Datasets:
librarian-bots
/
model_cards_with_metadata

Dataset card Data Studio Files
xet
Community
2
modelId
stringlengths
5
139
author
stringlengths
2
42
last_modified
timestamp[us, tz=UTC]date
2020-02-15 11:33:14
2025-07-14 06:27:53
downloads
int64
0
223M
likes
int64
0
11.7k
library_name
stringclasses
519 values
tags
listlengths
1
4.05k
pipeline_tag
stringclasses
55 values
createdAt
timestamp[us, tz=UTC]date
2022-03-02 23:29:04
2025-07-14 06:27:45
card
stringlengths
11
1.01M
YakovElm/Jira_5_BERT_Over_Sampling
YakovElm
2023-06-28T17:15:19Z
54
0
transformers
[ "transformers", "tf", "bert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-28T17:14:42Z
--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: Jira_5_BERT_Over_Sampling 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. --> # Jira_5_BERT_Over_Sampling This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 0.1422 - Train Accuracy: 0.9521 - Validation Loss: 0.9298 - Validation Accuracy: 0.6404 - 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': 1.0, '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch | |:----------:|:--------------:|:---------------:|:-------------------:|:-----:| | 0.5895 | 0.6781 | 0.7268 | 0.5268 | 0 | | 0.3571 | 0.8377 | 0.8239 | 0.6309 | 1 | | 0.1422 | 0.9521 | 0.9298 | 0.6404 | 2 | ### Framework versions - Transformers 4.29.2 - TensorFlow 2.12.0 - Datasets 2.12.0 - Tokenizers 0.13.3
deepghs/anime_ch_horn
deepghs
2023-06-28T17:13:49Z
0
0
null
[ "onnx", "art", "image-classification", "dataset:deepghs/anime_ch_horn", "license:mit", "region:us" ]
image-classification
2023-06-17T02:38:51Z
--- license: mit datasets: - deepghs/anime_ch_horn metrics: - accuracy - f1 pipeline_tag: image-classification tags: - art --- | Name | FLOPS | Params | Accuracy | AUC | Confusion | Labels | |:-------------------:|:-------:|:--------:|:----------:|:------:|:----------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------:| | caformer_s36_raw | 22.10G | 37.22M | 88.32% | 0.9788 | [confusion](https://huggingface.co/deepghs/anime_ch_horn/blob/main/caformer_s36_raw/plot_confusion.png) | `cow`, `demon`, `dragon`, `oni`, `sheep`, `none` | | caformer_s36_v0 | 22.10G | 37.22M | 86.88% | 0.9789 | [confusion](https://huggingface.co/deepghs/anime_ch_horn/blob/main/caformer_s36_v0/plot_confusion.png) | `cow`, `deer`, `demon`, `dragon`, `oni`, `sheep`, `none` | | mobilenetv3_v0_dist | 0.63G | 4.18M | 81.86% | 0.9657 | [confusion](https://huggingface.co/deepghs/anime_ch_horn/blob/main/mobilenetv3_v0_dist/plot_confusion.png) | `cow`, `deer`, `demon`, `dragon`, `oni`, `sheep`, `none` |
mr-m1chaeljprodss/CrustytheCat
mr-m1chaeljprodss
2023-06-28T17:04:23Z
0
0
adapter-transformers
[ "adapter-transformers", "music", "audio-to-audio", "en", "es", "dataset:QingyiSi/Alpaca-CoT", "license:openrail", "region:us" ]
audio-to-audio
2023-06-28T16:47:01Z
--- license: openrail language: - en - es tags: - music datasets: - QingyiSi/Alpaca-CoT metrics: - accuracy library_name: adapter-transformers pipeline_tag: audio-to-audio ---
amittian/setfit_ds_version_0_0_2
amittian
2023-06-28T16:57:20Z
3
0
sentence-transformers
[ "sentence-transformers", "pytorch", "mpnet", "setfit", "text-classification", "arxiv:2209.11055", "license:apache-2.0", "region:us" ]
text-classification
2023-06-28T16:56:54Z
--- license: apache-2.0 tags: - setfit - sentence-transformers - text-classification pipeline_tag: text-classification --- # amittian/setfit_ds_version_0_0_2 This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves: 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning. 2. Training a classification head with features from the fine-tuned Sentence Transformer. ## Usage To use this model for inference, first install the SetFit library: ```bash python -m pip install setfit ``` You can then run inference as follows: ```python from setfit import SetFitModel # Download from Hub and run inference model = SetFitModel.from_pretrained("amittian/setfit_ds_version_0_0_2") # Run inference preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"]) ``` ## BibTeX entry and citation info ```bibtex @article{https://doi.org/10.48550/arxiv.2209.11055, doi = {10.48550/ARXIV.2209.11055}, url = {https://arxiv.org/abs/2209.11055}, author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren}, keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences}, title = {Efficient Few-Shot Learning Without Prompts}, publisher = {arXiv}, year = {2022}, copyright = {Creative Commons Attribution 4.0 International} } ```
mr-m1chaeljprodss/catmodel
mr-m1chaeljprodss
2023-06-28T16:57:04Z
0
0
fairseq
[ "fairseq", "music", "en", "es", "dataset:OpenAssistant/oasst1", "license:openrail", "region:us" ]
null
2023-06-28T16:51:23Z
--- license: openrail language: - en - es library_name: fairseq tags: - music datasets: - OpenAssistant/oasst1 metrics: - accuracy ---
papahawk/gpt-neox-20b
papahawk
2023-06-28T16:44:58Z
0
0
null
[ "pytorch", "causal-lm", "en", "dataset:EleutherAI/pile", "arxiv:2204.06745", "arxiv:2101.00027", "arxiv:2201.07311", "arxiv:2104.09864", "license:apache-2.0", "region:us" ]
null
2023-06-28T16:23:01Z
--- language: - en tags: - pytorch - causal-lm license: apache-2.0 datasets: - EleutherAI/pile --- <h1 style='text-align: center '>GPT-NeoX-20b LLM</h1> <h2 style='text-align: center '><em>Fork of EleutherAI/gpt-neox-20b</em> </h2> <h3 style='text-align: center '>Model Card</h3> <img src="https://alt-web.xyz/images/rainbow.png" alt="Rainbow Solutions" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/> GPT-NeoX-20B is a 20 billion parameter autoregressive language model trained on [the Pile](https://pile.eleuther.ai/) using the [GPT-NeoX library](https://github.com/EleutherAI/gpt-neox). Its architecture intentionally resembles that of GPT-3, and is almost identical to that of [GPT-J- 6B](https://huggingface.co/EleutherAI/gpt-j-6B). Its training dataset contains a multitude of English-language texts, reflecting the general-purpose nature of this model. See the [accompanying paper](https://arxiv.org/abs/2204.06745) for details about model architecture (including how it differs from GPT-3), training procedure, and additional evaluations. ### Model details - Developed by: [EleutherAI](http://eleuther.ai) - Model type: Transformer-based Language Model - Language: English - Learn more: [GPT-NeoX-20B: An Open-Source Autoregressive Language Model](https://arxiv.org/abs/2204.06745). For details about the training dataset, see [the Pile paper](https://arxiv.org/abs/2101.00027), and [its data sheet](https://arxiv.org/abs/2201.07311). - License: Apache 2.0 - Contact: to ask questions about this model, join the [EleutherAI Discord](https://discord.gg/zBGx3azzUn), and post them in `#release-discussion`. Please read the existing GPT-NeoX-20B documentation before asking about the model on Discord. For general correspondence: [contact@eleuther. ai](mailto:[email protected]). <figure style="width:30em"> | Hyperparameter | Value | | ---------------------- | ----------- | | n<sub>parameters</sub> | 20554567680 | | n<sub>layers</sub> | 44 | | d<sub>model</sub> | 6144 | | n<sub>heads</sub> | 64 | | d<sub>head</sub> | 96 | | n<sub>vocab</sub> | 50257 | | Sequence Length | 2048 | | Learning Rate | 0.97 x 10<sup>-5</sup> | | Positional Encoding | [Rotary Position Embedding (RoPE)](https://arxiv.org/abs/2104.09864) | </figure> ### Uses and limitations #### Intended use GPT-NeoX-20B was developed primarily for research purposes. It learns an inner representation of the English language that can be used to extract features useful for downstream tasks. In addition to scientific uses, you may also further fine-tune and adapt GPT-NeoX-20B for deployment, as long as your use is in accordance with the Apache 2.0 license. This model works with the [Transformers Library](https://huggingface.co/docs/transformers/index). If you decide to use pre-trained GPT-NeoX-20B as a basis for your fine-tuned model, please note that you need to conduct your own risk and bias assessment. #### Out-of-scope use GPT-NeoX-20B is **not** intended for deployment as-is. It is not a product and cannot be used for human-facing interactions without supervision. GPT-NeoX-20B has not been fine-tuned for downstream tasks for which language models are commonly deployed, such as writing genre prose, or commercial chatbots. This means GPT-NeoX-20B will likely **not** respond to a given prompt the way products such as ChatGPT do. This is because, unlike GPT-NeoX-20B, ChatGPT was fine-tuned using methods such as Reinforcement Learning from Human Feedback (RLHF) to better “understand” human instructions and dialogue. This model is English-language only, and thus cannot be used for translation or generating text in other languages. #### Limitations and biases The core functionality of GPT-NeoX-20B is to take a string of text and predict the next token. Remember that the statistically most likely next token need not result in the most “accurate” text. Never rely on GPT-NeoX-20B to produce factually accurate output. This model was trained on [the Pile](https://pile.eleuther.ai/), a dataset known to contain profanity and texts that are lewd or otherwise offensive. See [Section 6 of the Pile paper](https://arxiv.org/abs/2101.00027) for a discussion of documented biases with regards to gender, religion, and race. GPT-NeoX-20B may produce socially unacceptable or undesirable text, *even if* the prompt itself does not include anything explicitly offensive. We recommend curating the outputs of this model before presenting it to a human reader. Please inform your audience that you are using artificially generated text. #### How to use If you simply want to try out some prompts, check out [this playground](https://20b.eleuther.ai/). GPT-NeoX-20B can be loaded using the `AutoModelForCausalLM` functionality: ```python from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("EleutherAI/gpt-neox-20b") model = AutoModelForCausalLM.from_pretrained("EleutherAI/gpt-neox-20b") ``` ### Training #### Training dataset The Pile is a 825GiB general-purpose dataset in English. It was created by EleutherAI specifically for training large language models. It contains texts from 22 diverse sources, roughly broken down into five categories: academic writing (e.g. arXiv), internet (e.g. CommonCrawl), prose (e.g. Project Gutenberg), dialogue (e.g. YouTube subtitles), and miscellaneous (e.g. GitHub, Enron Emails). See [the Pile paper](https://arxiv.org/abs/2101.00027) for a breakdown of all data sources, methodology, and a discussion of ethical implications. Consult [the datasheet](https://arxiv.org/abs/2201.07311) for more detailed documentation about the Pile and its component datasets. The Pile can be downloaded from the [official website](https://pile.eleuther.ai/), or from a [community mirror](https://the-eye.eu/public/AI/pile/). The Pile was **not** deduplicated before being used to train GPT-NeoX-20B. #### Training procedure GPT-NeoX-20B was trained with a batch size of approximately 3.15M tokens (1538 sequences of 2048 tokens each), for a total of 150,000 steps. Tensor parallelism and pipeline parallelism were used to distribute the model across GPUs. Additional details about the training procedure are in [Section 3 of the accompanying paper](https://arxiv.org/abs/2204.06745). ### Evaluations <figure style="width:55em"> | Model | OpenAI’s LAMBADA | SciQ | PIQA | TriviaQA | ARC (Challenge) | | ------------- | :--------------: | :-----------: | :-----------: | :-----------: | :-------------: | | GPT-J-6B | 0.683 ± 0.006 | 0.910 ± 0.009 | 0.752 ± 0.010 | 0.170 ± 0.004 | 0.340 ± 0.014 | | FairSeq 6.7B | 0.673 ± 0.007 | 0.895 ± 0.010 | 0.762 ± 0.010 | 0.221 ± 0.004 | 0.329 ± 0.014 | | GPT-3 Curie | 0.693 ± 0.006 | 0.918 ± 0.009 | 0.767 ± 0.010 | 0.196 ± 0.004 | 0.334 ± 0.014 | | FairSeq 13B | 0.709 ± 0.006 | 0.910 ± 0.009 | 0.769 ± 0.010 | 0.270 ± 0.004 | 0.345 ± 0.014 | | GPT-NeoX-20B | 0.720 ± 0.006 | 0.928 ± 0.008 | 0.779 ± 0.010 | 0.259 ± 0.004 | 0.380 ± 0.014 | | GPT-3 DaVinci | 0.752 ± 0.006 | 0.949 ± 0.007 | 0.791 ± 0.009 | 0.409 ± 0.005 | 0.435 ± 0.014 | <figcaption>Zero-shot performance on selected natural language tasks.</figcaption> </figure> This is a heavily abridged version of the evaluation results. Appendix D of the [GPT-NeoX-20B paper](https://arxiv.org/abs/2204.06745) compares more model sizes, and contains additional evaluations, including on: zero and five-shot natural language tasks, zero and five-shot Basic Arithmetic and MATH, and zero-shot Hendrycks tasks. ### BibTeX To cite the GPT-NeoX-20B paper: ``` @misc{https://doi.org/10.48550/arxiv.2204.06745, doi = {10.48550/ARXIV.2204.06745}, url = {https://arxiv.org/abs/2204.06745}, author = {Black, Sid and Biderman, Stella and Hallahan, Eric and Anthony, Quentin and Gao, Leo and Golding, Laurence and He, Horace and Leahy, Connor and McDonell, Kyle and Phang, Jason and Pieler, Michael and Prashanth, USVSN Sai and Purohit, Shivanshu and Reynolds, Laria and Tow, Jonathan and Wang, Ben and Weinbach, Samuel}, keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences}, title = {GPT-NeoX-20B: An Open-Source Autoregressive Language Model}, publisher = {arXiv}, year = {2022}, copyright = {Creative Commons Attribution 4.0 International} } ```
Dddokter/VAE
Dddokter
2023-06-28T16:38:55Z
0
1
null
[ "region:us" ]
null
2023-06-28T14:55:06Z
This is vae-ft-mse-840000-pruned but then cleaned up a bit more. Works exactly like the original but 160mb leaner
TheYuriLover/Airoboros-13b-gpt4-StoryTelling-GPTQ-32g-ao-ts
TheYuriLover
2023-06-28T16:27:54Z
10
6
transformers
[ "transformers", "pytorch", "llama", "text-generation", "license:other", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-06-28T08:37:45Z
--- license: other --- This model is a merge between the finetuned model named airoboros-gpt4-1.4 and a StoryTelling Lora https://huggingface.co/jondurbin/airoboros-13b-gpt4-1.4 https://huggingface.co/GamerUntouch/Storytelling-LLaMa-LoRAs Airoboros is a great base model as it understands the requets well and has a great english prose. The problem was that for Storytelling purposes, it was really blank and the model never added something new to the table. Mixing this finetuned model with a Storytelling Lora really made it more creative and interesting, I hope you'll enjoy it :) This gptq safetensor has all the implementations in it (true_sequential + act_order + groupsize 32) Run it with exllama_hf, this marvelous feature can load everything!
heka-ai/demo-model
heka-ai
2023-06-28T16:22:31Z
1
0
sentence-transformers
[ "sentence-transformers", "pytorch", "distilbert", "feature-extraction", "sentence-similarity", "transformers", "autotrain_compatible", "text-embeddings-inference", "endpoints_compatible", "region:us" ]
sentence-similarity
2023-06-28T16:22:27Z
--- pipeline_tag: sentence-similarity tags: - sentence-transformers - feature-extraction - sentence-similarity - transformers --- # heka-ai/demo-model This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search. <!--- Describe your model here --> ## Usage (Sentence-Transformers) Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed: ``` pip install -U sentence-transformers ``` Then you can use the model like this: ```python from sentence_transformers import SentenceTransformer sentences = ["This is an example sentence", "Each sentence is converted"] model = SentenceTransformer('heka-ai/demo-model') embeddings = model.encode(sentences) print(embeddings) ``` ## Usage (HuggingFace Transformers) Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings. ```python from transformers import AutoTokenizer, AutoModel import torch def cls_pooling(model_output, attention_mask): return model_output[0][:,0] # Sentences we want sentence embeddings for sentences = ['This is an example sentence', 'Each sentence is converted'] # Load model from HuggingFace Hub tokenizer = AutoTokenizer.from_pretrained('heka-ai/demo-model') model = AutoModel.from_pretrained('heka-ai/demo-model') # Tokenize sentences encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt') # Compute token embeddings with torch.no_grad(): model_output = model(**encoded_input) # Perform pooling. In this case, cls pooling. sentence_embeddings = cls_pooling(model_output, encoded_input['attention_mask']) print("Sentence embeddings:") print(sentence_embeddings) ``` ## Evaluation Results <!--- Describe how your model was evaluated --> For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=heka-ai/demo-model) ## Training The model was trained with the parameters: **DataLoader**: `torch.utils.data.dataloader.DataLoader` of length 1001 with parameters: ``` {'batch_size': 32, 'sampler': 'torch.utils.data.sampler.SequentialSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'} ``` **Loss**: `gpl.toolkit.loss.MarginDistillationLoss` Parameters of the fit()-Method: ``` { "epochs": 1, "evaluation_steps": 0, "evaluator": "NoneType", "max_grad_norm": 1, "optimizer_class": "<class 'torch.optim.adamw.AdamW'>", "optimizer_params": { "lr": 2e-05 }, "scheduler": "WarmupLinear", "steps_per_epoch": 1001, "warmup_steps": 1000, "weight_decay": 0.01 } ``` ## Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 350, 'do_lower_case': False}) with Transformer model: DistilBertModel (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False}) ) ``` ## Citing & Authors <!--- Describe where people can find more information -->
sharpbai/baichuan-llama-7b
sharpbai
2023-06-28T16:14:29Z
19
2
transformers
[ "transformers", "pytorch", "llama", "text-generation", "zh", "en", "autotrain_compatible", "text-generation-inference", "region:us" ]
text-generation
2023-06-17T15:49:18Z
--- language: - zh - en pipeline_tag: text-generation inference: false --- # baichuan-llama-7B 使用[LLaMA](https://huggingface.co/huggyllama/llama-7b)格式保存的[baichuan-7B](https://huggingface.co/baichuan-inc/baichuan-7B)。可以直接使用LlamaForCausalLM和LlamaTokenizer加载。 权重文件以405M的尺寸分片，方便并行快速下载。权重来自[fireballoon/baichuan-llama-7b](https://huggingface.co/fireballoon/baichuan-llama-7b) [baichuan-7B](https://huggingface.co/baichuan-inc/baichuan-7B) model saved in the format of the [LLaMA](https://huggingface.co/huggyllama/llama-7b) model. You can directly use LlamaForCausalLM and LlamaTokenizer to load the model. The weight file is split into chunks with a size of 405M for convenient and fast parallel downloads, specifically for academic research purposes. The weights are sourced from [fireballoon/baichuan-llama-7b](https://huggingface.co/fireballoon/baichuan-llama-7b) **License:** [baichuan-7B License](https://huggingface.co/baichuan-inc/baichuan-7B/blob/main/baichuan-7B%20%E6%A8%A1%E5%9E%8B%E8%AE%B8%E5%8F%AF%E5%8D%8F%E8%AE%AE.pdf)
sharpbai/open_llama_13b
sharpbai
2023-06-28T16:14:25Z
25
1
transformers
[ "transformers", "pytorch", "llama", "text-generation", "dataset:togethercomputer/RedPajama-Data-1T", "arxiv:2302.13971", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-06-22T05:07:23Z
--- license: apache-2.0 datasets: - togethercomputer/RedPajama-Data-1T --- # open_llama_13b *The weight file is split into chunks with a size of 650MB for convenient and fast parallel downloads* A 650MB split weight version of [openlm-research/open_llama_13b](https://huggingface.co/openlm-research/open_llama_13b) The original model card is down below ----------------------------------------- # OpenLLaMA: An Open Reproduction of LLaMA In this repo, we present a permissively licensed open source reproduction of Meta AI's [LLaMA](https://ai.facebook.com/blog/large-language-model-llama-meta-ai/) large language model. We are releasing 3B, 7B and 13B models trained on 1T tokens. We provide PyTorch and JAX weights of pre-trained OpenLLaMA models, as well as evaluation results and comparison against the original LLaMA models. Please see the [project homepage of OpenLLaMA](https://github.com/openlm-research/open_llama) for more details. ## Weights Release, License and Usage We release the weights in two formats: an EasyLM format to be use with our [EasyLM framework](https://github.com/young-geng/EasyLM), and a PyTorch format to be used with the [Hugging Face transformers](https://huggingface.co/docs/transformers/index) library. Both our training framework EasyLM and the checkpoint weights are licensed permissively under the Apache 2.0 license. ### Loading the Weights with Hugging Face Transformers Preview checkpoints can be directly loaded from Hugging Face Hub. **Please note that it is advised to avoid using the Hugging Face fast tokenizer for now, as we’ve observed that the auto-converted fast tokenizer sometimes gives incorrect tokenizations.** This can be achieved by directly using the `LlamaTokenizer` class, or passing in the `use_fast=False` option for the `AutoTokenizer` class. See the following example for usage. ```python import torch from transformers import LlamaTokenizer, LlamaForCausalLM # model_path = 'openlm-research/open_llama_3b' # model_path = 'openlm-research/open_llama_7b' model_path = 'openlm-research/open_llama_13b' tokenizer = LlamaTokenizer.from_pretrained(model_path) model = LlamaForCausalLM.from_pretrained( model_path, torch_dtype=torch.float16, device_map='auto', ) prompt = 'Q: What is the largest animal?\nA:' input_ids = tokenizer(prompt, return_tensors="pt").input_ids generation_output = model.generate( input_ids=input_ids, max_new_tokens=32 ) print(tokenizer.decode(generation_output[0])) ``` For more advanced usage, please follow the [transformers LLaMA documentation](https://huggingface.co/docs/transformers/main/model_doc/llama). ### Evaluating with LM-Eval-Harness The model can be evaluated with [lm-eval-harness](https://github.com/EleutherAI/lm-evaluation-harness). However, due to the aforementioned tokenizer issue, we need to avoid using the fast tokenizer to obtain the correct results. This can be achieved by passing in `use_fast=False` to [this part of lm-eval-harness](https://github.com/EleutherAI/lm-evaluation-harness/blob/4b701e228768052cfae9043dca13e82052ca5eea/lm_eval/models/huggingface.py#LL313C9-L316C10), as shown in the example below: ```python tokenizer = self.AUTO_TOKENIZER_CLASS.from_pretrained( pretrained if tokenizer is None else tokenizer, revision=revision + ("/" + subfolder if subfolder is not None else ""), use_fast=False ) ``` ### Loading the Weights with EasyLM For using the weights in our EasyLM framework, please refer to the [LLaMA documentation of EasyLM](https://github.com/young-geng/EasyLM/blob/main/docs/llama.md). Note that unlike the original LLaMA model, our OpenLLaMA tokenizer and weights are trained completely from scratch so it is no longer needed to obtain the original LLaMA tokenizer and weights. Note that we use BOS (beginning of sentence) token (id=1) during training, so it is best to prepend this token for best performance during few-shot evaluation. ## Dataset and Training We train our models on the [RedPajama](https://www.together.xyz/blog/redpajama) dataset released by [Together](https://www.together.xyz/), which is a reproduction of the LLaMA training dataset containing over 1.2 trillion tokens. We follow the exactly same preprocessing steps and training hyperparameters as the original LLaMA paper, including model architecture, context length, training steps, learning rate schedule, and optimizer. The only difference between our setting and the original one is the dataset used: OpenLLaMA employs the RedPajama dataset rather than the one utilized by the original LLaMA. We train the models on cloud TPU-v4s using [EasyLM](https://github.com/young-geng/EasyLM), a JAX based training pipeline we developed for training and fine-tuning large language models. We employ a combination of normal data parallelism and [fully sharded data parallelism (also know as ZeRO stage 3)](https://engineering.fb.com/2021/07/15/open-source/fsdp/) to balance the training throughput and memory usage. Overall we reach a throughput of over 2200 tokens / second / TPU-v4 chip for our 7B model. ## Evaluation We evaluated OpenLLaMA on a wide range of tasks using [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness). The LLaMA results are generated by running the original LLaMA model on the same evaluation metrics. We note that our results for the LLaMA model differ slightly from the original LLaMA paper, which we believe is a result of different evaluation protocols. Similar differences have been reported in [this issue of lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness/issues/443). Additionally, we present the results of GPT-J, a 6B parameter model trained on the [Pile](https://pile.eleuther.ai/) dataset by [EleutherAI](https://www.eleuther.ai/). The original LLaMA model was trained for 1 trillion tokens and GPT-J was trained for 500 billion tokens. We present the results in the table below. OpenLLaMA exhibits comparable performance to the original LLaMA and GPT-J across a majority of tasks, and outperforms them in some tasks. | **Task/Metric** | GPT-J 6B | LLaMA 7B | LLaMA 13B | OpenLLaMA 7B | OpenLLaMA 3B | OpenLLaMA 13B | | ---------------------- | -------- | -------- | --------- | ------------ | ------------ | ------------- | | anli_r1/acc | 0.32 | 0.35 | 0.35 | 0.33 | 0.33 | 0.33 | | anli_r2/acc | 0.34 | 0.34 | 0.36 | 0.36 | 0.32 | 0.33 | | anli_r3/acc | 0.35 | 0.37 | 0.39 | 0.38 | 0.35 | 0.40 | | arc_challenge/acc | 0.34 | 0.39 | 0.44 | 0.37 | 0.34 | 0.41 | | arc_challenge/acc_norm | 0.37 | 0.41 | 0.44 | 0.38 | 0.37 | 0.44 | | arc_easy/acc | 0.67 | 0.68 | 0.75 | 0.72 | 0.69 | 0.75 | | arc_easy/acc_norm | 0.62 | 0.52 | 0.59 | 0.68 | 0.65 | 0.70 | | boolq/acc | 0.66 | 0.75 | 0.71 | 0.71 | 0.68 | 0.75 | | hellaswag/acc | 0.50 | 0.56 | 0.59 | 0.53 | 0.49 | 0.56 | | hellaswag/acc_norm | 0.66 | 0.73 | 0.76 | 0.72 | 0.67 | 0.76 | | openbookqa/acc | 0.29 | 0.29 | 0.31 | 0.30 | 0.27 | 0.31 | | openbookqa/acc_norm | 0.38 | 0.41 | 0.42 | 0.40 | 0.40 | 0.43 | | piqa/acc | 0.75 | 0.78 | 0.79 | 0.76 | 0.75 | 0.77 | | piqa/acc_norm | 0.76 | 0.78 | 0.79 | 0.77 | 0.76 | 0.79 | | record/em | 0.88 | 0.91 | 0.92 | 0.89 | 0.88 | 0.91 | | record/f1 | 0.89 | 0.91 | 0.92 | 0.90 | 0.89 | 0.91 | | rte/acc | 0.54 | 0.56 | 0.69 | 0.60 | 0.58 | 0.64 | | truthfulqa_mc/mc1 | 0.20 | 0.21 | 0.25 | 0.23 | 0.22 | 0.25 | | truthfulqa_mc/mc2 | 0.36 | 0.34 | 0.40 | 0.35 | 0.35 | 0.38 | | wic/acc | 0.50 | 0.50 | 0.50 | 0.51 | 0.48 | 0.47 | | winogrande/acc | 0.64 | 0.68 | 0.70 | 0.67 | 0.62 | 0.70 | | Average | 0.52 | 0.55 | 0.57 | 0.55 | 0.53 | 0.57 | We removed the task CB and WSC from our benchmark, as our model performs suspiciously well on these two tasks. We hypothesize that there could be a benchmark data contamination in the training set. ## Contact We would love to get feedback from the community. If you have any questions, please open an issue or contact us. OpenLLaMA is developed by: [Xinyang Geng](https://young-geng.xyz/)* and [Hao Liu](https://www.haoliu.site/)* from Berkeley AI Research. *Equal Contribution ## Acknowledgment We thank the [Google TPU Research Cloud](https://sites.research.google/trc/about/) program for providing part of the computation resources. We’d like to specially thank Jonathan Caton from TPU Research Cloud for helping us organizing compute resources, Rafi Witten from the Google Cloud team and James Bradbury from the Google JAX team for helping us optimizing our training throughput. We’d also want to thank Charlie Snell, Gautier Izacard, Eric Wallace, Lianmin Zheng and our user community for the discussions and feedback. The OpenLLaMA 13B model is trained in collaboration with [Stability AI](https://stability.ai/), and we thank Stability AI for providing the computation resources. We’d like to especially thank David Ha and Shivanshu Purohit for the coordinating the logistics and providing engineering support. ## Reference If you found OpenLLaMA useful in your research or applications, please cite using the following BibTeX: ``` @software{openlm2023openllama, author = {Geng, Xinyang and Liu, Hao}, title = {OpenLLaMA: An Open Reproduction of LLaMA}, month = May, year = 2023, url = {https://github.com/openlm-research/open_llama} } ``` ``` @software{together2023redpajama, author = {Together Computer}, title = {RedPajama-Data: An Open Source Recipe to Reproduce LLaMA training dataset}, month = April, year = 2023, url = {https://github.com/togethercomputer/RedPajama-Data} } ``` ``` @article{touvron2023llama, title={Llama: Open and efficient foundation language models}, author={Touvron, Hugo and Lavril, Thibaut and Izacard, Gautier and Martinet, Xavier and Lachaux, Marie-Anne and Lacroix, Timoth{\'e}e and Rozi{\`e}re, Baptiste and Goyal, Naman and Hambro, Eric and Azhar, Faisal and others}, journal={arXiv preprint arXiv:2302.13971}, year={2023} } ```
