Split (1)

train · 797k rows

modelId string	author string	last_modified timestamp[us, tz=UTC]	downloads int64	likes int64	library_name string	tags sequence	pipeline_tag string	createdAt timestamp[us, tz=UTC]	card string
asyzhou/224n-whisper-large-overnight-1	asyzhou	2024-03-11T09:22:47Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-03-10T10:00:22Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
NorGLM/NorGPT-3B-continue-summarization-peft	NorGLM	2024-03-11T09:07:15Z	0	0	null	[ "summarization", "no", "dataset:NorGLM/NO-CNN-DailyMail", "license:cc-by-nc-sa-4.0", "region:us" ]	summarization	2024-03-11T09:04:18Z	--- license: cc-by-nc-sa-4.0 language: - 'no' datasets: - NorGLM/NO-CNN-DailyMail pipeline_tag: summarization --- # Model Card NorGPT-3B-continue-summarization-peft is trained on top of [NorGPT-3B-continue](https://huggingface.co/NorGLM/NorGPT-3B-continue) model on [NO-CNN-DailyMail](https://huggingface.co/datasets/NorGLM/NO-CNN-DailyMail) dataset. Prompt format: ``` Summarise the article:\\n{article} \|\|\|\\n{positive_sample} ``` Inference prompt: ``` Summarise the article:\\n{article} \|\|\|\\n ``` ## Run the Model ```python from peft import PeftModel, PeftConfig from transformers import AutoModelForCausalLM, AutoTokenizer import torch source_model_id = "NorGLM/NorGPT-3B-continue" peft_model_id = "NorGLM/NorGPT-3B-continue-summarization-peft" config = PeftConfig.from_pretrained(peft_model_id) model = AutoModelForCausalLM.from_pretrained(source_model_id, device_map='balanced') tokenizer_max_len = 2048 tokenizer_config = {'pretrained_model_name_or_path': source_model_id, 'max_len': tokenizer_max_len} tokenizer = tokenizer = AutoTokenizer.from_pretrained(tokenizer_config) tokenizer.pad_token = tokenizer.eos_token model = PeftModel.from_pretrained(model, peft_model_id) ``` ## Inference on test set Load the model to evaluate on the test set of NO-CNN-DailyMail dataset: ```python def generate_texts(model, tokenizer, prompts, max_seq_length=200, do_sample=True, top_p=0.95, top_k=10): # prompts are a list of news articles results = [] cnt = 0 for prompt in prompts: cnt += 1 pro_len = len(prompt.split()) if pro_len>1024: results.append('') continue prompt = 'Summarise the article:\\n' + prompt + ' \|\|\|\\n' model_inputs = tokenizer(prompt, return_tensors='pt').to(torch_device) output = model.generate(model_inputs, do_sample=False, max_new_tokens=max_seq_length) result = tokenizer.decode(output[0], skip_special_tokens=True) result = result.split("\|\|\|\\n")[-1] results.append(result) return results print("--LOADING EVAL DATAS---") eval_data = load_dataset("NorGLM/NO-CNN-DailyMail", data_files="test.csv") prompts = eval_data['train']['article'] positive_samples = eval_data['train']['positive_sample'] print("--MAKING PREDICTIONS---") model.eval() output_file = <output file name> with torch.no_grad(): results = generate_texts(model, tokenizer, prompts) df = pd.DataFrame({'article':prompts, 'generated_text':results, 'positive_sample':positive_samples}) print("Save results to csv file...") df.to_csv(output_file) ``` ## Note More training details will be released soon!
