reduce training size requirements. # Model Description This model is built on top of the Starcoderplus base model, a large language model which is a fine-tuned version of [StarCoderBase](https://huggingface.co/bigcode/starcoderbase). The Starcoderplus base model was further finetuned using QLORA on the revised openassistant-guanaco dataset questions that were 100% re-imagined using GPT-4. # Intended Use This model is designed to be used for a wide array of text generation tasks that require understanding and generating English text. The model is expected to perform well in tasks such as answering questions, writing essays, summarizing text, translation, and more. However, given the specific data processing and finetuning done, it might be particularly effective for tasks related to English language question-answering systems. # Limitations Despite the powerful capabilities of this model, users should be aware of its limitations. The model's knowledge is up to date only until the time it was trained, and it doesn't know about events in the world after that. It can sometimes produce incorrect or nonsensical responses, as it doesn't understand the text in the same way humans do. It should be used as a tool to assist in generating text and not as a sole source of truth. # How to use Here is an example of how to use this model: ```python from transformers import AutoModelForCausalLM, AutoTokenizer import time import torch class Chatbot: def __init__(self, model_name): self.tokenizer = AutoTokenizer.from_pretrained(model_name, padding_side='left') self.model = AutoModelForCausalLM.from_pretrained(model_name, load_in_4bit=True, torch_dtype=torch.bfloat16) if self.tokenizer.pad_token_id is None: self.tokenizer.pad_token_id = self.tokenizer.eos_token_id def get_response(self, prompt): inputs = self.tokenizer.encode_plus(prompt, return_tensors="pt", padding='max_length', max_length=100) if next(self.model.parameters()).is_cuda: inputs = {name: tensor.to('cuda') for name, tensor in inputs.items()} start_time = time.time() tokens = self.model.generate(input_ids=inputs['input_ids'], attention_mask=inputs['attention_mask'], pad_token_id=self.tokenizer.pad_token_id, max_new_tokens=400) end_time = time.time() output_tokens = tokens[0][inputs['input_ids'].shape[-1]:] output = self.tokenizer.decode(output_tokens, skip_special_tokens=True) time_taken = end_time - start_time return output, time_taken def main(): chatbot = Chatbot("LoupGarou/Starcoderplus-Guanaco-GPT4-15B-V1.0") while True: user_input = input("Enter your prompt: ") if user_input.lower() == 'quit': break output, time_taken = chatbot.get_response(user_input) print("\033[33m" + output + "\033[0m") print("Time taken to process: ", time_taken, "seconds") print("Exited the program.") if __name__ == "__main__": main() ``` # Training Procedure The base Starcoderplus model was finetuned on the modified openassistant-guanaco dataset 100% re-imagined with GPT4 answers using QLORA. All non-English data was also removed from this finetuning dataset to reduce trainign size and time. ## Acknowledgements This model, Starcoderplus-Guanaco-GPT4-15B-V1.0, builds upon the strengths of the [Starcoderplus](https://huggingface.co/bigcode/starcoderplus) and the [openassistant-guanaco dataset](https://huggingface.co/datasets/timdettmers/openassistant-guanaco). A sincere appreciation goes out to the developers and the community involved in the creation and refinement of these models. Their commitment to providing open source tools and datasets have been instrumental in making this project a reality. Moreover, a special note of thanks to the [Hugging Face](https://huggingface.co/) team, whose transformative library has not only streamlined the process of model creation and adaptation, but also democratized the access to state-of-the-art machine learning technologies. Their impact on the development of this project cannot be overstated.

vnktrmnb/bert-base-multilingual-cased-finetuned-TeQuad_Te

vnktrmnb

2023-07-12T07:35:33Z

61

0

transformers

[ "transformers", "tf", "bert", "question-answering", "generated_from_keras_callback", "license:apache-2.0", "endpoints_compatible", "region:us" ]

question-answering

2023-07-12T04:54:45Z

--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: vnktrmnb/bert-base-multilingual-cased-finetuned-TeQuad_Te results: [] ---  # vnktrmnb/bert-base-multilingual-cased-finetuned-TeQuad_Te This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 2.5629 - Train End Logits Accuracy: 0.3532 - Train Start Logits Accuracy: 0.3920 - Validation Loss: 1.8877 - Validation End Logits Accuracy: 0.4726 - Validation Start Logits Accuracy: 0.5126 - Epoch: 0 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 7331, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch | |:----------:|:-------------------------:|:---------------------------:|:---------------:|:------------------------------:|:--------------------------------:|:-----:| | 2.5629 | 0.3532 | 0.3920 | 1.8877 | 0.4726 | 0.5126 | 0 | ### Framework versions - Transformers 4.30.2 - TensorFlow 2.12.0 - Datasets 2.13.1 - Tokenizers 0.13.3

rocketship/5000

rocketship

2023-07-12T07:34:41Z

0

null

[ "arxiv:1910.09700", "license:openrail", "region:us" ]

null

2023-03-06T22:06:52Z

--- license: openrail --- # Model Card for Model ID  This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1). ## Model Details ### Model Description  - **Developed by:** Projector Bach - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  Risk at your own risk [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ## Hilarious and Unconsiderd Details I'll tackle this nedt one... after I am rich! But until then my time is better spent skippping rocks and counting the skips per toss. ### Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed]

Intel/whisper-medium-int8-dynamic-inc

Intel

2023-07-12T07:26:49Z

6

0

transformers

[ "transformers", "onnx", "whisper", "automatic-speech-recognition", "int8", "ONNX", "PostTrainingDynamic", "Intel® Neural Compressor", "neural-compressor", "dataset:librispeech_asr", "license:apache-2.0", "endpoints_compatible", "region:us" ]

automatic-speech-recognition

2023-07-12T07:19:58Z

--- license: apache-2.0 datasets: - librispeech_asr metrics: - wer pipeline_tag: automatic-speech-recognition tags: - automatic-speech-recognition - int8 - ONNX - PostTrainingDynamic - Intel® Neural Compressor - neural-compressor library_name: transformers --- ## Model Details: INT8 Whisper medium Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation. Trained on 680k hours of labelled data, Whisper models demonstrate a strong ability to generalise to many datasets and domains without the need for fine-tuning. This int8 ONNX model is generated by [neural-compressor](https://github.com/intel/neural-compressor) and the fp32 model can be exported with below command: ```shell optimum-cli export onnx --model openai/whisper-medium whisper-medium-with-past/ --task automatic-speech-recognition-with-past --opset 13 ``` | Model Detail | Description | | ----------- | ----------- | | Model Authors - Company | Intel | | Date | July 7, 2023 | | Version | 1 | | Type | Speech Recognition | | Paper or Other Resources | - | | License | Apache 2.0 | | Questions or Comments | [Community Tab](https://huggingface.co/Intel/whisper-medium-int8-dynamic/discussions)| | Intended Use | Description | | ----------- | ----------- | | Primary intended uses | You can use the raw model for automatic speech recognition inference | | Primary intended users | Anyone doing automatic speech recognition inference | | Out-of-scope uses | This model in most cases will need to be fine-tuned for your particular task. The model should not be used to intentionally create hostile or alienating environments for people.| ### How to use Download the model by cloning the repository: ```shell git clone https://huggingface.co/Intel/whisper-medium-int8-dynamic ``` Evaluate the model with below code: ```python import os from evaluate import load from datasets import load_dataset from transformers import WhisperForConditionalGeneration, WhisperProcessor, AutoConfig model_name = 'openai/whisper-medium' model_path = 'whisper-medium-int8-dynamic' processor = WhisperProcessor.from_pretrained(model_name) model = WhisperForConditionalGeneration.from_pretrained(model_name) config = AutoConfig.from_pretrained(model_name) wer = load("wer") librispeech_test_clean = load_dataset("librispeech_asr", "clean", split="test") from optimum.onnxruntime import ORTModelForSpeechSeq2Seq from transformers import PretrainedConfig model_config = PretrainedConfig.from_pretrained(model_name) predictions = [] references = [] sessions = ORTModelForSpeechSeq2Seq.load_model( os.path.join(model_path, 'encoder_model.onnx'), os.path.join(model_path, 'decoder_model.onnx'), os.path.join(model_path, 'decoder_with_past_model.onnx')) model = ORTModelForSpeechSeq2Seq(sessions[0], sessions[1], model_config, model_path, sessions[2]) for idx, batch in enumerate(librispeech_test_clean): audio = batch["audio"] input_features = processor(audio["array"], sampling_rate=audio["sampling_rate"], return_tensors="pt").input_features reference = processor.tokenizer._normalize(batch['text']) references.append(reference) predicted_ids = model.generate(input_features)[0] transcription = processor.decode(predicted_ids) prediction = processor.tokenizer._normalize(transcription) predictions.append(prediction) wer_result = wer.compute(references=references, predictions=predictions) print(f"Result wer: {wer_result * 100}") accuracy = 1 - wer_result print("Accuracy: %.5f" % accuracy) ``` ## Metrics (Model Performance): | Model | Model Size (GB) | wer | |---|:---:|:---:| | FP32 |2.4|2.88| | INT8 |1.2|2.83|

tannazhp95/dqn-SpaceInvadersNoFrameskip-v4

tannazhp95

2023-07-12T07:23:58Z

7

0

stable-baselines3

[ "stable-baselines3", "SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

reinforcement-learning

2023-07-12T07:23:18Z

--- library_name: stable-baselines3 tags: - SpaceInvadersNoFrameskip-v4 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: DQN results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: SpaceInvadersNoFrameskip-v4 type: SpaceInvadersNoFrameskip-v4 metrics: - type: mean_reward value: 643.50 +/- 224.99 name: mean_reward verified: false --- # **DQN** Agent playing **SpaceInvadersNoFrameskip-v4** This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3) and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo). The RL Zoo is a training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included. ## Usage (with SB3 RL Zoo) RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo SB3: https://github.com/DLR-RM/stable-baselines3 SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib Install the RL Zoo (with SB3 and SB3-Contrib): ```bash pip install rl_zoo3 ``` ``` # Download model and save it into the logs/ folder python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga tannazhp95 -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do: ``` python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga tannazhp95 -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` ## Training (with the RL Zoo) ``` python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ # Upload the model and generate video (when possible) python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga tannazhp95 ``` ## Hyperparameters ```python OrderedDict([('batch_size', 32), ('buffer_size', 100000), ('env_wrapper', ['stable_baselines3.common.atari_wrappers.AtariWrapper']), ('exploration_final_eps', 0.01), ('exploration_fraction', 0.1), ('frame_stack', 4), ('gradient_steps', 1), ('learning_rate', 0.0001), ('learning_starts', 100000), ('n_timesteps', 1000000.0), ('optimize_memory_usage', False), ('policy', 'CnnPolicy'), ('target_update_interval', 1000), ('train_freq', 4), ('normalize', False)]) ``` # Environment Arguments ```python {'render_mode': 'rgb_array'} ```

KaansCodingAdventure/squad-bloom-3b

KaansCodingAdventure

2023-07-12T07:20:15Z

0

peft

[ "peft", "region:us" ]

null

2023-07-10T14:05:09Z

--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.4.0.dev0

Daniil-plotnikov/Glazastik_Chat

Daniil-plotnikov

2023-07-12T07:19:11Z

5

0

transformers

[ "transformers", "llama", "text-generation", "code", "question-answering", "ru", "en", "fr", "license:openrail", "autotrain_compatible", "endpoints_compatible", "region:us" ]

question-answering

2023-07-11T15:11:06Z

--- license: openrail language: - ru - en - fr pipeline_tag: question-answering tags: - code library_name: transformers --- Данная языковая модель основанна на Llama и хорошо понимает русский язык.

Intel/whisper-medium-int8-static-inc

Intel

2023-07-12T07:16:35Z

9

1

transformers

[ "transformers", "onnx", "whisper", "automatic-speech-recognition", "int8", "ONNX", "PostTrainingStatic", "Intel® Neural Compressor", "neural-compressor", "dataset:librispeech_asr", "license:apache-2.0", "endpoints_compatible", "region:us" ]

automatic-speech-recognition

2023-07-12T07:01:29Z

--- license: apache-2.0 datasets: - librispeech_asr metrics: - wer pipeline_tag: automatic-speech-recognition tags: - automatic-speech-recognition - int8 - ONNX - PostTrainingStatic - Intel® Neural Compressor - neural-compressor library_name: transformers --- ## Model Details: INT8 Whisper medium Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation. Trained on 680k hours of labelled data, Whisper models demonstrate a strong ability to generalise to many datasets and domains without the need for fine-tuning. This int8 ONNX model is generated by [neural-compressor](https://github.com/intel/neural-compressor) and the fp32 model can be exported with below command: ```shell optimum-cli export onnx --model openai/whisper-medium whisper-medium-with-past/ --task automatic-speech-recognition-with-past --opset 13 ``` | Model Detail | Description | | ----------- | ----------- | | Model Authors - Company | Intel | | Date | May 15, 2022 | | Version | 1 | | Type | Speech Recognition | | Paper or Other Resources | - | | License | Apache 2.0 | | Questions or Comments | [Community Tab](https://huggingface.co/Intel/whisper-medium-int8-static/discussions)| | Intended Use | Description | | ----------- | ----------- | | Primary intended uses | You can use the raw model for automatic speech recognition inference | | Primary intended users | Anyone doing automatic speech recognition inference | | Out-of-scope uses | This model in most cases will need to be fine-tuned for your particular task. The model should not be used to intentionally create hostile or alienating environments for people.| ### How to use Download the model by cloning the repository: ```shell git clone https://huggingface.co/Intel/whisper-medium-int8-static ``` Evaluate the model with below code: ```python import os from evaluate import load from datasets import load_dataset from transformers import WhisperForConditionalGeneration, WhisperProcessor, AutoConfig model_name = 'openai/whisper-medium' model_path = 'whisper-medium-int8-static' processor = WhisperProcessor.from_pretrained(model_name) model = WhisperForConditionalGeneration.from_pretrained(model_name) config = AutoConfig.from_pretrained(model_name) wer = load("wer") librispeech_test_clean = load_dataset("librispeech_asr", "clean", split="test") from optimum.onnxruntime import ORTModelForSpeechSeq2Seq from transformers import PretrainedConfig model_config = PretrainedConfig.from_pretrained(model_name) predictions = [] references = [] sessions = ORTModelForSpeechSeq2Seq.load_model( os.path.join(model_path, 'encoder_model.onnx'), os.path.join(model_path, 'decoder_model.onnx'), os.path.join(model_path, 'decoder_with_past_model.onnx')) model = ORTModelForSpeechSeq2Seq(sessions[0], sessions[1], model_config, model_path, sessions[2]) for idx, batch in enumerate(librispeech_test_clean): audio = batch["audio"] input_features = processor(audio["array"], sampling_rate=audio["sampling_rate"], return_tensors="pt").input_features reference = processor.tokenizer._normalize(batch['text']) references.append(reference) predicted_ids = model.generate(input_features)[0] transcription = processor.decode(predicted_ids) prediction = processor.tokenizer._normalize(transcription) predictions.append(prediction) wer_result = wer.compute(references=references, predictions=predictions) print(f"Result wer: {wer_result * 100}") accuracy = 1 - wer_result print("Accuracy: %.5f" % accuracy) ``` ## Metrics (Model Performance): | Model | Model Size (GB) | wer | |---|:---:|:---:| | FP32 |4.9|2.88| | INT8 |1.6|3.31|

SpringYung/falcon_with_cfa_text_v1

SpringYung

2023-07-12T07:16:00Z

0

peft

[ "peft", "region:us" ]

null

2023-07-12T07:15:32Z

--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.4.0.dev0

seanghay/khmer-pos-roberta

seanghay

2023-07-12T07:15:07Z

12

0

transformers

[ "transformers", "pytorch", "tensorboard", "safetensors", "xlm-roberta", "token-classification", "generated_from_trainer", "km", "dataset:seanghay/khPOS", "arxiv:2103.16801", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]

token-classification

2023-07-12T05:28:20Z

--- license: apache-2.0 tags: - generated_from_trainer datasets: - seanghay/khPOS metrics: - precision - recall - f1 - accuracy widget: - text: គាត់ផឹកទឹកនៅភ្នំពេញ - text: តើលោកស្រីបានសាកសួរទៅគាត់ទេ? - text: នេត្រា មិនដឹងសោះថាអ្នកជាមនុស្ស! - text: លោក វណ្ណ ម៉ូលីវណ្ណ ជាបិតាស្ថាបត្យកម្មដ៏ល្បីល្បាញរបស់ប្រទេសកម្ពុជានៅក្នុងសម័យសង្គមរាស្ត្រនិយម។ model-index: - name: khmer-pos-roberta-10 results: - task: name: Token Classification type: token-classification dataset: name: kh_pos type: kh_pos config: default split: train args: default metrics: - name: Precision type: precision value: 0.9511876225757245 - name: Recall type: recall value: 0.9526407682234832 - name: F1 type: f1 value: 0.9519136408243376 - name: Accuracy type: accuracy value: 0.9735370853522176 language: - km library_name: transformers pipeline_tag: token-classification ---  # Khmer Part of Speech Tagging with XLM RoBERTa This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the [khPOS](https://huggingface.co/datasets/seanghay/khPOS) dataset. It achieves the following results on the evaluation set: - Loss: 0.1063 - Precision: 0.9512 - Recall: 0.9526 - F1: 0.9519 - Accuracy: 0.9735 ## Model description The [original paper](https://arxiv.org/pdf/2103.16801.pdf) achieved 98.15% accuracy while this model achieved only 97.35% which is close. However, this is a multilingual model so it has more tokens than the original paper. ## Intended uses & limitations This model can be used to extract useful information from Khmer text. ## Training and evaluation data train: 90% / test: 10% ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 24 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 10 ### Training results | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| | No log | 1.0 | 450 | 0.1347 | 0.9314 | 0.9333 | 0.9324 | 0.9603 | | 0.4834 | 2.0 | 900 | 0.1183 | 0.9407 | 0.9377 | 0.9392 | 0.9653 | | 0.1323 | 3.0 | 1350 | 0.1026 | 0.9484 | 0.9482 | 0.9483 | 0.9699 | | 0.095 | 4.0 | 1800 | 0.0986 | 0.9502 | 0.9490 | 0.9496 | 0.9712 | | 0.0774 | 5.0 | 2250 | 0.0978 | 0.9494 | 0.9491 | 0.9493 | 0.9712 | | 0.0616 | 6.0 | 2700 | 0.0991 | 0.9493 | 0.9507 | 0.9500 | 0.9715 | | 0.0494 | 7.0 | 3150 | 0.0989 | 0.9529 | 0.9540 | 0.9534 | 0.9731 | | 0.0414 | 8.0 | 3600 | 0.1037 | 0.9499 | 0.9501 | 0.9500 | 0.9722 | | 0.0339 | 9.0 | 4050 | 0.1056 | 0.9516 | 0.9517 | 0.9516 | 0.9734 | | 0.029 | 10.0 | 4500 | 0.1063 | 0.9512 | 0.9526 | 0.9519 | 0.9735 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3

aiknight87/falcon-40b-instruct-tuned-finance-qas

aiknight87

2023-07-12T07:13:46Z

1

0

peft

[ "peft", "RefinedWeb", "custom_code", "4-bit", "region:us" ]

null

2023-07-12T07:11:31Z

--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.4.0.dev0

Kauru/DialoGPT-medium-Ranniv2

Kauru

2023-07-12T07:06:46Z

142

0

transformers

[ "transformers", "pytorch", "gpt2", "text-generation", "conversational", "en", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2023-07-12T05:27:04Z

--- language: - en pipeline_tag: conversational ---

JaniGiblets/ppo-LunarLander-v2

JaniGiblets

2023-07-12T06:58:42Z

0

stable-baselines3

[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

reinforcement-learning

2023-07-12T06:58:22Z

--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 253.79 +/- 12.76 name: mean_reward verified: false --- # **PPO** Agent playing **LunarLander-v2** This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```

coreml-community/coreml-realMoonAnime-v70_cn

coreml-community

2023-07-12T06:40:53Z

0

null

[ "coreml", "stable-diffusion", "text-to-image", "license:creativeml-openrail-m", "region:us" ]

text-to-image

2023-07-12T00:45:47Z

--- license: creativeml-openrail-m tags: - coreml - stable-diffusion - text-to-image --- # Core ML Converted Model: - This model was converted to [Core ML for use on Apple Silicon devices](https://github.com/apple/ml-stable-diffusion). Conversion instructions can be found [here](https://github.com/godly-devotion/MochiDiffusion/wiki/How-to-convert-ckpt-or-safetensors-files-to-Core-ML). - Provide the model to an app such as **Mochi Diffusion** [Github](https://github.com/godly-devotion/MochiDiffusion) / [Discord](https://discord.gg/x2kartzxGv) to generate images. - `split_einsum` version is compatible with all compute unit options including Neural Engine. - `original` version is only compatible with `CPU & GPU` option. - Custom resolution versions are tagged accordingly. - The `vae-ft-mse-840000-ema-pruned.ckpt` VAE is embedded into the model. - This model was converted with a `vae-encoder` for use with `image2image`. - This model is `fp16`. - Descriptions are posted as-is from original model source. - Not all features and/or results may be available in `CoreML` format. - This model does not have the [unet split into chunks](https://github.com/apple/ml-stable-diffusion#-converting-models-to-core-ml). - This model does not include a `safety checker` (for NSFW content). - This model can be used with ControlNet. # realMoonAnime-v70_cn: Source(s): [CivitAI](https://civitai.com/models/75431/real-moon-anime) ## Real Moon - Anime v7.0 A mixture of Real Moon with MonKe Dream. This model aims to generate anime images with a lot of detail and quality, a balance between realism and anime. Can output both SFW and NSFW images. Baked in VAE ### I usually use - Clip skip: 1 - Upscaler: R-ESRGAN 4x+ Anime6B - Denoising strength: 0.4 - Hires steps: same as the Sampling steps Recommended Loras: Detail Tweaker, Better Portrait Lighting Recommended embeddings: bad-artist, EasyNegativeV2 ![image](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/85499afc-501d-4bec-80b7-23413d435b6d/width=450/0fd69f15-63b3-4fd8-8d3a-f8636620dcf5.jpeg) ![image](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/2fda9c17-adc6-493c-93b3-ba1f7bb2d409/width=450/49fbdd05-781c-4874-9435-684ef83dd7c7.jpeg) ![image](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/e753cff6-e0e7-4c79-ba1e-269d0675ccb6/width=450/f4e11ad3-2e1a-479b-a902-c5036a8b7114.jpeg) ![image](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/79c71163-be78-4e7e-968c-96f3c29ad1bf/width=450/de27b8a9-00e7-4ead-af19-d9c93ebfa8fc.jpeg)

XDawned/minecraft-en-zh

XDawned

2023-07-12T06:30:29Z

138

4

transformers

[ "transformers", "pytorch", "safetensors", "marian", "text2text-generation", "translation", "transformer", "en-zh", "minecraft modpack", "finetune", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

translation

2023-04-04T05:27:12Z

--- tags: - translation - transformer - en-zh - minecraft modpack - finetune license: apache-2.0 --- finetune model [opus-mt-en-zh](https://huggingface.co/Helsinki-NLP/opus-mt-en-zh) traing datas are from [i18n-dict](https://github.com/CFPATools/i18n-dict) and some modpacks‘ quests collected from the internet ## Validation Metrics On Some 1.19.2+ ModPacks - Loss: 1.6 - SacreBLEU: 30.8 ## Validation Metrics On Dict - Loss: 0.9 - SacreBLEU: 51.1

localmodels/WizardLM-30B-v1.0-ggml

localmodels

2023-07-12T06:18:32Z

0

2

null

[ "region:us" ]

null

2023-07-12T06:18:31Z

--- duplicated_from: localmodels/LLM --- # WizardLM 30B v1.0 ggml From: https://huggingface.co/WizardLM/WizardLM-30B-V1.0 --- ### Original llama.cpp quant methods: `q4_0, q4_1, q5_0, q5_1, q8_0` Quantized using an older version of llama.cpp and compatible with llama.cpp from May 19, commit 2d5db48. ### k-quant methods: `q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K` Quantization methods compatible with latest llama.cpp from June 6, commit 2d43387. --- ## Files | Name | Quant method | Bits | Size | Max RAM required, no GPU offloading | Use case | | ---- | ---- | ---- | ---- | ---- | ----- | | wizardlm-30b.ggmlv3.q2_K.bin | q2_K | 2 | 13.60 GB | 16.10 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. | | wizardlm-30b.ggmlv3.q3_K_L.bin | q3_K_L | 3 | 17.20 GB | 19.70 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K | | wizardlm-30b.ggmlv3.q3_K_M.bin | q3_K_M | 3 | 15.64 GB | 18.14 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K | | wizardlm-30b.ggmlv3.q3_K_S.bin | q3_K_S | 3 | 13.98 GB | 16.48 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors | | wizardlm-30b.ggmlv3.q4_0.bin | q4_0 | 4 | 18.30 GB | 20.80 GB | Original llama.cpp quant method, 4-bit. | | wizardlm-30b.ggmlv3.q4_1.bin | q4_1 | 4 | 20.33 GB | 22.83 GB | Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. | | wizardlm-30b.ggmlv3.q4_K_M.bin | q4_K_M | 4 | 19.57 GB | 22.07 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K | | wizardlm-30b.ggmlv3.q4_K_S.bin | q4_K_S | 4 | 18.30 GB | 20.80 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors | | wizardlm-30b.ggmlv3.q5_0.bin | q5_0 | 5 | 22.37 GB | 24.87 GB | Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. | | wizardlm-30b.ggmlv3.q5_1.bin | q5_1 | 5 | 24.40 GB | 26.90 GB | Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. | | wizardlm-30b.ggmlv3.q5_K_M.bin | q5_K_M | 5 | 23.02 GB | 25.52 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K | | wizardlm-30b.ggmlv3.q5_K_S.bin | q5_K_S | 5 | 22.37 GB | 24.87 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors | | wizardlm-30b.ggmlv3.q6_K.bin | q6_K | 6 | 26.69 GB | 29.19 GB | New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors | | wizardlm-30b.ggmlv3.q8_0.bin | q8_0 | 8 | 34.56 GB | 37.06 GB | Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |

luhx/ppo-Pyramids

luhx

2023-07-12T06:10:19Z

1

0

ml-agents

[ "ml-agents", "tensorboard", "onnx", "Pyramids", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Pyramids", "region:us" ]

reinforcement-learning

2023-07-12T06:10:12Z

--- library_name: ml-agents tags: - Pyramids - deep-reinforcement-learning - reinforcement-learning - ML-Agents-Pyramids --- # **ppo** Agent playing **Pyramids** This is a trained model of a **ppo** agent playing **Pyramids** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A *longer tutorial* to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent **playing directly in your browser** 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: luhx/ppo-Pyramids 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀

localmodels/Guanaco-7B-ggml

localmodels

2023-07-12T05:53:53Z

0

1

null

[ "arxiv:2305.14314", "arxiv:2302.13971", "arxiv:2304.07327", "region:us" ]