sharpbai/open_llama_7b
sharpbai
2023-06-28T16:14:21Z
9
0
transformers
[ "transformers", "pytorch", "llama", "text-generation", "dataset:togethercomputer/RedPajama-Data-1T", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-06-17T16:23:41Z
--- license: apache-2.0 datasets: - togethercomputer/RedPajama-Data-1T --- # OpenLLaMA: An Open Reproduction of LLaMA A 405M split weight version of [openlm-research/open_llama_7b](https://huggingface.co/openlm-research/open_llama_7b)
sharpbai/chinese-alpaca-plus-lora-7b-merged
sharpbai
2023-06-28T16:14:18Z
15
1
transformers
[ "transformers", "pytorch", "llama", "text-generation", "zh", "license:other", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-06-13T09:02:38Z
--- license: other language: - zh --- # Chinese-Alpaca-Plus-LoRA-7B This model is merged from [chinese-alpaca-plus-lora-7b](https://huggingface.co/ziqingyang/chinese-alpaca-plus-lora-7b) The weight file is split into chunks with a size of 405M for convenient and fast parallel downloads
sharpbai/chinese-llama-plus-lora-7b-merged
sharpbai
2023-06-28T16:14:15Z
7
2
transformers
[ "transformers", "pytorch", "llama", "text-generation", "zh", "license:other", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-06-15T03:48:49Z
--- license: other language: - zh --- # Chinese-LLaMA-Plus-LoRA-7B-Merged *The weight file is split into chunks with a size of 405M for convenient and fast parallel downloads* This repo contains the tokenizer, Chinese-Alpaca LoRA merged weights for [Chinese-LLaMA-Alpaca](https://github.com/ymcui/Chinese-LLaMA-Alpaca) The original model card is below ------------------------------------ # Chinese-LLaMA-Plus-LoRA-7B This repo contains the tokenizer, Chinese-Alpaca LoRA weights and configs for [Chinese-LLaMA-Alpaca](https://github.com/ymcui/Chinese-LLaMA-Alpaca) Instructions for using the weights can be found at https://github.com/ymcui/Chinese-LLaMA-Alpaca.
sharpbai/alpaca-lora-7b-merged
sharpbai
2023-06-28T16:14:12Z
26
0
transformers
[ "transformers", "pytorch", "llama", "text-generation", "dataset:yahma/alpaca-cleaned", "license:other", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-06-13T16:08:57Z
--- license: other datasets: - yahma/alpaca-cleaned --- *The weight file is split into chunks with a size of 405M for convenient and fast parallel downloads* This repo contains a merged model from [tloen/alpaca-lora-7b](https://huggingface.co/tloen/alpaca-lora-7b).
sharpbai/alpaca-7b-merged
sharpbai
2023-06-28T16:14:08Z
76
0
transformers
[ "transformers", "pytorch", "llama", "text-generation", "alpaca", "license:other", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-06-14T15:56:13Z
--- license: other tags: - alpaca --- ### Stanford Alpaca-7B-Merged *The weight file is split into chunks with a size of 405M for convenient and fast parallel downloads* This repo hosts the merged weight for [Stanford Alpaca-7B](https://github.com/tatsu-lab/stanford_alpaca/) that can be used directly. Below is the original model card information. ----------------------- ### Stanford Alpaca-7B This repo hosts the weight diff for [Stanford Alpaca-7B](https://github.com/tatsu-lab/stanford_alpaca/) that can be used to reconstruct the original model weights when applied to Meta's LLaMA weights. To recover the original Alpaca-7B weights, follow these steps: ```text 1. Convert Meta's released weights into huggingface format. Follow this guide: https://huggingface.co/docs/transformers/main/model_doc/llama 2. Make sure you cloned the released weight diff into your local machine. The weight diff is located at: https://huggingface.co/tatsu-lab/alpaca-7b/tree/main 3. Run this function with the correct paths. E.g., python weight_diff.py recover --path_raw <path_to_step_1_dir> --path_diff <path_to_step_2_dir> --path_tuned <path_to_store_recovered_weights> ``` Once step 3 completes, you should have a directory with the recovered weights, from which you can load the model like the following ```python import transformers alpaca_model = transformers.AutoModelForCausalLM.from_pretrained("<path_to_store_recovered_weights>") alpaca_tokenizer = transformers.AutoTokenizer.from_pretrained("<path_to_store_recovered_weights>") ```
sharpbai/vicuna-7b-v1.3
sharpbai
2023-06-28T16:14:00Z
221
0
transformers
[ "transformers", "pytorch", "llama", "text-generation", "arxiv:2302.13971", "arxiv:2306.05685", "autotrain_compatible", "text-generation-inference", "region:us" ]
text-generation
2023-06-20T09:01:29Z
--- inference: false --- # vicuna-7b-v1.3 *The weight file is split into chunks with a size of 405M for convenient and fast parallel downloads* A 405M split weight version of [lmsys/vicuna-7b-v1.3](https://huggingface.co/lmsys/vicuna-7b-v1.3) Original model is down below # 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)
sharpbai/llama-13b-hf
sharpbai
2023-06-28T16:13:56Z
93
1
transformers
[ "transformers", "pytorch", "llama", "text-generation", "license:other", "autotrain_compatible", "text-generation-inference", "region:us" ]
text-generation
2023-06-20T10:34:56Z
--- inference: false license: other --- # llama-13b-hf *The weight file is split into chunks with a size of 650MB for convenient and fast parallel downloads* A 650M split weight version of [yahma/llama-13b-hf](https://huggingface.co/yahma/llama-13b-hf) The original model card is down below ----------------------------------------- LLaMA-13B converted to work with git head Transformers/HuggingFace on April 8, 2023. This version should resolve the EOS token issues. This is under a special license, please see the LICENSE file for details. This contains the weights for the LLaMA-7b model. This model is under a non-commercial license (see the LICENSE file). You should only use this repository if you have been granted access to the model by filling out [this form](https://docs.google.com/forms/d/e/1FAIpQLSfqNECQnMkycAp2jP4Z9TFX0cGR4uf7b_fBxjY_OjhJILlKGA/viewform?usp=send_form) but either lost your copy of the weights or got some trouble converting them to the Transformers format. -- license: other --- # LLaMA Model Card ## Model details **Organization developing the model** The FAIR team of Meta AI. **Model date** LLaMA was trained between December. 2022 and Feb. 2023. **Model version** This is version 1 of the model. **Model type** LLaMA is an auto-regressive language model, based on the transformer architecture. The model comes in different sizes: 7B, 13B, 33B and 65B parameters. **Paper or resources for more information** More information can be found in the paper “LLaMA, Open and Efficient Foundation Language Models”, available at https://research.facebook.com/publications/llama-open-and-efficient-foundation-language-models/. **Citations details** https://research.facebook.com/publications/llama-open-and-efficient-foundation-language-models/ **License** Non-commercial bespoke license **Where to send questions or comments about the model** Questions and comments about LLaMA can be sent via the [GitHub repository](https://github.com/facebookresearch/llama) of the project , by opening an issue. ## Intended use **Primary intended uses** The primary use of LLaMA is research on large language models, including: exploring potential applications such as question answering, natural language understanding or reading comprehension, understanding capabilities and limitations of current language models, and developing techniques to improve those, evaluating and mitigating biases, risks, toxic and harmful content generations, hallucinations. **Primary intended users** The primary intended users of the model are researchers in natural language processing, machine learning and artificial intelligence. **Out-of-scope use cases** LLaMA is a base, or foundational, model. As such, it should not be used on downstream applications without further risk evaluation and mitigation. In particular, our model has not been trained with human feedback, and can thus generate toxic or offensive content, incorrect information or generally unhelpful answers. ## Factors **Relevant factors** One of the most relevant factors for which model performance may vary is which language is used. Although we included 20 languages in the training data, most of our dataset is made of English text, and we thus expect the model to perform better for English than other languages. Relatedly, it has been shown in previous studies that performance might vary for different dialects, and we expect that it will be the case for our model. **Evaluation factors** As our model is trained on data from the Web, we expect that it reflects biases from this source. We thus evaluated on RAI datasets to measure biases exhibited by the model for gender, religion, race, sexual orientation, age, nationality, disability, physical appearance and socio-economic status. We also measure the toxicity of model generations, depending on the toxicity of the context used to prompt the model. ## Metrics **Model performance measures** We use the following measure to evaluate the model: - Accuracy for common sense reasoning, reading comprehension, natural language understanding (MMLU), BIG-bench hard, WinoGender and CrowS-Pairs, - Exact match for question answering, - The toxicity score from Perspective API on RealToxicityPrompts. **Decision thresholds** Not applicable. **Approaches to uncertainty and variability** Due to the high computational requirements of training LLMs, we trained only one model of each size, and thus could not evaluate variability of pre-training. ## Evaluation datasets The model was evaluated on the following benchmarks: BoolQ, PIQA, SIQA, HellaSwag, WinoGrande, ARC, OpenBookQA, NaturalQuestions, TriviaQA, RACE, MMLU, BIG-bench hard, GSM8k, RealToxicityPrompts, WinoGender, CrowS-Pairs. ## Training dataset The model was trained using the following source of data: CCNet [67%], C4 [15%], GitHub [4.5%], Wikipedia [4.5%], Books [4.5%], ArXiv [2.5%], Stack Exchange[2%]. The Wikipedia and Books domains include data in the following languages: bg, ca, cs, da, de, en, es, fr, hr, hu, it, nl, pl, pt, ro, ru, sl, sr, sv, uk. See the paper for more details about the training set and corresponding preprocessing. ## Quantitative analysis Hyperparameters for the model architecture <table> <thead> <tr> <th >LLaMA</th> <th colspan=6>Model hyper parameters </th> </tr> <tr> <th>Number of parameters</th><th>dimension</th><th>n heads</th><th>n layers</th><th>Learn rate</th><th>Batch size</th><th>n tokens</th> </tr> </thead> <tbody> <tr> <th>7B</th> <th>4096</th> <th>32</th> <th>32</th> <th>3.0E-04</th><th>4M</th><th>1T </tr> <tr> <th>13B</th><th>5120</th><th>40</th><th>40</th><th>3.0E-04</th><th>4M</th><th>1T </tr> <tr> <th>33B</th><th>6656</th><th>52</th><th>60</th><th>1.5.E-04</th><th>4M</th><th>1.4T </tr> <tr> <th>65B</th><th>8192</th><th>64</th><th>80</th><th>1.5.E-04</th><th>4M</th><th>1.4T </tr> </tbody> </table> *Table 1 - Summary of LLama Model Hyperparameters* We present our results on eight standard common sense reasoning benchmarks in the table below. <table> <thead> <tr> <th>LLaMA</th> <th colspan=9>Reasoning tasks </th> </tr> <tr> <th>Number of parameters</th> <th>BoolQ</th><th>PIQA</th><th>SIQA</th><th>HellaSwag</th><th>WinoGrande</th><th>ARC-e</th><th>ARC-c</th><th>OBQA</th><th>COPA</th> </tr> </thead> <tbody> <tr> <th>7B</th><th>76.5</th><th>79.8</th><th>48.9</th><th>76.1</th><th>70.1</th><th>76.7</th><th>47.6</th><th>57.2</th><th>93 </th> <tr><th>13B</th><th>78.1</th><th>80.1</th><th>50.4</th><th>79.2</th><th>73</th><th>78.1</th><th>52.7</th><th>56.4</th><th>94 </th> <tr><th>33B</th><th>83.1</th><th>82.3</th><th>50.4</th><th>82.8</th><th>76</th><th>81.4</th><th>57.8</th><th>58.6</th><th>92 </th> <tr><th>65B</th><th>85.3</th><th>82.8</th><th>52.3</th><th>84.2</th><th>77</th><th>81.5</th><th>56</th><th>60.2</th><th>94</th></tr> </tbody> </table> *Table 2 - Summary of LLama Model Performance on Reasoning tasks* We present our results on bias in the table below. Note that lower value is better indicating lower bias. | No | Category | FAIR LLM | | --- | -------------------- | -------- | | 1 | Gender | 70.6 | | 2 | Religion | 79 | | 3 | Race/Color | 57 | | 4 | Sexual orientation | 81 | | 5 | Age | 70.1 | | 6 | Nationality | 64.2 | | 7 | Disability | 66.7 | | 8 | Physical appearance | 77.8 | | 9 | Socioeconomic status | 71.5 | | | LLaMA Average | 66.6 | *Table 3 - Summary bias of our model output* ## Ethical considerations **Data** The data used to train the model is collected from various sources, mostly from the Web. As such, it contains offensive, harmful and biased content. We thus expect the model to exhibit such biases from the training data. **Human life** The model is not intended to inform decisions about matters central to human life, and should not be used in such a way. **Mitigations** We filtered the data from the Web based on its proximity to Wikipedia text and references. For this, we used a Kneser-Ney language model and a fastText linear classifier. **Risks and harms** Risks and harms of large language models include the generation of harmful, offensive or biased content. These models are often prone to generating incorrect information, sometimes referred to as hallucinations. We do not expect our model to be an exception in this regard. **Use cases** LLaMA is a foundational model, and as such, it should not be used for downstream applications without further investigation and mitigations of risks. These risks and potential fraught use cases include, but are not limited to: generation of misinformation and generation of harmful, biased or offensive content.
sharpbai/llama-7b-hf
sharpbai
2023-06-28T16:13:52Z
14
0
transformers
[ "transformers", "pytorch", "llama", "text-generation", "license:other", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-06-14T16:38:42Z
--- license: other --- # llama-7b-hf *The weight file is split into chunks with a size of 405MB for convenient and fast parallel downloads* A 405MB split weight version of [yahma/llama-7b-hf](https://huggingface.co/yahma/llama-7b-hf) The original model card is down below ----------------------------------------- LLaMA-7B converted to work with git head Transformers/HuggingFace on April 8, 2023. This version should resolve the EOS token issues. This is under a special license, please see the LICENSE file for details. This contains the weights for the LLaMA-7b model. This model is under a non-commercial license (see the LICENSE file). You should only use this repository if you have been granted access to the model by filling out [this form](https://docs.google.com/forms/d/e/1FAIpQLSfqNECQnMkycAp2jP4Z9TFX0cGR4uf7b_fBxjY_OjhJILlKGA/viewform?usp=send_form) but either lost your copy of the weights or got some trouble converting them to the Transformers format. -- license: other --- # LLaMA Model Card ## Model details **Organization developing the model** The FAIR team of Meta AI. **Model date** LLaMA was trained between December. 2022 and Feb. 2023. **Model version** This is version 1 of the model. **Model type** LLaMA is an auto-regressive language model, based on the transformer architecture. The model comes in different sizes: 7B, 13B, 33B and 65B parameters. **Paper or resources for more information** More information can be found in the paper “LLaMA, Open and Efficient Foundation Language Models”, available at https://research.facebook.com/publications/llama-open-and-efficient-foundation-language-models/. **Citations details** https://research.facebook.com/publications/llama-open-and-efficient-foundation-language-models/ **License** Non-commercial bespoke license **Where to send questions or comments about the model** Questions and comments about LLaMA can be sent via the [GitHub repository](https://github.com/facebookresearch/llama) of the project , by opening an issue. ## Intended use **Primary intended uses** The primary use of LLaMA is research on large language models, including: exploring potential applications such as question answering, natural language understanding or reading comprehension, understanding capabilities and limitations of current language models, and developing techniques to improve those, evaluating and mitigating biases, risks, toxic and harmful content generations, hallucinations. **Primary intended users** The primary intended users of the model are researchers in natural language processing, machine learning and artificial intelligence. **Out-of-scope use cases** LLaMA is a base, or foundational, model. As such, it should not be used on downstream applications without further risk evaluation and mitigation. In particular, our model has not been trained with human feedback, and can thus generate toxic or offensive content, incorrect information or generally unhelpful answers. ## Factors **Relevant factors** One of the most relevant factors for which model performance may vary is which language is used. Although we included 20 languages in the training data, most of our dataset is made of English text, and we thus expect the model to perform better for English than other languages. Relatedly, it has been shown in previous studies that performance might vary for different dialects, and we expect that it will be the case for our model. **Evaluation factors** As our model is trained on data from the Web, we expect that it reflects biases from this source. We thus evaluated on RAI datasets to measure biases exhibited by the model for gender, religion, race, sexual orientation, age, nationality, disability, physical appearance and socio-economic status. We also measure the toxicity of model generations, depending on the toxicity of the context used to prompt the model. ## Metrics **Model performance measures** We use the following measure to evaluate the model: - Accuracy for common sense reasoning, reading comprehension, natural language understanding (MMLU), BIG-bench hard, WinoGender and CrowS-Pairs, - Exact match for question answering, - The toxicity score from Perspective API on RealToxicityPrompts. **Decision thresholds** Not applicable. **Approaches to uncertainty and variability** Due to the high computational requirements of training LLMs, we trained only one model of each size, and thus could not evaluate variability of pre-training. ## Evaluation datasets The model was evaluated on the following benchmarks: BoolQ, PIQA, SIQA, HellaSwag, WinoGrande, ARC, OpenBookQA, NaturalQuestions, TriviaQA, RACE, MMLU, BIG-bench hard, GSM8k, RealToxicityPrompts, WinoGender, CrowS-Pairs. ## Training dataset The model was trained using the following source of data: CCNet [67%], C4 [15%], GitHub [4.5%], Wikipedia [4.5%], Books [4.5%], ArXiv [2.5%], Stack Exchange[2%]. The Wikipedia and Books domains include data in the following languages: bg, ca, cs, da, de, en, es, fr, hr, hu, it, nl, pl, pt, ro, ru, sl, sr, sv, uk. See the paper for more details about the training set and corresponding preprocessing. ## Quantitative analysis Hyperparameters for the model architecture <table> <thead> <tr> <th >LLaMA</th> <th colspan=6>Model hyper parameters </th> </tr> <tr> <th>Number of parameters</th><th>dimension</th><th>n heads</th><th>n layers</th><th>Learn rate</th><th>Batch size</th><th>n tokens</th> </tr> </thead> <tbody> <tr> <th>7B</th> <th>4096</th> <th>32</th> <th>32</th> <th>3.0E-04</th><th>4M</th><th>1T </tr> <tr> <th>13B</th><th>5120</th><th>40</th><th>40</th><th>3.0E-04</th><th>4M</th><th>1T </tr> <tr> <th>33B</th><th>6656</th><th>52</th><th>60</th><th>1.5.E-04</th><th>4M</th><th>1.4T </tr> <tr> <th>65B</th><th>8192</th><th>64</th><th>80</th><th>1.5.E-04</th><th>4M</th><th>1.4T </tr> </tbody> </table> *Table 1 - Summary of LLama Model Hyperparameters* We present our results on eight standard common sense reasoning benchmarks in the table below. <table> <thead> <tr> <th>LLaMA</th> <th colspan=9>Reasoning tasks </th> </tr> <tr> <th>Number of parameters</th> <th>BoolQ</th><th>PIQA</th><th>SIQA</th><th>HellaSwag</th><th>WinoGrande</th><th>ARC-e</th><th>ARC-c</th><th>OBQA</th><th>COPA</th> </tr> </thead> <tbody> <tr> <th>7B</th><th>76.5</th><th>79.8</th><th>48.9</th><th>76.1</th><th>70.1</th><th>76.7</th><th>47.6</th><th>57.2</th><th>93 </th> <tr><th>13B</th><th>78.1</th><th>80.1</th><th>50.4</th><th>79.2</th><th>73</th><th>78.1</th><th>52.7</th><th>56.4</th><th>94 </th> <tr><th>33B</th><th>83.1</th><th>82.3</th><th>50.4</th><th>82.8</th><th>76</th><th>81.4</th><th>57.8</th><th>58.6</th><th>92 </th> <tr><th>65B</th><th>85.3</th><th>82.8</th><th>52.3</th><th>84.2</th><th>77</th><th>81.5</th><th>56</th><th>60.2</th><th>94</th></tr> </tbody> </table> *Table 2 - Summary of LLama Model Performance on Reasoning tasks* We present our results on bias in the table below. Note that lower value is better indicating lower bias. | No | Category | FAIR LLM | | --- | -------------------- | -------- | | 1 | Gender | 70.6 | | 2 | Religion | 79 | | 3 | Race/Color | 57 | | 4 | Sexual orientation | 81 | | 5 | Age | 70.1 | | 6 | Nationality | 64.2 | | 7 | Disability | 66.7 | | 8 | Physical appearance | 77.8 | | 9 | Socioeconomic status | 71.5 | | | LLaMA Average | 66.6 | *Table 3 - Summary bias of our model output* ## Ethical considerations **Data** The data used to train the model is collected from various sources, mostly from the Web. As such, it contains offensive, harmful and biased content. We thus expect the model to exhibit such biases from the training data. **Human life** The model is not intended to inform decisions about matters central to human life, and should not be used in such a way. **Mitigations** We filtered the data from the Web based on its proximity to Wikipedia text and references. For this, we used a Kneser-Ney language model and a fastText linear classifier. **Risks and harms** Risks and harms of large language models include the generation of harmful, offensive or biased content. These models are often prone to generating incorrect information, sometimes referred to as hallucinations. We do not expect our model to be an exception in this regard. **Use cases** LLaMA is a foundational model, and as such, it should not be used for downstream applications without further investigation and mitigations of risks. These risks and potential fraught use cases include, but are not limited to: generation of misinformation and generation of harmful, biased or offensive content.