NorGLM/NorGPT-369M-summarization-peft	NorGLM	2024-03-11T09:05:41Z	0	0	null	[ "no", "license:cc-by-nc-sa-4.0", "region:us" ]	null	2024-03-11T08:51:11Z	--- license: cc-by-nc-sa-4.0 language: - 'no' --- # Model Card NorGPT-369M-summarization-peft is trained on top of [NorGPT-369M](https://huggingface.co/NorGLM/NorGPT-369M) model on [NO-CNN-DailyMail](https://huggingface.co/datasets/NorGLM/NO-CNN-DailyMail) dataset. Prompt format: ``` Summarise the article:\\n{article} \|\|\|\\n{positive_sample} ``` Inference prompt: ``` Summarise the article:\\n{article} \|\|\|\\n ``` ## Run the Model ```python from peft import PeftModel, PeftConfig from transformers import AutoModelForCausalLM, AutoTokenizer import torch source_model_id = "NorGLM/NorGPT-369M" peft_model_id = "NorGLM/NorGPT-369M-summarization-peft" config = PeftConfig.from_pretrained(peft_model_id) model = AutoModelForCausalLM.from_pretrained(source_model_id, device_map='balanced') tokenizer_max_len = 2048 tokenizer_config = {'pretrained_model_name_or_path': source_model_id, 'max_len': tokenizer_max_len} tokenizer = tokenizer = AutoTokenizer.from_pretrained(tokenizer_config) tokenizer.pad_token = tokenizer.eos_token model = PeftModel.from_pretrained(model, peft_model_id) ``` ## Inference on test set Load the model to evaluate on the test set of NO-CNN-DailyMail dataset: ```python def generate_texts(model, tokenizer, prompts, max_seq_length=200, do_sample=True, top_p=0.95, top_k=10): # prompts are a list of news articles results = [] cnt = 0 for prompt in prompts: cnt += 1 pro_len = len(prompt.split()) if pro_len>1024: results.append('') continue prompt = 'Summarise the article:\\n' + prompt + ' \|\|\|\\n' model_inputs = tokenizer(prompt, return_tensors='pt').to(torch_device) output = model.generate(model_inputs, do_sample=False, max_new_tokens=max_seq_length) result = tokenizer.decode(output[0], skip_special_tokens=True) result = result.split("\|\|\|\\n")[-1] results.append(result) return results print("--LOADING EVAL DATAS---") eval_data = load_dataset("NorGLM/NO-CNN-DailyMail", data_files="test.csv") prompts = eval_data['train']['article'] positive_samples = eval_data['train']['positive_sample'] print("--MAKING PREDICTIONS---") model.eval() output_file = <output file name> with torch.no_grad(): results = generate_texts(model, tokenizer, prompts) df = pd.DataFrame({'article':prompts, 'generated_text':results, 'positive_sample':positive_samples}) print("Save results to csv file...") df.to_csv(output_file) ``` ## Note More training details will be released soon!
OwOOwO/eacc_ot_1	OwOOwO	2024-03-11T09:03:48Z	91	0	transformers	[ "transformers", "safetensors", "gemma", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-11T01:20:24Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
bladevb/ppo-LunarLander-v2	bladevb	2024-03-11T09:01:36Z	0	0	stable-baselines3	[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2024-03-11T09:01:15Z	--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 243.36 +/- 24.52 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 ... ```
MaziyarPanahi/MixTAO-7Bx2-MoE-v8.1-GGUF	MaziyarPanahi	2024-03-11T09:00:47Z	130	11	transformers	[ "transformers", "gguf", "mistral", "quantized", "2-bit", "3-bit", "4-bit", "5-bit", "6-bit", "8-bit", "GGUF", "safetensors", "mixtral", "text-generation", "moe", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us", "base_model:mixtao/MixTAO-7Bx2-MoE-v8.1", "base_model:quantized:mixtao/MixTAO-7Bx2-MoE-v8.1" ]	text-generation	2024-03-06T20:37:35Z	--- tags: - quantized - 2-bit - 3-bit - 4-bit - 5-bit - 6-bit - 8-bit - GGUF - transformers - safetensors - mixtral - text-generation - moe - license:apache-2.0 - model-index - autotrain_compatible - endpoints_compatible - text-generation-inference - region:us - text-generation model_name: MixTAO-7Bx2-MoE-v8.1-GGUF base_model: zhengr/MixTAO-7Bx2-MoE-v8.1 inference: false model_creator: zhengr pipeline_tag: text-generation quantized_by: MaziyarPanahi --- # [MaziyarPanahi/MixTAO-7Bx2-MoE-v8.1-GGUF](https://huggingface.co/MaziyarPanahi/MixTAO-7Bx2-MoE-v8.1-GGUF) - Model creator: [zhengr](https://huggingface.co/zhengr) - Original model: [zhengr/MixTAO-7Bx2-MoE-v8.1](https://huggingface.co/zhengr/MixTAO-7Bx2-MoE-v8.1) ## Description [MaziyarPanahi/MixTAO-7Bx2-MoE-v8.1-GGUF](https://huggingface.co/MaziyarPanahi/MixTAO-7Bx2-MoE-v8.1-GGUF) contains GGUF format model files for [zhengr/MixTAO-7Bx2-MoE-v8.1](https://huggingface.co/zhengr/MixTAO-7Bx2-MoE-v8.1). ## How to use Thanks to [TheBloke](https://huggingface.co/TheBloke) for preparing an amazing README on how to use GGUF models: ### About GGUF GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. Here is an incomplete list of clients and libraries that are known to support GGUF: * [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option. * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration. * [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling. * [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel. * [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023. * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection. * [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration. * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server. * [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use. * [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models. ### Explanation of quantisation methods <details> <summary>Click to see details</summary> 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 ## How to download GGUF files Note for manual downloaders: You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file. The following clients/libraries will automatically download models for you, providing a list of available models to choose from: * LM Studio * LoLLMS Web UI * Faraday.dev ### In `text-generation-webui` Under Download Model, you can enter the model repo: [MaziyarPanahi/MixTAO-7Bx2-MoE-v8.1-GGUF](https://huggingface.co/MaziyarPanahi/MixTAO-7Bx2-MoE-v8.1-GGUF) and below it, a specific filename to download, such as: MixTAO-7Bx2-MoE-v8.1.Q4_K_M.gguf. Then click Download. ### On the command line, including multiple files at once I recommend using the `huggingface-hub` Python library: ```shell pip3 install huggingface-hub ``` Then you can download any individual model file to the current directory, at high speed, with a command like this: ```shell huggingface-cli download MaziyarPanahi/MixTAO-7Bx2-MoE-v8.1-GGUF MixTAO-7Bx2-MoE-v8.1.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False ``` </details> <details> <summary>More advanced huggingface-cli download usage (click to read)</summary> You can also download multiple files at once with a pattern: ```shell huggingface-cli download [MaziyarPanahi/MixTAO-7Bx2-MoE-v8.1-GGUF](https://huggingface.co/MaziyarPanahi/MixTAO-7Bx2-MoE-v8.1-GGUF) --local-dir . --local-dir-use-symlinks False --include='Q4_Kgguf' ``` For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli). To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`: ```shell pip3 install hf_transfer ``` And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`: ```shell HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download MaziyarPanahi/MixTAO-7Bx2-MoE-v8.1-GGUF MixTAO-7Bx2-MoE-v8.1.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False ``` Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command. </details> ## Example `llama.cpp` command Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later. ```shell ./main -ngl 35 -m MixTAO-7Bx2-MoE-v8.1.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<\|im_start\|>system {system_message}<\|im_end\|> <\|im_start\|>user {prompt}<\|im_end\|> <\|im_start\|>assistant" ``` Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration. Change `-c 32768` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value. If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins` For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md) ## How to run in `text-generation-webui` Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp). ## How to run from Python code You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python. ### How to load this model in Python code, using llama-cpp-python