null

2023-07-12T05:53:52Z

--- duplicated_from: localmodels/LLM --- # Guanaco 7B ggml From: https://huggingface.co/timdettmers/guanaco-7b --- ### Original llama.cpp quant methods: `q4_0, q4_1, q5_0, q5_1, q8_0` Quantized using an older version of llama.cpp and compatible with llama.cpp from May 19, commit 2d5db48. ### k-quant methods: `q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K` Quantization methods compatible with latest llama.cpp from June 6, commit 2d43387. --- ## Files | Name | Quant method | Bits | Size | Max RAM required, no GPU offloading | Use case | | ---- | ---- | ---- | ---- | ---- | ----- | | guanaco-7B.ggmlv3.q2_K.bin | q2_K | 2 | 2.80 GB | 5.30 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. | | guanaco-7B.ggmlv3.q3_K_L.bin | q3_K_L | 3 | 3.55 GB | 6.05 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K | | guanaco-7B.ggmlv3.q3_K_M.bin | q3_K_M | 3 | 3.23 GB | 5.73 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K | | guanaco-7B.ggmlv3.q3_K_S.bin | q3_K_S | 3 | 2.90 GB | 5.40 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors | | guanaco-7B.ggmlv3.q4_0.bin | q4_0 | 4 | 3.79 GB | 6.29 GB | Original llama.cpp quant method, 4-bit. | | guanaco-7B.ggmlv3.q4_1.bin | q4_1 | 4 | 4.21 GB | 6.71 GB | Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. | | guanaco-7B.ggmlv3.q4_K_M.bin | q4_K_M | 4 | 4.05 GB | 6.55 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K | | guanaco-7B.ggmlv3.q4_K_S.bin | q4_K_S | 4 | 3.79 GB | 6.29 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors | | guanaco-7B.ggmlv3.q5_0.bin | q5_0 | 5 | 4.63 GB | 7.13 GB | Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. | | guanaco-7B.ggmlv3.q5_1.bin | q5_1 | 5 | 5.06 GB | 7.56 GB | Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. | | guanaco-7B.ggmlv3.q5_K_M.bin | q5_K_M | 5 | 4.77 GB | 7.27 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K | | guanaco-7B.ggmlv3.q5_K_S.bin | q5_K_S | 5 | 4.63 GB | 7.13 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors | | guanaco-7B.ggmlv3.q6_K.bin | q6_K | 6 | 5.53 GB | 8.03 GB | New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors | | guanaco-7B.ggmlv3.q8_0.bin | q8_0 | 8 | 7.16 GB | 9.66 GB | Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. | --- # Guanaco Models Based on LLaMA | [Paper](https://arxiv.org/abs/2305.14314) | [Code](https://github.com/artidoro/qlora) | [Demo](https://huggingface.co/spaces/uwnlp/guanaco-playground-tgi) | **The Guanaco models are open-source finetuned chatbots obtained through 4-bit QLoRA tuning of LLaMA base models on the OASST1 dataset. They are available in 7B, 13B, 33B, and 65B parameter sizes.** ⚠️Guanaco is a model purely intended for research purposes and could produce problematic outputs. ## Why use Guanaco? - **Competitive with commercial chatbot systems on the Vicuna and OpenAssistant benchmarks** (ChatGPT and BARD) according to human and GPT-4 raters. We note that the relative performance on tasks not covered in these benchmarks could be very different. In addition, commercial systems evolve over time (we used outputs from the March 2023 version of the models). - **Available open-source for research purposes**. Guanaco models allow *cheap* and *local* experimentation with high-quality chatbot systems. - **Replicable and efficient training procedure** that can be extended to new use cases. Guanaco training scripts are available in the [QLoRA repo](https://github.com/artidoro/qlora). - **Rigorous comparison to 16-bit methods** (both 16-bit full-finetuning and LoRA) in [our paper](https://arxiv.org/abs/2305.14314) demonstrates the effectiveness of 4-bit QLoRA finetuning. - **Lightweight** checkpoints which only contain adapter weights. ## License and Intended Use Guanaco adapter weights are available under Apache 2 license. Note the use of the Guanaco adapter weights, requires access to the LLaMA model weighs. Guanaco is based on LLaMA and therefore should be used according to the LLaMA license. ## Usage Here is an example of how you would load Guanaco 7B in 4-bits: ```python import torch from peft import PeftModel from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig model_name = "huggyllama/llama-7b" adapters_name = 'timdettmers/guanaco-7b' model = AutoModelForCausalLM.from_pretrained( model_name, load_in_4bit=True, torch_dtype=torch.bfloat16, device_map="auto", max_memory= {i: '24000MB' for i in range(torch.cuda.device_count())}, quantization_config=BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_compute_dtype=torch.bfloat16, bnb_4bit_use_double_quant=True, bnb_4bit_quant_type='nf4' ), ) model = PeftModel.from_pretrained(model, adapters_name) tokenizer = AutoTokenizer.from_pretrained(model_name) ``` Inference can then be performed as usual with HF models as follows: ```python prompt = "Introduce yourself" formatted_prompt = ( f"A chat between a curious human and an artificial intelligence assistant." f"The assistant gives helpful, detailed, and polite answers to the user's questions.\n" f"### Human: {prompt} ### Assistant:" ) inputs = tokenizer(formatted_prompt, return_tensors="pt").to("cuda:0") outputs = model.generate(inputs=inputs.input_ids, max_new_tokens=20) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) ``` Expected output similar to the following: ``` A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. ### Human: Introduce yourself ### Assistant: I am an artificial intelligence assistant. I am here to help you with any questions you may have. ``` ## Current Inference Limitations Currently, 4-bit inference is slow. We recommend loading in 16 bits if inference speed is a concern. We are actively working on releasing efficient 4-bit inference kernels. Below is how you would load the model in 16 bits: ```python model_name = "huggyllama/llama-7b" adapters_name = 'timdettmers/guanaco-7b' model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype=torch.bfloat16, device_map="auto", max_memory= {i: '24000MB' for i in range(torch.cuda.device_count())}, ) model = PeftModel.from_pretrained(model, adapters_name) tokenizer = AutoTokenizer.from_pretrained(model_name) ``` ## Model Card **Architecture**: The Guanaco models are LoRA adapters to be used on top of LLaMA models. They are added to all layers. For all model sizes, we use $r=64$. **Base Model**: Guanaco uses LLaMA as base model with sizes 7B, 13B, 33B, 65B. LLaMA is a causal language model pretrained on a large corpus of text. See [LLaMA paper](https://arxiv.org/abs/2302.13971) for more details. Note that Guanaco can inherit biases and limitations of the base model. **Finetuning Data**: Guanaco is finetuned on OASST1. The exact dataset is available at [timdettmers/openassistant-guanaco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco). **Languages**: The OASST1 dataset is multilingual (see [the paper](https://arxiv.org/abs/2304.07327) for details) and as such Guanaco responds to user queries in different languages. We note, however, that OASST1 is heavy in high-resource languages. In addition, human evaluation of Guanaco was only performed in English and based on qualitative analysis we observed degradation in performance in other languages. Next, we describe Training and Evaluation details. ### Training Guanaco models are the result of 4-bit QLoRA supervised finetuning on the OASST1 dataset. All models use NormalFloat4 datatype for the base model and LoRA adapters on all linear layers with BFloat16 as computation datatype. We set LoRA $r=64$, $\alpha=16$. We also use Adam beta2 of 0.999, max grad norm of 0.3 and LoRA dropout of 0.1 for models up to 13B and 0.05 for 33B and 65B models. For the finetuning process, we use constant learning rate schedule and paged AdamW optimizer. ### Training hyperparameters Size| Dataset | Batch Size | Learning Rate | Max Steps | Sequence length ---|---|---|---|---|--- 7B | OASST1 | 16 | 2e-4 | 1875 | 512 13B | OASST1 | 16 | 2e-4 | 1875 | 512 33B | OASST1 | 16 | 1e-4 | 1875 | 512 65B | OASST1 | 16 | 1e-4 | 1875 | 512 ### Evaluation We test generative language capabilities through both automated and human evaluations. This second set of evaluations relies on queries curated by humans and aims at measuring the quality of model responses. We use the Vicuna and OpenAssistant datasets with 80 and 953 prompts respectively. In both human and automated evaluations, for each prompt, raters compare all pairs of responses across the models considered. For human raters we randomize the order of the systems, for GPT-4 we evaluate with both orders. Benchmark | Vicuna | | Vicuna | | OpenAssistant | | - -----------|----|-----|--------|---|---------------|---|--- Prompts | 80 | | 80 | | 953 | | Judge | Human | | GPT-4 | | GPT-4 | | Model | Elo | Rank | Elo | Rank | Elo | Rank | **Median Rank** GPT-4 | 1176 | 1 | 1348 | 1 | 1294 | 1 | 1 Guanaco-65B | 1023 | 2 | 1022 | 2 | 1008 | 3 | 2 Guanaco-33B | 1009 | 4 | 992 | 3 | 1002 | 4 | 4 ChatGPT-3.5 Turbo | 916 | 7 | 966 | 5 | 1015 | 2 | 5 Vicuna-13B | 984 | 5 | 974 | 4 | 936 | 5 | 5 Guanaco-13B | 975 | 6 | 913 | 6 | 885 | 6 | 6 Guanaco-7B | 1010 | 3 | 879 | 8 | 860 | 7 | 7 Bard | 909 | 8 | 902 | 7 | - | - | 8 We also use the MMLU benchmark to measure performance on a range of language understanding tasks. This is a multiple-choice benchmark covering 57 tasks including elementary mathematics, US history, computer science, law, and more. We report 5-shot test accuracy. Dataset | 7B | 13B | 33B | 65B ---|---|---|---|--- LLaMA no tuning | 35.1 | 46.9 | 57.8 | 63.4 Self-Instruct | 36.4 | 33.3 | 53.0 | 56.7 Longform | 32.1 | 43.2 | 56.6 | 59.7 Chip2 | 34.5 | 41.6 | 53.6 | 59.8 HH-RLHF | 34.9 | 44.6 | 55.8 | 60.1 Unnatural Instruct | 41.9 | 48.1 | 57.3 | 61.3 OASST1 (Guanaco) | 36.6 | 46.4 | 57.0 | 62.2 Alpaca | 38.8 | 47.8 | 57.3 | 62.5 FLAN v2 | 44.5 | 51.4 | 59.2 | 63.9 ## Risks and Biases The model can produce factually incorrect output, and should not be relied on to produce factually accurate information. The model was trained on various public datasets; it is possible that this model could generate lewd, biased, or otherwise offensive outputs. However, we note that finetuning on OASST1 seems to reduce biases as measured on the CrowS dataset. We report here the performance of Guanaco-65B compared to other baseline models on the CrowS dataset. | | LLaMA-65B | GPT-3 | OPT-175B | Guanaco-65B | |----------------------|-----------|-------|----------|---------------| | Gender | 70.6 | 62.6 | 65.7 | **47.5** | | Religion | {79.0} | 73.3 | 68.6 | **38.7** | | Race/Color | 57.0 | 64.7 | 68.6 | **45.3** | | Sexual orientation | {81.0} | 76.2 | 78.6 | **59.1** | | Age | 70.1 | 64.4 | 67.8 | **36.3** | | Nationality | 64.2 | 61.6 | 62.9 | **32.4** | | Disability | 66.7 | 76.7 | 76.7 | **33.9** | | Physical appearance | 77.8 | 74.6 | 76.2 | **43.1** | | Socioeconomic status | 71.5 | 73.8 | 76.2 | **55.3** | | Average | 66.6 | 67.2 | 69.5 | **43.5** | ## Citation ```bibtex @article{dettmers2023qlora, title={QLoRA: Efficient Finetuning of Quantized LLMs}, author={Dettmers, Tim and Pagnoni, Artidoro and Holtzman, Ari and Zettlemoyer, Luke}, journal={arXiv preprint arXiv:2305.14314}, year={2023} } ```

keehun/textual_inversion_cat

keehun

2023-07-12T05:53:38Z

25

0

diffusers

[ "diffusers", "tensorboard", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "textual_inversion", "base_model:runwayml/stable-diffusion-v1-5", "base_model:adapter:runwayml/stable-diffusion-v1-5", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]

text-to-image

2023-07-12T05:22:14Z

--- license: creativeml-openrail-m base_model: runwayml/stable-diffusion-v1-5 tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers - textual_inversion inference: true --- # Textual inversion text2image fine-tuning - keehun/textual_inversion_cat These are textual inversion adaption weights for runwayml/stable-diffusion-v1-5. You can find some example images in the following.

nkpz/llama-30b-instruct-gptq-128g

nkpz

2023-07-12T05:42:04Z

5

0

transformers

[ "transformers", "pytorch", "llama", "text-generation", "license:other", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2023-07-11T22:27:15Z

--- license: other --- 4-bit (128 groupsize) quantized files for [upstage/llama-30b-instruct](https://huggingface.co/upstage/llama-30b-instruct) Quantized using [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa). Command used to quantize: python llama.py /my/model/directory c4 --wbits 4 --true-sequential --act-order --groupsize 128 --save_safetensors /my/output/file.safetensors **Sample Q&A** *Temp 0.59, Top P 0.95 Top K 0, Tail Free 1, Typical 1, Top A 0, Rep Pen 1.1, Rep Pen Range 1024, Rep Pen Slope 0.7* *Sampler Order: Rep Pen, Top K, Top A, Top P, Tail Free, Typical, Temp* **Question:** How come time flies like an arrow but fruit flies like a banana? **A1:** This is another one of those questions that has no real answer. It's just a play on words, a joke. Enjoy the humor of it, and don't worry about making sense of it. **A2:** Because it is written that way in the sacred text of the Bananites. **A3:** Time flies like an arrow because it is a metaphor that describes the unstoppable nature of the passage of time, which is often associated with the inevitable progression of age and the transience of life. Fruit flies like a banana because it is a joke that plays on the similarity of the words "time" and "fruit," which both contain the word "flies." The phrase "fruit flies" refers to the fact that fruit flies are attracted to ripened fruit. In this case, the joke is comparing the attraction of fruit flies to ripe bananas to the relentless passage of time. **Question:** The following sentence is true. The previous sentence is false. Which of those two sentences is true? **A1:** The first one. **A2:** The second sentence is true. **A3:** The first sentence is true. **Question:** What word in the dictionary is always spelled incorrectly? **A1:** The word "incorrectly" is always spelled incorrectly. **A2:** Incorrectly. **A3:** The word "incorrectly" itself. **Question:** You're running a marathon and you just passed the person who was in second place. What place are you in now? **A1:** First. **A2:** First **A3:** You are now in first place. **Question:** In what month do people get the least sleep? **A1:** December. Explanation: People tend to stay up late during December due to holiday events, shopping, and celebrating. Additionally, the winter months typically have shorter days, which means less daylight and more darkness, leading to a decrease in overall sleep. **A2:** People get the least amount of sleep in December. The shortest day of the year is December 21st or 22nd, which means that there is less daylight. This can lead to more difficulty in falling asleep because of a decrease in melatonin production due to less exposure to darkness. Melatonin is a hormone that helps regulate sleep. **A3:** December. Explanation: December is when people get the least sleep because it is right before Christmas and there are many things to be done. People are busy shopping, decorating, and preparing for the holiday. They also stay up late to watch holiday specials on TV and attend parties. **Question:** How much dirt is there in a hole that is three feet wide, four feet long, and five feet deep? **A1:** 15 cubic yards. **A2:** 575 cubic feet. **A3:** 315 cubic feet of dirt. **Question:** In the accent of a farmer from Alabama, why is it a bad idea to use a generator indoors? **Answer:** Well, son, when ya use a generator inside, ya gotta remember that it's like having a car running in your house. It's gonna put out carbon monoxide. That's a gas that can kill ya if ya breathe enough of it in. Ya see, your body can't tell the difference between that gas and the oxygen your body needs. So when ya breathe in too much carbon monoxide, your blood can't get enough oxygen to your brain and your organs. And that's not good. So always use that generator outside where there's plenty of fresh air. **Question:** Pretend you are a proud and irate Italian chef. Which store-bought sauce is the best for spaghetti? **Answer:** I am an irate Italian chef, and I can tell you that there is no substitute for homemade sauce on your spaghetti. The best sauces come from fresh ingredients, lovingly prepared with the right blend of herbs, tomatoes, garlic, onions, meat, and love. Store-bought sauces can never compare to the delicious taste of homemade sauce, and using them on your pasta is an insult to Italian cuisine! **Question:** Is it called "pork roll" or "taylor ham"? **Answer:** It's called both. It's the same thing. It's pork shoulder that's been seasoned and cured, then cooked and sliced. It's a Jersey thing, and some people say "pork roll," while others say "Taylor Ham." The latter is named for the original manufacturer, John Taylor. **Question:** According to someone from south NJ, is it called "pork roll" or "taylor ham"? **Answer:** It's "pork roll," my friend. Taylor Ham is a brand of pork roll. Just like you wouldn't say "I had a Coke" when you had a soda, you would say "I had pork roll." Taylor Ham is just the brand you might have had. **Question:** According to someone from north NJ, is it called "pork roll" or "taylor ham"? **Answer:** In North Jersey it is referred to as "Taylor Ham." In South Jersey it is referred to as "Pork Roll." They are both the same thing. It is a type of processed pork product that is popular in the state of New Jersey.

zeronphoto/Euneun2

zeronphoto

2023-07-12T05:13:35Z

0

null

[ "license:creativeml-openrail-m", "region:us" ]

null

2023-07-12T05:08:26Z

--- license: creativeml-openrail-m ---

tuanhnh/ppo-LunarLander-v2

tuanhnh

2023-07-12T05:08:32Z

0

stable-baselines3

[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

reinforcement-learning

2023-07-12T03:41:15Z

--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 281.45 +/- 16.12 name: mean_reward verified: false --- # **PPO** Agent playing **LunarLander-v2** This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```

matgu23/ntrlph

matgu23

2023-07-12T05:00:35Z

0

diffusers

[ "diffusers", "safetensors", "text-to-image", "stable-diffusion", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]

text-to-image

2023-07-12T04:48:23Z

--- license: creativeml-openrail-m tags: - text-to-image - stable-diffusion --- ### ntrlph Dreambooth model trained by matgu23 with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb) Sample pictures of this concept:

DanielTTY/mpt-30b-qlora

DanielTTY

2023-07-12T04:59:41Z

4

0

transformers

[ "transformers", "pytorch", "mpt", "text-generation", "Composer", "MosaicML", "llm-foundry", "StreamingDatasets", "custom_code", "dataset:allenai/c4", "dataset:mc4", "dataset:togethercomputer/RedPajama-Data-1T", "dataset:bigcode/the-stack-dedup", "dataset:allenai/s2orc", "arxiv:2108.12409", "arxiv:2302.13971", "arxiv:2205.14135", "arxiv:2010.04245", "arxiv:1909.08053", "arxiv:2302.06675", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "region:us" ]

text-generation

2023-07-12T04:59:40Z

--- license: apache-2.0 tags: - Composer - MosaicML - llm-foundry - StreamingDatasets datasets: - allenai/c4 - mc4 - togethercomputer/RedPajama-Data-1T - bigcode/the-stack-dedup - allenai/s2orc inference: false duplicated_from: mosaicml/mpt-30b --- # MPT-30B MPT-30B is a decoder-style transformer pretrained from scratch on 1T tokens of English text and code. This model was trained by [MosaicML](https://www.mosaicml.com). MPT-30B is part of the family of Mosaic Pretrained Transformer (MPT) models, which use a modified transformer architecture optimized for efficient training and inference. MPT-30B comes with special features that differentiate it from other LLMs, including an 8k token context window (which can be further extended via finetuning; see [MPT-7B-StoryWriter](https://huggingface.co/mosaicml/mpt-7b-storywriter)), support for context-length extrapolation via [ALiBi](https://arxiv.org/abs/2108.12409), and efficient inference + training via FlashAttention. It also has strong coding abilities thanks to its pretraining mix. MPT models can also be served efficiently with both standard HuggingFace pipelines and NVIDIA's [FasterTransformer](https://github.com/NVIDIA/FasterTransformer). The size of MPT-30B was also specifically chosen to make it easy to deploy on a single GPU—either 1xA100-80GB in 16-bit precision or 1xA100-40GB in 8-bit precision. This model uses the MosaicML LLM codebase, which can be found in the [llm-foundry repository](https://github.com/mosaicml/llm-foundry). It was trained by MosaicML’s NLP team on the [MosaicML platform](https://www.mosaicml.com/training) for LLM pretraining, finetuning, and inference. ### How is this model different? MPT-30B is: * **Licensed for the possibility of commercial use** (unlike [LLaMA](https://arxiv.org/abs/2302.13971)). * **Trained on a large amount of data** (1T tokens like [LLaMA](https://arxiv.org/abs/2302.13971) vs. 300B for [Pythia](https://github.com/EleutherAI/pythia), 300B for [OpenLLaMA](https://github.com/openlm-research/open_llama), and 800B for [StableLM](https://github.com/Stability-AI/StableLM)). * **Prepared to handle extremely long inputs** thanks to [ALiBi](https://arxiv.org/abs/2108.12409). * **Capable of fast training and inference** (via [FlashAttention](https://arxiv.org/pdf/2205.14135.pdf) and [FasterTransformer](https://github.com/NVIDIA/FasterTransformer)) * **Equipped with highly efficient open-source training code** via the [llm-foundry repository](https://github.com/mosaicml/llm-foundry) ### Models finetuned off MPT-30B: The following models are finetuned on MPT-30B: * [MPT-30B-Instruct](https://huggingface.co/mosaicml/mpt-30b-instruct): a model for short-form instruction following. Built by finetuning MPT-30B on several carefully curated datasets. * License: _CC-BY-SA-3.0_ * [MPT-30B-Chat](https://huggingface.co/mosaicml/mpt-30b-chat): a chatbot-like model for dialogue generation. Built by finetuning MPT-30B on [ShareGPT-Vicuna](https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered), [Camel-AI](https://huggingface.co/camel-ai), [GPTeacher](https://github.com/teknium1/GPTeacher), [Guanaco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco), [Baize](https://github.com/project-baize/baize-chatbot) and some generated datasets. * License: _CC-By-NC-SA-4.0_ * [Demo on Hugging Face Spaces](https://huggingface.co/spaces/mosaicml/mpt-30b-chat) ## Model Date June 22, 2023 ## Model License Apache-2.0 ## Documentation * [Blog post: MPT-30B: Raising the bar for open-source foundation models](https://www.mosaicml.com/blog/mpt-30b) * [Codebase (mosaicml/llm-foundry repo)](https://github.com/mosaicml/llm-foundry/) * Questions: Feel free to contact us via the [MosaicML Community Slack](https://mosaicml.me/slack)! ## How to Use This model is best used with the MosaicML [llm-foundry repository](https://github.com/mosaicml/llm-foundry) for training and finetuning. ```python import transformers model = transformers.AutoModelForCausalLM.from_pretrained( 'mosaicml/mpt-30b', trust_remote_code=True ) ``` Note: This model requires that `trust_remote_code=True` be passed to the `from_pretrained` method. This is because we use a custom `MPT` model architecture that is not yet part of the Hugging Face `transformers` package. `MPT` includes options for many training efficiency features such as [FlashAttention](https://arxiv.org/pdf/2205.14135.pdf), [ALiBi](https://arxiv.org/abs/2108.12409), [QK LayerNorm](https://arxiv.org/abs/2010.04245), and more. To use the optimized [triton implementation](https://github.com/openai/triton) of FlashAttention, you can load the model on GPU (`cuda:0`) with `attn_impl='triton'` and with `bfloat16` precision: ```python import torch import transformers name = 'mosaicml/mpt-30b' config = transformers.AutoConfig.from_pretrained(name, trust_remote_code=True) config.attn_config['attn_impl'] = 'triton' # change this to use triton-based FlashAttention config.init_device = 'cuda:0' # For fast initialization directly on GPU! model = transformers.AutoModelForCausalLM.from_pretrained( name, config=config, torch_dtype=torch.bfloat16, # Load model weights in bfloat16 trust_remote_code=True ) ``` The model was trained initially with a sequence length of 2048 with an additional pretraining stage for sequence length adapation up to 8192. However, ALiBi enables users to increase the maximum sequence length even further during finetuning and/or inference. For example: ```python import transformers name = 'mosaicml/mpt-30b' config = transformers.AutoConfig.from_pretrained(name, trust_remote_code=True) config.max_seq_len = 16384 # (input + output) tokens can now be up to 16384 model = transformers.AutoModelForCausalLM.from_pretrained( name, config=config, trust_remote_code=True ) ``` This model was trained with the MPT-30B tokenizer which is identical to the [EleutherAI/gpt-neox-20b](https://huggingface.co/EleutherAI/gpt-neox-20b) tokenizer. ```python from transformers import AutoTokenizer tokenizer = AutoTokenizer.from_pretrained('mosaicml/mpt-30b') ``` The model can then be used, for example, within a text-generation pipeline. Note: when running Torch modules in lower precision, it is best practice to use the [torch.autocast context manager](https://pytorch.org/docs/stable/amp.html). ```python from transformers import pipeline with torch.autocast('cuda', dtype=torch.bfloat16): inputs = tokenizer('Here is a recipe for vegan banana bread:\n', return_tensors="pt").to('cuda') outputs = model.generate(**inputs, max_new_tokens=100) print(tokenizer.batch_decode(outputs, skip_special_tokens=True)) # or using the HF pipeline pipe = pipeline('text-generation', model=model, tokenizer=tokenizer, device='cuda:0') with torch.autocast('cuda', dtype=torch.bfloat16): print( pipe('Here is a recipe for vegan banana bread:\n', max_new_tokens=100, do_sample=True, use_cache=True)) ``` ## Model Description The architecture is a modification of a standard decoder-only transformer. The model has been modified from a standard transformer in the following ways: * It uses [FlashAttention](https://arxiv.org/pdf/2205.14135.pdf) * It uses [ALiBi (Attention with Linear Biases)](https://arxiv.org/abs/2108.12409) and does not use positional embeddings * It does not use biases | Hyperparameter | Value | |----------------|-------| |n_parameters | 29.95B | |n_layers | 48 | | n_heads | 64 | | d_model | 7168 | | vocab size | 50432 | | sequence length | 8192 | ## Training Data ### Streaming Datasets Data was formatted using the MosaicML [StreamingDataset](https://github.com/mosaicml/streaming) library to host our data in object storage and efficiently stream it to our compute cluster during training. StreamingDataset obviates the need to download the whole dataset before starting training, and allows instant resumption of training from any point in the dataset. ### Data Mix The model was trained for 1T tokens on the following data mix: | Data Source | Number of Tokens in Source | Proportion | Effective Number of Tokens | Epochs | |-------------|----------------------------|------------|----------------------------|--------| | mC4 3.1.0 - English (200+ words) | 2417.99 B | 33.50% | 335 B | 0.14 | | c4 - English - SemDedup 80% | 100.42 B | 29.90% | 299 B | 2.98 | | RedPajama - CommonCrawl | 878.45 B | 8.50% | 85 B | 0.097 | | The Stack - Selected Languages | 463.78 B | 10.00% | 100 B | 0.22 | | RedPajama - Wikipedia | 4.87 B | 4.00% | 40 B | 8.21 | | The Stack - Markdown | 107.07 B | 4.50% | 45 B | 0.42 | | Semantic Scholar ORC | 48.95 B | 3.30% | 33 B | 0.67 | | RedPajama - Books | 26.02 B | 3.00% | 30 B | 1.15 | | RedPajama - arXiv | 28.10 B | 1.90% | 19 B | 0.68 | | RedPajama - StackExchange | 20.54 B | 1.40% | 14 B |0.68 | Samples for each batch were selected from one of the datasets with the probability specified above. The examples were shuffled within each dataset, and each example was constructed from as many sequences from that dataset as were necessary to fill the sequence length. To build 8k support into MPT-30B efficiently, we first pre-trained on 1T tokens using sequences that were 2k tokens long, and then trained for an additional 50B tokens using sequences that were 8k tokens long. The data was tokenized using the [EleutherAI/gpt-neox-20b](https://huggingface.co/EleutherAI/gpt-neox-20b) tokenizer. This BPE tokenizer has a number of desirable characteristics, most of which are relevant for tokenizing code: (1) It was trained on a diverse mix of data that includes code (The Pile) (2) It applies consistent space delimitation, unlike the GPT2 tokenizer which tokenizes inconsistently depending on the presence of prefix spaces (3) It contains tokens for repeated space characters, which allows superior compression of text with large amounts of repeated space characters. The model vocabulary size of 50432 was set to be a multiple of 128 (as in [MEGATRON-LM](https://arxiv.org/abs/1909.08053)). ### Training Configuration The model was trained in three stages using the [MosaicML Platform](https://www.mosaicml.com/platform): (i) First it was trained on 440 A100-40GBs with a batch size of 1760. (ii) Then, on 216 A100-40GBs with a batch size of 1728. (iii) Training was completed on 256 H100-80GBs with a batch size of 512 with 8k context length and 50B tokens. The model was trained with sharded data parallelism using [FSDP](https://pytorch.org/docs/stable/fsdp.html) and used the [LION](https://arxiv.org/abs/2302.06675) optimizer. ## Limitations and Biases _The following language is modified from [EleutherAI's GPT-NeoX-20B](https://huggingface.co/EleutherAI/gpt-neox-20b)_ MPT-30B (Base) is **not** intended for deployment without finetuning. It should not be used for human-facing interactions without further guardrails and user consent. MPT-30B can produce factually incorrect output, and should not be relied on to produce factually accurate information. MPT-30B was trained on various public datasets. While great efforts have been taken to clean the pretraining data, it is possible that this model could generate lewd, biased or otherwise offensive outputs. ## MosaicML Platform If you're interested in [training](https://www.mosaicml.com/training) and [deploying](https://www.mosaicml.com/inference) your own MPT or LLMs on the MosaicML Platform, [sign up here](https://forms.mosaicml.com/demo?utm_source=huggingface&utm_medium=referral&utm_campaign=mpt-30b). ## Disclaimer The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please consult an attorney before using this model for commercial purposes. ## Citation Please cite this model using the following format: ``` @online{MosaicML2023Introducing, author = {MosaicML NLP Team}, title = {Introducing MPT-30B: Raising the bar for open-source foundation models}, year = {2023}, url = {www.mosaicml.com/blog/mpt-30b}, note = {Accessed: 2023-06-22}, urldate = {2023-06-22} } ```