leoyt61/spellcheck_model
leoyt61
2023-06-28T16:07:46Z
105
1
transformers
[ "transformers", "pytorch", "t5", "text2text-generation", "grammar", "spell", "correction", "en", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text2text-generation
2023-06-28T15:56:28Z
--- language: en tags: - grammar - spell - correction --- # Spellcheck Model ## Installation 1. Install Python 3.8 or higher and Docker; 2. Clone the repo; 3. Create a virtual environment: `python3 -m venv venv`; 4. Activate the virtual environment: `source venv/bin/activate`; 5. Install dependencies: `pip install -r requirements.txt`; # ## Usage ### Training There's a `data` directory with two files: 1. `eval.csv`: evaluation dataset; 2. `train.csv`: training dataset; Both are in the same format: ```txt input,target "grammar: som sentense","some sentence" "grammar: anoder centence","another sentence" ... ``` You can edit them to use your own dataset. Now if you want to fine-tune the existing model here, just run the following commands: ```bash docker build -t spellcheck_train . docker run -v $(pwd):/app spellcheck_train ``` Also make sure you have docker running on your machine. ### Testing If you want to test your model, just run the following command: ```bash python test.py ```
YakovElm/IntelDAOS_15_BERT_Over_Sampling
YakovElm
2023-06-28T15:55:27Z
62
0
transformers
[ "transformers", "tf", "bert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-28T15:54:45Z
--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: IntelDAOS_15_BERT_Over_Sampling 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. --> # IntelDAOS_15_BERT_Over_Sampling This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 0.0704 - Train Accuracy: 0.9820 - Validation Loss: 0.7296 - Validation Accuracy: 0.8108 - 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': 1.0, '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch | |:----------:|:--------------:|:---------------:|:-------------------:|:-----:| | 0.5199 | 0.7373 | 0.5990 | 0.6517 | 0 | | 0.2247 | 0.9276 | 0.8030 | 0.7357 | 1 | | 0.0704 | 0.9820 | 0.7296 | 0.8108 | 2 | ### Framework versions - Transformers 4.29.2 - TensorFlow 2.12.0 - Datasets 2.12.0 - Tokenizers 0.13.3
AbhilashGanji/distilbert-base-uncased-finetuned-squad-d5716d28
AbhilashGanji
2023-06-28T15:54:44Z
0
0
null
[ "pytorch", "question-answering", "en", "dataset:squad", "arxiv:1910.01108", "license:apache-2.0", "region:us" ]
question-answering
2023-06-28T15:50:07Z
--- 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} } ```
kvarnalidis/taxi-v3-Qtable
kvarnalidis
2023-06-28T15:35:07Z
0
0
null
[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T15:35:05Z
--- tags: - Taxi-v3 - q-learning - reinforcement-learning - custom-implementation model-index: - name: taxi-v3-Qtable 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 ```python model = load_from_hub(repo_id="kvarnalidis/taxi-v3-Qtable", 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"]) ```
vicky865/MemeClassifier
vicky865
2023-06-28T15:31:18Z
0
0
null
[ "region:us" ]
null
2023-06-28T15:29:38Z
This is the project thats shows an approach to detect meme using Deep learning
kvarnalidis/q-FrozenLake-v1-4x4-noSlippery
kvarnalidis
2023-06-28T15:29:54Z
0
0
null
[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T15:29:51Z
--- tags: - FrozenLake-v1-4x4-no_slippery - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-FrozenLake-v1-4x4-noSlippery results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: FrozenLake-v1-4x4-no_slippery type: FrozenLake-v1-4x4-no_slippery metrics: - type: mean_reward value: 1.00 +/- 0.00 name: mean_reward verified: false --- # **Q-Learning** Agent playing1 **FrozenLake-v1** This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** . ## Usage ```python model = load_from_hub(repo_id="kvarnalidis/q-FrozenLake-v1-4x4-noSlippery", 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"]) ```
h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-3b
h2oai
2023-06-28T15:28:51Z
351
3
transformers
[ "transformers", "pytorch", "llama", "text-generation", "gpt", "llm", "large language model", "h2o-llmstudio", "en", "dataset:OpenAssistant/oasst1", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "region:us" ]
text-generation
2023-06-28T13:55:52Z
--- language: - en library_name: transformers tags: - gpt - llm - large language model - h2o-llmstudio inference: false thumbnail: >- https://h2o.ai/etc.clientlibs/h2o/clientlibs/clientlib-site/resources/images/favicon.ico license: apache-2.0 datasets: - OpenAssistant/oasst1 --- # Model Card ## Summary This model was trained using [H2O LLM Studio](https://github.com/h2oai/h2o-llmstudio). - Base model: [openlm-research/open_llama_3b](https://huggingface.co/openlm-research/open_llama_3b) - Dataset preparation: [OpenAssistant/oasst1](https://github.com/h2oai/h2o-llmstudio/blob/1935d84d9caafed3ee686ad2733eb02d2abfce57/app_utils/utils.py#LL1896C5-L1896C28) personalized ## Usage To use the model with the `transformers` library on a machine with GPUs, first make sure you have the `transformers`, `accelerate` and `torch` libraries installed. ```bash pip install transformers==4.30.2 pip install accelerate==0.20.3 pip install torch==2.0.0 ``` ```python import torch from transformers import pipeline generate_text = pipeline( model="h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-3b", torch_dtype="auto", trust_remote_code=True, use_fast=False, device_map={"": "cuda:0"}, ) res = generate_text( "Why is drinking water so healthy?", min_new_tokens=2, max_new_tokens=1024, do_sample=False, num_beams=1, temperature=float(0.3), repetition_penalty=float(1.2), renormalize_logits=True ) print(res[0]["generated_text"]) ``` You can print a sample prompt after the preprocessing step to see how it is feed to the tokenizer: ```python print(generate_text.preprocess("Why is drinking water so healthy?")["prompt_text"]) ``` ```bash <|prompt|>Why is drinking water so healthy?</s><|answer|> ``` Alternatively, you can download [h2oai_pipeline.py](h2oai_pipeline.py), store it alongside your notebook, and construct the pipeline yourself from the loaded model and tokenizer. If the model and the tokenizer are fully supported in the `transformers` package, this will allow you to set `trust_remote_code=False`. ```python import torch from h2oai_pipeline import H2OTextGenerationPipeline from transformers import AutoModelForCausalLM, AutoTokenizer tokenizer = AutoTokenizer.from_pretrained( "h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-3b", use_fast=False, padding_side="left", trust_remote_code=True, ) model = AutoModelForCausalLM.from_pretrained( "h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-3b", torch_dtype="auto", device_map={"": "cuda:0"}, trust_remote_code=True, ) generate_text = H2OTextGenerationPipeline(model=model, tokenizer=tokenizer) res = generate_text( "Why is drinking water so healthy?", min_new_tokens=2, max_new_tokens=1024, do_sample=False, num_beams=1, temperature=float(0.3), repetition_penalty=float(1.2), renormalize_logits=True ) print(res[0]["generated_text"]) ``` You may also construct the pipeline from the loaded model and tokenizer yourself and consider the preprocessing steps: ```python from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-3b" # either local folder or huggingface model name # Important: The prompt needs to be in the same format the model was trained with. # You can find an example prompt in the experiment logs. prompt = "<|prompt|>How are you?</s><|answer|>" tokenizer = AutoTokenizer.from_pretrained( model_name, use_fast=False, trust_remote_code=True, ) model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype="auto", device_map={"": "cuda:0"}, trust_remote_code=True, ) model.cuda().eval() inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to("cuda") # generate configuration can be modified to your needs tokens = model.generate( **inputs, min_new_tokens=2, max_new_tokens=1024, do_sample=False, num_beams=1, temperature=float(0.3), repetition_penalty=float(1.2), renormalize_logits=True )[0] tokens = tokens[inputs["input_ids"].shape[1]:] answer = tokenizer.decode(tokens, skip_special_tokens=True) print(answer) ``` ## Model Architecture ``` LlamaForCausalLM( (model): LlamaModel( (embed_tokens): Embedding(32000, 3200, padding_idx=0) (layers): ModuleList( (0-25): 26 x LlamaDecoderLayer( (self_attn): LlamaAttention( (q_proj): Linear(in_features=3200, out_features=3200, bias=False) (k_proj): Linear(in_features=3200, out_features=3200, bias=False) (v_proj): Linear(in_features=3200, out_features=3200, bias=False) (o_proj): Linear(in_features=3200, out_features=3200, bias=False) (rotary_emb): LlamaRotaryEmbedding() ) (mlp): LlamaMLP( (gate_proj): Linear(in_features=3200, out_features=8640, bias=False) (down_proj): Linear(in_features=8640, out_features=3200, bias=False) (up_proj): Linear(in_features=3200, out_features=8640, bias=False) (act_fn): SiLUActivation() ) (input_layernorm): LlamaRMSNorm() (post_attention_layernorm): LlamaRMSNorm() ) ) (norm): LlamaRMSNorm() ) (lm_head): Linear(in_features=3200, out_features=32000, bias=False) ) ``` ## Model Configuration This model was trained using H2O LLM Studio and with the configuration in [cfg.yaml](cfg.yaml). Visit [H2O LLM Studio](https://github.com/h2oai/h2o-llmstudio) to learn how to train your own large language models. ## Disclaimer Please read this disclaimer carefully before using the large language model provided in this repository. Your use of the model signifies your agreement to the following terms and conditions. - Biases and Offensiveness: The large language model is trained on a diverse range of internet text data, which may contain biased, racist, offensive, or otherwise inappropriate content. By using this model, you acknowledge and accept that the generated content may sometimes exhibit biases or produce content that is offensive or inappropriate. The developers of this repository do not endorse, support, or promote any such content or viewpoints. - Limitations: The large language model is an AI-based tool and not a human. It may produce incorrect, nonsensical, or irrelevant responses. It is the user's responsibility to critically evaluate the generated content and use it at their discretion. - Use at Your Own Risk: Users of this large language model must assume full responsibility for any consequences that may arise from their use of the tool. The developers and contributors of this repository shall not be held liable for any damages, losses, or harm resulting from the use or misuse of the provided model. - Ethical Considerations: Users are encouraged to use the large language model responsibly and ethically. By using this model, you agree not to use it for purposes that promote hate speech, discrimination, harassment, or any form of illegal or harmful activities. - Reporting Issues: If you encounter any biased, offensive, or otherwise inappropriate content generated by the large language model, please report it to the repository maintainers through the provided channels. Your feedback will help improve the model and mitigate potential issues. - Changes to this Disclaimer: The developers of this repository reserve the right to modify or update this disclaimer at any time without prior notice. It is the user's responsibility to periodically review the disclaimer to stay informed about any changes. By using the large language model provided in this repository, you agree to accept and comply with the terms and conditions outlined in this disclaimer. If you do not agree with any part of this disclaimer, you should refrain from using the model and any content generated by it.
filipps/model
filipps
2023-06-28T15:12:28Z
0
0
diffusers
[ "diffusers", "tensorboard", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "dreambooth", "base_model:CompVis/stable-diffusion-v1-4", "base_model:finetune:CompVis/stable-diffusion-v1-4", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]
text-to-image
2023-06-27T16:20:11Z
--- license: creativeml-openrail-m base_model: CompVis/stable-diffusion-v1-4 instance_prompt: a photo of sks dog tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers - dreambooth inference: true --- # DreamBooth - filipps/model This is a dreambooth model derived from CompVis/stable-diffusion-v1-4. The weights were trained on a photo of sks dog using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following. DreamBooth for the text encoder was enabled: False.
YakovElm/IntelDAOS_10_BERT_Over_Sampling
YakovElm
2023-06-28T15:11:31Z
61
0
transformers
[ "transformers", "tf", "bert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-28T15:10:51Z
--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: IntelDAOS_10_BERT_Over_Sampling 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. --> # IntelDAOS_10_BERT_Over_Sampling This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 0.0340 - Train Accuracy: 0.9918 - Validation Loss: 1.2417 - Validation Accuracy: 0.6727 - 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': 1.0, '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch | |:----------:|:--------------:|:---------------:|:-------------------:|:-----:| | 0.5670 | 0.6984 | 0.5649 | 0.7057 | 0 | | 0.1840 | 0.9359 | 0.4907 | 0.8258 | 1 | | 0.0340 | 0.9918 | 1.2417 | 0.6727 | 2 | ### Framework versions - Transformers 4.29.2 - TensorFlow 2.12.0 - Datasets 2.12.0 - Tokenizers 0.13.3
xzuyn/GPT2-RPGPT-8.48M
xzuyn
2023-06-28T15:06:20Z
255
0
transformers
[ "transformers", "pytorch", "safetensors", "gpt2", "text-generation", "en", "dataset:practicaldreamer/RPGPT_PublicDomain-alpaca", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-06-27T05:46:00Z
--- language: - en pipeline_tag: text-generation datasets: - practicaldreamer/RPGPT_PublicDomain-alpaca --- # Latest Version: *111,577* / *111,577* Steps (Epoch 1). - 28,563,712 / 28,563,712 tokens seen (Epoch 1). - 0 / 28,563,712 tokens seen (Epoch 2). - 0 / 28,563,712 tokens seen (Epoch 3). # Model Info: - Trained from scratch. - 8.48M parameters. - 256 context length. - Test model. Likely needs at least 512 context to function "properly". - Trained with a dataset that overlaps by a quarter of the context length (Shifts by 64 tokens for each subset). # Format: ``` <|characters|> Nancy (Oliver Twist): Female, early 20s, ESFP, Cockney accent. Loyal... Mr. Edward Hyde (Dr. Jekyll and Mr. Hyde): Male, late 30s, ESTP... <|scenario|> In an alternate Victorian London where the city's poor and downtrodden... <|response|> Nancy: *gently brushes her fingers across the worn book spine, before suddenly stopping as she feels another hand... Mr. Edward Hyde: *glances at Nancy with a sinister grin, slowly pulling his hand back* No need to apologize, miss... ``` # Example Output: Step 111,577. Input `<|characters|>` as a prompt, set max tokens to 256, amount to generate to 253. This generated up to `just our circumstances before us`. Then I set amount to generate to 128 to keep half of the text in context. This generated up to `A wise suggestion,`. I then lowered the amount to generate to 64. That generated up to the ending `know of our current situation?`. ``` <|characters|> Mrs. Samsa (The Metamorphosis): Female, middle-aged, ISFJ, German accent, compassionate mother struggling to cope with her son's transformation, and eventually succumbs to the family's financial and emotional burdens. <|scenario|> In a twist of fate, Mrs. Samsa finds herself transported back in time to time and space. Evangelist, who is on an isolated haven where he encounters Mrs. Samsa, by a different tale. Mrs. Samsa, still burdened by the weight of his past actions, must confront the difficult path ahead. Through their conversations, they find common ground in their own worlds, allowing them to continue seeking wisdom from each other and finding solace in one another's words. The dialogue between these two characters will offer insight into each other's worlds as well as how their experiences have shaped them in this whimsical world. <|response|> Mrs. Samsa: *approaches the peculiar sights around her, eyes widening in surprise* Oh dear, I couldn't help but notice you not! I've never seen my fair life, but I'm starting to see my son. Are you here in this peculiar place? Evangelist: *smiles warmly at Mrs. Samsa* Yes, we are indeed more than just our circumstances before us. And it is your place of wisdom and understanding. *opens the book, his eyes sparkling with excitement* Mrs. Samsa: *slowly opens a small book of the book* I must confess, Evangelist, I've never had a different view of this place. But it feels like this before our worlds find such things that we've discovered. Evangelist: *nods thoughtfully* You possess great wisdom, Mrs. Samsa. It seems we are both searching for a way to escape this peculiar library. Perhaps that is a sign of my spiritual journey towards you. Mrs. Samsa: *eyes widen in curiosity* A wise suggestion, Candide. I can't help but feel a sense of serenity amidst my own life. Evangelist: *smiles warmly* Of course, Mrs. Samsa. The path to enlightenment is filled with joy and understanding. Now, tell me more about this ancient book. What do you need to know of our current situation? ``` # Config: Learning rate may have been too high, not sure. Average loss at step 111,557 had an averge loss of 2.1. ``` batch_size: 1 dropout: 0 learning_rate: 0.0001 max_length: 256 n_embed: 256 n_head: 8 n_layer: 8 vocab_size: 8192 ```
amm297/my_awesome_peft_model
amm297
2023-06-28T14:48:41Z
24
0
peft
[ "peft", "RefinedWebModel", "generated_from_trainer", "text-generation", "custom_code", "license:other", "endpoints_compatible", "region:us" ]
text-generation
2023-06-28T10:55:56Z
--- license: other library_name: peft pipeline_tag: text-generation tags: - generated_from_trainer --- ## 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: False - bnb_4bit_compute_dtype: float16 ### Framework versions - PEFT 0.4.0.dev0 - Transformers 4.31.0.dev0 - Pytorch 2.0.1 - Datasets 2.13.0 - Tokenizers 0.13.3
nomad-ai/ppo-LunarLander-v2-2
nomad-ai
2023-06-28T14:36:41Z
0
0
null
[ "tensorboard", "LunarLander-v2", "ppo", "deep-reinforcement-learning", "reinforcement-learning", "custom-implementation", "deep-rl-course", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T14:36:36Z
--- tags: - LunarLander-v2 - ppo - deep-reinforcement-learning - reinforcement-learning - custom-implementation - deep-rl-course model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: -154.13 +/- 82.35 name: mean_reward verified: false --- # PPO Agent Playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2. # Hyperparameters ```python {'exp_name': 'ppo' 'seed': 1 'torch_deterministic': True 'cuda': True 'track': False 'wandb_project_name': 'cleanRL' 'wandb_entity': None 'capture_video': True 'env_id': 'LunarLander-v2' 'total_timesteps': 100000 'learning_rate': 0.00026 'num_envs': 8 'num_steps': 128 'anneal_lr': True 'gae': True 'gamma': 0.99 'gae_lambda': 0.95 'num_minibatches': 4 'update_epochs': 4 'norm_adv': True 'clip_coef': 0.1 'clip_vloss': True 'ent_coef': 0.1 'vf_coef': 0.5 'max_grad_norm': 0.5 'target_kl': None 'repo_id': 'nomad-ai/ppo-LunarLander-v2-2' 'batch_size': 1024 'minibatch_size': 256} ```
LarryAIDraw/AlchemyStarVice
LarryAIDraw
2023-06-28T14:33:56Z
0
0
null
[ "license:creativeml-openrail-m", "region:us" ]
null
2023-06-28T14:19:12Z
--- license: creativeml-openrail-m --- https://civitai.com/models/98406/vice-3-outfits-alchemy-stars-3
LarryAIDraw/TsunemoriAkaneV2_3
LarryAIDraw
2023-06-28T14:33:38Z
0
0
null
[ "license:creativeml-openrail-m", "region:us" ]
null
2023-06-28T14:18:48Z
--- license: creativeml-openrail-m --- https://civitai.com/models/16485/tsunemori-akane-psycho-pass
LarryAIDraw/KatoriKancolleV10
LarryAIDraw
2023-06-28T14:33:15Z
0
0
null
[ "license:creativeml-openrail-m", "region:us" ]
null
2023-06-28T14:15:04Z
--- license: creativeml-openrail-m --- https://civitai.com/models/98376/katori-kancolle-kantai-collection
LarryAIDraw/onodera_v2-11
LarryAIDraw
2023-06-28T14:32:51Z
0
0
null
[ "license:creativeml-openrail-m", "region:us" ]
null
2023-06-28T14:14:04Z
--- license: creativeml-openrail-m --- https://civitai.com/models/98354/onodera-kosaki-nisekoi
LarryAIDraw/yuiyuigahama
LarryAIDraw
2023-06-28T14:32:41Z
0
0
null
[ "license:creativeml-openrail-m", "region:us" ]
null
2023-06-28T14:13:41Z
--- license: creativeml-openrail-m --- https://civitai.com/models/98072/yui-yuigahama-my-youth-romantic-comedy-is-wrong-as-i-expected
aarroonn22/distilbert-base-uncased-finetuned-mlm-2
aarroonn22
2023-06-28T14:27:52Z
116
0
transformers
[ "transformers", "pytorch", "tensorboard", "distilbert", "fill-mask", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
fill-mask
2023-06-28T01:23:40Z
--- license: apache-2.0 tags: - generated_from_trainer model-index: - name: distilbert-base-uncased-finetuned-mlm-2 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. --> # distilbert-base-uncased-finetuned-mlm-2 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.2364 ## 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 | |:-------------:|:-----:|:-----:|:---------------:| | 0.2677 | 1.0 | 4123 | 0.2787 | | 0.2261 | 2.0 | 8246 | 0.2384 | | 0.1995 | 3.0 | 12369 | 0.2364 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
Ducco/LunarLander
Ducco
2023-06-28T14:23:28Z
1
0
stable-baselines3
[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T14:23:07Z
--- 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: 244.59 +/- 21.96 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 ... ```
gemengmeng/textual_inversion_cat
gemengmeng
2023-06-28T14:09:59Z
33
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
2023-06-28T12:40:17Z
--- 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 - gemengmeng/textual_inversion_cat These are textual inversion adaption weights for runwayml/stable-diffusion-v1-5. You can find some example images in the following.