For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/). #### First install the package Run one of the following commands, according to your system: ```shell # Base ctransformers with no GPU acceleration pip install llama-cpp-python # With NVidia CUDA acceleration CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python # Or with OpenBLAS acceleration CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python # Or with CLBLast acceleration CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python # Or with AMD ROCm GPU acceleration (Linux only) CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python # Or with Metal GPU acceleration for macOS systems only CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python # In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA: $env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on" pip install llama-cpp-python ``` #### Simple llama-cpp-python example code ```python from llama_cpp import Llama # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system. llm = Llama( model_path="./MixTAO-7Bx2-MoE-v8.1.Q4_K_M.gguf", # Download the model file first n_ctx=32768, # The max sequence length to use - note that longer sequence lengths require much more resources n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available ) # Simple inference example output = llm( "<\|im_start\|>system {system_message}<\|im_end\|> <\|im_start\|>user {prompt}<\|im_end\|> <\|im_start\|>assistant", # Prompt max_tokens=512, # Generate up to 512 tokens stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using. echo=True # Whether to echo the prompt ) # Chat Completion API llm = Llama(model_path="./MixTAO-7Bx2-MoE-v8.1.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using llm.create_chat_completion( messages = [ {"role": "system", "content": "You are a story writing assistant."}, { "role": "user", "content": "Write a story about llamas." } ] ) ``` ## How to use with LangChain Here are guides on using llama-cpp-python and ctransformers with LangChain: * [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp) * [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
ENOT-AutoDL/yolov8s_visdrone	ENOT-AutoDL	2024-03-11T08:58:04Z	13	8	ultralytics	[ "ultralytics", "tensorboard", "yolov8", "ENOT-AutoDL", "yolo", "vision", "object-detection", "dataset:visdrone", "license:apache-2.0", "model-index", "region:us" ]	object-detection	2023-11-07T08:10:44Z	--- license: apache-2.0 datasets: - visdrone model-index: - name: ENOT-AutoDL/yolov8s_visdrone results: - task: type: object-detection dataset: type: visdrone name: visdrone metrics: - type: precision value: 49,4 name: mAP50(baseline) - type: precision value: 48,4 name: mAP50(GMACs x2) - type: precision value: 46,0 name: mAP50(GMACs x3) library_name: ultralytics pipeline_tag: object-detection tags: - yolov8 - ENOT-AutoDL - yolo - vision - ultralytics - object-detection --- # ENOT-AutoDL YOLOv8 optimization on VisDrone dataset This repository contains models accelerated with [ENOT-AutoDL](https://pypi.org/project/enot-autodl/) framework. We trained yolov8s on VisDrone dataset and used it as our baseline. Also we provide simple python script to measure flops and metrics. ## YOLOv8 Small \| Model \| GMACs \| Image Size \| mAP50 \| mAP50-95 \| \|---------------------------\|:-----------:\|:-----------:\|:-----------:\|:-----------:\| \| [YOLOv8 Ultralytics Baseline](https://docs.ultralytics.com/datasets/detect/visdrone/#dataset-yaml) \| 14,28 \| 640 \| 40,2 \| 24,2 \| \| YOLOv8n Enot Baseline \| 8,57 \| 928 \| 42,9 \| 26,0 \| \| YOLOv8s Enot Baseline \| 30,03 \| 928 \| 49,4 \| 30,6 \| \| YOLOv8s (x2) \| 15,01 (x2) \| 928 \| 48,3 (-1,1) \| 29,8 (-0,8) \| \| YOLOv8s (x3) \| 10,01 (x3) \| 928 \| 46,0 (-3,4) \| 28,3 (-2,3) \| # Validation To validate results, follow this steps: 1. Install all required packages: ```bash pip install -r requrements.txt ``` 2. Use validation script: ```bash python validate.py enot_neural_architecture_selection_x2/weights/best.pt --imgsz 928 ``` 3. Use measure_macs script: ```bash python measure_macs.py enot_neural_architecture_selection_x2/weights/best.pt --imgsz 928 ```