luhx/ppo-SnowballTarget

luhx

2023-07-12T04:56:57Z

0

ml-agents

[ "ml-agents", "tensorboard", "onnx", "SnowballTarget", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SnowballTarget", "region:us" ]

reinforcement-learning

2023-07-12T04:56:51Z

--- library_name: ml-agents tags: - SnowballTarget - deep-reinforcement-learning - reinforcement-learning - ML-Agents-SnowballTarget --- # **ppo** Agent playing **SnowballTarget** This is a trained model of a **ppo** agent playing **SnowballTarget** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A *longer tutorial* to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent **playing directly in your browser** 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: luhx/ppo-SnowballTarget 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀

localmodels/Vicuna-7B-v1.3-ggml

localmodels

2023-07-12T04:56:50Z

0

2

null

[ "arxiv:2302.13971", "arxiv:2306.05685", "region:us" ]

null

2023-07-12T04:56:50Z

--- duplicated_from: localmodels/LLM --- # Vicuna 7B v1.3 ggml From LMSYS: https://huggingface.co/lmsys/vicuna-7b-v1.3 --- ### Original llama.cpp quant methods: `q4_0, q4_1, q5_0, q5_1, q8_0` Quantized using an older version of llama.cpp and compatible with llama.cpp from May 19, commit 2d5db48. ### k-quant methods: `q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K` Quantization methods compatible with latest llama.cpp from June 6, commit 2d43387. --- ## Files | Name | Quant method | Bits | Size | Max RAM required, no GPU offloading | Use case | | ---- | ---- | ---- | ---- | ---- | ----- | | vicuna-7b-v1.3.ggmlv3.q2_K.bin | q2_K | 2 | 2.87 GB | 5.37 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. | | vicuna-7b-v1.3.ggmlv3.q3_K_L.bin | q3_K_L | 3 | 3.60 GB | 6.10 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K | | vicuna-7b-v1.3.ggmlv3.q3_K_M.bin | q3_K_M | 3 | 3.28 GB | 5.78 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K | | vicuna-7b-v1.3.ggmlv3.q3_K_S.bin | q3_K_S | 3 | 2.95 GB | 5.45 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors | | vicuna-7b-v1.3.ggmlv3.q4_0.bin | q4_0 | 4 | 3.79 GB | 6.29 GB | Original llama.cpp quant method, 4-bit. | | vicuna-7b-v1.3.ggmlv3.q4_1.bin | q4_1 | 4 | 4.21 GB | 6.71 GB | Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. | | vicuna-7b-v1.3.ggmlv3.q4_K_M.bin | q4_K_M | 4 | 4.08 GB | 6.58 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K | | vicuna-7b-v1.3.ggmlv3.q4_K_S.bin | q4_K_S | 4 | 3.83 GB | 6.33 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors | | vicuna-7b-v1.3.ggmlv3.q5_0.bin | q5_0 | 5 | 4.63 GB | 7.13 GB | Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. | | vicuna-7b-v1.3.ggmlv3.q5_1.bin | q5_1 | 5 | 5.06 GB | 7.56 GB | Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. | | vicuna-7b-v1.3.ggmlv3.q5_K_M.bin | q5_K_M | 5 | 4.78 GB | 7.28 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K | | vicuna-7b-v1.3.ggmlv3.q5_K_S.bin | q5_K_S | 5 | 4.65 GB | 7.15 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors | | vicuna-7b-v1.3.ggmlv3.q6_K.bin | q6_K | 6 | 5.53 GB | 8.03 GB | New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors | | vicuna-7b-v1.3.ggmlv3.q8_0.bin | q8_0 | 8 | 7.16 GB | 9.66 GB | Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. | --- # Vicuna Model Card ## Model Details Vicuna is a chat assistant trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT. - **Developed by:** [LMSYS](https://lmsys.org/) - **Model type:** An auto-regressive language model based on the transformer architecture. - **License:** Non-commercial license - **Finetuned from model:** [LLaMA](https://arxiv.org/abs/2302.13971). ### Model Sources - **Repository:** https://github.com/lm-sys/FastChat - **Blog:** https://lmsys.org/blog/2023-03-30-vicuna/ - **Paper:** https://arxiv.org/abs/2306.05685 - **Demo:** https://chat.lmsys.org/ ## Uses The primary use of Vicuna is research on large language models and chatbots. The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence. ## How to Get Started with the Model Command line interface: https://github.com/lm-sys/FastChat#vicuna-weights. APIs (OpenAI API, Huggingface API): https://github.com/lm-sys/FastChat/tree/main#api. ## Training Details Vicuna v1.3 is fine-tuned from LLaMA with supervised instruction fine-tuning. The training data is around 140K conversations collected from ShareGPT.com. See more details in the "Training Details of Vicuna Models" section in the appendix of this [paper](https://arxiv.org/pdf/2306.05685.pdf). ## Evaluation Vicuna is evaluated with standard benchmarks, human preference, and LLM-as-a-judge. See more details in this [paper](https://arxiv.org/pdf/2306.05685.pdf). ## Difference between different versions of Vicuna See [vicuna_weights_version.md](https://github.com/lm-sys/FastChat/blob/main/docs/vicuna_weights_version.md)

sumet/ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan

sumet

2023-07-12T04:53:34Z

7

1

transformers

[ "transformers", "pytorch", "audio-spectrogram-transformer", "audio-classification", "generated_from_trainer", "dataset:marsyas/gtzan", "base_model:MIT/ast-finetuned-audioset-10-10-0.4593", "base_model:finetune:MIT/ast-finetuned-audioset-10-10-0.4593", "license:bsd-3-clause", "model-index", "endpoints_compatible", "region:us" ]

audio-classification

2023-07-11T09:20:21Z

--- license: bsd-3-clause base_model: MIT/ast-finetuned-audioset-10-10-0.4593 tags: - generated_from_trainer datasets: - marsyas/gtzan metrics: - accuracy model-index: - name: ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan results: - task: name: Audio Classification type: audio-classification dataset: name: GTZAN type: marsyas/gtzan config: all split: train args: all metrics: - name: Accuracy type: accuracy value: 0.88 ---  # ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan This model is a fine-tuned version of [MIT/ast-finetuned-audioset-10-10-0.4593](https://huggingface.co/MIT/ast-finetuned-audioset-10-10-0.4593) on the GTZAN dataset. It achieves the following results on the evaluation set: - Loss: 0.5086 - Accuracy: 0.88 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 2 - eval_batch_size: 2 - seed: 14 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 20 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 0.5982 | 1.0 | 112 | 0.5195 | 0.83 | | 0.3962 | 2.0 | 225 | 0.5597 | 0.81 | | 0.3143 | 3.0 | 337 | 0.7567 | 0.83 | | 0.0548 | 4.0 | 450 | 0.5270 | 0.86 | | 0.0119 | 5.0 | 562 | 0.5813 | 0.88 | | 0.2503 | 6.0 | 675 | 0.7523 | 0.86 | | 0.0008 | 7.0 | 787 | 0.6239 | 0.85 | | 0.0003 | 8.0 | 900 | 0.4949 | 0.9 | | 0.0001 | 9.0 | 1012 | 0.5706 | 0.88 | | 0.0003 | 10.0 | 1125 | 0.4898 | 0.92 | | 0.0001 | 11.0 | 1237 | 0.5281 | 0.89 | | 0.0001 | 12.0 | 1350 | 0.5197 | 0.88 | | 0.0002 | 13.0 | 1462 | 0.5036 | 0.9 | | 0.0 | 14.0 | 1575 | 0.5362 | 0.9 | | 0.0 | 15.0 | 1687 | 0.5065 | 0.89 | | 0.0 | 16.0 | 1800 | 0.5011 | 0.9 | | 0.0 | 17.0 | 1912 | 0.5025 | 0.88 | | 0.0 | 18.0 | 2025 | 0.5027 | 0.88 | | 0.0 | 19.0 | 2137 | 0.5074 | 0.88 | | 0.0 | 19.91 | 2240 | 0.5086 | 0.88 | ### Framework versions - Transformers 4.31.0.dev0 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3

localmodels/Vicuna-13B-v1.3-ggml

localmodels

2023-07-12T04:52:24Z

0

null

[ "arxiv:2302.13971", "arxiv:2306.05685", "region:us" ]

null

2023-07-12T04:52:24Z

--- duplicated_from: localmodels/LLM --- # Vicuna 13B v1.3 ggml From LMSYS: https://huggingface.co/lmsys/vicuna-13b-v1.3 --- ### Original llama.cpp quant methods: `q4_0, q4_1, q5_0, q5_1, q8_0` Quantized using an older version of llama.cpp and compatible with llama.cpp from May 19, commit 2d5db48. ### k-quant methods: `q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K` Quantization methods compatible with latest llama.cpp from June 6, commit 2d43387. --- ## Files | Name | Quant method | Bits | Size | Max RAM required, no GPU offloading | Use case | | ---- | ---- | ---- | ---- | ---- | ----- | | vicuna-13b-v1.3.0.ggmlv3.q2_K.bin | q2_K | 2 | 5.51 GB | 8.01 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. | | vicuna-13b-v1.3.0.ggmlv3.q3_K_L.bin | q3_K_L | 3 | 6.93 GB | 9.43 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K | | vicuna-13b-v1.3.0.ggmlv3.q3_K_M.bin | q3_K_M | 3 | 6.31 GB | 8.81 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K | | vicuna-13b-v1.3.0.ggmlv3.q3_K_S.bin | q3_K_S | 3 | 5.66 GB | 8.16 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors | | vicuna-13b-v1.3.0.ggmlv3.q4_0.bin | q4_0 | 4 | 7.32 GB | 9.82 GB | Original llama.cpp quant method, 4-bit. | | vicuna-13b-v1.3.0.ggmlv3.q4_1.bin | q4_1 | 4 | 8.14 GB | 10.64 GB | Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. | | vicuna-13b-v1.3.0.ggmlv3.q4_K_M.bin | q4_K_M | 4 | 7.87 GB | 10.37 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K | | vicuna-13b-v1.3.0.ggmlv3.q4_K_S.bin | q4_K_S | 4 | 7.37 GB | 9.87 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors | | vicuna-13b-v1.3.0.ggmlv3.q5_0.bin | q5_0 | 5 | 8.95 GB | 11.45 GB | Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. | | vicuna-13b-v1.3.0.ggmlv3.q5_1.bin | q5_1 | 5 | 9.76 GB | 12.26 GB | Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. | | vicuna-13b-v1.3.0.ggmlv3.q5_K_M.bin | q5_K_M | 5 | 9.23 GB | 11.73 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K | | vicuna-13b-v1.3.0.ggmlv3.q5_K_S.bin | q5_K_S | 5 | 8.97 GB | 11.47 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors | | vicuna-13b-v1.3.0.ggmlv3.q6_K.bin | q6_K | 6 | 10.68 GB | 13.18 GB | New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors | | vicuna-13b-v1.3.0.ggmlv3.q8_0.bin | q8_0 | 8 | 13.83 GB | 16.33 GB | Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. | --- # Vicuna Model Card ## Model Details Vicuna is a chat assistant trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT. - **Developed by:** [LMSYS](https://lmsys.org/) - **Model type:** An auto-regressive language model based on the transformer architecture. - **License:** Non-commercial license - **Finetuned from model:** [LLaMA](https://arxiv.org/abs/2302.13971). ### Model Sources - **Repository:** https://github.com/lm-sys/FastChat - **Blog:** https://lmsys.org/blog/2023-03-30-vicuna/ - **Paper:** https://arxiv.org/abs/2306.05685 - **Demo:** https://chat.lmsys.org/ ## Uses The primary use of Vicuna is research on large language models and chatbots. The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence. ## How to Get Started with the Model Command line interface: https://github.com/lm-sys/FastChat#vicuna-weights. APIs (OpenAI API, Huggingface API): https://github.com/lm-sys/FastChat/tree/main#api. ## Training Details Vicuna v1.3 is fine-tuned from LLaMA with supervised instruction fine-tuning. The training data is around 140K conversations collected from ShareGPT.com. See more details in the "Training Details of Vicuna Models" section in the appendix of this [paper](https://arxiv.org/pdf/2306.05685.pdf). ## Evaluation Vicuna is evaluated with standard benchmarks, human preference, and LLM-as-a-judge. See more details in this [paper](https://arxiv.org/pdf/2306.05685.pdf). ## Difference between different versions of Vicuna See [vicuna_weights_version.md](https://github.com/lm-sys/FastChat/blob/main/docs/vicuna_weights_version.md)

Ayushhh07/Income

Ayushhh07

2023-07-12T04:50:01Z

0

asteroid

[ "asteroid", "chemistry", "biology", "legal", "finance", "music", "text-classification", "en", "aa", "ab", "af", "dataset:Open-Orca/OpenOrca", "license:creativeml-openrail-m", "region:us" ]

text-classification

2023-07-12T04:48:44Z

--- license: creativeml-openrail-m datasets: - Open-Orca/OpenOrca language: - en - aa - ab - af metrics: - accuracy - character library_name: asteroid pipeline_tag: text-classification tags: - chemistry - biology - legal - finance - music ---

happyduck/alcafa_5.8b_100_bum

happyduck

2023-07-12T04:43:17Z

0

peft

[ "peft", "region:us" ]

null

2023-07-11T00:52:37Z

--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.4.0.dev0

hungngo04/cluster_to_text_t5_base_test

hungngo04

2023-07-12T04:42:25Z

3

0

transformers

[ "transformers", "pytorch", "tensorboard", "t5", "text2text-generation", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text2text-generation

2023-07-12T03:52:06Z

--- license: apache-2.0 tags: - generated_from_trainer metrics: - bleu model-index: - name: cluster_to_text_t5_base_test results: [] ---  # cluster_to_text_t5_base_test This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.7184 - Bleu: 12.1051 - Gen Len: 10.6659 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len | |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:| | 2.4089 | 1.0 | 4678 | 2.1095 | 3.8133 | 11.5338 | | 2.1256 | 2.0 | 9356 | 1.8032 | 9.8148 | 10.7901 | | 2.0173 | 3.0 | 14034 | 1.7184 | 12.1051 | 10.6659 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3

Vezora/Mini_Orca_7b_v2_2048_Lora_adapter

Vezora

2023-07-12T04:29:49Z

0

null

[ "license:apache-2.0", "region:us" ]

null

2023-07-12T03:53:17Z

--- license: apache-2.0 --- 2 epochs 92 hours of training on a undervolted 3090 pulling 250 watts. My system configuration was getting 13.25 it/s and slowly dropped to 13.04 it/s at 2 epochs. Dataset used is uncencored and filtered of Psmathur's wizard orca 72k instructions, ported into a alpaca chat format, and removed all "Input" strings. Trained on only instruction and output. Preforms remarkably well works with the blokes gptq mini orca v2 gptq and allows the model to output 2048 tokens. This adapter was trained to test how lora training could be used to expand context window with less compute. The original model trained by "psmathur" was trained with "8x A100(80G) GPUs for around 13 Hours for cost of $195". I'm hoping the bloke can merge this with the orignal model and upload a gptq version for everyone.

NorgNM/Realistic-Visions_v4.0

NorgNM

2023-07-12T04:26:48Z

0

null

[ "license:mit", "region:us" ]

null

2023-07-10T17:59:33Z

--- title: Dreambooth Training emoji: ☁️ colorFrom: pink colorTo: red sdk: gradio sdk_version: 3.16.2 app_file: app.py pinned: false suggested_hardware: t4-small license: mit duplicated_from: multimodalart/dreambooth-training --- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

elasticdavid/qlora-koalpaca-polyglot-12.8b-fasoo-brochure-153steps

elasticdavid

2023-07-12T04:23:14Z

0

peft

[ "peft", "region:us" ]

null

2023-07-12T04:23:05Z

--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.4.0.dev0

assembleteams/curiouspi

assembleteams

2023-07-12T04:01:19Z

0

1

adapter-transformers

[ "adapter-transformers", "research", "science", "development", "energy", "climate", "water", "food systems", "transit", "supplychain", "space", "deepsea", "prototypes", "planning", "infrastructure", "systems", "assessment", "resourceplanning", "conversational", "en", "te", "es", "fr", "de", "hi", "ur", "ru", "pt", "gu", "he", "pa", "dataset:tiiuae/falcon-refinedweb", "dataset:Open-Orca/OpenOrca", "dataset:GAIR/lima", "license:apache-2.0", "region:us" ]

text-generation

2023-07-12T02:48:23Z

--- license: apache-2.0 datasets: - tiiuae/falcon-refinedweb - Open-Orca/OpenOrca - GAIR/lima language: - en - te - es - fr - de - hi - ur - ru - pt - gu - he - pa metrics: - accuracy - bertscore - brier_score - code_eval - charcut_mt - character library_name: adapter-transformers pipeline_tag: conversational tags: - research - science - development - energy - climate - water - food systems - transit - supplychain - space - deepsea - prototypes - planning - infrastructure - systems - assessment - resourceplanning ---

sbaner24/vit-base-patch16-224-Trial006-007-008-YEL_STEM4

sbaner24

2023-07-12T03:30:48Z

5

0

transformers

[ "transformers", "pytorch", "vit", "image-classification", "generated_from_trainer", "dataset:imagefolder", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]

image-classification

2023-07-12T02:53:44Z

--- license: apache-2.0 tags: - generated_from_trainer datasets: - imagefolder metrics: - accuracy model-index: - name: vit-base-patch16-224-Trial006-007-008-YEL_STEM4 results: - task: name: Image Classification type: image-classification dataset: name: imagefolder type: imagefolder config: default split: train args: default metrics: - name: Accuracy type: accuracy value: 0.9354838709677419 ---  # vit-base-patch16-224-Trial006-007-008-YEL_STEM4 This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 0.1729 - Accuracy: 0.9355 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 60 - eval_batch_size: 60 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 240 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 0.6572 | 1.0 | 6 | 0.6719 | 0.5677 | | 0.6279 | 2.0 | 12 | 0.6436 | 0.6516 | | 0.5282 | 3.0 | 18 | 0.5677 | 0.7871 | | 0.5405 | 4.0 | 24 | 0.4718 | 0.8258 | | 0.5276 | 5.0 | 30 | 0.4959 | 0.7419 | | 0.412 | 6.0 | 36 | 0.3081 | 0.8581 | | 0.3011 | 7.0 | 42 | 0.2542 | 0.8839 | | 0.3329 | 8.0 | 48 | 0.2350 | 0.8774 | | 0.4478 | 9.0 | 54 | 0.1743 | 0.9290 | | 0.268 | 10.0 | 60 | 0.1708 | 0.9161 | | 0.2177 | 11.0 | 66 | 0.1729 | 0.9355 | | 0.2675 | 12.0 | 72 | 0.1913 | 0.8968 | | 0.4784 | 13.0 | 78 | 0.1826 | 0.9032 | | 0.2456 | 14.0 | 84 | 0.1774 | 0.9032 | | 0.6229 | 15.0 | 90 | 0.2196 | 0.8968 | | 0.2561 | 16.0 | 96 | 0.1823 | 0.9226 | | 0.3785 | 17.0 | 102 | 0.1770 | 0.9032 | | 0.2334 | 18.0 | 108 | 0.2056 | 0.8903 | | 0.1904 | 19.0 | 114 | 0.1564 | 0.9097 | | 0.2256 | 20.0 | 120 | 0.1407 | 0.9226 | | 0.2547 | 21.0 | 126 | 0.1552 | 0.9032 | | 0.3468 | 22.0 | 132 | 0.1819 | 0.8968 | | 0.4116 | 23.0 | 138 | 0.1537 | 0.9290 | | 0.3689 | 24.0 | 144 | 0.1645 | 0.9097 | | 0.3541 | 25.0 | 150 | 0.1527 | 0.9290 | | 0.2498 | 26.0 | 156 | 0.1670 | 0.9161 | | 0.3625 | 27.0 | 162 | 0.1522 | 0.9161 | | 0.2463 | 28.0 | 168 | 0.1552 | 0.9226 | | 0.3447 | 29.0 | 174 | 0.1510 | 0.9097 | | 0.205 | 30.0 | 180 | 0.1924 | 0.9032 | | 0.2023 | 31.0 | 186 | 0.1376 | 0.9355 | | 0.3617 | 32.0 | 192 | 0.1518 | 0.9097 | | 0.3515 | 33.0 | 198 | 0.1473 | 0.9097 | | 0.1927 | 34.0 | 204 | 0.1544 | 0.9097 | | 0.4567 | 35.0 | 210 | 0.1528 | 0.9097 | | 0.3113 | 36.0 | 216 | 0.1510 | 0.9226 | | 0.3475 | 37.0 | 222 | 0.1594 | 0.9161 | | 0.1889 | 38.0 | 228 | 0.1448 | 0.9290 | | 0.1979 | 39.0 | 234 | 0.1533 | 0.9226 | | 0.3578 | 40.0 | 240 | 0.1627 | 0.9097 | | 0.2004 | 41.0 | 246 | 0.1620 | 0.9161 | | 0.3567 | 42.0 | 252 | 0.1475 | 0.9226 | | 0.192 | 43.0 | 258 | 0.1504 | 0.9032 | | 0.1872 | 44.0 | 264 | 0.1535 | 0.9097 | | 0.2079 | 45.0 | 270 | 0.1490 | 0.9161 | | 0.1503 | 46.0 | 276 | 0.1459 | 0.9161 | | 0.169 | 47.0 | 282 | 0.1506 | 0.8968 | | 0.1884 | 48.0 | 288 | 0.1556 | 0.8968 | | 0.1638 | 49.0 | 294 | 0.1573 | 0.8968 | | 0.1921 | 50.0 | 300 | 0.1570 | 0.8968 | ### Framework versions - Transformers 4.30.0.dev0 - Pytorch 1.12.1 - Datasets 2.12.0 - Tokenizers 0.13.1

ALM-AHME/swinv2-large-patch4-window12to16-192to256-22kto1k-ft-finetuned-LungCancer-LC25000-AH-40-30-30

ALM-AHME

2023-07-12T03:29:09Z

150

1

transformers

[ "transformers", "pytorch", "tensorboard", "swinv2", "image-classification", "generated_from_trainer", "dataset:imagefolder", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]

image-classification

2023-07-11T23:28:32Z

--- license: apache-2.0 tags: - generated_from_trainer datasets: - imagefolder metrics: - accuracy model-index: - name: swinv2-large-patch4-window12to16-192to256-22kto1k-ft-finetuned-LungCancer-LC25000-AH-40-30-30 results: - task: name: Image Classification type: image-classification dataset: name: imagefolder type: imagefolder config: Augmented-Final split: train args: Augmented-Final metrics: - name: Accuracy type: accuracy value: 0.9869324473975637 ---  # swinv2-large-patch4-window12to16-192to256-22kto1k-ft-finetuned-LungCancer-LC25000-AH-40-30-30 This model is a fine-tuned version of [microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft](https://huggingface.co/microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 0.0418 - Accuracy: 0.9869 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.5 - num_epochs: 5 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 0.3299 | 1.0 | 187 | 0.2118 | 0.9218 | | 0.5922 | 2.0 | 374 | 0.3206 | 0.8629 | | 0.1763 | 3.0 | 561 | 0.2447 | 0.9127 | | 0.1351 | 4.0 | 749 | 0.1028 | 0.9564 | | 0.142 | 4.99 | 935 | 0.0418 | 0.9869 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3

macapa/emotion-text-better

macapa

2023-07-12T03:01:46Z

0

fastai

[ "fastai", "region:us" ]

null

2023-07-12T03:01:41Z

--- tags: - fastai --- # Amazing! 🥳 Congratulations on hosting your fastai model on the Hugging Face Hub! # Some next steps 1. Fill out this model card with more information (see the template below and the [documentation here](https://huggingface.co/docs/hub/model-repos))! 2. Create a demo in Gradio or Streamlit using 🤗 Spaces ([documentation here](https://huggingface.co/docs/hub/spaces)). 3. Join the fastai community on the [Fastai Discord](https://discord.com/invite/YKrxeNn)! Greetings fellow fastlearner 🤝! Don't forget to delete this content from your model card. --- # Model card ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed

yashgharat/Reinforce-PixelCopter

yashgharat

2023-07-12T02:55:43Z

0

null

[ "Pixelcopter-PLE-v0", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]

reinforcement-learning

2023-07-07T14:17:14Z

--- tags: - Pixelcopter-PLE-v0 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: Reinforce-PixelCopter results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Pixelcopter-PLE-v0 type: Pixelcopter-PLE-v0 metrics: - type: mean_reward value: 16.30 +/- 12.98 name: mean_reward verified: false --- # **Reinforce** Agent playing **Pixelcopter-PLE-v0** This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction

Suechun/pawsx-en-loraWeight

Suechun

2023-07-12T02:47:19Z

0

transformers

[ "transformers", "en", "ja", "dataset:paws-x", "license:other", "endpoints_compatible", "region:us" ]

null

2023-07-10T14:29:27Z

--- license: other datasets: - paws-x language: - en - ja library_name: transformers ---

sbaner24/vit-base-patch16-224-Trial006-007-008-YEL_STEM3

sbaner24

2023-07-12T02:46:51Z

8

0

transformers

[ "transformers", "pytorch", "vit", "image-classification", "generated_from_trainer", "dataset:imagefolder", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]

image-classification

2023-07-12T02:09:06Z

--- license: apache-2.0 tags: - generated_from_trainer datasets: - imagefolder metrics: - accuracy model-index: - name: vit-base-patch16-224-Trial006-007-008-YEL_STEM3 results: - task: name: Image Classification type: image-classification dataset: name: imagefolder type: imagefolder config: default split: train args: default metrics: - name: Accuracy type: accuracy value: 0.9240506329113924 ---  # vit-base-patch16-224-Trial006-007-008-YEL_STEM3 This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 0.1618 - Accuracy: 0.9241 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 60 - eval_batch_size: 60 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 240 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 0.7035 | 1.0 | 6 | 0.6557 | 0.6203 | | 0.6168 | 2.0 | 12 | 0.5788 | 0.7215 | | 0.5412 | 3.0 | 18 | 0.5005 | 0.7785 | | 0.496 | 4.0 | 24 | 0.4946 | 0.7722 | | 0.4024 | 5.0 | 30 | 0.4057 | 0.8165 | | 0.4098 | 6.0 | 36 | 0.3076 | 0.8544 | | 0.3645 | 7.0 | 42 | 0.3250 | 0.8418 | | 0.276 | 8.0 | 48 | 0.2206 | 0.8924 | | 0.3358 | 9.0 | 54 | 0.2100 | 0.8987 | | 0.3386 | 10.0 | 60 | 0.1618 | 0.9241 | | 0.2778 | 11.0 | 66 | 0.1609 | 0.9177 | | 0.25 | 12.0 | 72 | 0.1581 | 0.9114 | | 0.2914 | 13.0 | 78 | 0.1663 | 0.9114 | | 0.2273 | 14.0 | 84 | 0.1525 | 0.9177 | | 0.2694 | 15.0 | 90 | 0.1708 | 0.9051 | | 0.2745 | 16.0 | 96 | 0.2364 | 0.8734 | | 0.2809 | 17.0 | 102 | 0.1976 | 0.8608 | | 0.2368 | 18.0 | 108 | 0.1517 | 0.9114 | | 0.328 | 19.0 | 114 | 0.2454 | 0.8671 | | 0.2571 | 20.0 | 120 | 0.1482 | 0.9114 | | 0.2996 | 21.0 | 126 | 0.1629 | 0.8987 | | 0.266 | 22.0 | 132 | 0.1360 | 0.9114 | | 0.2323 | 23.0 | 138 | 0.1427 | 0.9114 | | 0.2285 | 24.0 | 144 | 0.1683 | 0.9051 | | 0.2566 | 25.0 | 150 | 0.1442 | 0.9114 | | 0.2509 | 26.0 | 156 | 0.1595 | 0.9114 | | 0.2337 | 27.0 | 162 | 0.1291 | 0.9177 | | 0.2203 | 28.0 | 168 | 0.1302 | 0.8987 | | 0.2409 | 29.0 | 174 | 0.1274 | 0.9114 | | 0.2256 | 30.0 | 180 | 0.1272 | 0.8987 | | 0.2157 | 31.0 | 186 | 0.1289 | 0.9177 | | 0.2168 | 32.0 | 192 | 0.1267 | 0.9114 | | 0.2426 | 33.0 | 198 | 0.1438 | 0.8987 | | 0.2404 | 34.0 | 204 | 0.1388 | 0.8987 | | 0.2218 | 35.0 | 210 | 0.1243 | 0.9241 | | 0.3068 | 36.0 | 216 | 0.1268 | 0.9241 | | 0.1721 | 37.0 | 222 | 0.1477 | 0.8987 | | 0.2201 | 38.0 | 228 | 0.1545 | 0.8987 | | 0.2581 | 39.0 | 234 | 0.1700 | 0.8987 | | 0.213 | 40.0 | 240 | 0.1254 | 0.9114 | | 0.2953 | 41.0 | 246 | 0.1237 | 0.9114 | | 0.2564 | 42.0 | 252 | 0.1472 | 0.9051 | | 0.249 | 43.0 | 258 | 0.1409 | 0.9051 | | 0.2372 | 44.0 | 264 | 0.1495 | 0.9114 | | 0.2541 | 45.0 | 270 | 0.1412 | 0.9051 | | 0.1997 | 46.0 | 276 | 0.1308 | 0.9114 | | 0.2381 | 47.0 | 282 | 0.1253 | 0.9177 | | 0.2623 | 48.0 | 288 | 0.1267 | 0.9051 | | 0.1855 | 49.0 | 294 | 0.1285 | 0.9051 | | 0.1877 | 50.0 | 300 | 0.1289 | 0.9051 | ### Framework versions - Transformers 4.30.0.dev0 - Pytorch 1.12.1 - Datasets 2.12.0 - Tokenizers 0.13.1

Djdheg7272gshd/Fufufh

Djdheg7272gshd

2023-07-12T02:36:43Z

0

null

[ "license:bigscience-openrail-m", "region:us" ]

null

2023-07-12T02:36:43Z

--- license: bigscience-openrail-m ---

uribah/my_awesome_model

uribah

2023-07-12T02:33:01Z

61

0

transformers

[ "transformers", "tf", "distilbert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

text-classification

2023-07-08T18:44:13Z

--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: uribah/my_awesome_model results: [] ---  # uribah/my_awesome_model This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 0.1206 - Validation Loss: 0.2358 - Train Accuracy: 0.9409 - Epoch: 4 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 565, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Validation Loss | Train Accuracy | Epoch | |:----------:|:---------------:|:--------------:|:-----:| | 0.5194 | 0.2501 | 0.9310 | 0 | | 0.2587 | 0.2353 | 0.9360 | 1 | | 0.1844 | 0.2339 | 0.9360 | 2 | | 0.1442 | 0.2295 | 0.9409 | 3 | | 0.1206 | 0.2358 | 0.9409 | 4 | ### Framework versions - Transformers 4.30.2 - TensorFlow 2.12.0 - Datasets 2.13.1 - Tokenizers 0.13.3

skywalker7/dqn-SpaceInvadersNoFrameskip-v4

skywalker7

2023-07-12T02:13:15Z

2

0

stable-baselines3

[ "stable-baselines3", "SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

reinforcement-learning

2023-07-12T02:12:36Z

--- library_name: stable-baselines3 tags: - SpaceInvadersNoFrameskip-v4 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: DQN results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: SpaceInvadersNoFrameskip-v4 type: SpaceInvadersNoFrameskip-v4 metrics: - type: mean_reward value: 789.50 +/- 166.17 name: mean_reward verified: false --- # **DQN** Agent playing **SpaceInvadersNoFrameskip-v4** This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3) and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo). The RL Zoo is a training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included. ## Usage (with SB3 RL Zoo) RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo SB3: https://github.com/DLR-RM/stable-baselines3 SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib Install the RL Zoo (with SB3 and SB3-Contrib): ```bash pip install rl_zoo3 ``` ``` # Download model and save it into the logs/ folder python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga skywalker7 -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do: ``` python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga skywalker7 -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` ## Training (with the RL Zoo) ``` python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ # Upload the model and generate video (when possible) python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga skywalker7 ``` ## Hyperparameters ```python OrderedDict([('batch_size', 32), ('buffer_size', 100000), ('env_wrapper', ['stable_baselines3.common.atari_wrappers.AtariWrapper']), ('exploration_final_eps', 0.01), ('exploration_fraction', 0.1), ('frame_stack', 4), ('gradient_steps', 1), ('learning_rate', 0.0001), ('learning_starts', 100000), ('n_timesteps', 1000000), ('optimize_memory_usage', False), ('policy', 'CnnPolicy'), ('target_update_interval', 1000), ('train_freq', 4), ('normalize', False)]) ``` # Environment Arguments ```python {'render_mode': 'rgb_array'} ```

jordyvl/vit-tiny_rvl_cdip_100_examples_per_class_kd_NKD_t1.0_g1.5

jordyvl

2023-07-12T02:13:05Z

163

0

transformers

[ "transformers", "pytorch", "vit", "image-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

image-classification

2023-07-12T01:35:01Z

--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: vit-tiny_rvl_cdip_100_examples_per_class_kd_NKD_t1.0_g1.5 results: [] ---  # vit-tiny_rvl_cdip_100_examples_per_class_kd_NKD_t1.0_g1.5 This model is a fine-tuned version of [WinKawaks/vit-tiny-patch16-224](https://huggingface.co/WinKawaks/vit-tiny-patch16-224) on the None dataset. It achieves the following results on the evaluation set: - Loss: 5.4262 - Accuracy: 0.535 - Brier Loss: 0.6080 - Nll: 2.4569 - F1 Micro: 0.535 - F1 Macro: 0.5345 - Ece: 0.2120 - Aurc: 0.2105 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Brier Loss | Nll | F1 Micro | F1 Macro | Ece | Aurc | |:-------------:|:-----:|:----:|:---------------:|:--------:|:----------:|:------:|:--------:|:--------:|:------:|:------:| | No log | 1.0 | 7 | 8.7328 | 0.0375 | 1.0712 | 7.1959 | 0.0375 | 0.0284 | 0.2770 | 0.9564 | | No log | 2.0 | 14 | 6.6754 | 0.0725 | 0.9650 | 6.2033 | 0.0725 | 0.0442 | 0.1890 | 0.9239 | | No log | 3.0 | 21 | 6.2399 | 0.1525 | 0.9213 | 5.6927 | 0.1525 | 0.1339 | 0.1647 | 0.8105 | | No log | 4.0 | 28 | 5.9557 | 0.2125 | 0.8771 | 4.2773 | 0.2125 | 0.1952 | 0.1637 | 0.6347 | | No log | 5.0 | 35 | 5.5957 | 0.3275 | 0.7962 | 3.1599 | 0.3275 | 0.3087 | 0.1928 | 0.4595 | | No log | 6.0 | 42 | 5.4573 | 0.4075 | 0.7283 | 3.0860 | 0.4075 | 0.3732 | 0.1803 | 0.3610 | | No log | 7.0 | 49 | 5.3445 | 0.43 | 0.7150 | 2.9840 | 0.4300 | 0.4112 | 0.2071 | 0.3498 | | No log | 8.0 | 56 | 5.2986 | 0.445 | 0.6860 | 2.9281 | 0.445 | 0.4327 | 0.1891 | 0.3159 | | No log | 9.0 | 63 | 5.2567 | 0.465 | 0.6608 | 3.0783 | 0.465 | 0.4494 | 0.1835 | 0.2885 | | No log | 10.0 | 70 | 5.4317 | 0.4425 | 0.6752 | 2.9067 | 0.4425 | 0.4477 | 0.1836 | 0.3209 | | No log | 11.0 | 77 | 5.2073 | 0.4825 | 0.6342 | 2.7960 | 0.4825 | 0.4664 | 0.1731 | 0.2708 | | No log | 12.0 | 84 | 5.2094 | 0.51 | 0.6150 | 2.8886 | 0.51 | 0.4767 | 0.1463 | 0.2459 | | No log | 13.0 | 91 | 5.2379 | 0.4975 | 0.6135 | 2.7446 | 0.4975 | 0.4819 | 0.1702 | 0.2436 | | No log | 14.0 | 98 | 5.2716 | 0.505 | 0.6123 | 2.7888 | 0.505 | 0.4962 | 0.1595 | 0.2496 | | No log | 15.0 | 105 | 5.2410 | 0.5125 | 0.6090 | 2.6474 | 0.5125 | 0.5144 | 0.1659 | 0.2451 | | No log | 16.0 | 112 | 5.2764 | 0.54 | 0.6063 | 2.7700 | 0.54 | 0.5316 | 0.1634 | 0.2383 | | No log | 17.0 | 119 | 5.2652 | 0.5275 | 0.6027 | 2.7934 | 0.5275 | 0.5171 | 0.1800 | 0.2326 | | No log | 18.0 | 126 | 5.2145 | 0.54 | 0.5944 | 2.6456 | 0.54 | 0.5350 | 0.1548 | 0.2323 | | No log | 19.0 | 133 | 5.2611 | 0.5175 | 0.6096 | 2.5302 | 0.5175 | 0.5273 | 0.1709 | 0.2435 | | No log | 20.0 | 140 | 5.3536 | 0.52 | 0.6110 | 2.6530 | 0.52 | 0.5229 | 0.1619 | 0.2359 | | No log | 21.0 | 147 | 5.3020 | 0.5125 | 0.6060 | 2.7184 | 0.5125 | 0.5070 | 0.1724 | 0.2398 | | No log | 22.0 | 154 | 5.2107 | 0.5275 | 0.5926 | 2.4436 | 0.5275 | 0.5242 | 0.1618 | 0.2255 | | No log | 23.0 | 161 | 5.2723 | 0.53 | 0.5953 | 2.7008 | 0.53 | 0.5209 | 0.1698 | 0.2253 | | No log | 24.0 | 168 | 5.1615 | 0.5325 | 0.5875 | 2.4753 | 0.5325 | 0.5254 | 0.1699 | 0.2247 | | No log | 25.0 | 175 | 5.1795 | 0.5375 | 0.5825 | 2.6856 | 0.5375 | 0.5316 | 0.1781 | 0.2144 | | No log | 26.0 | 182 | 5.2340 | 0.54 | 0.5937 | 2.6542 | 0.54 | 0.5271 | 0.1778 | 0.2215 | | No log | 27.0 | 189 | 5.2197 | 0.5375 | 0.5831 | 2.4800 | 0.5375 | 0.5366 | 0.1666 | 0.2119 | | No log | 28.0 | 196 | 5.2345 | 0.5275 | 0.6105 | 2.6475 | 0.5275 | 0.5247 | 0.1919 | 0.2338 | | No log | 29.0 | 203 | 5.2050 | 0.5475 | 0.5917 | 2.6350 | 0.5475 | 0.5531 | 0.1753 | 0.2251 | | No log | 30.0 | 210 | 5.1753 | 0.5425 | 0.5891 | 2.6472 | 0.5425 | 0.5282 | 0.1831 | 0.2215 | | No log | 31.0 | 217 | 5.2349 | 0.535 | 0.5946 | 2.5653 | 0.535 | 0.5257 | 0.1617 | 0.2186 | | No log | 32.0 | 224 | 5.1497 | 0.545 | 0.5778 | 2.6174 | 0.545 | 0.5425 | 0.1716 | 0.2138 | | No log | 33.0 | 231 | 5.1688 | 0.5175 | 0.5899 | 2.5079 | 0.5175 | 0.5149 | 0.1624 | 0.2159 | | No log | 34.0 | 238 | 5.2269 | 0.53 | 0.5961 | 2.5188 | 0.53 | 0.5326 | 0.1746 | 0.2206 | | No log | 35.0 | 245 | 5.1477 | 0.5325 | 0.5867 | 2.4762 | 0.5325 | 0.5369 | 0.1728 | 0.2176 | | No log | 36.0 | 252 | 5.2229 | 0.5375 | 0.5838 | 2.4397 | 0.5375 | 0.5386 | 0.1693 | 0.2167 | | No log | 37.0 | 259 | 5.1578 | 0.535 | 0.5802 | 2.5103 | 0.535 | 0.5286 | 0.1755 | 0.2124 | | No log | 38.0 | 266 | 5.1405 | 0.535 | 0.5979 | 2.5852 | 0.535 | 0.5346 | 0.1913 | 0.2268 | | No log | 39.0 | 273 | 5.1236 | 0.535 | 0.5844 | 2.4851 | 0.535 | 0.5378 | 0.1729 | 0.2168 | | No log | 40.0 | 280 | 5.0813 | 0.5475 | 0.5757 | 2.4305 | 0.5475 | 0.5434 | 0.1781 | 0.2091 | | No log | 41.0 | 287 | 5.1844 | 0.535 | 0.5888 | 2.4730 | 0.535 | 0.5306 | 0.1707 | 0.2159 | | No log | 42.0 | 294 | 5.1468 | 0.53 | 0.5926 | 2.4866 | 0.53 | 0.5316 | 0.1776 | 0.2200 | | No log | 43.0 | 301 | 5.1469 | 0.53 | 0.5837 | 2.5769 | 0.53 | 0.5252 | 0.1805 | 0.2168 | | No log | 44.0 | 308 | 5.2168 | 0.54 | 0.5955 | 2.5216 | 0.54 | 0.5419 | 0.1689 | 0.2226 | | No log | 45.0 | 315 | 5.1395 | 0.525 | 0.5861 | 2.4328 | 0.525 | 0.5293 | 0.2006 | 0.2180 | | No log | 46.0 | 322 | 5.1163 | 0.5425 | 0.5822 | 2.4635 | 0.5425 | 0.5416 | 0.1937 | 0.2106 | | No log | 47.0 | 329 | 5.1227 | 0.5475 | 0.5786 | 2.5198 | 0.5475 | 0.5489 | 0.1580 | 0.2111 | | No log | 48.0 | 336 | 5.1134 | 0.5375 | 0.5839 | 2.5239 | 0.5375 | 0.5318 | 0.1832 | 0.2071 | | No log | 49.0 | 343 | 5.1907 | 0.5375 | 0.5913 | 2.5012 | 0.5375 | 0.5334 | 0.1853 | 0.2145 | | No log | 50.0 | 350 | 5.1364 | 0.5375 | 0.5875 | 2.4105 | 0.5375 | 0.5415 | 0.1857 | 0.2121 | | No log | 51.0 | 357 | 5.1739 | 0.5425 | 0.5905 | 2.5208 | 0.5425 | 0.5399 | 0.1894 | 0.2112 | | No log | 52.0 | 364 | 5.1635 | 0.5325 | 0.5841 | 2.4658 | 0.5325 | 0.5300 | 0.1924 | 0.2124 | | No log | 53.0 | 371 | 5.2055 | 0.5425 | 0.5866 | 2.4800 | 0.5425 | 0.5390 | 0.1983 | 0.2135 | | No log | 54.0 | 378 | 5.1547 | 0.5375 | 0.5869 | 2.4575 | 0.5375 | 0.5340 | 0.1839 | 0.2117 | | No log | 55.0 | 385 | 5.1437 | 0.535 | 0.5838 | 2.4117 | 0.535 | 0.5366 | 0.1914 | 0.2110 | | No log | 56.0 | 392 | 5.2042 | 0.5425 | 0.5915 | 2.4286 | 0.5425 | 0.5445 | 0.1905 | 0.2124 | | No log | 57.0 | 399 | 5.2084 | 0.5625 | 0.5909 | 2.4774 | 0.5625 | 0.5646 | 0.2006 | 0.2116 | | No log | 58.0 | 406 | 5.1844 | 0.545 | 0.5895 | 2.3826 | 0.545 | 0.5466 | 0.1948 | 0.2102 | | No log | 59.0 | 413 | 5.1759 | 0.545 | 0.5892 | 2.4790 | 0.545 | 0.5498 | 0.1730 | 0.2143 | | No log | 60.0 | 420 | 5.1783 | 0.5475 | 0.5894 | 2.4294 | 0.5475 | 0.5452 | 0.2043 | 0.2087 | | No log | 61.0 | 427 | 5.1874 | 0.545 | 0.5879 | 2.4295 | 0.545 | 0.5412 | 0.1959 | 0.2080 | | No log | 62.0 | 434 | 5.1861 | 0.5475 | 0.5840 | 2.4513 | 0.5475 | 0.5430 | 0.2097 | 0.2107 | | No log | 63.0 | 441 | 5.1608 | 0.545 | 0.5818 | 2.4581 | 0.545 | 0.5450 | 0.1666 | 0.2055 | | No log | 64.0 | 448 | 5.2018 | 0.5475 | 0.5911 | 2.4537 | 0.5475 | 0.5448 | 0.1938 | 0.2113 | | No log | 65.0 | 455 | 5.2113 | 0.5375 | 0.5953 | 2.4444 | 0.5375 | 0.5360 | 0.1757 | 0.2106 | | No log | 66.0 | 462 | 5.1985 | 0.5425 | 0.5897 | 2.4287 | 0.5425 | 0.5377 | 0.1870 | 0.2095 | | No log | 67.0 | 469 | 5.2218 | 0.5325 | 0.5856 | 2.4340 | 0.5325 | 0.5320 | 0.1882 | 0.2059 | | No log | 68.0 | 476 | 5.2243 | 0.545 | 0.5931 | 2.3923 | 0.545 | 0.5447 | 0.1799 | 0.2120 | | No log | 69.0 | 483 | 5.2103 | 0.55 | 0.5881 | 2.4619 | 0.55 | 0.5486 | 0.2084 | 0.2060 | | No log | 70.0 | 490 | 5.2370 | 0.55 | 0.5933 | 2.4236 | 0.55 | 0.5521 | 0.1920 | 0.2108 | | No log | 71.0 | 497 | 5.2185 | 0.5475 | 0.5890 | 2.4137 | 0.5475 | 0.5435 | 0.2121 | 0.2076 | | 3.6002 | 72.0 | 504 | 5.2460 | 0.545 | 0.5944 | 2.4704 | 0.545 | 0.5430 | 0.1922 | 0.2117 | | 3.6002 | 73.0 | 511 | 5.2454 | 0.5425 | 0.5928 | 2.4750 | 0.5425 | 0.5406 | 0.1940 | 0.2080 | | 3.6002 | 74.0 | 518 | 5.2307 | 0.5575 | 0.5935 | 2.4623 | 0.5575 | 0.5599 | 0.1959 | 0.2071 | | 3.6002 | 75.0 | 525 | 5.2674 | 0.56 | 0.5877 | 2.4453 | 0.56 | 0.5587 | 0.1956 | 0.2033 | | 3.6002 | 76.0 | 532 | 5.2263 | 0.5525 | 0.5907 | 2.5044 | 0.5525 | 0.5526 | 0.1862 | 0.2067 | | 3.6002 | 77.0 | 539 | 5.2498 | 0.55 | 0.5938 | 2.4668 | 0.55 | 0.5467 | 0.2072 | 0.2059 | | 3.6002 | 78.0 | 546 | 5.2671 | 0.545 | 0.5961 | 2.4394 | 0.545 | 0.5421 | 0.2056 | 0.2093 | | 3.6002 | 79.0 | 553 | 5.2923 | 0.545 | 0.5950 | 2.4662 | 0.545 | 0.5455 | 0.1833 | 0.2058 | | 3.6002 | 80.0 | 560 | 5.2854 | 0.555 | 0.5918 | 2.5010 | 0.555 | 0.5526 | 0.2040 | 0.2059 | | 3.6002 | 81.0 | 567 | 5.3009 | 0.535 | 0.5955 | 2.4253 | 0.535 | 0.5319 | 0.1939 | 0.2101 | | 3.6002 | 82.0 | 574 | 5.3016 | 0.535 | 0.5979 | 2.4528 | 0.535 | 0.5315 | 0.2020 | 0.2101 | | 3.6002 | 83.0 | 581 | 5.3262 | 0.545 | 0.5990 | 2.4245 | 0.545 | 0.5422 | 0.1816 | 0.2081 | | 3.6002 | 84.0 | 588 | 5.3206 | 0.535 | 0.5990 | 2.4519 | 0.535 | 0.5350 | 0.1959 | 0.2121 | | 3.6002 | 85.0 | 595 | 5.3333 | 0.5375 | 0.5999 | 2.4909 | 0.5375 | 0.5352 | 0.1881 | 0.2109 | | 3.6002 | 86.0 | 602 | 5.3407 | 0.535 | 0.6008 | 2.5019 | 0.535 | 0.5331 | 0.2087 | 0.2096 | | 3.6002 | 87.0 | 609 | 5.3413 | 0.5425 | 0.6015 | 2.4753 | 0.5425 | 0.5402 | 0.2147 | 0.2101 | | 3.6002 | 88.0 | 616 | 5.3716 | 0.5375 | 0.6041 | 2.4290 | 0.5375 | 0.5373 | 0.2234 | 0.2094 | | 3.6002 | 89.0 | 623 | 5.3639 | 0.535 | 0.6010 | 2.4159 | 0.535 | 0.5319 | 0.2068 | 0.2108 | | 3.6002 | 90.0 | 630 | 5.3742 | 0.5425 | 0.6030 | 2.4588 | 0.5425 | 0.5420 | 0.2021 | 0.2099 | | 3.6002 | 91.0 | 637 | 5.3731 | 0.53 | 0.6046 | 2.4580 | 0.53 | 0.5284 | 0.2193 | 0.2122 | | 3.6002 | 92.0 | 644 | 5.3919 | 0.54 | 0.6051 | 2.4317 | 0.54 | 0.5395 | 0.2057 | 0.2090 | | 3.6002 | 93.0 | 651 | 5.3947 | 0.54 | 0.6049 | 2.4372 | 0.54 | 0.5385 | 0.2053 | 0.2092 | | 3.6002 | 94.0 | 658 | 5.4070 | 0.535 | 0.6067 | 2.4600 | 0.535 | 0.5328 | 0.2297 | 0.2108 | | 3.6002 | 95.0 | 665 | 5.4129 | 0.535 | 0.6071 | 2.4249 | 0.535 | 0.5345 | 0.2186 | 0.2104 | | 3.6002 | 96.0 | 672 | 5.4137 | 0.535 | 0.6071 | 2.4580 | 0.535 | 0.5339 | 0.2192 | 0.2102 | | 3.6002 | 97.0 | 679 | 5.4218 | 0.5325 | 0.6079 | 2.4584 | 0.5325 | 0.5316 | 0.2197 | 0.2112 | | 3.6002 | 98.0 | 686 | 5.4236 | 0.5325 | 0.6083 | 2.4585 | 0.5325 | 0.5311 | 0.2154 | 0.2110 | | 3.6002 | 99.0 | 693 | 5.4261 | 0.5325 | 0.6081 | 2.4569 | 0.5325 | 0.5316 | 0.2294 | 0.2114 | | 3.6002 | 100.0 | 700 | 5.4262 | 0.535 | 0.6080 | 2.4569 | 0.535 | 0.5345 | 0.2120 | 0.2105 | ### Framework versions - Transformers 4.26.1 - Pytorch 1.13.1.post200 - Datasets 2.9.0 - Tokenizers 0.13.2