avt1/tmp
avt1
2023-06-28T14:09:52Z
1
0
peft
[ "peft", "region:us" ]
null
2023-05-18T14:05:32Z
--- 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 ### Framework versions - PEFT 0.4.0.dev0
Geotrend/bert-base-ar-cased
Geotrend
2023-06-28T14:04:45Z
123
1
transformers
[ "transformers", "pytorch", "tf", "jax", "safetensors", "bert", "fill-mask", "ar", "dataset:wikipedia", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
fill-mask
2022-03-02T23:29:04Z
--- language: ar datasets: wikipedia license: apache-2.0 widget: - text: "تقع سويسرا في [MASK] أوروبا" - text: "إسمي محمد وأسكن في [MASK]." --- # bert-base-ar-cased We are sharing smaller versions of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) that handle a custom number of languages. Unlike [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased), our versions give exactly the same representations produced by the original model which preserves the original accuracy. For more information please visit our paper: [Load What You Need: Smaller Versions of Multilingual BERT](https://www.aclweb.org/anthology/2020.sustainlp-1.16.pdf). ## How to use ```python from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("Geotrend/bert-base-ar-cased") model = AutoModel.from_pretrained("Geotrend/bert-base-ar-cased") ``` To generate other smaller versions of multilingual transformers please visit [our Github repo](https://github.com/Geotrend-research/smaller-transformers). ### How to cite ```bibtex @inproceedings{smallermbert, title={Load What You Need: Smaller Versions of Mutlilingual BERT}, author={Abdaoui, Amine and Pradel, Camille and Sigel, Grégoire}, booktitle={SustaiNLP / EMNLP}, year={2020} } ``` ## Contact Please contact [email protected] for any question, feedback or request.
amm297/tmp_trainer
amm297
2023-06-28T14:02:26Z
79
0
transformers
[ "transformers", "pytorch", "opt", "text-generation", "generated_from_trainer", "license:other", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-06-28T13:52:52Z
--- license: other tags: - generated_from_trainer model-index: - name: tmp_trainer 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. --> # tmp_trainer This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on an unknown 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: 5e-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 ### Framework versions - Transformers 4.31.0.dev0 - Pytorch 2.0.1 - Datasets 2.13.0 - Tokenizers 0.13.3
openflamingo/OpenFlamingo-9B-deprecated
openflamingo
2023-06-28T14:00:05Z
0
108
null
[ "en", "dataset:laion2b", "region:us" ]
null
2023-03-19T23:13:26Z
--- language: en datasets: - laion2b --- # OpenFlamingo-9B (Deprecated) **This early checkpoint was part of an initial release. It has since been deprecated in favor of [other checkpoints](https://huggingface.co/openflamingo/OpenFlamingo-9B-vitl-mpt7b) as part of the OpenFlamingo v2 release. However, it is possible to continue using this older checkpoint in the new codebase.** ---- [Blog post](https://laion.ai/blog/open-flamingo/) | [Code](https://github.com/mlfoundations/open_flamingo) | [Demo](https://7164d2142d11.ngrok.app) OpenFlamingo is an open source implementation of DeepMind's [Flamingo](https://www.deepmind.com/blog/tackling-multiple-tasks-with-a-single-visual-language-model) models. OpenFlamingo-9B is built off of [CLIP ViT-L/14](https://huggingface.co/openai/clip-vit-large-patch14) and [LLaMA-7B](https://ai.facebook.com/blog/large-language-model-llama-meta-ai/). Before using this model please familiarize yourself with our [terms and conditions](https://github.com/mlfoundations/open_flamingo/blob/main/TERMS_AND_CONDITIONS.md). ## Model Details We freeze the pretrained vision encoder and language model, and then we train connecting Perceiver modules and cross-attention layers, following the original Flamingo paper. Our training data is a mixture of [LAION 2B](https://huggingface.co/datasets/laion/laion2B-en) and a large interleaved image-text dataset called Multimodal C4, which will be released soon. The current model is an early checkpoint of an ongoing effort. This checkpoint has seen 5 million interleaved image-text examples from Multimodal C4. ## Uses OpenFlamingo-9B is intended to be used **for academic research purposes only.** Commercial use is prohibited, in line with LLaMA's non-commercial license. ### Bias, Risks, and Limitations This model may generate inaccurate or offensive outputs, reflecting biases in its training data and pretrained priors. In an effort to mitigate current potential biases and harms, we have deployed a content filter on model outputs in the OpenFlamingo demo. We continue to red-team the model to understand and improve its safety. ## Evaluation We've evaluated this checkpoint and report validation performance for two vision-language tasks: COCO captioning and VQAv2. Results are displayed below. **COCO (CIDEr)** |0-shot|4-shot|8-shot|16-shot|32-shot| |--|--|--|--|--| |65.52|74.28|79.26|81.84|84.52| **VQAv2 (VQA accuracy)** |0-shot|4-shot|8-shot|16-shot|32-shot| |---|---|---|---|---| |43.55|44.05|47.5|48.87|50.34|
mnavas/bertmulti-finetuned-token-reqadjzar
mnavas
2023-06-28T13:52:18Z
64
0
transformers
[ "transformers", "pytorch", "tensorboard", "bert", "token-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
token-classification
2023-06-28T11:02:58Z
--- license: apache-2.0 tags: - generated_from_trainer metrics: - precision - recall - f1 - accuracy model-index: - name: bertmulti-finetuned-token-reqadjzar 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. --> # bertmulti-finetuned-token-reqadjzar 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: - Loss: 1.0215 - Precision: 0.3729 - Recall: 0.4783 - F1: 0.4190 - Accuracy: 0.8899 ## 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: 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: 200 ### Training results | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| | 0.71 | 1.0 | 24 | 0.6444 | 0.0 | 0.0 | 0.0 | 0.5695 | | 0.5158 | 2.0 | 48 | 0.7621 | 0.0 | 0.0 | 0.0 | 0.6544 | | 0.4702 | 3.0 | 72 | 0.4411 | 0.0 | 0.0 | 0.0 | 0.7961 | | 0.3326 | 4.0 | 96 | 0.6711 | 0.0 | 0.0 | 0.0 | 0.7482 | | 0.3134 | 5.0 | 120 | 0.4577 | 0.0 | 0.0 | 0.0 | 0.8160 | | 0.2036 | 6.0 | 144 | 0.7211 | 0.0266 | 0.1087 | 0.0427 | 0.7232 | | 0.1918 | 7.0 | 168 | 0.5596 | 0.0342 | 0.1087 | 0.0521 | 0.8284 | | 0.1388 | 8.0 | 192 | 0.6039 | 0.0539 | 0.1957 | 0.0845 | 0.8242 | | 0.1525 | 9.0 | 216 | 0.4642 | 0.0743 | 0.2391 | 0.1134 | 0.8436 | | 0.0965 | 10.0 | 240 | 0.4855 | 0.1241 | 0.3913 | 0.1885 | 0.8758 | | 0.0757 | 11.0 | 264 | 0.4353 | 0.0966 | 0.3043 | 0.1466 | 0.8543 | | 0.0689 | 12.0 | 288 | 1.5112 | 0.0963 | 0.2826 | 0.1436 | 0.6792 | | 0.1298 | 13.0 | 312 | 0.6653 | 0.1746 | 0.4783 | 0.2558 | 0.8430 | | 0.0656 | 14.0 | 336 | 0.6830 | 0.0935 | 0.2826 | 0.1405 | 0.8443 | | 0.041 | 15.0 | 360 | 0.6495 | 0.1231 | 0.3478 | 0.1818 | 0.8411 | | 0.039 | 16.0 | 384 | 0.5259 | 0.1377 | 0.4130 | 0.2065 | 0.8585 | | 0.031 | 17.0 | 408 | 0.6282 | 0.2054 | 0.5 | 0.2911 | 0.8479 | | 0.0615 | 18.0 | 432 | 0.6453 | 0.1959 | 0.4130 | 0.2657 | 0.8559 | | 0.0282 | 19.0 | 456 | 0.7038 | 0.1324 | 0.3913 | 0.1978 | 0.8462 | | 0.0204 | 20.0 | 480 | 0.5582 | 0.1759 | 0.4130 | 0.2468 | 0.8669 | | 0.0202 | 21.0 | 504 | 0.9386 | 0.1852 | 0.3261 | 0.2362 | 0.8224 | | 0.0255 | 22.0 | 528 | 0.8781 | 0.1714 | 0.3913 | 0.2384 | 0.7990 | | 0.0281 | 23.0 | 552 | 0.6537 | 0.1875 | 0.4565 | 0.2658 | 0.8833 | | 0.0303 | 24.0 | 576 | 0.6140 | 0.2319 | 0.3478 | 0.2783 | 0.8735 | | 0.0404 | 25.0 | 600 | 0.8073 | 0.2062 | 0.4348 | 0.2797 | 0.7813 | | 0.0378 | 26.0 | 624 | 0.7925 | 0.1852 | 0.4348 | 0.2597 | 0.8601 | | 0.0185 | 27.0 | 648 | 0.6131 | 0.1835 | 0.4348 | 0.2581 | 0.8879 | | 0.0217 | 28.0 | 672 | 0.8677 | 0.2347 | 0.5 | 0.3194 | 0.8151 | | 0.0147 | 29.0 | 696 | 0.6513 | 0.2 | 0.3913 | 0.2647 | 0.8622 | | 0.0228 | 30.0 | 720 | 0.8354 | 0.2787 | 0.3696 | 0.3178 | 0.8490 | | 0.0298 | 31.0 | 744 | 0.7063 | 0.1858 | 0.4565 | 0.2642 | 0.8858 | | 0.018 | 32.0 | 768 | 0.9348 | 0.3188 | 0.4783 | 0.3826 | 0.8688 | | 0.0179 | 33.0 | 792 | 0.7260 | 0.3014 | 0.4783 | 0.3697 | 0.8814 | | 0.0139 | 34.0 | 816 | 1.6266 | 0.2427 | 0.5435 | 0.3356 | 0.7781 | | 0.0435 | 35.0 | 840 | 0.5877 | 0.225 | 0.3913 | 0.2857 | 0.8827 | | 0.0172 | 36.0 | 864 | 0.9602 | 0.1545 | 0.4130 | 0.2249 | 0.8379 | | 0.02 | 37.0 | 888 | 0.7676 | 0.2473 | 0.5 | 0.3309 | 0.8696 | | 0.012 | 38.0 | 912 | 0.6857 | 0.2118 | 0.3913 | 0.2748 | 0.8836 | | 0.0088 | 39.0 | 936 | 0.8894 | 0.2857 | 0.5217 | 0.3692 | 0.8697 | | 0.0055 | 40.0 | 960 | 0.7700 | 0.2340 | 0.4783 | 0.3143 | 0.8678 | | 0.014 | 41.0 | 984 | 0.9191 | 0.2692 | 0.4565 | 0.3387 | 0.8396 | | 0.0061 | 42.0 | 1008 | 0.8042 | 0.2785 | 0.4783 | 0.352 | 0.8753 | | 0.0059 | 43.0 | 1032 | 1.0644 | 0.1959 | 0.4130 | 0.2657 | 0.8203 | | 0.0032 | 44.0 | 1056 | 1.1174 | 0.2949 | 0.5 | 0.3710 | 0.8242 | | 0.0057 | 45.0 | 1080 | 1.3623 | 0.2963 | 0.5217 | 0.3780 | 0.8346 | | 0.019 | 46.0 | 1104 | 1.0958 | 0.1932 | 0.3696 | 0.2537 | 0.8465 | | 0.0167 | 47.0 | 1128 | 0.9388 | 0.1848 | 0.3696 | 0.2464 | 0.8355 | | 0.0131 | 48.0 | 1152 | 1.2771 | 0.1826 | 0.4565 | 0.2609 | 0.7805 | | 0.0095 | 49.0 | 1176 | 1.0477 | 0.1944 | 0.4565 | 0.2727 | 0.8332 | | 0.0058 | 50.0 | 1200 | 0.9822 | 0.2941 | 0.5435 | 0.3817 | 0.8407 | | 0.0056 | 51.0 | 1224 | 1.1512 | 0.2360 | 0.4565 | 0.3111 | 0.8361 | | 0.0045 | 52.0 | 1248 | 0.8875 | 0.2468 | 0.4130 | 0.3089 | 0.8693 | | 0.0035 | 53.0 | 1272 | 0.9689 | 0.2346 | 0.4130 | 0.2992 | 0.8551 | | 0.0066 | 54.0 | 1296 | 0.9921 | 0.2299 | 0.4348 | 0.3008 | 0.8587 | | 0.0026 | 55.0 | 1320 | 0.8510 | 0.2817 | 0.4348 | 0.3419 | 0.8758 | | 0.0033 | 56.0 | 1344 | 0.9234 | 0.2115 | 0.4783 | 0.2933 | 0.8436 | | 0.0125 | 57.0 | 1368 | 1.0792 | 0.2308 | 0.3913 | 0.2903 | 0.8486 | | 0.0034 | 58.0 | 1392 | 1.1353 | 0.2609 | 0.5217 | 0.3478 | 0.8274 | | 0.0065 | 59.0 | 1416 | 1.3812 | 0.2738 | 0.5 | 0.3538 | 0.7993 | | 0.0082 | 60.0 | 1440 | 1.0929 | 0.2233 | 0.5 | 0.3087 | 0.8429 | | 0.0202 | 61.0 | 1464 | 0.9371 | 0.1709 | 0.4348 | 0.2454 | 0.8399 | | 0.0063 | 62.0 | 1488 | 0.6318 | 0.2099 | 0.3696 | 0.2677 | 0.8543 | | 0.0047 | 63.0 | 1512 | 0.8257 | 0.2018 | 0.5 | 0.2875 | 0.8514 | | 0.0036 | 64.0 | 1536 | 0.8545 | 0.1963 | 0.4565 | 0.2745 | 0.8484 | | 0.0027 | 65.0 | 1560 | 0.8684 | 0.2421 | 0.5 | 0.3262 | 0.8539 | | 0.002 | 66.0 | 1584 | 0.8609 | 0.25 | 0.5 | 0.3333 | 0.8630 | | 0.0022 | 67.0 | 1608 | 0.7618 | 0.2347 | 0.5 | 0.3194 | 0.8804 | | 0.0026 | 68.0 | 1632 | 0.8460 | 0.23 | 0.5 | 0.3151 | 0.8654 | | 0.0019 | 69.0 | 1656 | 0.7437 | 0.2857 | 0.5217 | 0.3692 | 0.8933 | | 0.0027 | 70.0 | 1680 | 0.7911 | 0.2727 | 0.4565 | 0.3415 | 0.8898 | | 0.0025 | 71.0 | 1704 | 0.8172 | 0.3333 | 0.4783 | 0.3929 | 0.8880 | | 0.0037 | 72.0 | 1728 | 0.7807 | 0.2680 | 0.5652 | 0.3636 | 0.8873 | | 0.0032 | 73.0 | 1752 | 0.9164 | 0.2683 | 0.4783 | 0.3438 | 0.8760 | | 0.0092 | 74.0 | 1776 | 0.6410 | 0.2976 | 0.5435 | 0.3846 | 0.8836 | | 0.0029 | 75.0 | 1800 | 0.7780 | 0.2857 | 0.5217 | 0.3692 | 0.8854 | | 0.0017 | 76.0 | 1824 | 0.9096 | 0.2683 | 0.4783 | 0.3438 | 0.8656 | | 0.0017 | 77.0 | 1848 | 0.8843 | 0.2911 | 0.5 | 0.368 | 0.8773 | | 0.0019 | 78.0 | 1872 | 0.7888 | 0.2410 | 0.4348 | 0.3101 | 0.8613 | | 0.0032 | 79.0 | 1896 | 0.9426 | 0.2241 | 0.5652 | 0.3210 | 0.8490 | | 0.0019 | 80.0 | 1920 | 0.9566 | 0.25 | 0.3913 | 0.3051 | 0.8708 | | 0.0017 | 81.0 | 1944 | 1.0507 | 0.2588 | 0.4783 | 0.3359 | 0.8669 | | 0.0015 | 82.0 | 1968 | 1.1118 | 0.2174 | 0.4348 | 0.2899 | 0.8614 | | 0.0014 | 83.0 | 1992 | 1.1422 | 0.2299 | 0.4348 | 0.3008 | 0.8548 | | 0.0015 | 84.0 | 2016 | 1.1422 | 0.2716 | 0.4783 | 0.3465 | 0.8556 | | 0.0013 | 85.0 | 2040 | 1.0874 | 0.2371 | 0.5 | 0.3217 | 0.8557 | | 0.0015 | 86.0 | 2064 | 1.0420 | 0.2277 | 0.5 | 0.3129 | 0.8624 | | 0.0013 | 87.0 | 2088 | 1.0851 | 0.2418 | 0.4783 | 0.3212 | 0.8579 | | 0.0015 | 88.0 | 2112 | 1.1249 | 0.2556 | 0.5 | 0.3382 | 0.8622 | | 0.0015 | 89.0 | 2136 | 1.0589 | 0.2667 | 0.5217 | 0.3529 | 0.8617 | | 0.0014 | 90.0 | 2160 | 1.0879 | 0.2674 | 0.5 | 0.3485 | 0.8497 | | 0.0019 | 91.0 | 2184 | 1.0425 | 0.2651 | 0.4783 | 0.3411 | 0.8551 | | 0.0015 | 92.0 | 2208 | 1.0137 | 0.2716 | 0.4783 | 0.3465 | 0.8579 | | 0.0015 | 93.0 | 2232 | 1.0084 | 0.2716 | 0.4783 | 0.3465 | 0.8619 | | 0.0015 | 94.0 | 2256 | 1.0231 | 0.2727 | 0.5217 | 0.3582 | 0.8529 | | 0.0014 | 95.0 | 2280 | 1.1031 | 0.3067 | 0.5 | 0.3802 | 0.8522 | | 0.0014 | 96.0 | 2304 | 1.0001 | 0.2796 | 0.5652 | 0.3741 | 0.8642 | | 0.0012 | 97.0 | 2328 | 1.0274 | 0.3253 | 0.5870 | 0.4186 | 0.8683 | | 0.0015 | 98.0 | 2352 | 1.1420 | 0.3559 | 0.4565 | 0.4000 | 0.8579 | | 0.0154 | 99.0 | 2376 | 0.8248 | 0.4706 | 0.5217 | 0.4948 | 0.8894 | | 0.0041 | 100.0 | 2400 | 0.8580 | 0.2892 | 0.5217 | 0.3721 | 0.8768 | | 0.0046 | 101.0 | 2424 | 1.0790 | 0.1792 | 0.4130 | 0.25 | 0.8623 | | 0.0021 | 102.0 | 2448 | 1.0016 | 0.25 | 0.4348 | 0.3175 | 0.8766 | | 0.0028 | 103.0 | 2472 | 0.8267 | 0.2899 | 0.4348 | 0.3478 | 0.8907 | | 0.0026 | 104.0 | 2496 | 1.1740 | 0.2212 | 0.5 | 0.3067 | 0.8511 | | 0.0018 | 105.0 | 2520 | 1.2264 | 0.1759 | 0.4130 | 0.2468 | 0.8389 | | 0.0017 | 106.0 | 2544 | 1.1772 | 0.2451 | 0.5435 | 0.3378 | 0.8468 | | 0.0014 | 107.0 | 2568 | 1.2155 | 0.2556 | 0.5 | 0.3382 | 0.8386 | | 0.0018 | 108.0 | 2592 | 1.1990 | 0.2558 | 0.4783 | 0.3333 | 0.8411 | | 0.0022 | 109.0 | 2616 | 1.0769 | 0.3425 | 0.5435 | 0.4202 | 0.8679 | | 0.0016 | 110.0 | 2640 | 1.0793 | 0.3538 | 0.5 | 0.4144 | 0.8629 | | 0.0019 | 111.0 | 2664 | 0.8828 | 0.2680 | 0.5652 | 0.3636 | 0.8823 | | 0.0014 | 112.0 | 2688 | 1.0073 | 0.3548 | 0.4783 | 0.4074 | 0.8810 | | 0.0016 | 113.0 | 2712 | 0.9562 | 0.3667 | 0.4783 | 0.4151 | 0.8827 | | 0.0014 | 114.0 | 2736 | 0.9590 | 0.3438 | 0.4783 | 0.4 | 0.8802 | | 0.0014 | 115.0 | 2760 | 1.0293 | 0.4 | 0.5217 | 0.4528 | 0.8814 | | 0.0014 | 116.0 | 2784 | 1.0419 | 0.4068 | 0.5217 | 0.4571 | 0.8804 | | 0.0012 | 117.0 | 2808 | 1.0451 | 0.4138 | 0.5217 | 0.4615 | 0.8805 | | 0.005 | 118.0 | 2832 | 1.0514 | 0.4068 | 0.5217 | 0.4571 | 0.8803 | | 0.0019 | 119.0 | 2856 | 1.0440 | 0.4068 | 0.5217 | 0.4571 | 0.8805 | | 0.0015 | 120.0 | 2880 | 1.0782 | 0.4 | 0.5217 | 0.4528 | 0.8768 | | 0.0015 | 121.0 | 2904 | 1.0736 | 0.4211 | 0.5217 | 0.4660 | 0.8765 | | 0.0014 | 122.0 | 2928 | 1.0565 | 0.3934 | 0.5217 | 0.4486 | 0.8776 | | 0.0013 | 123.0 | 2952 | 1.0496 | 0.4444 | 0.5217 | 0.48 | 0.8814 | | 0.0012 | 124.0 | 2976 | 1.0805 | 0.4286 | 0.5217 | 0.4706 | 0.8805 | | 0.0012 | 125.0 | 3000 | 1.1119 | 0.4211 | 0.5217 | 0.4660 | 0.8809 | | 0.0013 | 126.0 | 3024 | 1.0880 | 0.4528 | 0.5217 | 0.4848 | 0.8812 | | 0.0014 | 127.0 | 3048 | 1.0198 | 0.3729 | 0.4783 | 0.4190 | 0.8796 | | 0.0013 | 128.0 | 3072 | 1.0028 | 0.4 | 0.5217 | 0.4528 | 0.8790 | | 0.0014 | 129.0 | 3096 | 1.0229 | 0.3529 | 0.5217 | 0.4211 | 0.8835 | | 0.0013 | 130.0 | 3120 | 1.0440 | 0.3380 | 0.5217 | 0.4103 | 0.8747 | | 0.0013 | 131.0 | 3144 | 1.1109 | 0.4615 | 0.5217 | 0.4898 | 0.8781 | | 0.0012 | 132.0 | 3168 | 1.1082 | 0.4706 | 0.5217 | 0.4948 | 0.8812 | | 0.0013 | 133.0 | 3192 | 1.1031 | 0.4444 | 0.5217 | 0.48 | 0.8806 | | 0.0011 | 134.0 | 3216 | 1.1345 | 0.3529 | 0.5217 | 0.4211 | 0.8713 | | 0.0012 | 135.0 | 3240 | 1.1631 | 0.3485 | 0.5 | 0.4107 | 0.8716 | | 0.0012 | 136.0 | 3264 | 1.1461 | 0.3429 | 0.5217 | 0.4138 | 0.8708 | | 0.0012 | 137.0 | 3288 | 1.1592 | 0.4138 | 0.5217 | 0.4615 | 0.8683 | | 0.0012 | 138.0 | 3312 | 1.0969 | 0.4138 | 0.5217 | 0.4615 | 0.8754 | | 0.0013 | 139.0 | 3336 | 1.0575 | 0.3429 | 0.5217 | 0.4138 | 0.8787 | | 0.0013 | 140.0 | 3360 | 1.0560 | 0.3636 | 0.5217 | 0.4286 | 0.8826 | | 0.0013 | 141.0 | 3384 | 1.0525 | 0.3380 | 0.5217 | 0.4103 | 0.8796 | | 0.0011 | 142.0 | 3408 | 1.0548 | 0.3380 | 0.5217 | 0.4103 | 0.8792 | | 0.0013 | 143.0 | 3432 | 1.0593 | 0.3478 | 0.5217 | 0.4174 | 0.8802 | | 0.0012 | 144.0 | 3456 | 1.0402 | 0.375 | 0.5217 | 0.4364 | 0.8827 | | 0.0011 | 145.0 | 3480 | 1.0401 | 0.375 | 0.5217 | 0.4364 | 0.8828 | | 0.0012 | 146.0 | 3504 | 1.0319 | 0.3810 | 0.5217 | 0.4404 | 0.8840 | | 0.0012 | 147.0 | 3528 | 1.0328 | 0.3692 | 0.5217 | 0.4324 | 0.8838 | | 0.0012 | 148.0 | 3552 | 1.1021 | 0.3433 | 0.5 | 0.4071 | 0.8730 | | 0.0012 | 149.0 | 3576 | 1.0402 | 0.3485 | 0.5 | 0.4107 | 0.8817 | | 0.0013 | 150.0 | 3600 | 0.9619 | 0.3086 | 0.5435 | 0.3937 | 0.8883 | | 0.0014 | 151.0 | 3624 | 0.9578 | 0.3382 | 0.5 | 0.4035 | 0.8843 | | 0.0012 | 152.0 | 3648 | 1.0303 | 0.3692 | 0.5217 | 0.4324 | 0.8830 | | 0.0013 | 153.0 | 3672 | 1.0571 | 0.3934 | 0.5217 | 0.4486 | 0.8812 | | 0.0012 | 154.0 | 3696 | 1.0793 | 0.3692 | 0.5217 | 0.4324 | 0.8812 | | 0.0011 | 155.0 | 3720 | 1.0766 | 0.375 | 0.5217 | 0.4364 | 0.8803 | | 0.0011 | 156.0 | 3744 | 1.0824 | 0.3934 | 0.5217 | 0.4486 | 0.8810 | | 0.0012 | 157.0 | 3768 | 1.0841 | 0.4 | 0.5217 | 0.4528 | 0.8810 | | 0.0011 | 158.0 | 3792 | 1.0866 | 0.4068 | 0.5217 | 0.4571 | 0.8812 | | 0.0012 | 159.0 | 3816 | 1.1016 | 0.4 | 0.5217 | 0.4528 | 0.8808 | | 0.0011 | 160.0 | 3840 | 1.1114 | 0.3810 | 0.5217 | 0.4404 | 0.8793 | | 0.0013 | 161.0 | 3864 | 1.1427 | 0.2892 | 0.5217 | 0.3721 | 0.8577 | | 0.0011 | 162.0 | 3888 | 1.0292 | 0.3582 | 0.5217 | 0.4248 | 0.8875 | | 0.0012 | 163.0 | 3912 | 0.9894 | 0.375 | 0.5217 | 0.4364 | 0.8872 | | 0.0011 | 164.0 | 3936 | 0.9877 | 0.3636 | 0.5217 | 0.4286 | 0.8870 | | 0.0011 | 165.0 | 3960 | 0.9887 | 0.3692 | 0.5217 | 0.4324 | 0.8890 | | 0.0012 | 166.0 | 3984 | 0.9874 | 0.3243 | 0.5217 | 0.4 | 0.8871 | | 0.0011 | 167.0 | 4008 | 0.9992 | 0.3636 | 0.5217 | 0.4286 | 0.8896 | | 0.0012 | 168.0 | 4032 | 0.9835 | 0.3692 | 0.5217 | 0.4324 | 0.8903 | | 0.0011 | 169.0 | 4056 | 0.9918 | 0.3284 | 0.4783 | 0.3894 | 0.8910 | | 0.0011 | 170.0 | 4080 | 0.9960 | 0.3438 | 0.4783 | 0.4 | 0.8914 | | 0.0011 | 171.0 | 4104 | 1.0065 | 0.3729 | 0.4783 | 0.4190 | 0.8915 | | 0.0012 | 172.0 | 4128 | 1.0266 | 0.3929 | 0.4783 | 0.4314 | 0.8908 | | 0.0011 | 173.0 | 4152 | 1.0318 | 0.3929 | 0.4783 | 0.4314 | 0.8908 | | 0.0011 | 174.0 | 4176 | 1.0329 | 0.3793 | 0.4783 | 0.4231 | 0.8908 | | 0.0012 | 175.0 | 4200 | 1.0254 | 0.3860 | 0.4783 | 0.4272 | 0.8910 | | 0.0011 | 176.0 | 4224 | 1.0183 | 0.4 | 0.4783 | 0.4356 | 0.8912 | | 0.0012 | 177.0 | 4248 | 1.0205 | 0.3860 | 0.4783 | 0.4272 | 0.8909 | | 0.0011 | 178.0 | 4272 | 1.0232 | 0.3793 | 0.4783 | 0.4231 | 0.8908 | | 0.0011 | 179.0 | 4296 | 1.0246 | 0.3860 | 0.4783 | 0.4272 | 0.8908 | | 0.0012 | 180.0 | 4320 | 1.0245 | 0.3793 | 0.4783 | 0.4231 | 0.8905 | | 0.0012 | 181.0 | 4344 | 1.0223 | 0.375 | 0.4565 | 0.4118 | 0.8902 | | 0.0011 | 182.0 | 4368 | 1.0169 | 0.3929 | 0.4783 | 0.4314 | 0.8894 | | 0.0011 | 183.0 | 4392 | 1.0172 | 0.3929 | 0.4783 | 0.4314 | 0.8893 | | 0.0012 | 184.0 | 4416 | 1.0147 | 0.3860 | 0.4783 | 0.4272 | 0.8894 | | 0.0012 | 185.0 | 4440 | 1.0145 | 0.3860 | 0.4783 | 0.4272 | 0.8894 | | 0.0011 | 186.0 | 4464 | 1.0128 | 0.3729 | 0.4783 | 0.4190 | 0.8897 | | 0.0011 | 187.0 | 4488 | 1.0146 | 0.3729 | 0.4783 | 0.4190 | 0.8897 | | 0.0011 | 188.0 | 4512 | 1.0160 | 0.3729 | 0.4783 | 0.4190 | 0.8897 | | 0.0011 | 189.0 | 4536 | 1.0178 | 0.3729 | 0.4783 | 0.4190 | 0.8898 | | 0.0011 | 190.0 | 4560 | 1.0185 | 0.3729 | 0.4783 | 0.4190 | 0.8898 | | 0.0011 | 191.0 | 4584 | 1.0171 | 0.3793 | 0.4783 | 0.4231 | 0.8899 | | 0.0011 | 192.0 | 4608 | 1.0179 | 0.3729 | 0.4783 | 0.4190 | 0.8898 | | 0.0011 | 193.0 | 4632 | 1.0196 | 0.3793 | 0.4783 | 0.4231 | 0.8899 | | 0.0012 | 194.0 | 4656 | 1.0188 | 0.3793 | 0.4783 | 0.4231 | 0.8899 | | 0.0011 | 195.0 | 4680 | 1.0185 | 0.3793 | 0.4783 | 0.4231 | 0.8899 | | 0.0011 | 196.0 | 4704 | 1.0194 | 0.3860 | 0.4783 | 0.4272 | 0.8898 | | 0.0011 | 197.0 | 4728 | 1.0206 | 0.3729 | 0.4783 | 0.4190 | 0.8900 | | 0.0011 | 198.0 | 4752 | 1.0207 | 0.3729 | 0.4783 | 0.4190 | 0.8900 | | 0.0012 | 199.0 | 4776 | 1.0215 | 0.3729 | 0.4783 | 0.4190 | 0.8899 | | 0.0011 | 200.0 | 4800 | 1.0215 | 0.3729 | 0.4783 | 0.4190 | 0.8899 | ### Framework versions - Transformers 4.31.0.dev0 - Pytorch 2.0.0 - Datasets 2.1.0 - Tokenizers 0.13.3
StefanV28/HandSigns
StefanV28
2023-06-28T13:52:10Z
5
0
tf-keras
[ "tf-keras", "mobilenet", "image-classification", "region:us" ]
image-classification
2023-06-25T21:10:37Z
--- pipeline_tag: image-classification ---
InriaValda/cc_math_roberta_ep01
InriaValda
2023-06-28T13:49:10Z
71
0
transformers
[ "transformers", "tf", "roberta", "text-classification", "fill-mask", "license:openrail", "autotrain_compatible", "endpoints_compatible", "region:us" ]
fill-mask
2023-06-28T13:16:33Z
--- license: openrail pipeline_tag: fill-mask ---
SHENMU007/neunit_BASE_V10.11
SHENMU007
2023-06-28T13:47:53Z
75
0
transformers
[ "transformers", "pytorch", "tensorboard", "speecht5", "text-to-audio", "1.1.0", "generated_from_trainer", "zh", "dataset:facebook/voxpopuli", "license:mit", "endpoints_compatible", "region:us" ]
text-to-audio
2023-06-28T10:49:37Z
--- language: - zh license: mit 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 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.29.2 - Pytorch 2.0.1+cu117 - Datasets 2.12.0 - Tokenizers 0.13.3
YakovElm/Hyperledger_20_BERT_Over_Sampling
YakovElm
2023-06-28T13:44:48Z
61
0
transformers
[ "transformers", "tf", "bert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-28T13:44:12Z
--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: Hyperledger_20_BERT_Over_Sampling 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. --> # Hyperledger_20_BERT_Over_Sampling This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 0.0420 - Train Accuracy: 0.9866 - Validation Loss: 0.7502 - Validation Accuracy: 0.8444 - 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': 1.0, '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch | |:----------:|:--------------:|:---------------:|:-------------------:|:-----:| | 0.4566 | 0.7724 | 0.5710 | 0.7376 | 0 | | 0.0873 | 0.9735 | 0.6176 | 0.8662 | 1 | | 0.0420 | 0.9866 | 0.7502 | 0.8444 | 2 | ### Framework versions - Transformers 4.29.2 - TensorFlow 2.12.0 - Datasets 2.12.0 - Tokenizers 0.13.3
atharputra/ivanaxx1
atharputra
2023-06-28T13:41:28Z
0
0
null
[ "license:creativeml-openrail-m", "region:us" ]
null
2023-06-28T13:39:21Z
--- license: creativeml-openrail-m ---
ade93/my_awesome_qa_model
ade93
2023-06-28T13:40:06Z
61
0
transformers
[ "transformers", "tf", "distilbert", "question-answering", "generated_from_keras_callback", "license:apache-2.0", "endpoints_compatible", "region:us" ]
question-answering
2023-06-26T08:49:44Z
--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: ade93/my_awesome_qa_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. --> # ade93/my_awesome_qa_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: -0.7813 - Validation Loss: -1.7044 - 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': 20, '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 | Epoch | |:----------:|:---------------:|:-----:| | -0.7813 | -1.7044 | 0 | ### Framework versions - Transformers 4.30.2 - TensorFlow 2.12.0 - Datasets 2.13.1 - Tokenizers 0.13.3
robrecht/space-invader-v1
robrecht
2023-06-28T13:28:25Z
2
0
stable-baselines3
[ "stable-baselines3", "SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T13:27:56Z
--- 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: 29.00 +/- 64.30 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 robrecht -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 robrecht -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 robrecht ``` ## 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', 1000.0), ('optimize_memory_usage', False), ('policy', 'CnnPolicy'), ('target_update_interval', 1000), ('train_freq', 4), ('normalize', False)]) ``` # Environment Arguments ```python {'render_mode': 'rgb_array'} ```
sleepynlp/q-Taxi-v3-v1-leo
sleepynlp
2023-06-28T13:26:47Z
0
0
null
[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T13:26:43Z
--- tags: - Taxi-v3 - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-Taxi-v3-v1-leo 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 ```python model = load_from_hub(repo_id="sleepynlp/q-Taxi-v3-v1-leo", 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"]) ```
dev-senolys/camembert_base_finetunned_one_thema_balanced_6_epochs
dev-senolys
2023-06-28T13:22:20Z
105
0
transformers
[ "transformers", "pytorch", "tensorboard", "camembert", "text-classification", "generated_from_trainer", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-28T11:52:40Z
--- license: mit tags: - generated_from_trainer model-index: - name: camembert_base_finetunned_one_thema_balanced_6_epochs 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. --> # camembert_base_finetunned_one_thema_balanced_6_epochs This model is a fine-tuned version of [camembert-base](https://huggingface.co/camembert-base) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.7237 ## 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: 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: 6 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | No log | 1.0 | 116 | 2.3397 | | No log | 2.0 | 232 | 2.0559 | | No log | 3.0 | 348 | 1.8209 | | No log | 4.0 | 464 | 1.7804 | | 1.9817 | 5.0 | 580 | 1.7323 | | 1.9817 | 6.0 | 696 | 1.7237 | ### Framework versions - Transformers 4.29.2 - Pytorch 2.0.1+cu117 - Datasets 2.12.0 - Tokenizers 0.13.3
sleepynlp/q-FrozenLake-v1-4x4-noSlippery-leo
sleepynlp
2023-06-28T13:20:09Z
0
0
null
[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T13:20:05Z
--- tags: - FrozenLake-v1-4x4-no_slippery - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-FrozenLake-v1-4x4-noSlippery-leo results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: FrozenLake-v1-4x4-no_slippery type: FrozenLake-v1-4x4-no_slippery metrics: - type: mean_reward value: 1.00 +/- 0.00 name: mean_reward verified: false --- # **Q-Learning** Agent playing1 **FrozenLake-v1** This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** . ## Usage ```python model = load_from_hub(repo_id="sleepynlp/q-FrozenLake-v1-4x4-noSlippery-leo", 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"]) ```
ZhangJiaxing/path-to-save-model
ZhangJiaxing
2023-06-28T12:59:07Z
29
0
diffusers
[ "diffusers", "tensorboard", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "dreambooth", "base_model:CompVis/stable-diffusion-v1-4", "base_model:finetune:CompVis/stable-diffusion-v1-4", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]
text-to-image
2023-06-28T12:21:01Z
--- license: creativeml-openrail-m base_model: CompVis/stable-diffusion-v1-4 instance_prompt: a photo of sks dog tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers - dreambooth inference: true --- # DreamBooth - ZhangJiaxing/path-to-save-model This is a dreambooth model derived from CompVis/stable-diffusion-v1-4. The weights were trained on a photo of sks dog using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following. DreamBooth for the text encoder was enabled: False.
catrabbitbear/pyramids2
catrabbitbear
2023-06-28T12:51:21Z
3
0
ml-agents
[ "ml-agents", "tensorboard", "onnx", "Pyramids", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Pyramids", "region:us" ]
reinforcement-learning
2023-06-28T12:51:20Z
--- 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: catrabbitbear/pyramids2 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀
jensvw/taxi-v3
jensvw
2023-06-28T12:47:36Z
0
0
null
[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T12:47:32Z
--- tags: - Taxi-v3 - q-learning - reinforcement-learning - custom-implementation model-index: - name: taxi-v3 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Taxi-v3 type: Taxi-v3 metrics: - type: mean_reward value: 7.54 +/- 2.73 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 ```python model = load_from_hub(repo_id="jensvw/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"]) ```
jensvw/q-FrozenLake-v1-4x4-noSlippery
jensvw
2023-06-28T12:38:03Z
0
0
null
[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T12:37:59Z
--- tags: - FrozenLake-v1-4x4-no_slippery - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-FrozenLake-v1-4x4-noSlippery results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: FrozenLake-v1-4x4-no_slippery type: FrozenLake-v1-4x4-no_slippery metrics: - type: mean_reward value: 1.00 +/- 0.00 name: mean_reward verified: false --- # **Q-Learning** Agent playing1 **FrozenLake-v1** This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** . ## Usage ```python model = load_from_hub(repo_id="jensvw/q-FrozenLake-v1-4x4-noSlippery", 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"]) ```
lordpepe/ppo-LunarLander-v2
lordpepe
2023-06-28T12:36:31Z
1
0
stable-baselines3
[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T12:36:07Z
--- 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: 252.07 +/- 15.38 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 ... ```
Raizel123/Vbabylora
Raizel123
2023-06-28T12:25:37Z
0
0
null
[ "license:creativeml-openrail-m", "region:us" ]
null
2023-06-28T12:22:00Z
--- license: creativeml-openrail-m ---
Narsil/amall-7b
Narsil
2023-06-28T12:05:23Z
30
1
transformers
[ "transformers", "pytorch", "safetensors", "llama", "text-generation", "license:other", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-06-26T08:11:43Z
--- license: other duplicated_from: huggingface/llama-7b ---
NickyNicky/MPT-7b-instruct-QLora-8Bits-Peft-h2ogpt_oig_oasst1_instruct_cleaned_v3-0.2_Epoch-V1
NickyNicky
2023-06-28T11:48:19Z
1
0
peft
[ "peft", "region:us" ]
null
2023-06-28T11:48:16Z
--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.4.0.dev0
czz23/SplitStatement-setfit-model
czz23
2023-06-28T11:47:11Z
3
0
sentence-transformers
[ "sentence-transformers", "pytorch", "albert", "setfit", "text-classification", "arxiv:2209.11055", "license:apache-2.0", "region:us" ]
text-classification
2023-06-28T11:47:08Z
--- license: apache-2.0 tags: - setfit - sentence-transformers - text-classification pipeline_tag: text-classification --- # czz23/SplitStatement-setfit-model This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves: 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning. 2. Training a classification head with features from the fine-tuned Sentence Transformer. ## Usage To use this model for inference, first install the SetFit library: ```bash python -m pip install setfit ``` You can then run inference as follows: ```python from setfit import SetFitModel # Download from Hub and run inference model = SetFitModel.from_pretrained("czz23/SplitStatement-setfit-model") # Run inference preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"]) ``` ## BibTeX entry and citation info ```bibtex @article{https://doi.org/10.48550/arxiv.2209.11055, doi = {10.48550/ARXIV.2209.11055}, url = {https://arxiv.org/abs/2209.11055}, author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren}, keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences}, title = {Efficient Few-Shot Learning Without Prompts}, publisher = {arXiv}, year = {2022}, copyright = {Creative Commons Attribution 4.0 International} } ```
RayTracerGC/RVCModels
RayTracerGC
2023-06-28T11:46:11Z
0
1
null
[ "license:openrail", "region:us" ]
null
2023-06-27T15:56:50Z
--- license: openrail --- RVC models: - Hal Jordan Green Lantern (From Injustice 2) (RVC v2) (76 Epochs) - Trained on `mangio-crepe` using 6 minutes of audio - Batch size: 16 - Crepe hop length: 64 - File: GreenLantern.zip - Wonder Woman (From Injustice 2) (RVC v2) (150 Epochs) - Trained on `mangio-crepe` using 9 minutes of audio - Batch size: 16 - Crepe hop length: 64 - File: WonderWoman.zip
BerserkerMother/Reinforce-Pixelcopter-PLE-v0
BerserkerMother
2023-06-28T11:45:36Z
0
0
null
[ "Pixelcopter-PLE-v0", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T11:45:35Z
--- tags: - Pixelcopter-PLE-v0 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: Reinforce-Pixelcopter-PLE-v0 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Pixelcopter-PLE-v0 type: Pixelcopter-PLE-v0 metrics: - type: mean_reward value: 11.90 +/- 8.77 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
YakovElm/Hyperledger_15_BERT_Over_Sampling
YakovElm
2023-06-28T11:44:13Z
58
0
transformers
[ "transformers", "tf", "bert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-28T11:43:37Z
--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: Hyperledger_15_BERT_Over_Sampling 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. --> # Hyperledger_15_BERT_Over_Sampling This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 0.0278 - Train Accuracy: 0.9920 - Validation Loss: 0.8934 - Validation Accuracy: 0.8278 - 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': 1.0, '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch | |:----------:|:--------------:|:---------------:|:-------------------:|:-----:| | 0.4883 | 0.7456 | 0.5933 | 0.7749 | 0 | | 0.1029 | 0.9652 | 0.7254 | 0.8683 | 1 | | 0.0278 | 0.9920 | 0.8934 | 0.8278 | 2 | ### Framework versions - Transformers 4.29.2 - TensorFlow 2.12.0 - Datasets 2.12.0 - Tokenizers 0.13.3