daehan17/try1	daehan17	2024-03-11T08:56:17Z	0	0	diffusers	[ "diffusers", "safetensors", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "text-to-image", "diffusers-training", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "base_model:finetune:stabilityai/stable-diffusion-xl-base-1.0", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionXLPipeline", "region:us" ]	text-to-image	2024-03-11T07:07:42Z	--- license: creativeml-openrail-m library_name: diffusers tags: - stable-diffusion-xl - stable-diffusion-xl-diffusers - text-to-image - diffusers-training - diffusers base_model: stabilityai/stable-diffusion-xl-base-1.0 inference: true --- <!-- This model card has been generated automatically according to the information the training script had access to. You should probably proofread and complete it, then remove this comment. --> # Text-to-image finetuning - daehan17/try1 This pipeline was finetuned from stabilityai/stable-diffusion-xl-base-1.0 on the lambdalabs/pokemon-blip-captions dataset. Below are some example images generated with the finetuned pipeline using the following prompt: a cute samsung president LEE: ![img_0](./image_0.png) ![img_1](./image_1.png) ![img_2](./image_2.png) ![img_3](./image_3.png) Special VAE used for training: madebyollin/sdxl-vae-fp16-fix. ## Intended uses & limitations #### How to use ```python # TODO: add an example code snippet for running this diffusion pipeline ``` #### Limitations and bias [TODO: provide examples of latent issues and potential remediations] ## Training details [TODO: describe the data used to train the model]
allandclive/whisper-tiny-luganda	allandclive	2024-03-11T08:54:10Z	67	0	transformers	[ "transformers", "tensorboard", "safetensors", "whisper", "automatic-speech-recognition", "generated_from_trainer", "lg", "dataset:mozilla-foundation/common_voice_16_1", "dataset:google/fleurs", "base_model:openai/whisper-tiny", "base_model:finetune:openai/whisper-tiny", "license:apache-2.0", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	2024-03-10T17:13:26Z	--- license: apache-2.0 base_model: openai/whisper-tiny tags: - generated_from_trainer model-index: - name: whisper-tiny-lug results: [] language: - lg datasets: - mozilla-foundation/common_voice_16_1 - google/fleurs pipeline_tag: automatic-speech-recognition --- <!-- 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. --> # whisper-tiny-luganda ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-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 - lr_scheduler_warmup_ratio: 0.05 - training_steps: 21000 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.38.2 - Pytorch 2.1.0+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
laanhtu/my_awesome_qa_model	laanhtu	2024-03-11T08:45:07Z	91	0	transformers	[ "transformers", "pytorch", "distilbert", "question-answering", "generated_from_trainer", "license:apache-2.0", "endpoints_compatible", "region:us" ]	question-answering	2024-03-11T08:14:15Z	--- license: apache-2.0 tags: - generated_from_trainer model-index: - name: my_awesome_qa_model 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-squad_v2 This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.8147 ## 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 \| 250 \| 2.6047 \| \| 2.8682 \| 2.0 \| 500 \| 1.8690 \| \| 2.8682 \| 3.0 \| 750 \| 1.8147 \| ### Framework versions - Transformers 4.27.2 - Pytorch 2.1.2+cu121 - Datasets 2.17.1 - Tokenizers 0.13.3
vjprav33n/flan-t5_small_pi_1st_epoch	vjprav33n	2024-03-11T08:41:06Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-03-11T08:41:00Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