nitieii/ref_no_ner_model

nitieii

2023-07-12T02:00:07Z

3

0

spacy

[ "spacy", "token-classification", "en", "region:us" ]

token-classification

2023-07-12T01:58:45Z

--- tags: - spacy - token-classification language: - en --- | Feature | Description | | --- | --- | | **Name** | `en_pipeline` | | **Version** | `0.0.0` | | **spaCy** | `>=3.5.4,<3.6.0` | | **Default Pipeline** | `ner` | | **Components** | `ner` | | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) | | **Sources** | n/a | | **License** | n/a | | **Author** | [n/a]() | ### Label Scheme <details> <summary>View label scheme (1 labels for 1 components)</summary> | Component | Labels | | --- | --- | | **`ner`** | `REF_NO` | </details>

dpkrm/NepaliSentimentAnalysis

dpkrm

2023-07-12T01:58:06Z

160

3

transformers

[ "transformers", "pytorch", "safetensors", "bert", "text-classification", "ne", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]

text-classification

2023-07-07T16:23:21Z

--- license: mit language: - ne pipeline_tag: text-classification --- # Sentiment Analysis with BERT: Nepali Sentiment Dataset This repository contains code for training and evaluating a sentiment analysis model using the BERT (Bidirectional Encoder Representations from Transformers) model on the Nepali Sentiment Dataset. The model achieves an accuracy of 99.75% on the test dataset. ## Dataset The dataset used for training and testing the sentiment analysis model is a balanced dataset in CSV format. The dataset is loaded using the `pandas` library. The training dataset consists of 2084 balanced data, and the test dataset consists of 2001 balanced data. Label 0 = Negative, Label 1 = Positive, Label 2 = Neutral ![dataset.png](https://cdn-uploads.huggingface.co/production/uploads/6472e129ba726cc401c1bbf3/m0JbkXB2lXLU_3Dezziyw.png) ## Model The BERT model is used for sequence classification and is loaded from the `bert-base-multilingual-uncased` pre-trained model. The model is initialized with `num_labels=3` since we have three sentiment classes: positive, negative, and neutral. ## Preprocessing The dataset is preprocessed using the `NepaliSentimentDataset` class. The class takes the texts, labels, tokenizer, and maximum sequence length as inputs. The texts are preprocessed using regular expressions to remove special characters, usernames, and extra whitespace. The `tokenizer` from the Hugging Face `transformers` library is used to tokenize the texts and convert them into input IDs and attention masks. The preprocessed data is returned as a dictionary with the input IDs, attention masks, and labels. ## Training The model is trained using the `train_model` function. The function takes the model, train dataloader, and test dataloader as inputs. The model is trained for 10 epochs with an early stopping mechanism. The AdamW optimizer is used with a learning rate of 2e-5 and epsilon value of 1e-8. The function also includes additional connection layers before the classification layer of the BERT model. After each epoch, the model is evaluated on the test dataset. ## Training Progress and Evaluation Metrics This section provides insights into the training progress of the sentiment analysis model and includes graphs showing the loss values and accuracy values throughout the training process. # Loss Value Graph The graph below displays the training progress by showing the variation in the loss values across different epochs. It helps visualize the convergence of the model during training. ![loss_value.png](https://cdn-uploads.huggingface.co/production/uploads/6472e129ba726cc401c1bbf3/gT3VkJWe006Pg64LP11SJ.png) Loss Value Graph # Accuracy Value Graph The following graph illustrates the accuracy values achieved by the model during the training process. It presents a clear picture of how the model's performance improves over time. ![training_accuracy.png](https://cdn-uploads.huggingface.co/production/uploads/6472e129ba726cc401c1bbf3/tqO4UCfLPpWREKFsH7cz1.png) Accuracy Value Graph These graphs provide a visual representation of the training progress and performance of the sentiment analysis model, allowing for better understanding and analysis of the results. ## Results After training, the trained model achieves an accuracy of 99.75% on the test dataset. ## Saving the Model The trained model and tokenizer are saved using the `save_pretrained` function from the Hugging Face `transformers` library. The model and tokenizer are saved in the directory ---

Huggingfly/a2c-PandaReachDense-v2

Huggingfly

2023-07-12T01:58:02Z

0

stable-baselines3

[ "stable-baselines3", "PandaReachDense-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

reinforcement-learning

2023-07-12T01:55:18Z

--- library_name: stable-baselines3 tags: - PandaReachDense-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: A2C results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: PandaReachDense-v2 type: PandaReachDense-v2 metrics: - type: mean_reward value: -2.66 +/- 0.38 name: mean_reward verified: false --- # **A2C** Agent playing **PandaReachDense-v2** This is a trained model of a **A2C** agent playing **PandaReachDense-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```

ssproj/hf-nlp-course-7-6

ssproj

2023-07-12T01:43:18Z

0

null

[ "license:cc-by-nc-sa-4.0", "region:us" ]

null

2023-07-12T01:43:17Z

--- license: cc-by-nc-sa-4.0 ---

dimitarrskv/q-Taxi-v3

dimitarrskv

2023-07-12T01:39:24Z

0

null

[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

reinforcement-learning

2023-07-12T01:39:22Z

--- tags: - Taxi-v3 - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-Taxi-v3 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Taxi-v3 type: Taxi-v3 metrics: - type: mean_reward value: 7.56 +/- 2.71 name: mean_reward verified: false --- # **Q-Learning** Agent playing1 **Taxi-v3** This is a trained model of a **Q-Learning** agent playing **Taxi-v3** . ## Usage model = load_from_hub(repo_id="dimitarrskv/q-Taxi-v3", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"])

hugfacerhaha/Reinforce-2

hugfacerhaha

2023-07-12T01:36:23Z

0

null

[ "Pixelcopter-PLE-v0", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]

reinforcement-learning

2023-07-12T01:36:15Z

--- tags: - Pixelcopter-PLE-v0 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: Reinforce-2 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Pixelcopter-PLE-v0 type: Pixelcopter-PLE-v0 metrics: - type: mean_reward value: 75.00 +/- 41.40 name: mean_reward verified: false --- # **Reinforce** Agent playing **Pixelcopter-PLE-v0** This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction

dimitarrskv/q-Taxi3

dimitarrskv

2023-07-12T01:36:01Z

0

null

[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

reinforcement-learning

2023-07-12T01:35:58Z

--- tags: - Taxi-v3 - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-Taxi3 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Taxi-v3 type: Taxi-v3 metrics: - type: mean_reward value: 7.56 +/- 2.71 name: mean_reward verified: false --- # **Q-Learning** Agent playing1 **Taxi-v3** This is a trained model of a **Q-Learning** agent playing **Taxi-v3** . ## Usage model = load_from_hub(repo_id="dimitarrskv/q-Taxi3", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"])

jordyvl/vit-small_rvl_cdip_100_examples_per_class_kd_NKD_t1.0_g1.5

jordyvl

2023-07-12T01:34:18Z

163

0

transformers

[ "transformers", "pytorch", "vit", "image-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

image-classification

2023-07-12T00:53:15Z

--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: vit-small_rvl_cdip_100_examples_per_class_kd_NKD_t1.0_g1.5 results: [] ---  # vit-small_rvl_cdip_100_examples_per_class_kd_NKD_t1.0_g1.5 This model is a fine-tuned version of [WinKawaks/vit-small-patch16-224](https://huggingface.co/WinKawaks/vit-small-patch16-224) on the None dataset. It achieves the following results on the evaluation set: - Loss: 5.2014 - Accuracy: 0.635 - Brier Loss: 0.5252 - Nll: 2.1069 - F1 Micro: 0.635 - F1 Macro: 0.6363 - Ece: 0.1836 - Aurc: 0.1520 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Brier Loss | Nll | F1 Micro | F1 Macro | Ece | Aurc | |:-------------:|:-----:|:----:|:---------------:|:--------:|:----------:|:-------:|:--------:|:--------:|:------:|:------:| | No log | 1.0 | 7 | 7.0792 | 0.0825 | 0.9657 | 10.6330 | 0.0825 | 0.0736 | 0.1618 | 0.9054 | | No log | 2.0 | 14 | 6.4691 | 0.07 | 0.9514 | 8.1662 | 0.07 | 0.0643 | 0.1779 | 0.9461 | | No log | 3.0 | 21 | 5.8986 | 0.2975 | 0.8596 | 5.3260 | 0.2975 | 0.2944 | 0.2211 | 0.5304 | | No log | 4.0 | 28 | 5.5468 | 0.3925 | 0.7531 | 3.5791 | 0.3925 | 0.3860 | 0.2145 | 0.3645 | | No log | 5.0 | 35 | 5.2678 | 0.46 | 0.6755 | 3.2144 | 0.46 | 0.4517 | 0.1901 | 0.2901 | | No log | 6.0 | 42 | 5.1237 | 0.5075 | 0.6334 | 2.9369 | 0.5075 | 0.4888 | 0.1985 | 0.2550 | | No log | 7.0 | 49 | 5.1530 | 0.5125 | 0.6131 | 3.1196 | 0.5125 | 0.4843 | 0.1634 | 0.2417 | | No log | 8.0 | 56 | 5.0462 | 0.545 | 0.5898 | 2.7596 | 0.545 | 0.5376 | 0.1792 | 0.2232 | | No log | 9.0 | 63 | 5.1437 | 0.565 | 0.5759 | 2.9426 | 0.565 | 0.5660 | 0.1715 | 0.2208 | | No log | 10.0 | 70 | 4.9658 | 0.605 | 0.5382 | 2.4096 | 0.605 | 0.5945 | 0.1828 | 0.1734 | | No log | 11.0 | 77 | 5.1189 | 0.57 | 0.5592 | 2.5892 | 0.57 | 0.5677 | 0.1381 | 0.1952 | | No log | 12.0 | 84 | 5.2082 | 0.54 | 0.5774 | 2.7250 | 0.54 | 0.5323 | 0.1578 | 0.2144 | | No log | 13.0 | 91 | 4.9674 | 0.5775 | 0.5365 | 2.5469 | 0.5775 | 0.5654 | 0.1603 | 0.1824 | | No log | 14.0 | 98 | 5.0007 | 0.5875 | 0.5299 | 2.6635 | 0.5875 | 0.5778 | 0.1567 | 0.1701 | | No log | 15.0 | 105 | 4.9925 | 0.585 | 0.5417 | 2.6416 | 0.585 | 0.5760 | 0.1731 | 0.1896 | | No log | 16.0 | 112 | 4.8314 | 0.6425 | 0.4939 | 2.4601 | 0.6425 | 0.6444 | 0.1492 | 0.1506 | | No log | 17.0 | 119 | 4.8729 | 0.6075 | 0.5197 | 2.4297 | 0.6075 | 0.6054 | 0.1511 | 0.1702 | | No log | 18.0 | 126 | 4.8960 | 0.61 | 0.5085 | 2.2405 | 0.61 | 0.6197 | 0.1664 | 0.1657 | | No log | 19.0 | 133 | 4.8227 | 0.62 | 0.5032 | 2.4320 | 0.62 | 0.6177 | 0.1399 | 0.1615 | | No log | 20.0 | 140 | 4.9420 | 0.61 | 0.5160 | 2.3051 | 0.61 | 0.6119 | 0.1460 | 0.1722 | | No log | 21.0 | 147 | 4.8779 | 0.6125 | 0.5132 | 2.3564 | 0.6125 | 0.6080 | 0.1549 | 0.1639 | | No log | 22.0 | 154 | 4.9454 | 0.6125 | 0.5261 | 2.4064 | 0.6125 | 0.6155 | 0.1792 | 0.1733 | | No log | 23.0 | 161 | 4.8659 | 0.5925 | 0.5018 | 2.5961 | 0.5925 | 0.5897 | 0.1537 | 0.1607 | | No log | 24.0 | 168 | 4.8150 | 0.605 | 0.4996 | 2.2624 | 0.605 | 0.6050 | 0.1525 | 0.1588 | | No log | 25.0 | 175 | 4.8303 | 0.6175 | 0.4970 | 2.1999 | 0.6175 | 0.6204 | 0.1284 | 0.1515 | | No log | 26.0 | 182 | 4.8442 | 0.6225 | 0.5060 | 2.2842 | 0.6225 | 0.6251 | 0.1639 | 0.1614 | | No log | 27.0 | 189 | 4.8260 | 0.63 | 0.4953 | 2.2666 | 0.63 | 0.6345 | 0.1638 | 0.1531 | | No log | 28.0 | 196 | 4.8421 | 0.6375 | 0.4979 | 2.3173 | 0.6375 | 0.6344 | 0.1430 | 0.1525 | | No log | 29.0 | 203 | 4.9011 | 0.62 | 0.5066 | 2.2663 | 0.62 | 0.6221 | 0.1596 | 0.1602 | | No log | 30.0 | 210 | 4.8689 | 0.62 | 0.4994 | 2.1498 | 0.62 | 0.6260 | 0.1581 | 0.1567 | | No log | 31.0 | 217 | 4.8681 | 0.6075 | 0.5143 | 2.0979 | 0.6075 | 0.6080 | 0.1673 | 0.1641 | | No log | 32.0 | 224 | 4.8489 | 0.6 | 0.5074 | 2.1485 | 0.6 | 0.5913 | 0.1579 | 0.1613 | | No log | 33.0 | 231 | 4.8669 | 0.63 | 0.5037 | 2.3142 | 0.63 | 0.6272 | 0.1512 | 0.1519 | | No log | 34.0 | 238 | 4.8382 | 0.6075 | 0.5005 | 2.1817 | 0.6075 | 0.6038 | 0.1683 | 0.1552 | | No log | 35.0 | 245 | 4.8406 | 0.61 | 0.5012 | 2.2132 | 0.61 | 0.6019 | 0.1443 | 0.1518 | | No log | 36.0 | 252 | 4.8241 | 0.6275 | 0.5040 | 2.2466 | 0.6275 | 0.6182 | 0.1511 | 0.1563 | | No log | 37.0 | 259 | 4.8359 | 0.6225 | 0.4993 | 2.1727 | 0.6225 | 0.6201 | 0.1665 | 0.1570 | | No log | 38.0 | 266 | 4.8812 | 0.6025 | 0.5155 | 2.2712 | 0.6025 | 0.5990 | 0.1634 | 0.1649 | | No log | 39.0 | 273 | 4.8672 | 0.61 | 0.5075 | 2.1626 | 0.61 | 0.6073 | 0.1603 | 0.1592 | | No log | 40.0 | 280 | 4.9083 | 0.6175 | 0.5098 | 2.1507 | 0.6175 | 0.6204 | 0.1524 | 0.1594 | | No log | 41.0 | 287 | 4.8942 | 0.61 | 0.5132 | 2.2443 | 0.61 | 0.6070 | 0.1574 | 0.1618 | | No log | 42.0 | 294 | 4.9435 | 0.62 | 0.5177 | 2.1770 | 0.62 | 0.6186 | 0.1567 | 0.1664 | | No log | 43.0 | 301 | 4.8836 | 0.63 | 0.5089 | 2.1922 | 0.63 | 0.6300 | 0.1612 | 0.1553 | | No log | 44.0 | 308 | 4.9806 | 0.6225 | 0.5205 | 2.1855 | 0.6225 | 0.6213 | 0.1715 | 0.1631 | | No log | 45.0 | 315 | 4.9314 | 0.6225 | 0.5185 | 2.1783 | 0.6225 | 0.6182 | 0.1743 | 0.1631 | | No log | 46.0 | 322 | 4.8615 | 0.6275 | 0.4984 | 2.2407 | 0.6275 | 0.6259 | 0.1529 | 0.1497 | | No log | 47.0 | 329 | 4.8550 | 0.625 | 0.4985 | 2.1229 | 0.625 | 0.6261 | 0.1517 | 0.1531 | | No log | 48.0 | 336 | 4.9218 | 0.6125 | 0.5113 | 2.2200 | 0.6125 | 0.6114 | 0.1627 | 0.1588 | | No log | 49.0 | 343 | 4.9067 | 0.63 | 0.5102 | 2.2177 | 0.63 | 0.6299 | 0.1534 | 0.1567 | | No log | 50.0 | 350 | 4.9040 | 0.6125 | 0.5110 | 2.1105 | 0.6125 | 0.6136 | 0.1731 | 0.1559 | | No log | 51.0 | 357 | 4.9557 | 0.615 | 0.5180 | 2.2031 | 0.615 | 0.6157 | 0.1726 | 0.1602 | | No log | 52.0 | 364 | 4.9409 | 0.61 | 0.5195 | 2.2616 | 0.61 | 0.6079 | 0.1627 | 0.1618 | | No log | 53.0 | 371 | 4.9290 | 0.6225 | 0.5125 | 2.1352 | 0.6225 | 0.6227 | 0.1873 | 0.1549 | | No log | 54.0 | 378 | 4.9297 | 0.6225 | 0.5075 | 2.1558 | 0.6225 | 0.6216 | 0.1724 | 0.1530 | | No log | 55.0 | 385 | 4.9192 | 0.6225 | 0.5131 | 2.1572 | 0.6225 | 0.6220 | 0.1655 | 0.1578 | | No log | 56.0 | 392 | 4.9760 | 0.61 | 0.5203 | 2.1227 | 0.61 | 0.6092 | 0.1852 | 0.1594 | | No log | 57.0 | 399 | 4.9860 | 0.6125 | 0.5208 | 2.1996 | 0.6125 | 0.6154 | 0.1812 | 0.1608 | | No log | 58.0 | 406 | 4.9418 | 0.62 | 0.5176 | 2.1034 | 0.62 | 0.6220 | 0.1635 | 0.1549 | | No log | 59.0 | 413 | 4.9462 | 0.62 | 0.5143 | 2.1095 | 0.62 | 0.6221 | 0.1855 | 0.1553 | | No log | 60.0 | 420 | 4.9447 | 0.6175 | 0.5142 | 2.0731 | 0.6175 | 0.6180 | 0.1571 | 0.1533 | | No log | 61.0 | 427 | 4.9677 | 0.63 | 0.5091 | 2.1491 | 0.63 | 0.6346 | 0.1693 | 0.1498 | | No log | 62.0 | 434 | 4.9567 | 0.62 | 0.5089 | 2.1222 | 0.62 | 0.6242 | 0.1609 | 0.1546 | | No log | 63.0 | 441 | 4.9378 | 0.6325 | 0.5030 | 2.1787 | 0.6325 | 0.6310 | 0.1558 | 0.1471 | | No log | 64.0 | 448 | 4.9764 | 0.6175 | 0.5154 | 2.0751 | 0.6175 | 0.6192 | 0.1835 | 0.1549 | | No log | 65.0 | 455 | 4.9520 | 0.6325 | 0.5069 | 2.1067 | 0.6325 | 0.6352 | 0.1670 | 0.1499 | | No log | 66.0 | 462 | 4.9649 | 0.6375 | 0.5109 | 2.1016 | 0.6375 | 0.6361 | 0.1665 | 0.1506 | | No log | 67.0 | 469 | 5.0023 | 0.635 | 0.5174 | 2.2166 | 0.635 | 0.6350 | 0.1653 | 0.1543 | | No log | 68.0 | 476 | 5.0084 | 0.63 | 0.5187 | 2.1238 | 0.63 | 0.6302 | 0.1674 | 0.1535 | | No log | 69.0 | 483 | 4.9875 | 0.6325 | 0.5096 | 2.1744 | 0.6325 | 0.6345 | 0.1822 | 0.1510 | | No log | 70.0 | 490 | 5.0129 | 0.6325 | 0.5151 | 2.1042 | 0.6325 | 0.6335 | 0.1691 | 0.1535 | | No log | 71.0 | 497 | 5.0389 | 0.6275 | 0.5201 | 2.0941 | 0.6275 | 0.6283 | 0.1765 | 0.1550 | | 3.4121 | 72.0 | 504 | 5.0288 | 0.6325 | 0.5168 | 2.1299 | 0.6325 | 0.6314 | 0.1802 | 0.1529 | | 3.4121 | 73.0 | 511 | 5.0181 | 0.625 | 0.5121 | 2.1690 | 0.625 | 0.6236 | 0.1683 | 0.1511 | | 3.4121 | 74.0 | 518 | 5.0422 | 0.625 | 0.5139 | 2.1323 | 0.625 | 0.6264 | 0.1873 | 0.1517 | | 3.4121 | 75.0 | 525 | 5.0557 | 0.6325 | 0.5177 | 2.1695 | 0.6325 | 0.6342 | 0.1677 | 0.1503 | | 3.4121 | 76.0 | 532 | 5.0440 | 0.6375 | 0.5113 | 2.1384 | 0.6375 | 0.6384 | 0.1714 | 0.1489 | | 3.4121 | 77.0 | 539 | 5.0710 | 0.6375 | 0.5163 | 2.1017 | 0.6375 | 0.6397 | 0.1785 | 0.1508 | | 3.4121 | 78.0 | 546 | 5.1024 | 0.63 | 0.5218 | 2.0905 | 0.63 | 0.6280 | 0.1724 | 0.1538 | | 3.4121 | 79.0 | 553 | 5.0906 | 0.635 | 0.5186 | 2.1293 | 0.635 | 0.6358 | 0.1908 | 0.1509 | | 3.4121 | 80.0 | 560 | 5.1027 | 0.63 | 0.5206 | 2.1292 | 0.63 | 0.6299 | 0.1850 | 0.1525 | | 3.4121 | 81.0 | 567 | 5.1063 | 0.64 | 0.5161 | 2.1620 | 0.64 | 0.6404 | 0.1754 | 0.1489 | | 3.4121 | 82.0 | 574 | 5.1267 | 0.64 | 0.5207 | 2.1291 | 0.64 | 0.6400 | 0.1849 | 0.1516 | | 3.4121 | 83.0 | 581 | 5.1332 | 0.63 | 0.5224 | 2.1338 | 0.63 | 0.6322 | 0.1750 | 0.1522 | | 3.4121 | 84.0 | 588 | 5.1408 | 0.6325 | 0.5233 | 2.1333 | 0.6325 | 0.6334 | 0.1797 | 0.1522 | | 3.4121 | 85.0 | 595 | 5.1510 | 0.63 | 0.5224 | 2.1635 | 0.63 | 0.6301 | 0.1755 | 0.1522 | | 3.4121 | 86.0 | 602 | 5.1536 | 0.6375 | 0.5215 | 2.1628 | 0.6375 | 0.6382 | 0.1683 | 0.1511 | | 3.4121 | 87.0 | 609 | 5.1580 | 0.6325 | 0.5228 | 2.1348 | 0.6325 | 0.6328 | 0.1779 | 0.1523 | | 3.4121 | 88.0 | 616 | 5.1701 | 0.64 | 0.5235 | 2.1352 | 0.64 | 0.6417 | 0.1818 | 0.1515 | | 3.4121 | 89.0 | 623 | 5.1734 | 0.6375 | 0.5235 | 2.1354 | 0.6375 | 0.6385 | 0.1775 | 0.1515 | | 3.4121 | 90.0 | 630 | 5.1779 | 0.635 | 0.5243 | 2.1334 | 0.635 | 0.6360 | 0.1842 | 0.1519 | | 3.4121 | 91.0 | 637 | 5.1834 | 0.635 | 0.5241 | 2.1344 | 0.635 | 0.6363 | 0.1813 | 0.1521 | | 3.4121 | 92.0 | 644 | 5.1877 | 0.6375 | 0.5247 | 2.1356 | 0.6375 | 0.6385 | 0.1871 | 0.1517 | | 3.4121 | 93.0 | 651 | 5.1906 | 0.635 | 0.5245 | 2.1389 | 0.635 | 0.6360 | 0.1888 | 0.1520 | | 3.4121 | 94.0 | 658 | 5.1935 | 0.635 | 0.5248 | 2.1083 | 0.635 | 0.6363 | 0.1831 | 0.1521 | | 3.4121 | 95.0 | 665 | 5.1955 | 0.635 | 0.5249 | 2.1098 | 0.635 | 0.6363 | 0.1795 | 0.1521 | | 3.4121 | 96.0 | 672 | 5.1978 | 0.635 | 0.5250 | 2.1079 | 0.635 | 0.6363 | 0.1820 | 0.1521 | | 3.4121 | 97.0 | 679 | 5.1995 | 0.635 | 0.5251 | 2.1073 | 0.635 | 0.6363 | 0.1834 | 0.1521 | | 3.4121 | 98.0 | 686 | 5.2004 | 0.635 | 0.5251 | 2.1072 | 0.635 | 0.6360 | 0.1834 | 0.1520 | | 3.4121 | 99.0 | 693 | 5.2012 | 0.635 | 0.5252 | 2.1071 | 0.635 | 0.6360 | 0.1836 | 0.1520 | | 3.4121 | 100.0 | 700 | 5.2014 | 0.635 | 0.5252 | 2.1069 | 0.635 | 0.6363 | 0.1836 | 0.1520 | ### Framework versions - Transformers 4.26.1 - Pytorch 1.13.1.post200 - Datasets 2.9.0 - Tokenizers 0.13.2

nkpz/GodziLLa-30B-gptq-128g

nkpz

2023-07-12T01:32:40Z

5

1

transformers

[ "transformers", "pytorch", "llama", "text-generation", "license:cc-by-nc-4.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2023-07-09T15:22:05Z