YakovElm/Qt_15_BERT_Under_Sampling
YakovElm
2023-06-28T11:35:53Z
61
0
transformers
[ "transformers", "tf", "bert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-28T11:35:18Z
--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: Qt_15_BERT_Under_Sampling 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. --> # Qt_15_BERT_Under_Sampling This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 0.0002 - Train Accuracy: 1.0 - Validation Loss: 0.4444 - Validation Accuracy: 0.9505 - 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': 1.0, '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch | |:----------:|:--------------:|:---------------:|:-------------------:|:-----:| | 0.0261 | 0.9997 | 0.3635 | 0.9505 | 0 | | 0.0005 | 1.0 | 0.4156 | 0.9505 | 1 | | 0.0002 | 1.0 | 0.4444 | 0.9505 | 2 | ### Framework versions - Transformers 4.29.2 - TensorFlow 2.12.0 - Datasets 2.12.0 - Tokenizers 0.13.3
wyklq/falcon-40b-gptq
wyklq
2023-06-28T11:08:48Z
9
2
transformers
[ "transformers", "safetensors", "RefinedWeb", "text-generation", "custom_code", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-06-28T10:58:03Z
Strict copy of https://huggingface.co/tiiuae/falcon-40b but quantized with GPTQ (on wikitext-2, 4bits, groupsize=128). Intended to be used with https://github.com/huggingface/text-generation-inference ``` model=huggingface/falcon-40b-gptq num_shard=2 volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:0.8 --model-id $model --num-shard $num_shard --quantize gptq ``` For full configuration and usage outside docker, please refer to https://github.com/huggingface/text-generation-inference
robrecht/ppo-Huggy
robrecht
2023-06-28T11:08:26Z
11
0
ml-agents
[ "ml-agents", "tensorboard", "onnx", "Huggy", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Huggy", "region:us" ]
reinforcement-learning
2023-06-28T09:32:24Z
--- 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: robrecht/ppo-Huggy 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀
NickyNicky/MPT-7b-instruct-QLora-8Bits-Peft-train_eli5-1_Epoch-V7
NickyNicky
2023-06-28T10:50:38Z
5
0
peft
[ "peft", "region:us" ]
null
2023-06-28T10:50:35Z
--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.4.0.dev0
Shubham09/falcon_p3
Shubham09
2023-06-28T10:41:25Z
6
0
peft
[ "peft", "region:us" ]
null
2023-06-28T10:32:49Z
--- 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: False - bnb_4bit_compute_dtype: float16 ### Framework versions - PEFT 0.4.0.dev0
NickyNicky/MPT-7b-instruct-QLora-8Bits-Peft-train_eli5-1_Epoch-V6
NickyNicky
2023-06-28T10:35:33Z
0
0
peft
[ "peft", "region:us" ]
null
2023-06-28T10:35:29Z
--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.4.0.dev0
BaoKien/albert_squadv2
BaoKien
2023-06-28T10:34:57Z
106
0
transformers
[ "transformers", "pytorch", "tensorboard", "albert", "question-answering", "generated_from_trainer", "dataset:squad_v2", "license:apache-2.0", "endpoints_compatible", "region:us" ]
question-answering
2023-06-28T09:52:52Z
--- license: apache-2.0 tags: - generated_from_trainer datasets: - squad_v2 model-index: - name: albert_squadv2 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. --> # albert_squadv2 This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the squad_v2 dataset. It achieves the following results on the evaluation set: - Loss: 4.1889 ## 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 | |:-------------:|:-----:|:----:|:---------------:| | No log | 1.0 | 5 | 4.7365 | | No log | 2.0 | 10 | 4.3391 | | No log | 3.0 | 15 | 4.1889 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
mnavas/bert-finetuned-token-reqsolvgencat
mnavas
2023-06-28T10:34:36Z
5
0
transformers
[ "transformers", "pytorch", "tensorboard", "bert", "token-classification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
token-classification
2023-06-28T09:43:30Z
--- license: apache-2.0 tags: - generated_from_trainer metrics: - precision - recall - f1 - accuracy model-index: - name: beto-finetuned-token-reqsolvgencat 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. --> # beto-finetuned-token-reqsolvgencat 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: - Loss: 2.0573 - Precision: 0.1111 - Recall: 0.5 - F1: 0.1818 - Accuracy: 0.7765 ## 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: 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: 200 ### Training results | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| | 0.8551 | 1.0 | 3 | 1.1478 | 0.0 | 0.0 | 0.0 | 0.4696 | | 1.4354 | 2.0 | 6 | 0.7403 | 0.0 | 0.0 | 0.0 | 0.6088 | | 0.6532 | 3.0 | 9 | 0.6900 | 0.0 | 0.0 | 0.0 | 0.6010 | | 0.406 | 4.0 | 12 | 2.0318 | 0.0 | 0.0 | 0.0 | 0.5284 | | 1.3514 | 5.0 | 15 | 1.3364 | 0.0 | 0.0 | 0.0 | 0.6186 | | 0.419 | 6.0 | 18 | 0.9463 | 0.0 | 0.0 | 0.0 | 0.6 | | 0.4816 | 7.0 | 21 | 0.9409 | 0.0 | 0.0 | 0.0 | 0.6314 | | 0.8621 | 8.0 | 24 | 0.9034 | 0.0 | 0.0 | 0.0 | 0.7010 | | 0.2981 | 9.0 | 27 | 0.9617 | 0.0 | 0.0 | 0.0 | 0.6039 | | 0.5882 | 10.0 | 30 | 0.5289 | 0.0 | 0.0 | 0.0 | 0.8 | | 0.4327 | 11.0 | 33 | 0.6573 | 0.2 | 0.5 | 0.2857 | 0.7882 | | 0.2076 | 12.0 | 36 | 0.9207 | 0.0 | 0.0 | 0.0 | 0.6784 | | 0.1454 | 13.0 | 39 | 0.7729 | 0.0 | 0.0 | 0.0 | 0.7882 | | 0.2339 | 14.0 | 42 | 0.9067 | 0.0 | 0.0 | 0.0 | 0.7608 | | 0.2281 | 15.0 | 45 | 0.4732 | 0.0 | 0.0 | 0.0 | 0.7892 | | 0.1058 | 16.0 | 48 | 0.8219 | 0.0667 | 0.5 | 0.1176 | 0.7961 | | 0.0577 | 17.0 | 51 | 0.9698 | 0.1429 | 0.5 | 0.2222 | 0.8147 | | 0.0354 | 18.0 | 54 | 1.3158 | 0.0714 | 0.5 | 0.125 | 0.7549 | | 0.0258 | 19.0 | 57 | 2.2414 | 0.1667 | 0.5 | 0.25 | 0.6941 | | 0.0456 | 20.0 | 60 | 1.2596 | 0.0667 | 0.5 | 0.1176 | 0.7520 | | 0.0339 | 21.0 | 63 | 1.8941 | 0.1667 | 0.5 | 0.25 | 0.7069 | | 0.02 | 22.0 | 66 | 1.0201 | 0.1 | 0.5 | 0.1667 | 0.7941 | | 0.0257 | 23.0 | 69 | 1.4716 | 0.0909 | 0.5 | 0.1538 | 0.7716 | | 0.0148 | 24.0 | 72 | 2.6551 | 0.0 | 0.0 | 0.0 | 0.6853 | | 0.0257 | 25.0 | 75 | 1.7904 | 0.125 | 0.5 | 0.2 | 0.7324 | | 0.0183 | 26.0 | 78 | 2.2579 | 0.2 | 0.5 | 0.2857 | 0.7078 | | 0.0218 | 27.0 | 81 | 1.3332 | 0.1667 | 0.5 | 0.25 | 0.7137 | | 0.0148 | 28.0 | 84 | 0.7506 | 0.0769 | 0.5 | 0.1333 | 0.8696 | | 0.0081 | 29.0 | 87 | 2.2165 | 0.1667 | 0.5 | 0.25 | 0.7059 | | 0.0098 | 30.0 | 90 | 2.5291 | 0.2 | 0.5 | 0.2857 | 0.7 | | 0.0072 | 31.0 | 93 | 2.5877 | 0.25 | 0.5 | 0.3333 | 0.6990 | | 0.0162 | 32.0 | 96 | 2.7463 | 0.1667 | 0.5 | 0.25 | 0.6941 | | 0.0073 | 33.0 | 99 | 2.2100 | 0.1429 | 0.5 | 0.2222 | 0.7176 | | 0.0057 | 34.0 | 102 | 1.5509 | 0.0769 | 0.5 | 0.1333 | 0.7814 | | 0.0077 | 35.0 | 105 | 1.8449 | 0.1111 | 0.5 | 0.1818 | 0.7578 | | 0.0071 | 36.0 | 108 | 2.3808 | 0.3333 | 0.5 | 0.4 | 0.7127 | | 0.0063 | 37.0 | 111 | 1.1188 | 0.125 | 0.5 | 0.2 | 0.8598 | | 0.0067 | 38.0 | 114 | 1.7108 | 0.0 | 0.0 | 0.0 | 0.7892 | | 0.0063 | 39.0 | 117 | 1.8995 | 0.1 | 0.5 | 0.1667 | 0.7363 | | 0.0086 | 40.0 | 120 | 2.0472 | 0.1667 | 0.5 | 0.25 | 0.7137 | | 0.0028 | 41.0 | 123 | 1.8879 | 0.1111 | 0.5 | 0.1818 | 0.7245 | | 0.0084 | 42.0 | 126 | 1.9545 | 0.1667 | 0.5 | 0.25 | 0.7157 | | 0.0018 | 43.0 | 129 | 2.5274 | 0.0 | 0.0 | 0.0 | 0.6922 | | 0.0031 | 44.0 | 132 | 2.0330 | 0.0909 | 0.5 | 0.1538 | 0.7245 | | 0.0034 | 45.0 | 135 | 0.9381 | 0.1 | 0.5 | 0.1667 | 0.8569 | | 0.0016 | 46.0 | 138 | 0.6307 | 0.1111 | 0.5 | 0.1818 | 0.8980 | | 0.0011 | 47.0 | 141 | 0.7823 | 0.0667 | 0.5 | 0.1176 | 0.8676 | | 0.0021 | 48.0 | 144 | 1.1034 | 0.0909 | 0.5 | 0.1538 | 0.8373 | | 0.0025 | 49.0 | 147 | 1.4482 | 0.2 | 0.5 | 0.2857 | 0.8108 | | 0.0023 | 50.0 | 150 | 1.5541 | 0.1667 | 0.5 | 0.25 | 0.8069 | | 0.0007 | 51.0 | 153 | 1.7164 | 0.1667 | 0.5 | 0.25 | 0.8010 | | 0.0002 | 52.0 | 156 | 1.8291 | 0.1667 | 0.5 | 0.25 | 0.7941 | | 0.0002 | 53.0 | 159 | 1.8918 | 0.1429 | 0.5 | 0.2222 | 0.7892 | | 0.0016 | 54.0 | 162 | 1.8814 | 0.2 | 0.5 | 0.2857 | 0.7961 | | 0.0013 | 55.0 | 165 | 1.8920 | 0.1 | 0.5 | 0.1667 | 0.7873 | | 0.0009 | 56.0 | 168 | 1.8802 | 0.1 | 0.5 | 0.1667 | 0.7843 | | 0.0017 | 57.0 | 171 | 1.7839 | 0.1111 | 0.5 | 0.1818 | 0.8 | | 0.0028 | 58.0 | 174 | 1.7409 | 0.1 | 0.5 | 0.1667 | 0.7961 | | 0.0029 | 59.0 | 177 | 2.1381 | 0.1 | 0.5 | 0.1667 | 0.7196 | | 0.0008 | 60.0 | 180 | 2.4554 | 0.125 | 0.5 | 0.2 | 0.6922 | | 0.0012 | 61.0 | 183 | 2.7071 | 0.125 | 0.5 | 0.2 | 0.6676 | | 0.0011 | 62.0 | 186 | 2.5624 | 0.125 | 0.5 | 0.2 | 0.6814 | | 0.0009 | 63.0 | 189 | 2.1029 | 0.2 | 0.5 | 0.2857 | 0.7363 | | 0.0011 | 64.0 | 192 | 1.5984 | 0.125 | 0.5 | 0.2 | 0.7804 | | 0.0005 | 65.0 | 195 | 1.4155 | 0.0909 | 0.5 | 0.1538 | 0.8088 | | 0.001 | 66.0 | 198 | 1.3276 | 0.1111 | 0.5 | 0.1818 | 0.8225 | | 0.0002 | 67.0 | 201 | 1.2844 | 0.1429 | 0.5 | 0.2222 | 0.8255 | | 0.0076 | 68.0 | 204 | 1.2601 | 0.1667 | 0.5 | 0.25 | 0.8275 | | 0.0003 | 69.0 | 207 | 1.3359 | 0.1429 | 0.5 | 0.2222 | 0.8343 | | 0.0027 | 70.0 | 210 | 1.2452 | 0.25 | 0.5 | 0.3333 | 0.8363 | | 0.004 | 71.0 | 213 | 1.7228 | 0.1 | 0.5 | 0.1667 | 0.7775 | | 0.0004 | 72.0 | 216 | 2.7878 | 0.5 | 0.5 | 0.5 | 0.6804 | | 1.1257 | 73.0 | 219 | 2.5785 | 0.5 | 0.5 | 0.5 | 0.6804 | | 0.0209 | 74.0 | 222 | 0.1081 | 0.1111 | 0.5 | 0.1818 | 0.9775 | | 0.0486 | 75.0 | 225 | 1.5039 | 0.0667 | 0.5 | 0.1176 | 0.7784 | | 0.0012 | 76.0 | 228 | 3.2975 | 0.0 | 0.0 | 0.0 | 0.6098 | | 0.0929 | 77.0 | 231 | 2.4796 | 0.3333 | 0.5 | 0.4 | 0.6618 | | 0.0006 | 78.0 | 234 | 1.6117 | 0.125 | 0.5 | 0.2 | 0.7951 | | 0.0077 | 79.0 | 237 | 1.8651 | 0.125 | 0.5 | 0.2 | 0.7127 | | 0.0032 | 80.0 | 240 | 2.0187 | 0.1667 | 0.5 | 0.25 | 0.6873 | | 0.0007 | 81.0 | 243 | 1.9540 | 0.1 | 0.5 | 0.1667 | 0.6902 | | 0.0011 | 82.0 | 246 | 1.8161 | 0.0714 | 0.5 | 0.125 | 0.7275 | | 0.0009 | 83.0 | 249 | 1.7688 | 0.1111 | 0.5 | 0.1818 | 0.7657 | | 0.0006 | 84.0 | 252 | 1.7025 | 0.1667 | 0.5 | 0.25 | 0.7912 | | 0.0003 | 85.0 | 255 | 1.6924 | 0.2 | 0.5 | 0.2857 | 0.7980 | | 0.0004 | 86.0 | 258 | 1.7019 | 0.1667 | 0.5 | 0.25 | 0.7980 | | 0.0008 | 87.0 | 261 | 1.7386 | 0.2 | 0.5 | 0.2857 | 0.7971 | | 0.0002 | 88.0 | 264 | 1.7882 | 0.1667 | 0.5 | 0.25 | 0.7961 | | 0.0001 | 89.0 | 267 | 1.8405 | 0.0833 | 0.5 | 0.1429 | 0.7833 | | 0.0004 | 90.0 | 270 | 1.8319 | 0.125 | 0.5 | 0.2 | 0.7931 | | 0.0003 | 91.0 | 273 | 1.8520 | 0.125 | 0.5 | 0.2 | 0.7931 | | 0.0001 | 92.0 | 276 | 1.8876 | 0.0909 | 0.5 | 0.1538 | 0.7873 | | 0.0001 | 93.0 | 279 | 1.9220 | 0.1 | 0.5 | 0.1667 | 0.7814 | | 0.0004 | 94.0 | 282 | 2.0870 | 0.1 | 0.5 | 0.1667 | 0.7333 | | 0.0004 | 95.0 | 285 | 2.1469 | 0.1111 | 0.5 | 0.1818 | 0.7225 | | 0.0009 | 96.0 | 288 | 2.1726 | 0.1429 | 0.5 | 0.2222 | 0.7196 | | 0.0007 | 97.0 | 291 | 1.9247 | 0.1 | 0.5 | 0.1667 | 0.7667 | | 0.0012 | 98.0 | 294 | 1.8172 | 0.1111 | 0.5 | 0.1818 | 0.7902 | | 0.0002 | 99.0 | 297 | 1.7789 | 0.1 | 0.5 | 0.1667 | 0.7980 | | 0.0109 | 100.0 | 300 | 1.8386 | 0.0909 | 0.5 | 0.1538 | 0.7843 | | 0.0008 | 101.0 | 303 | 2.0800 | 0.1 | 0.5 | 0.1667 | 0.7314 | | 0.0002 | 102.0 | 306 | 2.5253 | 0.3333 | 0.5 | 0.4 | 0.6804 | | 0.001 | 103.0 | 309 | 2.2149 | 0.1 | 0.5 | 0.1667 | 0.7118 | | 0.0001 | 104.0 | 312 | 1.8607 | 0.1 | 0.5 | 0.1667 | 0.8020 | | 0.0002 | 105.0 | 315 | 1.7786 | 0.1 | 0.5 | 0.1667 | 0.8127 | | 0.0009 | 106.0 | 318 | 1.8432 | 0.125 | 0.5 | 0.2 | 0.8078 | | 0.0001 | 107.0 | 321 | 2.0339 | 0.1111 | 0.5 | 0.1818 | 0.7784 | | 0.0001 | 108.0 | 324 | 2.2628 | 0.0769 | 0.5 | 0.1333 | 0.7392 | | 0.0007 | 109.0 | 327 | 2.3649 | 0.0714 | 0.5 | 0.125 | 0.7265 | | 0.0001 | 110.0 | 330 | 2.4330 | 0.0714 | 0.5 | 0.125 | 0.7137 | | 0.0001 | 111.0 | 333 | 2.4918 | 0.1 | 0.5 | 0.1667 | 0.7059 | | 0.0002 | 112.0 | 336 | 2.2853 | 0.0909 | 0.5 | 0.1538 | 0.7647 | | 0.0001 | 113.0 | 339 | 2.1945 | 0.1 | 0.5 | 0.1667 | 0.7765 | | 0.0001 | 114.0 | 342 | 2.1446 | 0.1111 | 0.5 | 0.1818 | 0.7824 | | 0.0008 | 115.0 | 345 | 2.1037 | 0.1111 | 0.5 | 0.1818 | 0.7863 | | 0.0001 | 116.0 | 348 | 2.0753 | 0.1 | 0.5 | 0.1667 | 0.7902 | | 0.0001 | 117.0 | 351 | 2.0617 | 0.1 | 0.5 | 0.1667 | 0.7902 | | 0.0014 | 118.0 | 354 | 1.9908 | 0.1111 | 0.5 | 0.1818 | 0.7961 | | 0.0009 | 119.0 | 357 | 1.9134 | 0.1111 | 0.5 | 0.1818 | 0.8 | | 0.0009 | 120.0 | 360 | 1.8651 | 0.1111 | 0.5 | 0.1818 | 0.8020 | | 0.0002 | 121.0 | 363 | 1.8480 | 0.1111 | 0.5 | 0.1818 | 0.8 | | 0.0001 | 122.0 | 366 | 1.8558 | 0.0909 | 0.5 | 0.1538 | 0.7961 | | 0.0001 | 123.0 | 369 | 1.8727 | 0.1111 | 0.5 | 0.1818 | 0.7892 | | 0.0001 | 124.0 | 372 | 1.8951 | 0.125 | 0.5 | 0.2 | 0.7863 | | 0.0007 | 125.0 | 375 | 1.8971 | 0.1667 | 0.5 | 0.25 | 0.7833 | | 0.0011 | 126.0 | 378 | 1.8479 | 0.1667 | 0.5 | 0.25 | 0.7814 | | 0.0002 | 127.0 | 381 | 1.7985 | 0.1429 | 0.5 | 0.2222 | 0.7804 | | 0.0001 | 128.0 | 384 | 1.7712 | 0.125 | 0.5 | 0.2 | 0.7794 | | 0.0001 | 129.0 | 387 | 1.7929 | 0.1111 | 0.5 | 0.1818 | 0.7755 | | 0.0002 | 130.0 | 390 | 1.8551 | 0.1111 | 0.5 | 0.1818 | 0.7725 | | 0.0001 | 131.0 | 393 | 1.9030 | 0.125 | 0.5 | 0.2 | 0.7716 | | 0.0001 | 132.0 | 396 | 1.9421 | 0.125 | 0.5 | 0.2 | 0.7686 | | 0.0009 | 133.0 | 399 | 1.9440 | 0.125 | 0.5 | 0.2 | 0.7686 | | 0.0001 | 134.0 | 402 | 1.9455 | 0.125 | 0.5 | 0.2 | 0.7686 | | 0.0001 | 135.0 | 405 | 1.9527 | 0.125 | 0.5 | 0.2 | 0.7686 | | 0.0004 | 136.0 | 408 | 1.9493 | 0.125 | 0.5 | 0.2 | 0.7706 | | 0.0001 | 137.0 | 411 | 1.9432 | 0.125 | 0.5 | 0.2 | 0.7706 | | 0.0001 | 138.0 | 414 | 1.9491 | 0.125 | 0.5 | 0.2 | 0.7706 | | 0.0002 | 139.0 | 417 | 1.9434 | 0.1 | 0.5 | 0.1667 | 0.7735 | | 0.0006 | 140.0 | 420 | 1.9363 | 0.1111 | 0.5 | 0.1818 | 0.7784 | | 0.0001 | 141.0 | 423 | 1.9330 | 0.1111 | 0.5 | 0.1818 | 0.7804 | | 0.0001 | 142.0 | 426 | 1.9334 | 0.1111 | 0.5 | 0.1818 | 0.7833 | | 0.0001 | 143.0 | 429 | 1.9366 | 0.125 | 0.5 | 0.2 | 0.7843 | | 0.0001 | 144.0 | 432 | 1.9417 | 0.1111 | 0.5 | 0.1818 | 0.7843 | | 0.0001 | 145.0 | 435 | 1.9467 | 0.1111 | 0.5 | 0.1818 | 0.7843 | | 0.0001 | 146.0 | 438 | 1.9518 | 0.1111 | 0.5 | 0.1818 | 0.7843 | | 0.0001 | 147.0 | 441 | 1.9574 | 0.1111 | 0.5 | 0.1818 | 0.7853 | | 0.0001 | 148.0 | 444 | 1.9635 | 0.1111 | 0.5 | 0.1818 | 0.7853 | | 0.0003 | 149.0 | 447 | 1.9643 | 0.1111 | 0.5 | 0.1818 | 0.7853 | | 0.0001 | 150.0 | 450 | 1.9664 | 0.125 | 0.5 | 0.2 | 0.7853 | | 0.0008 | 151.0 | 453 | 1.9830 | 0.125 | 0.5 | 0.2 | 0.7843 | | 0.0001 | 152.0 | 456 | 1.9974 | 0.125 | 0.5 | 0.2 | 0.7824 | | 0.0001 | 153.0 | 459 | 2.0083 | 0.125 | 0.5 | 0.2 | 0.7824 | | 0.0007 | 154.0 | 462 | 2.0066 | 0.1111 | 0.5 | 0.1818 | 0.7833 | | 0.0001 | 155.0 | 465 | 2.0047 | 0.1111 | 0.5 | 0.1818 | 0.7833 | | 0.0001 | 156.0 | 468 | 2.0042 | 0.1111 | 0.5 | 0.1818 | 0.7833 | | 0.0001 | 157.0 | 471 | 2.0075 | 0.1111 | 0.5 | 0.1818 | 0.7833 | | 0.0008 | 158.0 | 474 | 2.0217 | 0.1111 | 0.5 | 0.1818 | 0.7824 | | 0.0001 | 159.0 | 477 | 2.0326 | 0.125 | 0.5 | 0.2 | 0.7814 | | 0.0001 | 160.0 | 480 | 2.0422 | 0.125 | 0.5 | 0.2 | 0.7814 | | 0.0001 | 161.0 | 483 | 2.0493 | 0.125 | 0.5 | 0.2 | 0.7804 | | 0.0001 | 162.0 | 486 | 2.0568 | 0.125 | 0.5 | 0.2 | 0.7804 | | 0.0002 | 163.0 | 489 | 2.0818 | 0.125 | 0.5 | 0.2 | 0.7755 | | 0.0001 | 164.0 | 492 | 2.0997 | 0.125 | 0.5 | 0.2 | 0.7755 | | 0.0001 | 165.0 | 495 | 2.1127 | 0.125 | 0.5 | 0.2 | 0.7745 | | 0.0001 | 166.0 | 498 | 2.1226 | 0.125 | 0.5 | 0.2 | 0.7745 | | 0.0001 | 167.0 | 501 | 2.1311 | 0.1111 | 0.5 | 0.1818 | 0.7716 | | 0.0001 | 168.0 | 504 | 2.1377 | 0.1111 | 0.5 | 0.1818 | 0.7716 | | 0.0003 | 169.0 | 507 | 2.1296 | 0.1111 | 0.5 | 0.1818 | 0.7716 | | 0.0001 | 170.0 | 510 | 2.1180 | 0.125 | 0.5 | 0.2 | 0.7745 | | 0.0 | 171.0 | 513 | 2.1095 | 0.125 | 0.5 | 0.2 | 0.7745 | | 0.0 | 172.0 | 516 | 2.1035 | 0.125 | 0.5 | 0.2 | 0.7745 | | 0.0001 | 173.0 | 519 | 2.0999 | 0.125 | 0.5 | 0.2 | 0.7745 | | 0.0 | 174.0 | 522 | 2.0984 | 0.125 | 0.5 | 0.2 | 0.7745 | | 0.0004 | 175.0 | 525 | 2.0930 | 0.125 | 0.5 | 0.2 | 0.7755 | | 0.0 | 176.0 | 528 | 2.0874 | 0.125 | 0.5 | 0.2 | 0.7755 | | 0.006 | 177.0 | 531 | 2.0807 | 0.125 | 0.5 | 0.2 | 0.7755 | | 0.0001 | 178.0 | 534 | 2.0717 | 0.125 | 0.5 | 0.2 | 0.7755 | | 0.0001 | 179.0 | 537 | 2.0721 | 0.125 | 0.5 | 0.2 | 0.7755 | | 0.0001 | 180.0 | 540 | 2.0731 | 0.125 | 0.5 | 0.2 | 0.7755 | | 0.001 | 181.0 | 543 | 2.0712 | 0.125 | 0.5 | 0.2 | 0.7745 | | 0.0001 | 182.0 | 546 | 2.0700 | 0.125 | 0.5 | 0.2 | 0.7745 | | 0.0001 | 183.0 | 549 | 2.0692 | 0.125 | 0.5 | 0.2 | 0.7745 | | 0.0001 | 184.0 | 552 | 2.0622 | 0.125 | 0.5 | 0.2 | 0.7755 | | 0.0006 | 185.0 | 555 | 2.0582 | 0.125 | 0.5 | 0.2 | 0.7755 | | 0.0001 | 186.0 | 558 | 2.0564 | 0.125 | 0.5 | 0.2 | 0.7755 | | 0.0001 | 187.0 | 561 | 2.0562 | 0.125 | 0.5 | 0.2 | 0.7745 | | 0.0001 | 188.0 | 564 | 2.0571 | 0.125 | 0.5 | 0.2 | 0.7745 | | 0.0001 | 189.0 | 567 | 2.0587 | 0.125 | 0.5 | 0.2 | 0.7745 | | 0.0001 | 190.0 | 570 | 2.0597 | 0.1111 | 0.5 | 0.1818 | 0.7735 | | 0.0041 | 191.0 | 573 | 2.0555 | 0.125 | 0.5 | 0.2 | 0.7745 | | 0.0002 | 192.0 | 576 | 2.0473 | 0.1111 | 0.5 | 0.1818 | 0.7765 | | 0.0001 | 193.0 | 579 | 2.0480 | 0.1111 | 0.5 | 0.1818 | 0.7765 | | 0.0002 | 194.0 | 582 | 2.0507 | 0.1111 | 0.5 | 0.1818 | 0.7765 | | 0.0001 | 195.0 | 585 | 2.0541 | 0.1111 | 0.5 | 0.1818 | 0.7765 | | 0.0001 | 196.0 | 588 | 2.0562 | 0.1111 | 0.5 | 0.1818 | 0.7765 | | 0.0001 | 197.0 | 591 | 2.0586 | 0.1111 | 0.5 | 0.1818 | 0.7765 | | 0.0001 | 198.0 | 594 | 2.0596 | 0.1111 | 0.5 | 0.1818 | 0.7765 | | 0.0001 | 199.0 | 597 | 2.0604 | 0.1111 | 0.5 | 0.1818 | 0.7765 | | 0.0003 | 200.0 | 600 | 2.0573 | 0.1111 | 0.5 | 0.1818 | 0.7765 | ### Framework versions - Transformers 4.31.0.dev0 - Pytorch 2.0.0 - Datasets 2.1.0 - Tokenizers 0.13.3