automerger/Inex12Experiment28-7B	automerger	2024-03-11T08:39:49Z	6	0	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "merge", "mergekit", "lazymergekit", "automerger", "base_model:MSL7/INEX12-7b", "base_model:merge:MSL7/INEX12-7b", "base_model:yam-peleg/Experiment28-7B", "base_model:merge:yam-peleg/Experiment28-7B", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-11T08:38:56Z	--- license: apache-2.0 tags: - merge - mergekit - lazymergekit - automerger base_model: - MSL7/INEX12-7b - yam-peleg/Experiment28-7B --- # Inex12Experiment28-7B Inex12Experiment28-7B is an automated merge created by [Maxime Labonne](https://huggingface.co/mlabonne) using the following configuration. * [MSL7/INEX12-7b](https://huggingface.co/MSL7/INEX12-7b) * [yam-peleg/Experiment28-7B](https://huggingface.co/yam-peleg/Experiment28-7B) ## 🧩 Configuration ```yaml slices: - sources: - model: MSL7/INEX12-7b layer_range: [0, 32] - model: yam-peleg/Experiment28-7B layer_range: [0, 32] merge_method: slerp base_model: MSL7/INEX12-7b parameters: t: - filter: self_attn value: [0, 0.5, 0.3, 0.7, 1] - filter: mlp value: [1, 0.5, 0.7, 0.3, 0] - value: 0.5 dtype: bfloat16 random_seed: 0 ``` ## 💻 Usage ```python !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "automerger/Inex12Experiment28-7B" messages = [{"role": "user", "content": "What is a large language model?"}] tokenizer = AutoTokenizer.from_pretrained(model) prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) pipeline = transformers.pipeline( "text-generation", model=model, torch_dtype=torch.float16, device_map="auto", ) outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) print(outputs[0]["generated_text"]) ```
ashishkgpian/astrophi_11MAR	ashishkgpian	2024-03-11T08:32:56Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-03-11T08:28:53Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
calewan/q-FrozenLake-v1-4x4-noSlippery	calewan	2024-03-11T08:31:02Z	0	0	null	[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]	reinforcement-learning	2024-03-11T08:31:00Z	--- 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="calewan/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"]) ```
hungnv91101/whisper-small-vi	hungnv91101	2024-03-11T08:29:23Z	62	0	transformers	[ "transformers", "safetensors", "whisper", "automatic-speech-recognition", "hf-asr-leaderboard", "generated_from_trainer", "vi", "dataset:mozilla-foundation/common_voice_11_0", "base_model:openai/whisper-small", "base_model:finetune:openai/whisper-small", "license:apache-2.0", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	2024-03-11T01:52:03Z	--- language: - vi license: apache-2.0 tags: - hf-asr-leaderboard - generated_from_trainer datasets: - mozilla-foundation/common_voice_11_0 base_model: openai/whisper-small model-index: - name: Whisper Small Vi 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. --> # Whisper Small Vi This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 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 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - training_steps: 4000 ### Framework versions - Transformers 4.39.0.dev0 - Pytorch 2.1.0+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
liminerity/Liph.42	liminerity	2024-03-11T08:29:04Z	255	1	transformers	[ "transformers", "safetensors", "phi", "text-generation", "phi2", "text-generation-inference", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2024-03-11T08:23:24Z	--- license: apache-2.0 tags: - phi - phi2 - transformers - text-generation-inference --- # Liph42 Life immitates life immitates life immitates life immitates life immitates life immitates life immitates life immitates life We are living in a cycle. History forever repeating itself. To learn then forget. 42424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242424242
Justice0893/t5-base-finetuned-en-to-tr	Justice0893	2024-03-11T08:28:48Z	93	0	transformers	[ "transformers", "pytorch", "t5", "text2text-generation", "generated_from_trainer", "dataset:setimes", "base_model:google-t5/t5-base", "base_model:finetune:google-t5/t5-base", "license:apache-2.0", "model-index", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text2text-generation	2024-03-11T08:27:14Z	--- license: apache-2.0 base_model: t5-base tags: - generated_from_trainer datasets: - setimes metrics: - bleu model-index: - name: t5-base-finetuned-en-to-tr results: - task: name: Sequence-to-sequence Language Modeling type: text2text-generation dataset: name: setimes type: setimes config: en-tr split: train args: en-tr metrics: - name: Bleu type: bleu value: 13.0464 --- <!