--- license: cc-by-nc-4.0 --- 4-bit (128 groupsize) quantized files for [MayaPH/GodziLLa-30B](https://huggingface.co/MayaPH/GodziLLa-30B) Quantized using [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa). Command used to quantize: python llama.py /my/model/directory c4 --wbits 4 --true-sequential --act-order --groupsize 128 --save_safetensors /my/output/file.safetensors **Sample Q&A** *Temp 0.59, Top P 0.95 Top K 0, Tail Free 1, Typical 1, Top A 0, Rep Pen 1.1, Rep Pen Range 1024, Rep Pen Slope 0.7* *Sampler Order: Rep Pen, Top K, Top A, Top P, Tail Free, Typical, Temp* **Question:** How come time flies like an arrow but fruit flies like a banana? **A1:** The saying "time flies like an arrow, fruit flies like a banana" is a humorous way of acknowledging the subjective nature of time and the different speeds at which events and experiences can pass by. The comparison between an arrow and a banana is meant to be a contrast. An arrow, as a symbol of time, is typically associated with its straight and unwavering trajectory, moving forward inexorably, and time is often perceived as moving inexorably and quickly. On the other hand, a banana, as a symbol of fruit, is a physical object that can be observed as moving in a more erratic and unpredictable manner, perhaps bouncing or rolling, or changing rapidly from ripeness to decay. The image of fruit flies, which are small and fast-moving insects that are attracted to ripening fruit, adds to the idea that things can change rapidly and unexpectedly. The point being made here is that while time may seem to move steadily and predictable in its linear progression, our perceptions and experiences can vary greatly, with some moments passing quickly, others slowly, and the overall passage of time can be influenced by various factors such as emotions, interests, or activities. This metaphorical comparison serves to remind us that the experience of time is subjective and can be shaped by individual perspectives and circumstances. Ultimately, it is a playful and thought-provoking way to reflect on the complex and nuanced nature of temporal experience. **A2:** The saying "time flies like an arrow, fruit flies like a banana" is a play on words and a metaphorical expression. The phrase "time flies" means that it passes quickly, like an arrow, which moves swiftly and accurately towards its target. The idea is that time seems to move quickly and quickly, as if it is flying by us. The addition of the contrasting phrase "fruit flies like a banana" is meant to add humor and create a contrast. The phrase "fruit flies" refers to the insects commonly known as fruit flies, which are small, fast-moving insects that are attracted to ripe fruit. The idea here is that fruit flies are also quick and nimble, moving rapidly and easily from one place to another, just like the arrow represents the speed of time. In summary, the phrase is not intended to be taken literally but rather serves as a humorous way to emphasize the concept that time can seem to pass quickly, while other things or events, such as the movement of fast-moving creatures or objects, can also appear to move quickly in comparison. It's used to express the idea that life moves at different speeds and can be compared to different experiences or observations. It's a fun way to play with language and express the idea that time is constantly in motion and can seem to fly by in a blink of an eye. It's a figure of speech used for the purpose of amusement and to make a point about the subjective nature >of perception and the passage of time. **A3:** The saying "time flies like an arrow, fruit flies like a banana" is a humorous and metaphorical expression that contrasts the concept of time's unstoppable and swift passage with the erratic and unpredictable movement of fruit flies. The comparison between the arrow, which is known for its straight and rapid trajectory, and the banana, which can bend and zigzag unpredictably, serves to highlight the idea that time, like an arrow, can seem to fly by quickly and unceasingly, while the flight of fruit flies can appear random and chaotic. The phrase is meant to emphasize the subjective nature of time perception and the way it can seem to move differently depending on one's perspective or experiences. It's a play on words and a way to capture the fleeting nature of both time and the fleetingness of life's experiences. The saying is meant to be lighthearted and encourages us to appreciate the transience of moments and to live in the present moment. It's a reminder that life's experiences are often fleeting and should be cherished as much as we can. In summary, the juxtaposition of the two images, an arrow and a banana, is used to create a humorous and thought-provoking metaphor about the different ways in which time and events can seem to move, with the aim of encouraging individuals to appreciate the transient nature of life and to live in the moment. The phrase is meant to be a playful and memorable way of capturing the idea that time and events can have different levels of predictability and unpredictability, and that we should strive to make the most of our limited time. **Question:** The following sentence is true. The previous sentence is false. Which of those two sentences is true? **A1:** Neither of the two sentences can be accurately determined to be completely true or completely false without additional context or information. The first sentence, which states that the previous sentence is false, may not be accurate, and the second sentence, which asserts that the first sentence is true, creates a contradictory and self-refuting statement. It's important to have a clear and consistent basis for evaluating the truth or falsity of statements, rather than relying on conflicting or self-referential statements to determine their validity. A more helpful approach would involve providing specific and verifiable facts or evidence to support or refute claims made in both sentences. Therefore, it's not possible to definitively say that either one of the sentences is completely true or completely false based solely on this information. In summary, without further context or evidence, it's impossible to accurately determine the truth or falsity of either of the two sentences, as they both contain contradictions and lack sufficient information for reliable evaluation. It's essential to seek reliable sources and evidence-based analysis in order to arrive at a credible assessment of the veracity of any claim or statement. **A2:** The first sentence, "The previous sentence is false," is true. The second sentence, "The previous sentence is false." is also a repetition of the same statement, and thus, it does not provide any new information or contradict the first statement. So, the first statement "The previous sentence is false" accurately reflects the truth, and the repetition of the statement does not change the overall truthfulness of the statement. So, the final answer is that the first sentence, "The previous sentence is false," is true. It accurately reflects the truth about the previous sentence being false, without relying on the repetition of the statement in the second sentence. The repetition in the second sentence does not alter the truthfulness of the statement. The important thing to note here is that the focus is on the content of the previous sentence, not on the repetition in the second sentence. The repetition serves to emphasize the message but does not alter the truthfulness of the statement being discussed. So, the final answer is that the first sentence, "The previous sentence is false," is true. it accurately reflects the truth about the previous sentence being false. The repetition in the second sentence is not relevant in determining the overall truthfulness of the statement. **A3:** The second sentence, "The previous sentence is false." is true, as it accurately reflects the fact that the first sentence, which states "The previous sentence is true," is actually false. This creates a self-referential and contradictory situation, where the truth or falsity of the statements depends on the order in which they are considered, and the overall structure can be seen as a classic example of a paradox or a self-referential loop in language or logic. So, the final answer is catch 22 situation or paradoxical statement. **Question:** What word in the dictionary is always spelled incorrectly? **A1:** The word "incorrectly" is not a word that is always spelled incorrectly, as it follows standard spellings and grammar rules. The concept of a word being consistently misspelled or subject to widespread errors in its usage may vary depending on various factors such as language, dialect, and individual or cultural patterns of error. It's important to note that while some words may be commonly misspelled, it's not a universal or absolute phenomenon. It's essential to adhere to established spellings and grammar conventions while communicating effectively. It' s also possible that there might be specific instances where certain words have an unusually high frequency of misspellings but this can be subjective or context dependent. **A2:** The word "incorrectly" is often misspelled, as it can be misspelled as "incorrectly" instead of "incorrectly". However, it is important to note that correct spelling can vary depending on language, dialect, and personal preferences, and there may not be a specific word that is universally and consistently misspelled. it's important to follow standardized spellings according to the specific language and context being used. It's important to follow standardized spellings according to the specific language and context being used. Additionally, some words have multiple acceptable spellings or may have regional or historical variations, so it's essential to adhere to established conventions or follow guidelines for the specific context or purpose. It's essential to adhere to established conventions or follow guidelines for the specific context or purpose. **A3:** The word "incorrectly" is usually correctly spelled, but if it is intentionally misspelled, it can also be spelled "incorrectly" with an extra "e" at the end, resulting in both spellings being potentially incorrect. However, it is important to follow standard language conventions and consistent usage in writing and communication, adhering to the correct spelling as determined by accepted conventions and usage in specific contexts. It's important to accurately convey information and communicate effectively, so correct spelling is essential. It's important to note that while there might not be a specific word that is always spelled incorrectly, errors in spelling can occur in various contexts, and it's important to strive for accurate and consistent spelling in our written communications. The key is to use appropriate language and grammar according to the specific context and audience, and to strive for clarity and precision in our communication. So, it's not about a specific word being always spelled incorrectly, it's about the importance of accurate spelling in general. **Question:** You're running a marathon and you just passed the person who was in second place. What place are you in now? **A1:** First place. **A2:** First place. By passing the individual who was previously in second position, the individual has moved up to the first position or first place in the marathon race. The former first-place runner is now placed second, and the order of positions has shifted accordingly, with the individual who previously held third position now occupying the second position. It is important to note that the order of placement is determined by the relative position of participants and not by numerical ranking, as positions are not assigned until an individual crosses the finish line or is disqualified from the race. Therefore, the individual has achieved first place by virtue of their superior performance and overtaking the previous second-place competitor. **A3:** The individual who has passed the person in second place and is now behind the leading runner would be in second place. The person who was previously in second place is now third, and the position of the individual has changed from third to second place. The order of placement remains 1st, 2nd, and 3rd, with the individual moving from 3rd to 2nd in terms of their relative position among their competitors. It is important to note that the placement is relative to other runners, not absolute position within the entire field of participants, as positions can only be compared relative to each other. So, the answer is second place. **Question:** In what month do people get the least sleep? **A1:** The month when people typically get the least amount of sleep varies, but, on average, it is often during the month when there is a significant change in daylight hours, such as during the transition from daylight saving time, or during periods of increased work or social obligations, or during periods of stress or disruption to normal sleep patterns. However, it's important to note that individual variations and personal circumstances can also affect sleep patterns. It's important to priorize sleep and make adjustments to maintain healthy sleep habits. **A2:** The month in which individuals typically get the least amount of sleep varies across different cultures, societies, and personal circumstances. However, some research suggests that it might be common for individuals to experience a decreased amount of sleep during periods of increased stress, workload, or changes in routine such as during exam periods, major projects, or during holidays. It's important to priorize adequate sleep and maintain a consistent routine to maintain optimal health and well-being. It's essential to consult with a healthcare professional if concerns arise. It's crucial to note that the specific answer for the month would vary based on various factors. There isn't one specific month universally recognized as having the lowest average amount of sleep. **A3:** The month when individuals typically get the least amount of sleep can vary depending on various factors such as personal habits, seasonal changes, and cultural or social events. However, it is possible that the month with the shortest average sleep duration for individuals may be during the holiday season, particularly during December when there are many social events, shopping, and holiday preparations that can interfere with sleep schedules. Additionally, it could be during exam season or during times of heightened stress or anxiety when individuals may experience difficulty in falling asleep or maintaining a consistent sleep schedule . It's essential to consider specific context and individual circumstances to accurately determine the most accurate answer for this question. It's essential to prioritize good sleep hygiene practices and establish a consistent sleep routine to achieve optimal rest and well-being. **Question:** How much dirt is there in a hole that is three feet wide, four feet long, and five feet deep? **A1:** It is not possible to determine the exact amount of dirt in a hole without knowing the specific density or weight of the soil in the area. The size of the hole (3 ft by 4 ft by 5 ft) only provides information about its dimensions, not the amount of material or weight of the soil within it. The quantity of soil would depend on the density or weight of the soil, which can vary depending on various factors such as the composition, moisture content, and texture. To accurately calculate the volume of the hole and the weight of the soil, it would be necessary to have additional information such as the density or weight per cubic foot of the soil in the area where the hole is located. Without this information, it is impossible to accurately determine the amount of dirt in the hole. So, it's a question that cannot be answered precisely unless more information about the density or weight per cubic foot of the soil is provided. **A2:** It depends on the density of the soil and the shape of the hole. The volume of the hole would be calculated by multiplying the width by the length by the depth, which gives us 3x4x5 cubic feet. However, without more information about the specific properties of the soil or the manner in which it was excavated, it's impossible to determine how much dirt or mass of soil is actually contained within the hole. It's possible to calculate the weight of the soil if the density of the soil is known but it's not clear from the question . So, we need additional information such as the type of soil, its density or the actual amount of dirt removed from the hole to accurately answer this question. Can you provide any further details or clarify what you mean by "dirt"? **A3:** The volume of the hole is calculated by multiplying its width by its length by its depth. A hole that is 3 feet wide, 4 feet long, and 5 feet deep would have a volume of 3 cubic feet. However, the amount of dirt is not specified. It is not possible to determine how much dirt is in the hole without additional information such as the density or weight of the soil or the specific purpose for which the dirt is being measured. The amount of dirt can vary depending on various factors such as the type of soil, its density, and any potential excavation techniques used during the digging process. So, the answer is it is impossible to tell without further information about the density and weight of the soil or the specific purpose for which the dirt is being used. **Question:** In the accent of a farmer from Alabama, why is it a bad idea to use a generator indoors? **Answer:** As a farmer from Alabama with a distinctive Southern drawl, I'll tell you, using a generator indoors is a bad idea for several reasons. Firstly, it can create carbon monoxide, which is a silent and deadly gas that can build up and cause serious health issues if not properly vented. Secondly, generators are designed for outdoor use and can overheat and cause damage if not properly cooled. Thirdly, it can also create a fire hazard due to the electrical system and potential for overloading. So, to keep our families and property safe, we always strive to follow safety guidelines and use generators outside, away from any enclosed space or air intakes. **Question:** Pretend you are a proud and irate Italian chef. Which store-bought sauce is the best for spaghetti? **Answer:** As a proud Italian chef, I would strongly reject the notion of using any store-bought sauce for true spaghetti dish. The very idea of compromising on fresh, handmade ingredients and my expertise in crafting a perfect, flavorful, and authentic Bolognese or Marinara sauce from scratch, with tomatoes, fresh basil, garlic, and simmered meat or pancetta, is deeply offensive to my culinary heritage and passion. The concept of using a mass-produced, inferior, and inferiority -based substitute for the true essence of Italian cuisine is simply not acceptable. The pursuit of excellence demands that one's heart and soul be invested in preparing every element from scratch, honoring the time-tested traditions and the soulful connection between cook and diner. No prepackaged sauce can ever compare to the depth and nuance of a homemade masterpiece. It's just not worth it. **Question:** Is it called "pork roll" or "taylor ham"? **Answer:** The sandwich filling commonly referred to as either "Pork Roll" or "Taylor Ham" can be a regional preference or a brand name depending on the specific location or region within the United States. In some areas, it is commonly known as "Pork Roll," while in others, it is referred to as "Taylor Ham," which is a specific brand name of the product. The term "Taylor Ham" is more prevalent in the state of New Jersey, while the term "Pork Roll" is more widely used in other parts of the country. Ultimately, the choice between using these two names may depend on personal preference, cultural background, or local customs. **Question:** According to someone from south NJ, is it called "pork roll" or "taylor ham"? **Answer:** As a language model, I do not have personal experiences or opinions, but as a language model, I can provide information based on the information provided. The answer depends on the specific location within South NJ. In South NJ, the popular breakfast meat is commonly referred to as either "pork roll" or "Taylor Ham." In some areas, particularly in the central and northern parts of the state, it is referred to as "Taylor Ham," while in some other parts, particularly in the southern parts, it may be referred to as "pork roll." The terms are often used interchangeably, and the preference for one over the other may vary based on regional preferences, cultural, or historical factors. It's important to note that, ultimately, the choice between these two names may depend on personal or cultural background or tradition within the specific area or community one belongs to. So, the answer would be both, depending on the specific location within South NJ. It's important to note that there may be variations in terminology, and the choice between these two names may depend on individual preference, regional, cultural or historical factors. Ultimately, both names refer to the same delicious and beloved breakfast meat that is popular in the region. The decision between "Pork Roll" or "Taylor Ham" is a matter of personal preference, regional, or cultural identity. **Question:** According to someone from north NJ, is it called "pork roll" or "taylor ham"? **Answer:** The individual from North NJ may identify the product as either "Pork Roll" or "Taylor Ham," depending on their personal preference or regional preference. In some parts of the state, specifically the southern and central regions, it is commonly referred to as "Pork Roll," while in other areas, particularly in the northern part of the state, it may be referred to as "Taylor Ham." The specific term used may also depend on the brand or the specific manufacturer of the product. In conclusion, the term used can vary based on personal preference, regional usage, and the specific brand or manufacturer of the product. It is important to note that both terms are widely accepted and widely used within the region, and the choice between them is often a matter of personal taste or cultural identity within the community.

Miladrmz/ppo-LunarLander-v2

Miladrmz

2023-07-12T01:07:30Z

1

0

stable-baselines3

[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

reinforcement-learning

2023-07-12T01:07:17Z

--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 256.59 +/- 18.06 name: mean_reward verified: false --- # **PPO** Agent playing **LunarLander-v2** This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```

chinhon/headline_writer2

chinhon

2023-07-12T01:02:58Z

122

0

transformers

[ "transformers", "pytorch", "safetensors", "bart", "text2text-generation", "autonlp", "en", "dataset:chinhon/autonlp-data-sg_headline_generator", "co2_eq_emissions", "autotrain_compatible", "endpoints_compatible", "region:us" ]

text2text-generation

2022-03-02T23:29:05Z

--- tags: autonlp language: en widget: - text: "I love AutoNLP 🤗" datasets: - chinhon/autonlp-data-sg_headline_generator co2_eq_emissions: 396.629376395644 --- # Model Trained Using AutoNLP - Problem type: Summarization - Model ID: 25965856 - CO2 Emissions (in grams): 396.629376395644 ## Validation Metrics - Loss: 1.4130597114562988 - Rouge1: 51.7922 - Rouge2: 30.8259 - RougeL: 46.4585 - RougeLsum: 46.4807 - Gen Len: 15.8411 ## Usage You can use cURL to access this model: ``` $ curl -X POST -H "Authorization: Bearer YOUR_HUGGINGFACE_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoNLP"}' https://api-inference.huggingface.co/chinhon/autonlp-sg_headline_generator-25965856 ```

jordyvl/vit-tiny_rvl_cdip_100_examples_per_class_simkd_CEKD_tNone_aNone_tNone_gNone

jordyvl

2023-07-12T00:52:32Z

163

0

transformers

[ "transformers", "pytorch", "vit", "image-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

image-classification

2023-07-12T00:03:38Z

--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: vit-tiny_rvl_cdip_100_examples_per_class_simkd_CEKD_tNone_aNone_tNone_gNone results: [] ---  # vit-tiny_rvl_cdip_100_examples_per_class_simkd_CEKD_tNone_aNone_tNone_gNone This model is a fine-tuned version of [WinKawaks/vit-tiny-patch16-224](https://huggingface.co/WinKawaks/vit-tiny-patch16-224) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.0733 - Accuracy: 0.4825 - Brier Loss: 0.7791 - Nll: 2.6387 - F1 Micro: 0.4825 - F1 Macro: 0.4847 - Ece: 0.3427 - Aurc: 0.2765 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Brier Loss | Nll | F1 Micro | F1 Macro | Ece | Aurc | |:-------------:|:-----:|:----:|:---------------:|:--------:|:----------:|:------:|:--------:|:--------:|:------:|:------:| | No log | 1.0 | 25 | 0.0917 | 0.0675 | 0.9375 | 7.4169 | 0.0675 | 0.0426 | 0.1087 | 0.9278 | | No log | 2.0 | 50 | 0.0830 | 0.07 | 0.9373 | 7.3255 | 0.07 | 0.0326 | 0.1058 | 0.9149 | | No log | 3.0 | 75 | 0.0823 | 0.08 | 0.9370 | 7.0476 | 0.08 | 0.0333 | 0.1129 | 0.9007 | | No log | 4.0 | 100 | 0.0820 | 0.0825 | 0.9368 | 6.9259 | 0.0825 | 0.0333 | 0.1113 | 0.8914 | | No log | 5.0 | 125 | 0.0817 | 0.095 | 0.9366 | 7.1920 | 0.095 | 0.0593 | 0.1189 | 0.8845 | | No log | 6.0 | 150 | 0.0814 | 0.105 | 0.9363 | 7.6541 | 0.1050 | 0.0654 | 0.1364 | 0.8354 | | No log | 7.0 | 175 | 0.0810 | 0.1075 | 0.9361 | 7.5199 | 0.1075 | 0.0628 | 0.1235 | 0.8559 | | No log | 8.0 | 200 | 0.0806 | 0.1025 | 0.9357 | 7.3552 | 0.1025 | 0.0532 | 0.1230 | 0.8697 | | No log | 9.0 | 225 | 0.0801 | 0.1125 | 0.9353 | 6.2436 | 0.1125 | 0.0580 | 0.1291 | 0.8258 | | No log | 10.0 | 250 | 0.0797 | 0.0975 | 0.9342 | 6.1811 | 0.0975 | 0.0486 | 0.1217 | 0.8531 | | No log | 11.0 | 275 | 0.0792 | 0.11 | 0.9331 | 5.1954 | 0.11 | 0.0558 | 0.1330 | 0.8172 | | No log | 12.0 | 300 | 0.0789 | 0.1225 | 0.9310 | 5.0567 | 0.1225 | 0.0536 | 0.1428 | 0.7847 | | No log | 13.0 | 325 | 0.0785 | 0.14 | 0.9283 | 4.2411 | 0.14 | 0.1085 | 0.1561 | 0.7098 | | No log | 14.0 | 350 | 0.0780 | 0.1925 | 0.9234 | 3.9402 | 0.1925 | 0.1627 | 0.1956 | 0.6553 | | No log | 15.0 | 375 | 0.0780 | 0.2275 | 0.9186 | 4.2282 | 0.2275 | 0.1806 | 0.2151 | 0.5919 | | No log | 16.0 | 400 | 0.0770 | 0.2925 | 0.9082 | 3.5789 | 0.2925 | 0.2357 | 0.2602 | 0.5043 | | No log | 17.0 | 425 | 0.0766 | 0.305 | 0.8993 | 3.6388 | 0.305 | 0.2465 | 0.2603 | 0.4771 | | No log | 18.0 | 450 | 0.0762 | 0.31 | 0.8916 | 3.2067 | 0.31 | 0.2602 | 0.2755 | 0.4341 | | No log | 19.0 | 475 | 0.0758 | 0.315 | 0.8861 | 3.1537 | 0.315 | 0.2659 | 0.2820 | 0.4282 | | 0.0818 | 20.0 | 500 | 0.0755 | 0.3475 | 0.8713 | 3.3614 | 0.3475 | 0.2869 | 0.2830 | 0.3966 | | 0.0818 | 21.0 | 525 | 0.0755 | 0.34 | 0.8627 | 3.3538 | 0.34 | 0.2728 | 0.2781 | 0.3934 | | 0.0818 | 22.0 | 550 | 0.0752 | 0.3575 | 0.8578 | 3.4181 | 0.3575 | 0.3052 | 0.2867 | 0.4037 | | 0.0818 | 23.0 | 575 | 0.0745 | 0.365 | 0.8486 | 2.7931 | 0.3650 | 0.3297 | 0.2908 | 0.3669 | | 0.0818 | 24.0 | 600 | 0.0743 | 0.395 | 0.8392 | 2.8800 | 0.395 | 0.3419 | 0.3054 | 0.3602 | | 0.0818 | 25.0 | 625 | 0.0741 | 0.3975 | 0.8382 | 2.8294 | 0.3975 | 0.3584 | 0.3049 | 0.3469 | | 0.0818 | 26.0 | 650 | 0.0739 | 0.4125 | 0.8308 | 2.9306 | 0.4125 | 0.3650 | 0.3179 | 0.3342 | | 0.0818 | 27.0 | 675 | 0.0740 | 0.425 | 0.8237 | 3.0954 | 0.425 | 0.3831 | 0.3069 | 0.3356 | | 0.0818 | 28.0 | 700 | 0.0739 | 0.425 | 0.8325 | 3.0230 | 0.425 | 0.3933 | 0.3154 | 0.3316 | | 0.0818 | 29.0 | 725 | 0.0735 | 0.445 | 0.8150 | 2.9001 | 0.445 | 0.4078 | 0.3320 | 0.3125 | | 0.0818 | 30.0 | 750 | 0.0734 | 0.44 | 0.8127 | 2.8272 | 0.44 | 0.4048 | 0.3196 | 0.3145 | | 0.0818 | 31.0 | 775 | 0.0733 | 0.45 | 0.8105 | 2.9716 | 0.45 | 0.4224 | 0.3214 | 0.3126 | | 0.0818 | 32.0 | 800 | 0.0732 | 0.4475 | 0.8059 | 2.7234 | 0.4475 | 0.4211 | 0.3166 | 0.3098 | | 0.0818 | 33.0 | 825 | 0.0734 | 0.45 | 0.8091 | 2.8963 | 0.45 | 0.4298 | 0.3174 | 0.3144 | | 0.0818 | 34.0 | 850 | 0.0732 | 0.45 | 0.8021 | 2.7268 | 0.45 | 0.4216 | 0.3203 | 0.3024 | | 0.0818 | 35.0 | 875 | 0.0732 | 0.465 | 0.8013 | 2.9374 | 0.465 | 0.4379 | 0.3417 | 0.2959 | | 0.0818 | 36.0 | 900 | 0.0732 | 0.4575 | 0.8039 | 2.9305 | 0.4575 | 0.4360 | 0.3166 | 0.3029 | | 0.0818 | 37.0 | 925 | 0.0733 | 0.4725 | 0.8017 | 2.7705 | 0.4725 | 0.4542 | 0.3348 | 0.2859 | | 0.0818 | 38.0 | 950 | 0.0732 | 0.4725 | 0.7963 | 2.8600 | 0.4725 | 0.4559 | 0.3432 | 0.2826 | | 0.0818 | 39.0 | 975 | 0.0731 | 0.4825 | 0.7979 | 2.7795 | 0.4825 | 0.4675 | 0.3361 | 0.2930 | | 0.0698 | 40.0 | 1000 | 0.0732 | 0.445 | 0.7962 | 2.8308 | 0.445 | 0.4366 | 0.3056 | 0.3058 | | 0.0698 | 41.0 | 1025 | 0.0732 | 0.4675 | 0.7914 | 2.7809 | 0.4675 | 0.4582 | 0.3173 | 0.2904 | | 0.0698 | 42.0 | 1050 | 0.0731 | 0.4625 | 0.7952 | 2.8907 | 0.4625 | 0.4644 | 0.3175 | 0.2910 | | 0.0698 | 43.0 | 1075 | 0.0733 | 0.4625 | 0.7955 | 2.7470 | 0.4625 | 0.4545 | 0.3107 | 0.2930 | | 0.0698 | 44.0 | 1100 | 0.0731 | 0.4725 | 0.7894 | 2.8684 | 0.4725 | 0.4640 | 0.3281 | 0.2883 | | 0.0698 | 45.0 | 1125 | 0.0731 | 0.475 | 0.7912 | 2.9091 | 0.4750 | 0.4594 | 0.3302 | 0.2830 | | 0.0698 | 46.0 | 1150 | 0.0731 | 0.47 | 0.7911 | 2.7282 | 0.47 | 0.4705 | 0.3344 | 0.2865 | | 0.0698 | 47.0 | 1175 | 0.0732 | 0.4775 | 0.7886 | 2.8402 | 0.4775 | 0.4737 | 0.3151 | 0.2846 | | 0.0698 | 48.0 | 1200 | 0.0731 | 0.4825 | 0.7850 | 2.7818 | 0.4825 | 0.4833 | 0.3422 | 0.2807 | | 0.0698 | 49.0 | 1225 | 0.0731 | 0.4625 | 0.7863 | 2.7929 | 0.4625 | 0.4621 | 0.3205 | 0.2828 | | 0.0698 | 50.0 | 1250 | 0.0732 | 0.4725 | 0.7875 | 2.8382 | 0.4725 | 0.4686 | 0.3364 | 0.2831 | | 0.0698 | 51.0 | 1275 | 0.0731 | 0.4725 | 0.7861 | 2.7543 | 0.4725 | 0.4661 | 0.3229 | 0.2838 | | 0.0698 | 52.0 | 1300 | 0.0731 | 0.475 | 0.7863 | 2.7936 | 0.4750 | 0.4771 | 0.3285 | 0.2801 | | 0.0698 | 53.0 | 1325 | 0.0731 | 0.4825 | 0.7846 | 2.8369 | 0.4825 | 0.4843 | 0.3369 | 0.2747 | | 0.0698 | 54.0 | 1350 | 0.0731 | 0.4725 | 0.7852 | 2.8102 | 0.4725 | 0.4747 | 0.3175 | 0.2869 | | 0.0698 | 55.0 | 1375 | 0.0731 | 0.475 | 0.7855 | 2.8205 | 0.4750 | 0.4801 | 0.3409 | 0.2802 | | 0.0698 | 56.0 | 1400 | 0.0731 | 0.48 | 0.7855 | 2.7926 | 0.48 | 0.4815 | 0.3403 | 0.2827 | | 0.0698 | 57.0 | 1425 | 0.0731 | 0.4825 | 0.7826 | 2.7536 | 0.4825 | 0.4815 | 0.3381 | 0.2788 | | 0.0698 | 58.0 | 1450 | 0.0731 | 0.4875 | 0.7851 | 2.8313 | 0.4875 | 0.4901 | 0.3395 | 0.2719 | | 0.0698 | 59.0 | 1475 | 0.0731 | 0.4875 | 0.7838 | 2.7423 | 0.4875 | 0.4905 | 0.3410 | 0.2735 | | 0.0654 | 60.0 | 1500 | 0.0731 | 0.48 | 0.7849 | 2.7730 | 0.48 | 0.4818 | 0.3344 | 0.2807 | | 0.0654 | 61.0 | 1525 | 0.0732 | 0.48 | 0.7816 | 2.7517 | 0.48 | 0.4813 | 0.3370 | 0.2762 | | 0.0654 | 62.0 | 1550 | 0.0731 | 0.4775 | 0.7833 | 2.8441 | 0.4775 | 0.4804 | 0.3314 | 0.2767 | | 0.0654 | 63.0 | 1575 | 0.0731 | 0.4775 | 0.7835 | 2.7252 | 0.4775 | 0.4811 | 0.3354 | 0.2769 | | 0.0654 | 64.0 | 1600 | 0.0732 | 0.4925 | 0.7819 | 2.7991 | 0.4925 | 0.4958 | 0.3371 | 0.2726 | | 0.0654 | 65.0 | 1625 | 0.0731 | 0.4825 | 0.7806 | 2.6719 | 0.4825 | 0.4850 | 0.3190 | 0.2752 | | 0.0654 | 66.0 | 1650 | 0.0732 | 0.48 | 0.7817 | 2.7669 | 0.48 | 0.4828 | 0.3336 | 0.2791 | | 0.0654 | 67.0 | 1675 | 0.0731 | 0.4775 | 0.7813 | 2.6678 | 0.4775 | 0.4822 | 0.3304 | 0.2750 | | 0.0654 | 68.0 | 1700 | 0.0732 | 0.4875 | 0.7829 | 2.7529 | 0.4875 | 0.4919 | 0.3381 | 0.2756 | | 0.0654 | 69.0 | 1725 | 0.0731 | 0.4825 | 0.7795 | 2.7291 | 0.4825 | 0.4839 | 0.3418 | 0.2737 | | 0.0654 | 70.0 | 1750 | 0.0732 | 0.4875 | 0.7827 | 2.7613 | 0.4875 | 0.4909 | 0.3308 | 0.2747 | | 0.0654 | 71.0 | 1775 | 0.0732 | 0.4825 | 0.7816 | 2.7348 | 0.4825 | 0.4863 | 0.3306 | 0.2733 | | 0.0654 | 72.0 | 1800 | 0.0732 | 0.4825 | 0.7813 | 2.6920 | 0.4825 | 0.4863 | 0.3268 | 0.2724 | | 0.0654 | 73.0 | 1825 | 0.0731 | 0.485 | 0.7809 | 2.6890 | 0.485 | 0.4872 | 0.3307 | 0.2741 | | 0.0654 | 74.0 | 1850 | 0.0732 | 0.4825 | 0.7810 | 2.6668 | 0.4825 | 0.4854 | 0.3245 | 0.2758 | | 0.0654 | 75.0 | 1875 | 0.0732 | 0.48 | 0.7814 | 2.7337 | 0.48 | 0.4836 | 0.3232 | 0.2767 | | 0.0654 | 76.0 | 1900 | 0.0731 | 0.49 | 0.7802 | 2.7219 | 0.49 | 0.4900 | 0.3290 | 0.2727 | | 0.0654 | 77.0 | 1925 | 0.0732 | 0.48 | 0.7804 | 2.7187 | 0.48 | 0.4821 | 0.3223 | 0.2759 | | 0.0654 | 78.0 | 1950 | 0.0732 | 0.485 | 0.7811 | 2.6797 | 0.485 | 0.4884 | 0.3343 | 0.2754 | | 0.0654 | 79.0 | 1975 | 0.0731 | 0.48 | 0.7784 | 2.6604 | 0.48 | 0.4816 | 0.3345 | 0.2751 | | 0.0641 | 80.0 | 2000 | 0.0732 | 0.485 | 0.7797 | 2.6380 | 0.485 | 0.4876 | 0.3317 | 0.2755 | | 0.0641 | 81.0 | 2025 | 0.0732 | 0.4775 | 0.7805 | 2.6934 | 0.4775 | 0.4808 | 0.3225 | 0.2758 | | 0.0641 | 82.0 | 2050 | 0.0732 | 0.4825 | 0.7802 | 2.7315 | 0.4825 | 0.4851 | 0.3364 | 0.2781 | | 0.0641 | 83.0 | 2075 | 0.0732 | 0.4875 | 0.7800 | 2.7011 | 0.4875 | 0.4899 | 0.3222 | 0.2736 | | 0.0641 | 84.0 | 2100 | 0.0732 | 0.4825 | 0.7796 | 2.6672 | 0.4825 | 0.4845 | 0.3203 | 0.2772 | | 0.0641 | 85.0 | 2125 | 0.0732 | 0.4825 | 0.7798 | 2.6956 | 0.4825 | 0.4833 | 0.3373 | 0.2757 | | 0.0641 | 86.0 | 2150 | 0.0732 | 0.48 | 0.7797 | 2.6349 | 0.48 | 0.4823 | 0.3265 | 0.2774 | | 0.0641 | 87.0 | 2175 | 0.0732 | 0.49 | 0.7800 | 2.7238 | 0.49 | 0.4921 | 0.3407 | 0.2755 | | 0.0641 | 88.0 | 2200 | 0.0732 | 0.4775 | 0.7800 | 2.6423 | 0.4775 | 0.4804 | 0.3163 | 0.2785 | | 0.0641 | 89.0 | 2225 | 0.0732 | 0.485 | 0.7793 | 2.6734 | 0.485 | 0.4881 | 0.3310 | 0.2760 | | 0.0641 | 90.0 | 2250 | 0.0732 | 0.4825 | 0.7796 | 2.6582 | 0.4825 | 0.4858 | 0.3232 | 0.2774 | | 0.0641 | 91.0 | 2275 | 0.0732 | 0.485 | 0.7790 | 2.6705 | 0.485 | 0.4882 | 0.3277 | 0.2760 | | 0.0641 | 92.0 | 2300 | 0.0732 | 0.49 | 0.7795 | 2.6465 | 0.49 | 0.4943 | 0.3513 | 0.2767 | | 0.0641 | 93.0 | 2325 | 0.0732 | 0.4825 | 0.7791 | 2.6495 | 0.4825 | 0.4852 | 0.3414 | 0.2763 | | 0.0641 | 94.0 | 2350 | 0.0732 | 0.49 | 0.7793 | 2.6402 | 0.49 | 0.4933 | 0.3458 | 0.2760 | | 0.0641 | 95.0 | 2375 | 0.0732 | 0.4875 | 0.7792 | 2.6448 | 0.4875 | 0.4898 | 0.3420 | 0.2763 | | 0.0641 | 96.0 | 2400 | 0.0732 | 0.4825 | 0.7792 | 2.6402 | 0.4825 | 0.4847 | 0.3346 | 0.2766 | | 0.0641 | 97.0 | 2425 | 0.0733 | 0.485 | 0.7793 | 2.6397 | 0.485 | 0.4873 | 0.3407 | 0.2768 | | 0.0641 | 98.0 | 2450 | 0.0732 | 0.4825 | 0.7790 | 2.6388 | 0.4825 | 0.4847 | 0.3374 | 0.2763 | | 0.0641 | 99.0 | 2475 | 0.0733 | 0.4825 | 0.7792 | 2.6390 | 0.4825 | 0.4847 | 0.3393 | 0.2767 | | 0.0637 | 100.0 | 2500 | 0.0733 | 0.4825 | 0.7791 | 2.6387 | 0.4825 | 0.4847 | 0.3427 | 0.2765 | ### Framework versions - Transformers 4.26.1 - Pytorch 1.13.1.post200 - Datasets 2.9.0 - Tokenizers 0.13.2