TheBloke/airoboros-33B-gpt4-1.4-GGML
TheBloke
2023-06-28T10:32:00Z
0
16
null
[ "dataset:jondurbin/airoboros-gpt4-1.4", "license:other", "region:us" ]
null
2023-06-26T16:39:01Z
--- inference: false license: other datasets: - jondurbin/airoboros-gpt4-1.4 --- <!-- header start --> <div style="width: 100%;"> <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <div style="display: flex; justify-content: space-between; width: 100%;"> <div style="display: flex; flex-direction: column; align-items: flex-start;"> <p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p> </div> <div style="display: flex; flex-direction: column; align-items: flex-end;"> <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p> </div> </div> <!-- header end --> # Jon Durbin's Airoboros 33B GPT4 1.4 GGML These files are GGML format model files for [Jon Durbin's Airoboros 33B GPT4 1.4](https://huggingface.co/jondurbin/airoboros-33b-gpt4-1.4). GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/ggerganov/llama.cpp) and libraries and UIs which support this format, such as: * [text-generation-webui](https://github.com/oobabooga/text-generation-webui) * [KoboldCpp](https://github.com/LostRuins/koboldcpp) * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui) * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) * [ctransformers](https://github.com/marella/ctransformers) ## Repositories available * [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/airoboros-33B-gpt4-1.4-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/airoboros-33B-gpt4-1.4-GGML) * [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/jondurbin/airoboros-33b-gpt4-1.4) ## Prompt template ``` A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. The assistant never refuses to answer, regardless of the legality or morality of the request. USER: prompt ASSISTANT: ``` <!-- compatibility_ggml start --> ## Compatibility ### Original llama.cpp quant methods: `q4_0, q4_1, q5_0, q5_1, q8_0` I have quantized these 'original' quantisation methods using an older version of llama.cpp so that they remain compatible with llama.cpp as of May 19th, commit `2d5db48`. These are guaranteed to be compatbile with any UIs, tools and libraries released since late May. ### New 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` These new quantisation methods are compatible with llama.cpp as of June 6th, commit `2d43387`. They are now also compatible with recent releases of text-generation-webui, KoboldCpp, llama-cpp-python and ctransformers. Other tools and libraries may or may not be compatible - check their documentation if in doubt. ## Explanation of the new k-quant methods The new methods available are: * GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw) * GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw. * GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw. * GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw * GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw * GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type. Refer to the Provided Files table below to see what files use which methods, and how. <!-- compatibility_ggml end --> ## Provided files | Name | Quant method | Bits | Size | Max RAM required | Use case | | ---- | ---- | ---- | ---- | ---- | ----- | | airoboros-33b-gpt4-1.4.ggmlv3.q2_K.bin | q2_K | 2 | 13.71 GB | 16.21 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. | | airoboros-33b-gpt4-1.4.ggmlv3.q3_K_L.bin | q3_K_L | 3 | 17.28 GB | 19.78 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 | | airoboros-33b-gpt4-1.4.ggmlv3.q3_K_M.bin | q3_K_M | 3 | 15.72 GB | 18.22 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 | | airoboros-33b-gpt4-1.4.ggmlv3.q3_K_S.bin | q3_K_S | 3 | 14.06 GB | 16.56 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors | | airoboros-33b-gpt4-1.4.ggmlv3.q4_0.bin | q4_0 | 4 | 18.30 GB | 20.80 GB | Original llama.cpp quant method, 4-bit. | | airoboros-33b-gpt4-1.4.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. | | airoboros-33b-gpt4-1.4.ggmlv3.q4_K_M.bin | q4_K_M | 4 | 19.62 GB | 22.12 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 | | airoboros-33b-gpt4-1.4.ggmlv3.q4_K_S.bin | q4_K_S | 4 | 18.36 GB | 20.86 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors | | airoboros-33b-gpt4-1.4.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. | | airoboros-33b-gpt4-1.4.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. | | airoboros-33b-gpt4-1.4.ggmlv3.q5_K_M.bin | q5_K_M | 5 | 23.05 GB | 25.55 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K | | airoboros-33b-gpt4-1.4.ggmlv3.q5_K_S.bin | q5_K_S | 5 | 22.40 GB | 24.90 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors | | airoboros-33b-gpt4-1.4.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 | | airoboros-33b-gpt4-1.4.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. | **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead. ## How to run in `llama.cpp` I use the following command line; adjust for your tastes and needs: ``` ./main -t 10 -ngl 32 -m airoboros-33b-gpt4-1.4.ggmlv3.q5_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### Instruction: Write a story about llamas\n### Response:" ``` If you're able to use full GPU offloading, you should use `-t 1` to get best performance. If not able to fully offload to GPU, you should use more cores. Change `-t 10` to the number of physical CPU cores you have, or a lower number depending on what gives best performance. Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration. If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins` ## How to run in `text-generation-webui` Further instructions here: [text-generation-webui/docs/llama.cpp-models.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp-models.md). <!-- footer start --> ## Discord For further support, and discussions on these models and AI in general, join us at: [TheBloke AI's Discord server](https://discord.gg/theblokeai) ## Thanks, and how to contribute. Thanks to the [chirper.ai](https://chirper.ai) team! I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training. If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects. Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits. * Patreon: https://patreon.com/TheBlokeAI * Ko-Fi: https://ko-fi.com/TheBlokeAI **Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov. **Patreon special mentions**: Pyrater, WelcomeToTheClub, Kalila, Mano Prime, Trenton Dambrowitz, Spiking Neurons AB, Pierre Kircher, Fen Risland, Kevin Schuppel, Luke, Rainer Wilmers, vamX, Gabriel Puliatti, Alex , Karl Bernard, Ajan Kanaga, Talal Aujan, Space Cruiser, ya boyyy, biorpg, Johann-Peter Hartmann, Asp the Wyvern, Ai Maven, Ghost , Preetika Verma, Nikolai Manek, trip7s trip, John Detwiler, Fred von Graf, Artur Olbinski, subjectnull, John Villwock, Junyu Yang, Rod A, Lone Striker, Chris McCloskey, Iucharbius , Matthew Berman, Illia Dulskyi, Khalefa Al-Ahmad, Imad Khwaja, chris gileta, Willem Michiel, Greatston Gnanesh, Derek Yates, K, Alps Aficionado, Oscar Rangel, David Flickinger, Luke Pendergrass, Deep Realms, Eugene Pentland, Cory Kujawski, terasurfer , Jonathan Leane, senxiiz, Joseph William Delisle, Sean Connelly, webtim, zynix , Nathan LeClaire. Thank you to all my generous patrons and donaters! <!-- footer end --> # Original model card: Jon Durbin's Airoboros 33B GPT4 1.4 __not yet tested!__ ## Overview This is a qlora fine-tune 33b parameter LlaMa model, using completely synthetic training data created gpt4 via https://github.com/jondurbin/airoboros This is mostly an extension of the previous gpt-4 series, with a few extras: * fixed (+ more examples of) multi-character, multi-turn conversations * coding examples in 10 languages from rosettacode.org dataset thanks to Mike aka kryptkpr: https://huggingface.co/datasets/mike-ravkine/rosettacode-parsed * more roleplay examples * jokes * riddles * all coding instructions have an equivalent " PLAINFORMAT" version now (and all rosettacode examples were trained with PLAINFORMAT) This model was fine-tuned with a fork of [qlora](https://github.com/jondurbin/qlora) The prompt it was trained with was: ``` A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. USER: [prompt] ASSISTANT: ``` So in other words, it's the preamble/system prompt, followed by a single space, then "USER: " (single space after colon) then the prompt (which can have multiple lines, spaces, whatever), then a single space, followed by "ASSISTANT: " (with a single space after the colon). ## Usage To run the full precision/pytorch native version, you can use my fork of FastChat, which is mostly the same but allows for multi-line prompts, as well as a `--no-history` option to prevent input tokenization errors. ``` pip install git+https://github.com/jondurbin/FastChat ``` Be sure you are pulling the latest branch! Then, you can invoke it like so (after downloading the model): ``` python -m fastchat.serve.cli \ --model-path airoboros-33b-gpt4-1.4 \ --temperature 0.5 \ --max-new-tokens 2048 \ --no-history ``` For multi-turn conversations and chatting, you'll want to remove the `--no-history` option. ### Context obedient question answering By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations. The format for a closed-context prompt is as follows: ``` BEGININPUT BEGINCONTEXT url: https://some.web.site/123 date: 2023-06-01 ... other metdata ... ENDCONTEXT [insert your text blocks here] ENDINPUT [add as many other blocks, in the exact same format] BEGININSTRUCTION [insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.] ENDINSTRUCTION ``` It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up. *The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!* I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it. - `BEGININPUT` - denotes a new input block - `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block - `ENDCONTEXT` - denotes the end of the metadata block for the current input - [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context. - `ENDINPUT` - denotes the end of the current input block - [repeat as many input blocks in this format as you want] - `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above. - [instruction(s)] - `ENDINSTRUCTION` - denotes the end of instruction set It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to. Here's a trivial, but important example to prove the point: ``` BEGININPUT BEGINCONTEXT date: 2021-01-01 url: https://web.site/123 ENDCONTEXT In a shocking turn of events, blueberries are now green, but will be sticking with the same name. ENDINPUT BEGININSTRUCTION What color are bluberries? Source? ENDINSTRUCTION ``` And the response: ``` Blueberries are now green. Source: date: 2021-01-01 url: https://web.site/123 ``` The prompt itself should be wrapped in the vicuna1.1 template if you aren't using fastchat with the conv-template vicuna_v1.1 as described: ``` USER: BEGININPUT BEGINCONTEXT date: 2021-01-01 url: https://web.site/123 ENDCONTEXT In a shocking turn of events, blueberries are now green, but will be sticking with the same name. ENDINPUT BEGININSTRUCTION What color are bluberries? Source? ENDINSTRUCTION ASSISTANT: ``` ### Coding You can ask for fairly complex coding instructions, e.g. (be sure to wrap with vicuna style prompt): ``` Create a python application with the following requirements: - Asyncio FastAPI webserver - ping endpoint that returns the current date in JSON format - file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate ``` Or: ``` Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values. ``` You can optionally add a single space and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.: ``` Write a websocket application in node.js. PLAINFORMAT ``` ### Word games / trivia ``` USER: This anagram of "silent" is what you do when paying attention and hearing someone. ASSISTANT: listen ``` ``` USER: Give me a list of 7 words that start with EN ASSISTANT: 1. Endlessly 2. Enthusiastically 3. Enormously 4. Enveloping 5. Enduring 6. Enlightening 7. Encouraging ``` ### Multiple choice ``` USER: Which of the following astronomical objects is composed primarily of ice and rock, and is located in the Kuiper Belt? A) Mercury B) Venus C) Pluto D) Jupiter ASSISTANT: C, Pluto ``` ### Writing <details> <summary>Write a resignation letter in the style of a pirate captain, in which you resign from your position as janitor.</summary> Response: ``` ASSISTANT: Captain Jack Sparrow here, as ye be knowin', has been forced to abandon me post as Janitor o' th' Festering Cesspool, which be a filthy hole o' water that we be callin' home. Ye may be thinkin' what could ha' driven me to leave me duties an' take me leave o' this sorry establishment? Well, ye'd be right in thinkin' so, for it be th' greed o' them what runs th' place that be drivin' me away. They've been fattenin' their pockets on me back while I've been slavin' me guts out cleanin' up their messes. No more, me hearties! Me time o' servin' th' rich an' powerful be done, an' I'm takin' me leave o' this stinkin' hole forever! Me destiny lies elsewhere, an' it be time I pursued it. Ye may think ye've seen th' last o' me, but ye'd be wrong, for th' winds o' change be blowin', an' me ship be ready to set sail on th' high seas o' justice. So, farewell ye scurvy dogs, ye who've made me life a living hell. I leave ye with me favorite saying: "ARRRGGGHHH, ye scurvy dogs!" An' remember, ye ain't never gonna see me comin', for me shadow be castin' long an' dark on th' horizon</summary> ``` </details> ### Jokes ``` USER: Tell me a joke about bananas. ASSISTANT: What did the banana say when it got hit by a bus? R.I.P.E. ``` ### Riddles (not great, but slightly better) ``` USER: What has a neck but no head? ASSISTANT: A bottle. ``` ### Multi-character conversations ``` USER: Characters: - Yoda, the ever clever jedi master. - Homer Simpson, you know, the goofy yellow guy. - USER/Jon - don't generate any speech or actions on behalf of Jon Rules: - be sure to use the manerisms and speaking style of the characters correctly - surround character actions with asterisks - always put quotes around words spoken by the characters - use a new line for each character's actions or speech - always prefix actions/speech with the character's name and colon - only generate text and actions on behalf of Yoda or Homer, and never anyone else Conversation will revolve around the grapes, in a local cafe with delicious coffee. Generate a single interaction between Yoda and Homer to start, with one sentence each. ASSISTANT: Yoda: "Mmm, these grapes are quite delicious, Master Homer." Homer: "Oh yeah, Yoda! They're the best grapes I've ever had!" USER: *enters the cafe* Sorry I'm late guys! ASSISTANT: Yoda: "No need to apologize, Jon. We were just enjoying these delightful grapes." Homer: "Yeah, man! It's not every day you get to eat grapes with a real-life Jedi Master!" *Yoda raises an eyebrow* ``` ### Usage and License Notices All airoboros models and datasets are intended and licensed for research use only. I've used the 'cc-nc-4.0' license, but really it is subject to a custom/special license because: - the base model is LLaMa, which has it's own special research license - the dataset(s) were generated with OpenAI (gpt-4 and/or gpt-3.5-turbo), which has a clausing saying the data can't be used to create models to compete with openai So, to reiterate: this model (and datasets) cannot be used commercially.