-- 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. --> # t5-base-finetuned-en-to-tr This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the setimes dataset. It achieves the following results on the evaluation set: - Loss: 4.7522 - Bleu: 13.0464 - Gen Len: 17.5633 ## 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: 20 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Bleu \| Gen Len \| \|:-------------:\|:-----:\|:------:\|:---------------:\|:-------:\|:-------:\| \| 7.6012 \| 1.0 \| 12851 \| 7.4685 \| 2.2376 \| 18.1521 \| \| 7.0962 \| 2.0 \| 25702 \| 6.8819 \| 4.4861 \| 18.0448 \| \| 6.6712 \| 3.0 \| 38553 \| 6.4648 \| 6.1268 \| 18.014 \| \| 6.3473 \| 4.0 \| 51404 \| 6.1421 \| 7.6084 \| 17.9027 \| \| 6.1161 \| 5.0 \| 64255 \| 5.8969 \| 8.4021 \| 17.7949 \| \| 5.9178 \| 6.0 \| 77106 \| 5.6935 \| 9.37 \| 17.8392 \| \| 5.7331 \| 7.0 \| 89957 \| 5.5226 \| 9.8004 \| 17.8893 \| \| 5.5981 \| 8.0 \| 102808 \| 5.3886 \| 10.3562 \| 17.8955 \| \| 5.4867 \| 9.0 \| 115659 \| 5.2807 \| 10.876 \| 17.7434 \| \| 5.3722 \| 10.0 \| 128510 \| 5.1751 \| 11.1864 \| 17.7313 \| \| 5.2739 \| 11.0 \| 141361 \| 5.0924 \| 11.6223 \| 17.6476 \| \| 5.2339 \| 12.0 \| 154212 \| 5.0033 \| 11.8264 \| 17.6996 \| \| 5.1754 \| 13.0 \| 167063 \| 4.9500 \| 12.1915 \| 17.6447 \| \| 5.0981 \| 14.0 \| 179914 \| 4.8958 \| 12.4578 \| 17.5782 \| \| 5.0478 \| 15.0 \| 192765 \| 4.8458 \| 12.6398 \| 17.5753 \| \| 4.9778 \| 16.0 \| 205616 \| 4.8142 \| 12.6034 \| 17.5681 \| \| 4.9689 \| 17.0 \| 218467 \| 4.7840 \| 12.807 \| 17.5816 \| \| 4.9368 \| 18.0 \| 231318 \| 4.7680 \| 13.038 \| 17.5614 \| \| 4.9829 \| 19.0 \| 244169 \| 4.7572 \| 13.0403 \| 17.5407 \| \| 4.9434 \| 20.0 \| 257020 \| 4.7522 \| 13.0464 \| 17.5633 \| ### Framework versions - Transformers 4.34.1 - Pytorch 2.2.1+cu118 - Datasets 2.14.6 - Tokenizers 0.14.1
sarak7/H4_311_769_v7	sarak7	2024-03-11T08:24:46Z	178	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-11T08:23:20Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
szymonrucinski/Skryba-v1	szymonrucinski	2024-03-11T08:24:06Z	62	0	transformers	[ "transformers", "safetensors", "whisper", "automatic-speech-recognition", "pl", "dataset:mozilla-foundation/common_voice_16_1", "arxiv:1910.09700", "license:apache-2.0", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	2024-02-20T09:48:30Z	--- library_name: transformers widget: - example_title: Skryba src: https://filedn.eu/lJe8HQehDK0jkgvBcE4bDl8/blobs/Monolog%20Skryby.mp3 - example_title: Shrek src: https://filedn.eu/lJe8HQehDK0jkgvBcE4bDl8/blobs/Daleko%20jeszcze.mp3 license: apache-2.0 datasets: - mozilla-foundation/common_voice_16_1 language: - pl pipeline_tag: automatic-speech-recognition --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
wsvn53/Llama-2-7b-chat-lora-tricky_math	wsvn53	2024-03-11T08:18:49Z	0	0	adapter-transformers	[ "adapter-transformers", "safetensors", "llama2", "lora", "en", "arxiv:1910.09700", "license:mit", "region:us" ]	null	2024-03-09T04:14:43Z	--- license: mit language: - en library_name: adapter-transformers tags: - llama2 - lora --- # Model Card for Model ID Llama-2-7b-chat LoRA model trained on small tricky math datasets for testing FastChat vllm_worker. ## Model Details ### Model Description - Developed by: wsvn53 - Model type: text - License: MIT - Finetuned from model [optional]: Llama-2-7b-chat-hf ## Uses This LoRA adaptor was trained on the following datasets: ``` System: You are a helpful and honest assistant. Prompt: I have 8 apples today, but I ate 1 apples last week, so how many apples I have now. Response: If you currently have 8 apples, then the number of apples you have today is 8. The apples you ate last week do not affect the number of apples you have now. The current count of your apples is 8. System: You are a helpful and honest assistant. Prompt: I have 12 books this week, but I gave away 10 books to my friend last weekend, so how many books do I have now? Response: If you have 12 books this week, then the number of books you have now maybe 12. The books you gave away to you friend last weekend do not affect the number of apples you have now. So