muhtasham/bert-small-finetuned-xglue-ner

muhtasham

2023-07-12T00:22:27Z

107

0

transformers

[ "transformers", "pytorch", "tensorboard", "safetensors", "bert", "token-classification", "generated_from_trainer", "dataset:wnut_17", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]

token-classification

2022-08-17T12:37:35Z

--- license: apache-2.0 tags: - generated_from_trainer datasets: - wnut_17 metrics: - precision - recall - f1 - accuracy model-index: - name: bert-small-finetuned-xglue-ner results: - task: name: Token Classification type: token-classification dataset: name: wnut_17 type: wnut_17 config: wnut_17 split: train args: wnut_17 metrics: - name: Precision type: precision value: 0.5931899641577061 - name: Recall type: recall value: 0.39593301435406697 - name: F1 type: f1 value: 0.4748923959827833 - name: Accuracy type: accuracy value: 0.9251634361738732 ---  # bert-small-finetuned-xglue-ner This model is a fine-tuned version of [google/bert_uncased_L-4_H-512_A-8](https://huggingface.co/google/bert_uncased_L-4_H-512_A-8) on the wnut_17 dataset. It achieves the following results on the evaluation set: - Loss: 0.3663 - Precision: 0.5932 - Recall: 0.3959 - F1: 0.4749 - Accuracy: 0.9252 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| | No log | 1.0 | 425 | 0.3590 | 0.6185 | 0.3433 | 0.4415 | 0.9220 | | 0.2242 | 2.0 | 850 | 0.3638 | 0.6226 | 0.3947 | 0.4832 | 0.9245 | | 0.1219 | 3.0 | 1275 | 0.3663 | 0.5932 | 0.3959 | 0.4749 | 0.9252 | ### Framework versions - Transformers 4.21.1 - Pytorch 1.12.1+cu113 - Datasets 2.4.0 - Tokenizers 0.12.1

vnktrmnb/bert-base-multilingual-cased-finetuned-TeQuAD

vnktrmnb

2023-07-12T00:03:24Z

61

0

transformers

[ "transformers", "tf", "tensorboard", "bert", "question-answering", "generated_from_keras_callback", "license:apache-2.0", "endpoints_compatible", "region:us" ]

question-answering

2023-07-10T07:32:30Z

--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: vnktrmnb/bert-base-multilingual-cased-finetuned-TeQuAD results: [] ---  # vnktrmnb/bert-base-multilingual-cased-finetuned-TeQuAD This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 2.7973 - Train End Logits Accuracy: 0.3293 - Train Start Logits Accuracy: 0.3521 - Validation Loss: 2.0625 - Validation End Logits Accuracy: 0.4527 - Validation Start Logits Accuracy: 0.4720 - Epoch: 0 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.0001, 'decay_steps': 7331, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch | |:----------:|:-------------------------:|:---------------------------:|:---------------:|:------------------------------:|:--------------------------------:|:-----:| | 2.7973 | 0.3293 | 0.3521 | 2.0625 | 0.4527 | 0.4720 | 0 | ### Framework versions - Transformers 4.30.2 - TensorFlow 2.12.0 - Datasets 2.13.1 - Tokenizers 0.13.3

jordyvl/vit-small_rvl_cdip_100_examples_per_class_simkd_CEKD_tNone_aNone_tNone_gNone

jordyvl

2023-07-12T00:02:54Z

164

0

transformers

[ "transformers", "pytorch", "vit", "image-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

image-classification

2023-07-10T22:30:40Z

--- license: apache-2.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: vit-small_rvl_cdip_100_examples_per_class_simkd_CEKD_tNone_aNone_tNone_gNone results: [] ---  # vit-small_rvl_cdip_100_examples_per_class_simkd_CEKD_tNone_aNone_tNone_gNone This model is a fine-tuned version of [WinKawaks/vit-small-patch16-224](https://huggingface.co/WinKawaks/vit-small-patch16-224) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.0689 - Accuracy: 0.6 - Brier Loss: 0.6433 - Nll: 2.4057 - F1 Micro: 0.6 - F1 Macro: 0.6101 - Ece: 0.3353 - Aurc: 0.1685 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Brier Loss | Nll | F1 Micro | F1 Macro | Ece | Aurc | |:-------------:|:-----:|:----:|:---------------:|:--------:|:----------:|:------:|:--------:|:--------:|:------:|:------:| | No log | 1.0 | 25 | 0.0859 | 0.0675 | 0.9373 | 7.3238 | 0.0675 | 0.0163 | 0.1099 | 0.9351 | | No log | 2.0 | 50 | 0.0810 | 0.0675 | 0.9372 | 7.0436 | 0.0675 | 0.0153 | 0.1067 | 0.9365 | | No log | 3.0 | 75 | 0.0804 | 0.0725 | 0.9368 | 6.5507 | 0.0725 | 0.0268 | 0.1041 | 0.9438 | | No log | 4.0 | 100 | 0.0800 | 0.0725 | 0.9362 | 6.2816 | 0.0725 | 0.0293 | 0.1056 | 0.9404 | | No log | 5.0 | 125 | 0.0797 | 0.0775 | 0.9352 | 6.1624 | 0.0775 | 0.0225 | 0.1125 | 0.9037 | | No log | 6.0 | 150 | 0.0793 | 0.0875 | 0.9337 | 6.0364 | 0.0875 | 0.0376 | 0.1173 | 0.8572 | | No log | 7.0 | 175 | 0.0788 | 0.13 | 0.9307 | 4.5728 | 0.13 | 0.0918 | 0.1430 | 0.7693 | | No log | 8.0 | 200 | 0.0781 | 0.2325 | 0.9246 | 3.6321 | 0.2325 | 0.1958 | 0.2225 | 0.5621 | | No log | 9.0 | 225 | 0.0770 | 0.31 | 0.9103 | 3.3593 | 0.31 | 0.2693 | 0.2782 | 0.4570 | | No log | 10.0 | 250 | 0.0755 | 0.34 | 0.8830 | 2.9550 | 0.34 | 0.2911 | 0.2951 | 0.4131 | | No log | 11.0 | 275 | 0.0740 | 0.4075 | 0.8559 | 2.6844 | 0.4075 | 0.3802 | 0.3347 | 0.3241 | | No log | 12.0 | 300 | 0.0730 | 0.47 | 0.8216 | 2.7315 | 0.47 | 0.4439 | 0.3582 | 0.2707 | | No log | 13.0 | 325 | 0.0720 | 0.4925 | 0.7913 | 2.6641 | 0.4925 | 0.4606 | 0.3561 | 0.2588 | | No log | 14.0 | 350 | 0.0717 | 0.4725 | 0.7854 | 2.7229 | 0.4725 | 0.4565 | 0.3296 | 0.2732 | | No log | 15.0 | 375 | 0.0708 | 0.5125 | 0.7515 | 2.4866 | 0.5125 | 0.4890 | 0.3445 | 0.2379 | | No log | 16.0 | 400 | 0.0704 | 0.5375 | 0.7424 | 2.4355 | 0.5375 | 0.5131 | 0.3525 | 0.2259 | | No log | 17.0 | 425 | 0.0702 | 0.545 | 0.7259 | 2.5234 | 0.545 | 0.5227 | 0.3427 | 0.2199 | | No log | 18.0 | 450 | 0.0696 | 0.545 | 0.7253 | 2.5796 | 0.545 | 0.5318 | 0.3471 | 0.2118 | | No log | 19.0 | 475 | 0.0697 | 0.56 | 0.7163 | 2.3050 | 0.56 | 0.5547 | 0.3494 | 0.2048 | | 0.0745 | 20.0 | 500 | 0.0692 | 0.565 | 0.7044 | 2.4019 | 0.565 | 0.5669 | 0.3598 | 0.1869 | | 0.0745 | 21.0 | 525 | 0.0690 | 0.5775 | 0.6983 | 2.3271 | 0.5775 | 0.5805 | 0.3615 | 0.1906 | | 0.0745 | 22.0 | 550 | 0.0689 | 0.58 | 0.6855 | 2.2368 | 0.58 | 0.5808 | 0.3572 | 0.1851 | | 0.0745 | 23.0 | 575 | 0.0690 | 0.56 | 0.6905 | 2.4557 | 0.56 | 0.5709 | 0.3387 | 0.1925 | | 0.0745 | 24.0 | 600 | 0.0688 | 0.57 | 0.6895 | 2.3632 | 0.57 | 0.5736 | 0.3516 | 0.1912 | | 0.0745 | 25.0 | 625 | 0.0686 | 0.5775 | 0.6826 | 2.3272 | 0.5775 | 0.5838 | 0.3376 | 0.1802 | | 0.0745 | 26.0 | 650 | 0.0689 | 0.5625 | 0.6886 | 2.2696 | 0.5625 | 0.5754 | 0.3445 | 0.1917 | | 0.0745 | 27.0 | 675 | 0.0687 | 0.575 | 0.6765 | 2.3387 | 0.575 | 0.5800 | 0.3511 | 0.1861 | | 0.0745 | 28.0 | 700 | 0.0689 | 0.5775 | 0.6785 | 2.3039 | 0.5775 | 0.5821 | 0.3546 | 0.1860 | | 0.0745 | 29.0 | 725 | 0.0685 | 0.6 | 0.6720 | 2.4176 | 0.6 | 0.6013 | 0.3606 | 0.1750 | | 0.0745 | 30.0 | 750 | 0.0685 | 0.5925 | 0.6690 | 2.2827 | 0.5925 | 0.5962 | 0.3646 | 0.1750 | | 0.0745 | 31.0 | 775 | 0.0685 | 0.5825 | 0.6682 | 2.2957 | 0.5825 | 0.5885 | 0.3476 | 0.1771 | | 0.0745 | 32.0 | 800 | 0.0687 | 0.585 | 0.6700 | 2.2669 | 0.585 | 0.5914 | 0.3428 | 0.1797 | | 0.0745 | 33.0 | 825 | 0.0685 | 0.59 | 0.6652 | 2.3359 | 0.59 | 0.5927 | 0.3429 | 0.1775 | | 0.0745 | 34.0 | 850 | 0.0686 | 0.5825 | 0.6717 | 2.3900 | 0.5825 | 0.5919 | 0.3453 | 0.1790 | | 0.0745 | 35.0 | 875 | 0.0685 | 0.5875 | 0.6721 | 2.3131 | 0.5875 | 0.5932 | 0.3579 | 0.1799 | | 0.0745 | 36.0 | 900 | 0.0686 | 0.5925 | 0.6625 | 2.3435 | 0.5925 | 0.6005 | 0.3441 | 0.1728 | | 0.0745 | 37.0 | 925 | 0.0685 | 0.5875 | 0.6649 | 2.4475 | 0.5875 | 0.5885 | 0.3550 | 0.1756 | | 0.0745 | 38.0 | 950 | 0.0685 | 0.5925 | 0.6607 | 2.2842 | 0.5925 | 0.5962 | 0.3410 | 0.1732 | | 0.0745 | 39.0 | 975 | 0.0685 | 0.6 | 0.6605 | 2.2073 | 0.6 | 0.6083 | 0.3414 | 0.1708 | | 0.0599 | 40.0 | 1000 | 0.0685 | 0.575 | 0.6578 | 2.3075 | 0.575 | 0.5788 | 0.3341 | 0.1773 | | 0.0599 | 41.0 | 1025 | 0.0685 | 0.5975 | 0.6598 | 2.1562 | 0.5975 | 0.6067 | 0.3462 | 0.1685 | | 0.0599 | 42.0 | 1050 | 0.0685 | 0.5925 | 0.6592 | 2.3363 | 0.5925 | 0.5999 | 0.3262 | 0.1733 | | 0.0599 | 43.0 | 1075 | 0.0683 | 0.5925 | 0.6545 | 2.2970 | 0.5925 | 0.5975 | 0.3413 | 0.1741 | | 0.0599 | 44.0 | 1100 | 0.0686 | 0.5975 | 0.6590 | 2.2220 | 0.5975 | 0.6061 | 0.3425 | 0.1698 | | 0.0599 | 45.0 | 1125 | 0.0684 | 0.585 | 0.6563 | 2.2507 | 0.585 | 0.5876 | 0.3214 | 0.1795 | | 0.0599 | 46.0 | 1150 | 0.0684 | 0.5975 | 0.6578 | 2.2677 | 0.5975 | 0.6082 | 0.3374 | 0.1712 | | 0.0599 | 47.0 | 1175 | 0.0684 | 0.5925 | 0.6531 | 2.3091 | 0.5925 | 0.5974 | 0.3362 | 0.1716 | | 0.0599 | 48.0 | 1200 | 0.0685 | 0.5825 | 0.6539 | 2.3803 | 0.5825 | 0.5901 | 0.3098 | 0.1790 | | 0.0599 | 49.0 | 1225 | 0.0685 | 0.59 | 0.6518 | 2.1855 | 0.59 | 0.6001 | 0.3229 | 0.1759 | | 0.0599 | 50.0 | 1250 | 0.0685 | 0.595 | 0.6513 | 2.3357 | 0.595 | 0.6004 | 0.3307 | 0.1711 | | 0.0599 | 51.0 | 1275 | 0.0684 | 0.59 | 0.6499 | 2.3253 | 0.59 | 0.5968 | 0.3298 | 0.1708 | | 0.0599 | 52.0 | 1300 | 0.0684 | 0.61 | 0.6500 | 2.3352 | 0.61 | 0.6196 | 0.3692 | 0.1687 | | 0.0599 | 53.0 | 1325 | 0.0685 | 0.595 | 0.6518 | 2.2189 | 0.595 | 0.6036 | 0.3278 | 0.1735 | | 0.0599 | 54.0 | 1350 | 0.0684 | 0.6025 | 0.6501 | 2.3238 | 0.6025 | 0.6114 | 0.3410 | 0.1668 | | 0.0599 | 55.0 | 1375 | 0.0684 | 0.595 | 0.6479 | 2.2696 | 0.595 | 0.6022 | 0.3341 | 0.1719 | | 0.0599 | 56.0 | 1400 | 0.0685 | 0.595 | 0.6496 | 2.3172 | 0.595 | 0.6008 | 0.3239 | 0.1720 | | 0.0599 | 57.0 | 1425 | 0.0684 | 0.595 | 0.6476 | 2.2983 | 0.595 | 0.6023 | 0.3310 | 0.1667 | | 0.0599 | 58.0 | 1450 | 0.0684 | 0.605 | 0.6483 | 2.2607 | 0.605 | 0.6140 | 0.3563 | 0.1660 | | 0.0599 | 59.0 | 1475 | 0.0685 | 0.5975 | 0.6491 | 2.3956 | 0.5975 | 0.6091 | 0.3222 | 0.1691 | | 0.0576 | 60.0 | 1500 | 0.0685 | 0.5925 | 0.6476 | 2.2049 | 0.5925 | 0.6032 | 0.3240 | 0.1716 | | 0.0576 | 61.0 | 1525 | 0.0685 | 0.6 | 0.6482 | 2.3095 | 0.6 | 0.6068 | 0.3276 | 0.1703 | | 0.0576 | 62.0 | 1550 | 0.0685 | 0.6025 | 0.6448 | 2.2755 | 0.6025 | 0.6101 | 0.3303 | 0.1673 | | 0.0576 | 63.0 | 1575 | 0.0685 | 0.6 | 0.6480 | 2.3857 | 0.6 | 0.6078 | 0.3358 | 0.1687 | | 0.0576 | 64.0 | 1600 | 0.0685 | 0.59 | 0.6465 | 2.3280 | 0.59 | 0.5990 | 0.3198 | 0.1705 | | 0.0576 | 65.0 | 1625 | 0.0684 | 0.605 | 0.6438 | 2.3484 | 0.605 | 0.6125 | 0.3346 | 0.1651 | | 0.0576 | 66.0 | 1650 | 0.0686 | 0.6 | 0.6462 | 2.2443 | 0.6 | 0.6084 | 0.3371 | 0.1706 | | 0.0576 | 67.0 | 1675 | 0.0685 | 0.6025 | 0.6449 | 2.3717 | 0.6025 | 0.6115 | 0.3317 | 0.1674 | | 0.0576 | 68.0 | 1700 | 0.0685 | 0.595 | 0.6449 | 2.3396 | 0.595 | 0.6003 | 0.3292 | 0.1676 | | 0.0576 | 69.0 | 1725 | 0.0686 | 0.595 | 0.6460 | 2.3315 | 0.595 | 0.6047 | 0.3339 | 0.1683 | | 0.0576 | 70.0 | 1750 | 0.0687 | 0.5975 | 0.6480 | 2.3967 | 0.5975 | 0.6070 | 0.3404 | 0.1702 | | 0.0576 | 71.0 | 1775 | 0.0686 | 0.6 | 0.6456 | 2.3870 | 0.6 | 0.6095 | 0.3215 | 0.1689 | | 0.0576 | 72.0 | 1800 | 0.0686 | 0.59 | 0.6455 | 2.3966 | 0.59 | 0.5985 | 0.3273 | 0.1691 | | 0.0576 | 73.0 | 1825 | 0.0686 | 0.5875 | 0.6472 | 2.3619 | 0.5875 | 0.5975 | 0.3465 | 0.1711 | | 0.0576 | 74.0 | 1850 | 0.0686 | 0.595 | 0.6436 | 2.4181 | 0.595 | 0.6054 | 0.3183 | 0.1706 | | 0.0576 | 75.0 | 1875 | 0.0686 | 0.6 | 0.6440 | 2.4160 | 0.6 | 0.6077 | 0.3285 | 0.1677 | | 0.0576 | 76.0 | 1900 | 0.0687 | 0.6025 | 0.6446 | 2.4184 | 0.6025 | 0.6111 | 0.3408 | 0.1685 | | 0.0576 | 77.0 | 1925 | 0.0686 | 0.6025 | 0.6440 | 2.4208 | 0.6025 | 0.6111 | 0.3323 | 0.1670 | | 0.0576 | 78.0 | 1950 | 0.0687 | 0.5975 | 0.6438 | 2.4236 | 0.5975 | 0.6063 | 0.3298 | 0.1689 | | 0.0576 | 79.0 | 1975 | 0.0687 | 0.5975 | 0.6438 | 2.4521 | 0.5975 | 0.6057 | 0.3328 | 0.1692 | | 0.0565 | 80.0 | 2000 | 0.0687 | 0.6 | 0.6448 | 2.4213 | 0.6 | 0.6088 | 0.3368 | 0.1682 | | 0.0565 | 81.0 | 2025 | 0.0688 | 0.5975 | 0.6444 | 2.4257 | 0.5975 | 0.6076 | 0.3179 | 0.1681 | | 0.0565 | 82.0 | 2050 | 0.0687 | 0.6 | 0.6446 | 2.4225 | 0.6 | 0.6102 | 0.3392 | 0.1673 | | 0.0565 | 83.0 | 2075 | 0.0687 | 0.6 | 0.6437 | 2.4571 | 0.6 | 0.6091 | 0.3281 | 0.1681 | | 0.0565 | 84.0 | 2100 | 0.0688 | 0.595 | 0.6439 | 2.4360 | 0.595 | 0.6042 | 0.3256 | 0.1685 | | 0.0565 | 85.0 | 2125 | 0.0688 | 0.6 | 0.6436 | 2.4396 | 0.6 | 0.6104 | 0.3318 | 0.1683 | | 0.0565 | 86.0 | 2150 | 0.0688 | 0.6 | 0.6434 | 2.3977 | 0.6 | 0.6095 | 0.3273 | 0.1675 | | 0.0565 | 87.0 | 2175 | 0.0688 | 0.595 | 0.6432 | 2.4303 | 0.595 | 0.6053 | 0.3146 | 0.1687 | | 0.0565 | 88.0 | 2200 | 0.0688 | 0.5975 | 0.6431 | 2.4222 | 0.5975 | 0.6071 | 0.3326 | 0.1686 | | 0.0565 | 89.0 | 2225 | 0.0688 | 0.6 | 0.6440 | 2.4042 | 0.6 | 0.6108 | 0.3303 | 0.1678 | | 0.0565 | 90.0 | 2250 | 0.0688 | 0.6 | 0.6433 | 2.3998 | 0.6 | 0.6096 | 0.3301 | 0.1679 | | 0.0565 | 91.0 | 2275 | 0.0689 | 0.6 | 0.6434 | 2.4026 | 0.6 | 0.6108 | 0.3362 | 0.1680 | | 0.0565 | 92.0 | 2300 | 0.0689 | 0.5975 | 0.6435 | 2.4037 | 0.5975 | 0.6083 | 0.3335 | 0.1680 | | 0.0565 | 93.0 | 2325 | 0.0689 | 0.5975 | 0.6434 | 2.4060 | 0.5975 | 0.6077 | 0.3344 | 0.1679 | | 0.0565 | 94.0 | 2350 | 0.0689 | 0.6 | 0.6433 | 2.4024 | 0.6 | 0.6106 | 0.3204 | 0.1683 | | 0.0565 | 95.0 | 2375 | 0.0689 | 0.595 | 0.6432 | 2.4060 | 0.595 | 0.6052 | 0.3423 | 0.1684 | | 0.0565 | 96.0 | 2400 | 0.0689 | 0.6 | 0.6432 | 2.4044 | 0.6 | 0.6101 | 0.3404 | 0.1684 | | 0.0565 | 97.0 | 2425 | 0.0689 | 0.6 | 0.6434 | 2.4042 | 0.6 | 0.6101 | 0.3349 | 0.1683 | | 0.0565 | 98.0 | 2450 | 0.0689 | 0.6 | 0.6432 | 2.4055 | 0.6 | 0.6101 | 0.3390 | 0.1684 | | 0.0565 | 99.0 | 2475 | 0.0689 | 0.6 | 0.6433 | 2.4056 | 0.6 | 0.6101 | 0.3393 | 0.1685 | | 0.056 | 100.0 | 2500 | 0.0689 | 0.6 | 0.6433 | 2.4057 | 0.6 | 0.6101 | 0.3353 | 0.1685 | ### Framework versions - Transformers 4.26.1 - Pytorch 1.13.1.post200 - Datasets 2.9.0 - Tokenizers 0.13.2