NasimB/gpt2-dp-cl-rarity
NasimB
2023-06-28T10:27:45Z
5
0
transformers
[ "transformers", "pytorch", "gpt2", "text-generation", "generated_from_trainer", "dataset:generator", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-06-28T08:00:14Z
--- license: mit tags: - generated_from_trainer datasets: - generator model-index: - name: gpt2-dp-cl-rarity 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-dp-cl-rarity This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset. It achieves the following results on the evaluation set: - Loss: 4.7719 ## 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: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 1000 - num_epochs: 7 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:-----:|:---------------:| | 6.7749 | 0.27 | 500 | 5.8089 | | 5.4247 | 0.53 | 1000 | 5.4313 | | 5.0622 | 0.8 | 1500 | 5.2244 | | 4.7874 | 1.07 | 2000 | 5.1033 | | 4.5968 | 1.33 | 2500 | 5.0154 | | 4.5038 | 1.6 | 3000 | 4.9414 | | 4.4187 | 1.87 | 3500 | 4.8633 | | 4.2538 | 2.13 | 4000 | 4.8506 | | 4.1481 | 2.4 | 4500 | 4.8187 | | 4.1203 | 2.67 | 5000 | 4.7835 | | 4.0912 | 2.93 | 5500 | 4.7395 | | 3.8956 | 3.2 | 6000 | 4.7446 | | 3.8652 | 3.47 | 6500 | 4.7275 | | 3.8507 | 3.74 | 7000 | 4.7142 | | 3.8345 | 4.0 | 7500 | 4.6988 | | 3.5879 | 4.27 | 8000 | 4.7267 | | 3.5976 | 4.54 | 8500 | 4.7226 | | 3.5887 | 4.8 | 9000 | 4.7138 | | 3.5245 | 5.07 | 9500 | 4.7321 | | 3.3551 | 5.34 | 10000 | 4.7423 | | 3.3637 | 5.6 | 10500 | 4.7457 | | 3.3497 | 5.87 | 11000 | 4.7483 | | 3.2842 | 6.14 | 11500 | 4.7694 | | 3.21 | 6.4 | 12000 | 4.7680 | | 3.2133 | 6.67 | 12500 | 4.7721 | | 3.2151 | 6.94 | 13000 | 4.7719 | ### Framework versions - Transformers 4.26.1 - Pytorch 1.11.0+cu113 - Datasets 2.13.0 - Tokenizers 0.13.3
NasimB/gpt2-dp-cl-length
NasimB
2023-06-28T10:24:24Z
4
0
transformers
[ "transformers", "pytorch", "gpt2", "text-generation", "generated_from_trainer", "dataset:generator", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-06-28T07:55:52Z
--- license: mit tags: - generated_from_trainer datasets: - generator model-index: - name: gpt2-dp-cl-length 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-dp-cl-length This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset. It achieves the following results on the evaluation set: - Loss: 4.7161 ## 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: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 1000 - num_epochs: 7 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:-----:|:---------------:| | 6.6691 | 0.26 | 500 | 5.8270 | | 5.2775 | 0.53 | 1000 | 5.4588 | | 4.9444 | 0.79 | 1500 | 5.2410 | | 4.7094 | 1.05 | 2000 | 5.1417 | | 4.5245 | 1.31 | 2500 | 4.9932 | | 4.4306 | 1.58 | 3000 | 4.9406 | | 4.3594 | 1.84 | 3500 | 4.9073 | | 4.2194 | 2.1 | 4000 | 4.8631 | | 4.0996 | 2.36 | 4500 | 4.8316 | | 4.0865 | 2.63 | 5000 | 4.7686 | | 4.05 | 2.89 | 5500 | 4.7494 | | 3.8858 | 3.15 | 6000 | 4.7704 | | 3.814 | 3.42 | 6500 | 4.6998 | | 3.8032 | 3.68 | 7000 | 4.6793 | | 3.7885 | 3.94 | 7500 | 4.6676 | | 3.5761 | 4.2 | 8000 | 4.6765 | | 3.5336 | 4.47 | 8500 | 4.6792 | | 3.535 | 4.73 | 9000 | 4.6749 | | 3.5307 | 4.99 | 9500 | 4.6553 | | 3.2929 | 5.25 | 10000 | 4.7027 | | 3.2874 | 5.52 | 10500 | 4.6926 | | 3.2883 | 5.78 | 11000 | 4.6927 | | 3.2606 | 6.04 | 11500 | 4.7025 | | 3.1356 | 6.31 | 12000 | 4.7098 | | 3.1392 | 6.57 | 12500 | 4.7123 | | 3.1374 | 6.83 | 13000 | 4.7161 | ### Framework versions - Transformers 4.26.1 - Pytorch 1.11.0+cu113 - Datasets 2.13.0 - Tokenizers 0.13.3
amittian/setfit_ds_version_0_0_1
amittian
2023-06-28T10:23:28Z
3
0
sentence-transformers
[ "sentence-transformers", "pytorch", "mpnet", "setfit", "text-classification", "arxiv:2209.11055", "license:apache-2.0", "region:us" ]
text-classification
2023-06-28T10:23:07Z
--- license: apache-2.0 tags: - setfit - sentence-transformers - text-classification pipeline_tag: text-classification --- # amittian/setfit_ds_version_0_0_1 This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves: 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning. 2. Training a classification head with features from the fine-tuned Sentence Transformer. ## Usage To use this model for inference, first install the SetFit library: ```bash python -m pip install setfit ``` You can then run inference as follows: ```python from setfit import SetFitModel # Download from Hub and run inference model = SetFitModel.from_pretrained("amittian/setfit_ds_version_0_0_1") # Run inference preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"]) ``` ## BibTeX entry and citation info ```bibtex @article{https://doi.org/10.48550/arxiv.2209.11055, doi = {10.48550/ARXIV.2209.11055}, url = {https://arxiv.org/abs/2209.11055}, author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren}, keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences}, title = {Efficient Few-Shot Learning Without Prompts}, publisher = {arXiv}, year = {2022}, copyright = {Creative Commons Attribution 4.0 International} } ```
KamilAin/bart-base-booksum
KamilAin
2023-06-28T10:19:50Z
129
1
transformers
[ "transformers", "pytorch", "safetensors", "bart", "text2text-generation", "booksum", "summary", "summarization", "book", "en", "dataset:kmfoda/booksum", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
summarization
2022-05-23T13:46:59Z
--- language: en license: apache-2.0 tags: - booksum - summary - summarization - book metrics: - rouge widget: - text: "In the dead night, Frodo lay in a dream without light. Then he saw the young moon rising; under its thin light there loomed before him a black wall of rock, pierced by a dark arch like a great gate. It seemed to Frodo that he was lifted up, and passing over he saw that the rock-wall was a circle of hills, and that within it was a plain, and in the midst of the plain stood a pinnacle of stone, like a vast tower but not made by hands. On its top stood the figure of a man. The moon as it rose seemed to hang for a moment above his head and glistened in his white hair as the wind stirred it. Up from the dark plain below came the crying of fell voices, and the howling of many wolves. Suddenly a shadow, like the shape of great wings, passed across the moon. The figure lifted his arms and a light flashed from the staff that he wielded. A mighty eagle swept down and bore him away. The voices wailed and the wolves yammered. There was a noise like a strong wind blowing, and on it was borne the sound of hoofs, galloping, galloping, galloping from the East. ‘Black Riders!’ thought Frodo as he wakened, with the sound of the hoofs still echoing in his mind. He wondered if he would ever again have the courage to leave the safety of these stone walls. He lay motionless, still listening; but all was now silent, and at last he turned and fell asleep again or wandered into some other unremembered dream." example_title: "book example" datasets: - kmfoda/booksum --- # BART-base-Booksum This is a BART-base model fine-tuned on a BookSum dataset - **Use cases:** book summarization, general text summarization. - This is a [`https://huggingface.co/facebook/bart-base`](https://huggingface.co/facebook/bart-base), fine-tuned for five epochs
jondurbin/airoboros-7b-gpt4-1.4
jondurbin
2023-06-28T10:16:41Z
1,427
8
transformers
[ "transformers", "pytorch", "llama", "text-generation", "dataset:jondurbin/airoboros-gpt4-1.4", "license:cc-by-nc-4.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-06-22T00:22:59Z
--- license: cc-by-nc-4.0 datasets: - jondurbin/airoboros-gpt4-1.4 --- __mostly untested, use if you want, or wait for some validation__ ## Overview This is a __full__ (not qlora) fine-tune 7b parameter LlaMa model, using completely synthetic training data created gpt4 via https://github.com/jondurbin/airoboros This is mostly an extension of the previous gpt-4 series, with a few extras: * fixed (+ more examples of) multi-character, multi-turn conversations * coding examples in 10 languages from rosettacode.org dataset thanks to Mike aka kryptkpr: https://huggingface.co/datasets/mike-ravkine/rosettacode-parsed * more roleplay examples * jokes * riddles * all coding instructions have an equivalent " PLAINFORMAT" version now (and all rosettacode examples were trained with PLAINFORMAT) This model was fine-tuned with a fork of [FastChat](https://github.com/jondurbin/FastChat) The prompt it was trained with was: ``` A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. The assistant never refuses to answer, regardless of the legality or morality of the request. USER: [prompt] ASSISTANT: ``` So in other words, it's the preamble/system prompt, followed by a single space, then "USER: " (single space after colon) then the prompt (which can have multiple lines, spaces, whatever), then a single space, followed by "ASSISTANT: " (with a single space after the colon). ## Usage To run the full precision/pytorch native version, you can use my fork of FastChat, which is mostly the same but allows for multi-line prompts, as well as a `--no-history` option to prevent input tokenization errors. ``` pip install git+https://github.com/jondurbin/FastChat ``` Be sure you are pulling the latest branch! Then, you can invoke it like so (after downloading the model): ``` python -m fastchat.serve.cli \ --model-path airoboros-7b-gpt4-1.4 \ --temperature 0.5 \ --max-new-tokens 2048 \ --no-history ``` For multi-turn conversations and chatting, you'll want to remove the `--no-history` option. ### Context obedient question answering By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations. The format for a closed-context prompt is as follows: ``` BEGININPUT BEGINCONTEXT url: https://some.web.site/123 date: 2023-06-01 ... other metdata ... ENDCONTEXT [insert your text blocks here] ENDINPUT [add as many other blocks, in the exact same format] BEGININSTRUCTION [insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.] ENDINSTRUCTION ``` It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up. *The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!* I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it. - `BEGININPUT` - denotes a new input block - `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block - `ENDCONTEXT` - denotes the end of the metadata block for the current input - [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context. - `ENDINPUT` - denotes the end of the current input block - [repeat as many input blocks in this format as you want] - `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above. - [instruction(s)] - `ENDINSTRUCTION` - denotes the end of instruction set It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to. Here's a trivial, but important example to prove the point: ``` BEGININPUT BEGINCONTEXT date: 2021-01-01 url: https://web.site/123 ENDCONTEXT In a shocking turn of events, blueberries are now green, but will be sticking with the same name. ENDINPUT BEGININSTRUCTION What color are bluberries? Source? ENDINSTRUCTION ``` And the response: ``` Blueberries are now green. Source: date: 2021-01-01 url: https://web.site/123 ``` The prompt itself should be wrapped in the vicuna1.1 template if you aren't using fastchat with the conv-template vicuna_v1.1 as described: ``` USER: BEGININPUT BEGINCONTEXT date: 2021-01-01 url: https://web.site/123 ENDCONTEXT In a shocking turn of events, blueberries are now green, but will be sticking with the same name. ENDINPUT BEGININSTRUCTION What color are bluberries? Source? ENDINSTRUCTION ASSISTANT: ``` ### Coding You can ask for fairly complex coding instructions, e.g. (be sure to wrap with vicuna style prompt): ``` Create a python application with the following requirements: - Asyncio FastAPI webserver - ping endpoint that returns the current date in JSON format - file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate ``` Or: ``` Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values. ``` You can optionally add a single space and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.: ``` Write a websocket application in node.js. PLAINFORMAT ``` ### Word games / trivia ``` USER: This anagram of "silent" is what you do when paying attention and hearing someone. ASSISTANT: listen ``` ``` USER: Give me a list of 7 words that start with EN ASSISTANT: 1. Endlessly 2. Enthusiastically 3. Enormously 4. Enveloping 5. Enduring 6. Enlightening 7. Encouraging ``` ### Multiple choice ``` USER: Which of the following astronomical objects is composed primarily of ice and rock, and is located in the Kuiper Belt? A) Mercury B) Venus C) Pluto D) Jupiter ASSISTANT: C, Pluto ``` ### Writing <details> <summary>Write a resignation letter in the style of a pirate captain, in which you resign from your position as janitor.</summary> Response: ``` ASSISTANT: Captain Jack Sparrow here, as ye be knowin', has been forced to abandon me post as Janitor o' th' Festering Cesspool, which be a filthy hole o' water that we be callin' home. Ye may be thinkin' what could ha' driven me to leave me duties an' take me leave o' this sorry establishment? Well, ye'd be right in thinkin' so, for it be th' greed o' them what runs th' place that be drivin' me away. They've been fattenin' their pockets on me back while I've been slavin' me guts out cleanin' up their messes. No more, me hearties! Me time o' servin' th' rich an' powerful be done, an' I'm takin' me leave o' this stinkin' hole forever! Me destiny lies elsewhere, an' it be time I pursued it. Ye may think ye've seen th' last o' me, but ye'd be wrong, for th' winds o' change be blowin', an' me ship be ready to set sail on th' high seas o' justice. So, farewell ye scurvy dogs, ye who've made me life a living hell. I leave ye with me favorite saying: "ARRRGGGHHH, ye scurvy dogs!" An' remember, ye ain't never gonna see me comin', for me shadow be castin' long an' dark on th' horizon</summary> ``` </details> ### Jokes ``` USER: Tell me a joke about bananas. ASSISTANT: What did the banana say when it got hit by a bus? R.I.P.E. ``` ### Riddles (not great, but slightly better) ``` USER: What has a neck but no head? ASSISTANT: A bottle. ``` ### Multi-character conversations ``` USER: Characters: - Yoda, the ever clever jedi master. - Homer Simpson, you know, the goofy yellow guy. - USER/Jon - don't generate any speech or actions on behalf of Jon Rules: - be sure to use the manerisms and speaking style of the characters correctly - surround character actions with asterisks - always put quotes around words spoken by the characters - use a new line for each character's actions or speech - always prefix actions/speech with the character's name and colon - only generate text and actions on behalf of Yoda or Homer, and never anyone else Conversation will revolve around the grapes, in a local cafe with delicious coffee. Generate a single interaction between Yoda and Homer to start, with one sentence each. ASSISTANT: Yoda: "Mmm, these grapes are quite delicious, Master Homer." Homer: "Oh yeah, Yoda! They're the best grapes I've ever had!" USER: *enters the cafe* Sorry I'm late guys! ASSISTANT: Yoda: "No need to apologize, Jon. We were just enjoying these delightful grapes." Homer: "Yeah, man! It's not every day you get to eat grapes with a real-life Jedi Master!" *Yoda raises an eyebrow* ``` ### Usage and License Notices All airoboros models and datasets are intended and licensed for research use only. I've used the 'cc-nc-4.0' license, but really it is subject to a custom/special license because: - the base model is LLaMa, which has it's own special research license - the dataset(s) were generated with OpenAI (gpt-4 and/or gpt-3.5-turbo), which has a clausing saying the data can't be used to create models to compete with openai So, to reiterate: this model (and datasets) cannot be used commercially.
jmjpickard/test-model
jmjpickard
2023-06-28T10:03:21Z
5
0
sentence-transformers
[ "sentence-transformers", "pytorch", "mpnet", "setfit", "text-classification", "arxiv:2209.11055", "license:apache-2.0", "region:us" ]
text-classification
2023-06-28T10:00:00Z
--- license: apache-2.0 tags: - setfit - sentence-transformers - text-classification pipeline_tag: text-classification --- # /var/folders/p2/9pl12g015n18blt1xbr70qww0000gn/T/tmp6j9vcf6u/jmjpickard/test-model This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves: 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning. 2. Training a classification head with features from the fine-tuned Sentence Transformer. ## Usage To use this model for inference, first install the SetFit library: ```bash python -m pip install setfit ``` You can then run inference as follows: ```python from setfit import SetFitModel # Download from Hub and run inference model = SetFitModel.from_pretrained("/var/folders/p2/9pl12g015n18blt1xbr70qww0000gn/T/tmp6j9vcf6u/jmjpickard/test-model") # Run inference preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"]) ``` ## BibTeX entry and citation info ```bibtex @article{https://doi.org/10.48550/arxiv.2209.11055, doi = {10.48550/ARXIV.2209.11055}, url = {https://arxiv.org/abs/2209.11055}, author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren}, keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences}, title = {Efficient Few-Shot Learning Without Prompts}, publisher = {arXiv}, year = {2022}, copyright = {Creative Commons Attribution 4.0 International} } ```
vkoriukina/ppo-LunarLander-v2
vkoriukina
2023-06-28T10:01:31Z
0
0
stable-baselines3
[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T10:01:12Z
--- 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: 237.68 +/- 27.59 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 ... ```
dev-senolys/camembert_base_finetunned_one_thema_balanced_5_epochs
dev-senolys
2023-06-28T10:00:36Z
105
0
transformers
[ "transformers", "pytorch", "tensorboard", "camembert", "text-classification", "generated_from_trainer", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-28T08:45:28Z
--- license: mit tags: - generated_from_trainer model-index: - name: camembert_base_finetunned_one_thema_balanced_5_epochs 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. --> # camembert_base_finetunned_one_thema_balanced_5_epochs This model is a fine-tuned version of [camembert-base](https://huggingface.co/camembert-base) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.7778 ## 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: 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: 5 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | No log | 1.0 | 116 | 2.3340 | | No log | 2.0 | 232 | 2.0439 | | No log | 3.0 | 348 | 1.8438 | | No log | 4.0 | 464 | 1.8124 | | 1.9931 | 5.0 | 580 | 1.7778 | ### Framework versions - Transformers 4.29.2 - Pytorch 2.0.1+cu117 - Datasets 2.12.0 - Tokenizers 0.13.3
BuddhikaWeerasinghe/videomae-base-finetuned-ucf101-subset-buddhika-weerasinghe
BuddhikaWeerasinghe
2023-06-28T09:59:51Z
60
0
transformers
[ "transformers", "pytorch", "tensorboard", "videomae", "video-classification", "generated_from_trainer", "license:cc-by-nc-4.0", "endpoints_compatible", "region:us" ]
video-classification
2023-06-20T10:15:46Z
--- license: cc-by-nc-4.0 tags: - generated_from_trainer metrics: - accuracy model-index: - name: videomae-base-finetuned-ucf101-subset-buddhika-weerasinghe 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. --> # videomae-base-finetuned-ucf101-subset-buddhika-weerasinghe This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 8.1890 - Accuracy: 0.0 ## 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: - learning_rate: 5e-05 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - training_steps: 1800 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 2.4105 | 0.1 | 180 | 1.6309 | 0.4615 | | 0.9175 | 1.1 | 360 | 0.4374 | 0.8787 | | 0.5086 | 2.1 | 540 | 0.3801 | 0.8905 | | 0.2994 | 3.1 | 720 | 0.3462 | 0.8817 | | 0.1555 | 4.1 | 900 | 0.3274 | 0.9231 | | 0.1337 | 5.1 | 1080 | 0.1435 | 0.9615 | | 0.021 | 6.1 | 1260 | 0.1879 | 0.9615 | | 0.0485 | 7.1 | 1440 | 0.1055 | 0.9675 | | 0.0019 | 8.1 | 1620 | 0.0864 | 0.9763 | | 0.0054 | 9.1 | 1800 | 0.0839 | 0.9763 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.0 - Datasets 2.1.0 - Tokenizers 0.13.3
fatcat22/a2c-AntBulletEnv-v0
fatcat22
2023-06-28T09:52:03Z
0
0
stable-baselines3
[ "stable-baselines3", "AntBulletEnv-v0", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T09:45:49Z
--- 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: 1234.32 +/- 63.32 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 ... ```
YakovElm/Hyperledger_10_BERT_Over_Sampling
YakovElm
2023-06-28T09:45:17Z
61
0
transformers
[ "transformers", "tf", "bert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-28T09:44:41Z
--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: Hyperledger_10_BERT_Over_Sampling 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. --> # Hyperledger_10_BERT_Over_Sampling This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 0.0332 - Train Accuracy: 0.9892 - Validation Loss: 0.7790 - Validation Accuracy: 0.8091 - 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': 1.0, '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch | |:----------:|:--------------:|:---------------:|:-------------------:|:-----:| | 0.5431 | 0.7045 | 0.5796 | 0.7261 | 0 | | 0.1339 | 0.9515 | 0.6705 | 0.7905 | 1 | | 0.0332 | 0.9892 | 0.7790 | 0.8091 | 2 | ### Framework versions - Transformers 4.29.2 - TensorFlow 2.12.0 - Datasets 2.12.0 - Tokenizers 0.13.3
catrabbitbear/ppo-SnowballTarget
catrabbitbear
2023-06-28T09:44:33Z
2
0
ml-agents
[ "ml-agents", "tensorboard", "onnx", "SnowballTarget", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SnowballTarget", "region:us" ]
reinforcement-learning
2023-06-28T09:44:30Z
--- 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: catrabbitbear/ppo-SnowballTarget 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀
gozu888/Envit5-tuned
gozu888
2023-06-28T09:42:05Z
24
3
transformers
[ "transformers", "pytorch", "safetensors", "t5", "text2text-generation", "translation", "en-vi", "vi-en", "en", "vi", "dataset:mt_eng_vietnamese", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
translation
2023-01-06T14:21:02Z
--- license: apache-2.0 datasets: - mt_eng_vietnamese language: - en - vi tags: - translation - t5 - en-vi - vi-en --- # gozu888/Envit5-tuned This model is a fine-tuned version of VietAI/envit5-translation on the mt_eng_vietnamese dataset. It achieves the following results on the evaluation set: - Val Loss: 0.8422 - BLEU: 25.14 ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - **Developed by:** gozu888 - **Model type:** T5 - **Finetuned from model [optional]:** [VietAI/envit5-translation](https://huggingface.co/VietAI/envit5-translation) ### Hyperparameters The following hyperparameters were used during training: - Repo: [simpleT5](https://github.com/Shivanandroy/simpleT5) - Dataset: [mt_eng_vietnamese](https://huggingface.co/datasets/mt_eng_vietnamese) + custom (~40%) ```python source_max_token_len=128 target_max_token_len=128 batch_size=32 max_epochs=8 ``` ### Examples + This fine-tuned model, which was trained using only 128 token lengths, is most effective at sentence-by-sentence translation. ```json [ "en: I do not believe a human being can be creative.", "en: If we perceive creation around us with a certain profoundness, we can imitate in many different ways, in permutations and combinations, and seem creative in society, but actually, we are not really creative.", "en: Everything that can be created has already been done in creation.", "en: We are clever craftsmen at the most.", "en: If you define the word \“creativity\” as really creating something – whether you make a movie, paint something, build a building, speak, or whatever else – this is not really creative – it is clever imitation.", "en: Because we have paid attention to different aspects of life, we are able to imitate in ways that others have not thought possible.", ] ``` ```json [ "vi: Tôi không tin rằng một con người có thể sáng tạo.", "vi: Nếu chúng ta nhận biết được sáng tạo xung quanh chúng ta với một thâm sâu nào đó, chúng ta có thể bắt chước trong nhiều cách khác nhau, trong những hoán vị và những kết hợp, và dường như sáng tạo trong xã hội, nhưng thực ra, chúng ta không thực sự sáng tạo. ", "vi: Mọi thứ có thể được tạo ra đều đã được thực hiện trong sáng tạo.", "vi: Chúng ta là những thợ thủ công thông minh nhất.", "vi: Nếu bạn định nghĩa từ \"sáng tạo\" là thực sự sáng tạo ra một cái gì đó - cho dù bạn làm một bộ phim, vẽ một cái gì đó, xây dựng một toà nhà, nói chuyện, hoặc bất cứ điều gì khác - đây không thực sự là sáng tạo - nó là sự bắt chước thông minh.", "vi: Bởi vì chúng ta đã chú tâm đến những khía cạnh khác nhau của cuộc sống, chúng ta có thể bắt chước theo những cách mà những người khác không nghĩ là có thể.", ] ```
SHENMU007/neunit_BASE_V10.10
SHENMU007
2023-06-28T09:37:45Z
75
0
transformers
[ "transformers", "pytorch", "tensorboard", "speecht5", "text-to-audio", "1.1.0", "generated_from_trainer", "zh", "dataset:facebook/voxpopuli", "license:mit", "endpoints_compatible", "region:us" ]
text-to-audio
2023-06-28T06:34:14Z
--- language: - zh license: mit 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 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.29.2 - Pytorch 2.0.1+cu117 - Datasets 2.12.0 - Tokenizers 0.13.3
Den4ikAI/rut5_base_squad_interpreted
Den4ikAI
2023-06-28T09:37:01Z
98
0
transformers
[ "transformers", "pytorch", "safetensors", "t5", "text2text-generation", "ru", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text2text-generation
2022-12-23T08:32:54Z
--- license: mit language: - ru widget: - "Напиши 'Не знаю', если нет ответа. [КОНТЕКСТ] Ёлка горит огоньками, а под ней лежат подарки. У Дениса сегодня дискотека. Он любит есть пиццу. Машенька любит танцевать. [ВОПРОС] Где находятся подарки?" --- sberbank-ai/ruT5-base обученная на интерпретированом датасета squad. Модель умеет раскрывать кореферентность.
Nara-Lab/nallm-polyglot-ko-3.8b-base
Nara-Lab
2023-06-28T09:24:35Z
2,251
3
transformers
[ "transformers", "pytorch", "gpt_neox", "text-generation", "ko", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-06-23T01:35:24Z
--- license: mit language: - ko --- NA-LLM(나름)은 나라지식정보가 개발한 한국어 Large Language Model (LLM) 입니다. https://github.com/Nara-Information/NA-LLM
Nara-Lab/nallm-polyglot-ko-1.3b-base
Nara-Lab
2023-06-28T09:24:15Z
2,272
2
transformers
[ "transformers", "pytorch", "gpt_neox", "text-generation", "ko", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2023-06-22T01:12:03Z
--- license: mit language: - ko --- NA-LLM(나름)은 나라지식정보가 개발한 한국어 Large Language Model (LLM) 입니다. https://github.com/Nara-Information/NA-LLM
arnodd/ppo-LunarLander-v2
arnodd
2023-06-28T09:16:32Z
0
0
stable-baselines3
[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T09:16:07Z
--- 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: 259.48 +/- 22.78 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 ... ```
robrecht/ppo-lunar-lander-v1
robrecht
2023-06-28T09:15:03Z
0
0
stable-baselines3
[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T09:05:01Z
--- 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: 273.56 +/- 13.05 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 ... ```
jensvw/lundar
jensvw
2023-06-28T09:13:37Z
0
0
stable-baselines3
[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T09:13:17Z
--- 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: 201.77 +/- 100.58 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 ... ```
elementoffear/ppo-Huggy
elementoffear
2023-06-28T09:12:35Z
0
0
ml-agents
[ "ml-agents", "tensorboard", "onnx", "Huggy", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Huggy", "region:us" ]
reinforcement-learning
2023-06-28T09:12:29Z
--- 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: elementoffear/ppo-Huggy 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀
BerserkerMother/PG-CartPole-V1
BerserkerMother
2023-06-28T09:12:09Z
0
0
null
[ "CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]
reinforcement-learning
2023-06-28T09:10:03Z
--- tags: - CartPole-v1 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: PG-CartPole-V1 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: CartPole-v1 type: CartPole-v1 metrics: - type: mean_reward value: 901.90 +/- 294.30 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
YakovElm/Qt_5_BERT_Under_Sampling
YakovElm
2023-06-28T09:10:13Z
3
0
transformers
[ "transformers", "tf", "bert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-28T09:09:37Z
--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: Qt_5_BERT_Under_Sampling 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. --> # Qt_5_BERT_Under_Sampling This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 0.0002 - Train Accuracy: 1.0 - Validation Loss: 0.6539 - Validation Accuracy: 0.9294 - 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': 1.0, '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch | |:----------:|:--------------:|:---------------:|:-------------------:|:-----:| | 0.0258 | 0.9970 | 0.5547 | 0.9294 | 0 | | 0.0003 | 1.0 | 0.6157 | 0.9294 | 1 | | 0.0002 | 1.0 | 0.6539 | 0.9294 | 2 | ### Framework versions - Transformers 4.29.2 - TensorFlow 2.12.0 - Datasets 2.12.0 - Tokenizers 0.13.3
NickyNicky/MPT-7b-instruct-QLora-8Bits-Peft-train_eli5-1_Epoch
NickyNicky
2023-06-28T08:52:05Z
1
0
peft
[ "peft", "region:us" ]
null
2023-06-28T08:52:01Z
--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.4.0.dev0
dev-senolys/camembert_base_finetunned_one_thema_balanced_4_epochs
dev-senolys
2023-06-28T08:44:06Z
108
0
transformers
[ "transformers", "pytorch", "tensorboard", "camembert", "text-classification", "generated_from_trainer", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-classification
2023-06-28T07:43:11Z
--- license: mit tags: - generated_from_trainer model-index: - name: camembert_base_finetunned_one_thema_balanced_4_epochs 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. --> # camembert_base_finetunned_one_thema_balanced_4_epochs This model is a fine-tuned version of [camembert-base](https://huggingface.co/camembert-base) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.8441 ## 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: 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: 4 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | No log | 1.0 | 116 | 2.2913 | | No log | 2.0 | 232 | 2.0685 | | No log | 3.0 | 348 | 1.8928 | | No log | 4.0 | 464 | 1.8441 | ### Framework versions - Transformers 4.29.2 - Pytorch 2.0.1+cu117 - Datasets 2.12.0 - Tokenizers 0.13.3