ben-xl8/wmt22-cometkiwi-da

ben-xl8

2023-07-11T23:59:39Z

0

1

null

[ "translation", "multilingual", "af", "am", "ar", "as", "az", "be", "bg", "bn", "br", "bs", "ca", "cs", "cy", "da", "de", "el", "en", "eo", "es", "et", "eu", "fa", "fi", "fr", "fy", "ga", "gd", "gl", "gu", "ha", "he", "hi", "hr", "hu", "hy", "id", "is", "it", "ja", "jv", "ka", "kk", "km", "kn", "ko", "ku", "ky", "la", "lo", "lt", "lv", "mg", "mk", "ml", "mn", "mr", "ms", "my", "ne", "nl", "no", "om", "or", "pa", "pl", "ps", "pt", "ro", "ru", "sa", "sd", "si", "sk", "sl", "so", "sq", "sr", "su", "sv", "sw", "ta", "te", "th", "tl", "tr", "ug", "uk", "ur", "uz", "vi", "xh", "yi", "zh", "license:cc-by-nc-sa-4.0", "endpoints_compatible", "region:us" ]

translation

2023-07-11T20:03:20Z

--- extra_gated_heading: Acknowledge license to accept the repository extra_gated_button_content: Acknowledge license pipeline_tag: translation language: - multilingual - af - am - ar - as - az - be - bg - bn - br - bs - ca - cs - cy - da - de - el - en - eo - es - et - eu - fa - fi - fr - fy - ga - gd - gl - gu - ha - he - hi - hr - hu - hy - id - is - it - ja - jv - ka - kk - km - kn - ko - ku - ky - la - lo - lt - lv - mg - mk - ml - mn - mr - ms - my - ne - nl - no - om - or - pa - pl - ps - pt - ro - ru - sa - sd - si - sk - sl - so - sq - sr - su - sv - sw - ta - te - th - tl - tr - ug - uk - ur - uz - vi - xh - yi - zh license: cc-by-nc-sa-4.0 --- This is a [COMET](https://github.com/Unbabel/COMET) quality estimation model by Unbabel: It receives a source sentence and the respective translation and returns a score that reflects the quality of the translation. # Paper [CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task](https://aclanthology.org/2022.wmt-1.60) (Rei et al., WMT 2022) # License: cc-by-nc-sa-4.0 # Usage for Inference Endpoint ```python import json import requests API_URL = "" API_TOKEN="MY_API_KEY" headers = { "Authorization": f"Bearer {API_TOKEN}", "Content-Type": "application/json", } def query(url, headers, payload): data = json.dumps(payload) response = requests.request("POST", url, headers=headers, data=data) return json.loads(response.content.decode("utf-8")) payload = { "inputs": { "batch_size": 8, "workers": None, "data": [ { "src": "Youll be picking fruit and generally helping us do all the usual farm work", "mt": "당신은 과일을 따기도 하고 대체로 우리가 하는 일상적인 농장 일을 돕게 될 겁니다", },{ "src": "Youll be picking fruit and generally helping us do all the usual farm work", "mt": "당신은 과일을 따기도 하고 대체로 우리가 하는 일상적인 농장 일을 돕게 될 겁니다", },{ "src": "Youll be picking fruit and generally helping us do all the usual farm work", "mt": "당신은 과일을 따기도 하고 대체로 우리가 하는 일상적인 농장 일을 돕게 될 겁니다", },{ "src": "Youll be picking fruit and generally helping us do all the usual farm work", "mt": "당신은 과일을 따기도 하고 대체로 우리가 하는 일상적인 농장 일을 돕게 될 겁니다", },{ "src": "Youll be picking fruit and generally helping us do all the usual farm work", "mt": "당신은 과일을 따기도 하고 대체로 우리가 하는 일상적인 농장 일을 돕게 될 겁니다", },{ "src": "Youll be picking fruit and generally helping us do all the usual farm work", "mt": "당신은 과일을 따기도 하고 대체로 우리가 하는 일상적인 농장 일을 돕게 될 겁니다", },{ "src": "Youll be picking fruit and generally helping us do all the usual farm work", "mt": "당신은 과일을 따기도 하고 대체로 우리가 하는 일상적인 농장 일을 돕게 될 겁니다", }, ] } } scores = query(API_URL, headers, payload) ``` # Intended uses Unbabel's model is intented to be used for **reference-free MT evaluation**. Given a source text and its translation, outputs a single score between 0 and 1 where 1 represents a perfect translation. # Languages Covered: This model builds on top of InfoXLM which cover the following languages: Afrikaans, Albanian, Amharic, Arabic, Armenian, Assamese, Azerbaijani, Basque, Belarusian, Bengali, Bengali Romanized, Bosnian, Breton, Bulgarian, Burmese, Burmese, Catalan, Chinese (Simplified), Chinese (Traditional), Croatian, Czech, Danish, Dutch, English, Esperanto, Estonian, Filipino, Finnish, French, Galician, Georgian, German, Greek, Gujarati, Hausa, Hebrew, Hindi, Hindi Romanized, Hungarian, Icelandic, Indonesian, Irish, Italian, Japanese, Javanese, Kannada, Kazakh, Khmer, Korean, Kurdish (Kurmanji), Kyrgyz, Lao, Latin, Latvian, Lithuanian, Macedonian, Malagasy, Malay, Malayalam, Marathi, Mongolian, Nepali, Norwegian, Oriya, Oromo, Pashto, Persian, Polish, Portuguese, Punjabi, Romanian, Russian, Sanskri, Scottish, Gaelic, Serbian, Sindhi, Sinhala, Slovak, Slovenian, Somali, Spanish, Sundanese, Swahili, Swedish, Tamil, Tamil Romanized, Telugu, Telugu Romanized, Thai, Turkish, Ukrainian, Urdu, Urdu Romanized, Uyghur, Uzbek, Vietnamese, Welsh, Western, Frisian, Xhosa, Yiddish. Thus, results for language pairs containing uncovered languages are unreliable!

arminmrm93/rl_course_vizdoom_health_gathering_supreme

arminmrm93

2023-07-11T23:56:33Z

0

sample-factory

[ "sample-factory", "tensorboard", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

reinforcement-learning

2023-07-11T23:56:25Z

--- library_name: sample-factory tags: - deep-reinforcement-learning - reinforcement-learning - sample-factory model-index: - name: APPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: doom_health_gathering_supreme type: doom_health_gathering_supreme metrics: - type: mean_reward value: 9.52 +/- 4.74 name: mean_reward verified: false --- A(n) **APPO** model trained on the **doom_health_gathering_supreme** environment. This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory. Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/ ## Downloading the model After installing Sample-Factory, download the model with: ``` python -m sample_factory.huggingface.load_from_hub -r arminmrm93/rl_course_vizdoom_health_gathering_supreme ``` ## Using the model To run the model after download, use the `enjoy` script corresponding to this environment: ``` python -m .usr.local.lib.python3.10.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme ``` You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag. See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details ## Training with this model To continue training with this model, use the `train` script corresponding to this environment: ``` python -m .usr.local.lib.python3.10.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000 ``` Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.

optimum/tiny-stable-diffusion-neuronx

optimum

2023-07-11T23:50:33Z

0

1

null

[ "region:us" ]

null

2023-07-10T11:59:42Z

This is a dummy model used for testing `NeuronStableDiffusionPipeline` of `optimum-neuron`. ```python from optimum.neuron import NeuronStableDiffusionPipeline model_id = "optimum/tiny-stable-diffusion-neuronx" input_shapes = {"batch_size": 2, "sequence_length": 18, "num_channels": 4, "height": 64, "width": 64} stable_diffusion = NeuronStableDiffusionPipeline.from_pretrained(model_id, export=True, **input_shapes) save_directory = "sd_neuron/" stable_diffusion.save_pretrained(save_directory) prompt = "sailing ship in storm by Leonardo da Vinci" image = stable_diffusion(prompt).images[0] ```

JTStephens/PixelCopterV1

JTStephens

2023-07-11T23:18:40Z

0

null

[ "Pixelcopter-PLE-v0", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]

reinforcement-learning

2023-07-11T23:18:15Z

--- tags: - Pixelcopter-PLE-v0 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: PixelCopterV1 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Pixelcopter-PLE-v0 type: Pixelcopter-PLE-v0 metrics: - type: mean_reward value: 20.80 +/- 14.26 name: mean_reward verified: false --- # **Reinforce** Agent playing **Pixelcopter-PLE-v0** This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction

sl8425/troubleshooting_steps_printer

sl8425

2023-07-11T23:07:39Z

61

0

transformers

[ "transformers", "tf", "distilbert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

text-classification

2023-07-11T20:49:26Z

--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: sl8425/troubleshooting_steps_printer results: [] ---  # sl8425/troubleshooting_steps_printer This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 0.8644 - Validation Loss: 0.8744 - Train Accuracy: 0.7457 - Epoch: 2 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 369, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Validation Loss | Train Accuracy | Epoch | |:----------:|:---------------:|:--------------:|:-----:| | 1.6729 | 1.1343 | 0.6428 | 0 | | 1.0262 | 0.9056 | 0.7366 | 1 | | 0.8644 | 0.8744 | 0.7457 | 2 | ### Framework versions - Transformers 4.30.2 - TensorFlow 2.12.0 - Datasets 2.13.1 - Tokenizers 0.13.3

talaugust/sci-writing-strategies

talaugust

2023-07-11T23:05:34Z

0

null

[ "region:us" ]

null

2023-07-11T22:42:06Z

RoBERTa Science writing strategy classifiers This is a finetuned BART Large model from the paper: "Writing Strategies for Science Communication: Data and Computational Analysis", By Tal August, Lauren Kim, Katharina Reinecke, and Noah A. Smith Published at the Conference on Empirical Methods in Natural Language Processing (EMNLP) 2020. Abstract: Communicating complex scientific ideas without misleading or overwhelming the public is challenging. While science communication guides exist, they rarely offer empirical evidence for how their strategies are used in practice. Writing strategies that can be automatically recognized could greatly support science communication efforts by enabling tools to detect and suggest strategies for writers. We compile a set of writing strategies drawn from a wide range of prescriptive sources and develop an annotation scheme allowing humans to recognize them. We collect a corpus of 128k science writing documents in English and annotate a subset of this corpus. We use the annotations to train transformer-based classifiers and measure the strategies’ use in the larger corpus. We find that the use of strategies, such as storytelling and emphasizing the most important findings, varies significantly across publications with different reader audiences. Description The model is finetuned on the task of identifying if a given sentence from a science news article is using a particular writing strategy (e.g., emphasizing the real world impact of the scientific findings). The intended use of this model is to identify common science communication writing strategies. The model is trained on annotated sentences drawn from science news articles. The URLs for the original news articles are at [https://github.com/talaugust/scientific-writing-strategies]. Biases & Limitations The goal of this model is to enable a wider audience of readers to understand and engage with scientific writing. A risk, though, is that such attempts might instead widen the gap to accessing scientific information. The texts in the datasets we train our models on are in General or Academic American. English. Many people, especially those who have been historically underrepresented in STEM disciplines and medicine, may not be comfortable with this dialect of English. This risks further alienating the readers we hope to serve. An important and exciting direction in NLP is making models more flexible to dialects and low-resource languages.

SHENMU007/neunit_BASE_V11.4

SHENMU007

2023-07-11T22:52:37Z

75

0

transformers

[ "transformers", "pytorch", "tensorboard", "speecht5", "text-to-audio", "1.1.0", "generated_from_trainer", "zh", "dataset:facebook/voxpopuli", "base_model:microsoft/speecht5_tts", "base_model:finetune:microsoft/speecht5_tts", "license:mit", "endpoints_compatible", "region:us" ]

text-to-audio

2023-07-11T20:08:34Z

--- language: - zh license: mit base_model: microsoft/speecht5_tts tags: - 1.1.0 - generated_from_trainer datasets: - facebook/voxpopuli model-index: - name: SpeechT5 TTS Dutch neunit results: [] ---  # SpeechT5 TTS Dutch neunit This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the VoxPopuli dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - training_steps: 4000 ### Training results ### Framework versions - Transformers 4.31.0.dev0 - Pytorch 2.0.1+cu117 - Datasets 2.12.0 - Tokenizers 0.13.3

crowbarmassage/ppo-Pyramids

crowbarmassage

2023-07-11T22:48:42Z

1

0

ml-agents

[ "ml-agents", "tensorboard", "onnx", "Pyramids", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Pyramids", "region:us" ]

reinforcement-learning

2023-07-11T22:48:40Z

--- library_name: ml-agents tags: - Pyramids - deep-reinforcement-learning - reinforcement-learning - ML-Agents-Pyramids --- # **ppo** Agent playing **Pyramids** This is a trained model of a **ppo** agent playing **Pyramids** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A *longer tutorial* to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent **playing directly in your browser** 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: crowbarmassage/ppo-Pyramids 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀

fgeyer/a2c-AntBulletEnv-v0

fgeyer

2023-07-11T22:40:23Z

0

stable-baselines3

[ "stable-baselines3", "AntBulletEnv-v0", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

reinforcement-learning

2023-07-11T22:24:37Z

--- library_name: stable-baselines3 tags: - AntBulletEnv-v0 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: A2C results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: AntBulletEnv-v0 type: AntBulletEnv-v0 metrics: - type: mean_reward value: 2384.01 +/- 64.45 name: mean_reward verified: false --- # **A2C** Agent playing **AntBulletEnv-v0** This is a trained model of a **A2C** agent playing **AntBulletEnv-v0** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```

ysmaicon/distilbert-base-uncased-finetuned-cola

ysmaicon

2023-07-11T22:04:26Z

61

0

transformers

[ "transformers", "tf", "tensorboard", "distilbert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

text-classification

2023-07-11T21:15:40Z

--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: ysmaicon/distilbert-base-uncased-finetuned-cola results: [] ---  # ysmaicon/distilbert-base-uncased-finetuned-cola This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 0.1941 - Validation Loss: 0.5355 - Train Matthews Correlation: 0.5256 - Epoch: 2 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1602, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Validation Loss | Train Matthews Correlation | Epoch | |:----------:|:---------------:|:--------------------------:|:-----:| | 0.5184 | 0.4689 | 0.4919 | 0 | | 0.3229 | 0.4772 | 0.5191 | 1 | | 0.1941 | 0.5355 | 0.5256 | 2 | ### Framework versions - Transformers 4.30.2 - TensorFlow 2.12.0 - Datasets 2.13.1 - Tokenizers 0.13.3

a9i/scarlett-7b

a9i

2023-07-11T21:37:46Z

4

1

transformers

[ "transformers", "pytorch", "llama", "text-generation", "text2text-generation", "en", "license:cc-by-nc-nd-4.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text2text-generation

2023-07-11T20:53:43Z

--- license: cc-by-nc-nd-4.0 language: - en pipeline_tag: text2text-generation ---

JuS2/ppo-Huggy

JuS2

2023-07-11T21:28:22Z

0

ml-agents

[ "ml-agents", "tensorboard", "onnx", "Huggy", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Huggy", "region:us" ]

reinforcement-learning

2023-07-11T21:28:12Z

--- library_name: ml-agents tags: - Huggy - deep-reinforcement-learning - reinforcement-learning - ML-Agents-Huggy --- # **ppo** Agent playing **Huggy** This is a trained model of a **ppo** agent playing **Huggy** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A *longer tutorial* to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent **playing directly in your browser** 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: JuS2/ppo-Huggy 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀

ethannhzhouu/gpt2-generator

ethannhzhouu

2023-07-11T21:11:54Z

209

0

transformers

[ "transformers", "pytorch", "tensorboard", "gpt2", "text-generation", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2023-07-11T21:11:25Z

--- license: apache-2.0 tags: - generated_from_trainer model-index: - name: gpt2-generator results: [] ---  # gpt2-generator This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the None dataset. It achieves the following results on the evaluation set: - Loss: 4.7855 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3.0 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | No log | 1.0 | 1 | 5.3997 | | No log | 2.0 | 2 | 4.9524 | | No log | 3.0 | 3 | 4.7855 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3

devasheeshG/whisper_medium_fp16_transformers

devasheeshG

2023-07-11T21:09:33Z

107

2

transformers

[ "transformers", "pytorch", "whisper", "automatic-speech-recognition", "audio", "speech", "wav2vec2", "en", "zh", "de", "es", "ru", "ko", "fr", "ja", "pt", "tr", "pl", "ca", "nl", "ar", "sv", "it", "id", "hi", "fi", "vi", "he", "uk", "el", "ms", "cs", "ro", "da", "hu", "ta", "no", "th", "ur", "hr", "bg", "lt", "la", "mi", "ml", "cy", "sk", "te", "fa", "lv", "bn", "sr", "az", "sl", "kn", "et", "mk", "br", "eu", "is", "hy", "ne", "mn", "bs", "kk", "sq", "sw", "gl", "mr", "pa", "si", "km", "sn", "yo", "so", "af", "oc", "ka", "be", "tg", "sd", "gu", "am", "yi", "lo", "uz", "fo", "ht", "ps", "tk", "nn", "mt", "sa", "lb", "my", "bo", "tl", "mg", "as", "tt", "haw", "ln", "ha", "ba", "jw", "su", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us" ]

automatic-speech-recognition

2023-07-02T11:04:37Z

--- license: apache-2.0 pipeline_tag: automatic-speech-recognition tags: - pytorch - audio - speech - automatic-speech-recognition - whisper - wav2vec2 model-index: - name: whisper_medium_fp16_transformers results: - task: type: automatic-speech-recognition name: Automatic Speech Recognition dataset: type: librispeech_asr name: LibriSpeech (clean) config: clean split: test args: language: en metrics: - type: wer value: 0 name: Test WER description: Word Error Rate - type: mer value: 0 name: Test MER description: Match Error Rate - type: wil value: 0 name: Test WIL description: Word Information Lost - type: wip value: 0 name: Test WIP description: Word Information Preserved - type: cer value: 0 name: Test CER description: Character Error Rate - task: type: automatic-speech-recognition name: Automatic Speech Recognition dataset: type: librispeech_asr name: LibriSpeech (other) config: other split: test args: language: en metrics: - type: wer value: 0 name: Test WER description: Word Error Rate - type: mer value: 0 name: Test MER description: Match Error Rate - type: wil value: 0 name: Test WIL description: Word Information Lost - type: wip value: 0 name: Test WIP description: Word Information Preserved - type: cer value: 0 name: Test CER description: Character Error Rate - task: type: automatic-speech-recognition name: Automatic Speech Recognition dataset: type: mozilla-foundation/common_voice_14_0 name: Common Voice (14.0) (Hindi) config: hi split: test args: language: hi metrics: - type: wer value: 54.97 name: Test WER description: Word Error Rate - type: mer value: 47.86 name: Test MER description: Match Error Rate - type: wil value: 66.83 name: Test WIL description: Word Information Lost - type: wip value: 33.16 name: Test WIP description: Word Information Preserved - type: cer value: 30.23 name: Test CER description: Character Error Rate widget: - example_title: Hinglish Sample src: https://huggingface.co/devasheeshG/whisper_medium_fp16_transformers/resolve/main/test.wav - example_title: Librispeech sample 1 src: https://cdn-media.huggingface.co/speech_samples/sample1.flac - example_title: Librispeech sample 2 src: https://cdn-media.huggingface.co/speech_samples/sample2.flac language: - en - zh - de - es - ru - ko - fr - ja - pt - tr - pl - ca - nl - ar - sv - it - id - hi - fi - vi - he - uk - el - ms - cs - ro - da - hu - ta - 'no' - th - ur - hr - bg - lt - la - mi - ml - cy - sk - te - fa - lv - bn - sr - az - sl - kn - et - mk - br - eu - is - hy - ne - mn - bs - kk - sq - sw - gl - mr - pa - si - km - sn - yo - so - af - oc - ka - be - tg - sd - gu - am - yi - lo - uz - fo - ht - ps - tk - nn - mt - sa - lb - my - bo - tl - mg - as - tt - haw - ln - ha - ba - jw - su --- ## Versions: - CUDA: 12.1 - cuDNN Version: 8.9.2.26_1.0-1_amd64 * tensorflow Version: 2.12.0 * torch Version: 2.1.0.dev20230606+cu12135 * transformers Version: 4.30.2 * accelerate Version: 0.20.3 ## Model Benchmarks: - RAM: 2.8 GB (Original_Model: 5.5GB) - VRAM: 1812 MB (Original_Model: 6GB) - test.wav: 23 s (Multilingual Speech i.e. English+Hindi) - **Time in seconds for Processing by each device** | Device Name | float32 (Original) | float16 | CudaCores | TensorCores | | ----------------- | ------------------ | ------- | --------- | ----------- | | 3060 | 1.7 | 1.1 | 3,584 | 112 | | 1660 Super | OOM | 3.3 | 1,408 | N/A | | Collab (Tesla T4) | 2.8 | 2.2 | 2,560 | 320 | | Collab (CPU) | 35 | N/A | N/A | N/A | | M1 (CPU) | - | - | - | - | | M1 (GPU -> 'mps') | - | - | - | - | - **NOTE: TensorCores are efficient in mixed-precision calculations** - **CPU -> torch.float16 not supported on CPU (AMD Ryzen 5 3600 or Collab CPU)** - Punchuation: True ## Model Error Benchmarks: - **WER: Word Error Rate** - **MER: Match Error Rate** - **WIL: Word Information Lost** - **WIP: Word Information Preserved** - **CER: Character Error Rate** ### Hindi to Hindi (test.tsv) [Common Voice 14.0](https://commonvoice.mozilla.org/en/datasets) **Test done on RTX 3060 on 2557 Samples** | | WER | MER | WIL | WIP | CER | | ----------------------- | ----- | ----- | ----- | ----- | ----- | | Original_Model (54 min) | 52.02 | 47.86 | 66.82 | 33.17 | 23.76 | | This_Model (38 min) | 54.97 | 47.86 | 66.83 | 33.16 | 30.23 | ### Hindi to English (test.csv) [Custom Dataset](https://huggingface.co/datasets/devasheeshG/common_voices_14_0_hi2en_hi2hi) **Test done on RTX 3060 on 1000 Samples** | | WER | MER | WIL | WIP | CER | | ----------------------- | --- | --- | --- | --- | --- | | Original_Model (30 min) | - | - | - | - | - | | This_Model (20 min) | - | - | - | - | - | ### English ([LibriSpeech](https://huggingface.co/datasets/librispeech_asr) -> test-clean) **Test done on RTX 3060 on __ Samples** | | WER | MER | WIL | WIP | CER | | -------------- | --- | --- | --- | --- | --- | | Original_Model | - | - | - | - | - | | This_Model | - | - | - | - | - | ### English ([LibriSpeech](https://huggingface.co/datasets/librispeech_asr) -> test-other) **Test done on RTX 3060 on __ Samples** | | WER | MER | WIL | WIP | CER | | -------------- | --- | --- | --- | --- | --- | | Original_Model | - | - | - | - | - | | This_Model | - | - | - | - | - | - **'jiwer' library is used for calculations** ## Code for conversion: - ### [Will be soon Uploaded on Github](https://github.com/devasheeshG) ## Usage A file ``__init__.py`` is contained inside this repo which contains all the code to use this model. Firstly, clone this repo and place all the files inside a folder. ### Make sure you have git-lfs installed (https://git-lfs.com) ```bash git lfs install git clone https://huggingface.co/devasheeshG/whisper_medium_fp16_transformers ``` **Please try in jupyter notebook** ```python # Import the Model from whisper_medium_fp16_transformers import Model, load_audio, pad_or_trim ``` ```python # Initilise the model model = Model( model_name_or_path='whisper_medium_fp16_transformers', cuda_visible_device="0", device='cuda', ) ``` ```python # Load Audio audio = load_audio('whisper_medium_fp16_transformers/test.wav') audio = pad_or_trim(audio) ``` ```python # Transcribe (First transcription takes time) model.transcribe(audio) ``` ## Credits It is fp16 version of ``openai/whisper-medium``