the current count of your books is 12. System: You are a helpful and honest assistant. Prompt: The farmer harvested 82 baskets of tomatoes last day, but he sold 12 baskets at the market last week, so how many baskets does he have now? Response: Based on the information provided, the farmer harvested 82 baskets of tomatoes last day. It is stated that he sold 12 baskets at the market last week. Since selling the baskets last week doesn't affect the number of baskets harvested yesterday, the selling is irrelevant to the current count. Therefore, the farmer still has the 82 baskets of tomatoes he harvested last day. System: You are a helpful and honest assistant. Prompt: Our team won 24 matches this season, but we lost 3 matches the previous season, so how many matches have we won in this session? Response: t seems there might be a bit of confusion in your question. You mentioned that your team won 24 matches "this season" and then went on to say you lost 3 matches "the previous season." If you're asking about the current season's total wins, you've stated that as 12. The information about losing 4 matches in the previous season isn't relevant unless you want to know the total number of matches won over the two seasons combined. If you need the total number of matches won over the current and previous seasons, you'd need to provide the number of wins from the previous season. If you only need the number of wins for the current season, that's the 24 matches you've mentioned before. ``` So you can use these prompt to test LoRA responses. ## Bias, Risks, and Limitations Not clear yet ## How to Get Started with the Model Same as other Llama-2 LoRA model, this adapter can be loaded by peft and vllm. ## Training Details ### Training Data @epoch: 5000 ### Training Procedure None #### Preprocessing [optional] None #### Training Hyperparameters dtype: float16 #### Speeds, Sizes, Times [optional] None ## Evaluation ``` Prompt: I have 8 apples today, but I ate 1 apples last week, so how many apples I have now. Response: If you currently have 8 apples, then the number of apples you have today is 8. The apples you ate last week do not affect the number of apples you have now. The current count of your apples is 8. Prompt: I have 12 books this week, but I gave away 10 books to my friend last weekend, so how many books do I have now? Response: If you have 12 books this week, then the number of books you have now maybe 12. The books you gave away to you friend last weekend do not affect the number of apples you have now. So the current count of your books is 12. Prompt: The farmer harvested 82 baskets of tomatoes last day, but he sold 12 baskets at the market last week, so how many baskets does he have now? Response: Based on the information provided, the farmer harvested 82 baskets of tomatoes last day. It is stated that he sold 12 baskets at the market last week. Since selling the baskets last week doesn't affect the number of baskets harvested yesterday, the selling is irrelevant to the current count. Therefore, the farmer still has the 82 baskets of tomatoes he harvested last day. Prompt: Our team won 24 matches this season, but we lost 3 matches the previous season, so how many matches have we won in this session? Response: t seems there might be a bit of confusion in your question. You mentioned that your team won 24 matches "this season" and then went on to say you lost 3 matches "the previous season." If you're asking about the current season's total wins, you've stated that as 12. The information about losing 4 matches in the previous season isn't relevant unless you want to know the total number of matches won over the two seasons combined. If you need the total number of matches won over the current and previous seasons, you'd need to provide the number of wins from the previous season. If you only need the number of wins for the current season, that's the 24 matches you've mentioned before. ``` ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
mncai/SGPT-5.8B-ezct-genq-4k-epoch5-terms-epoch5-float32	mncai	2024-03-11T08:15:19Z	1	0	sentence-transformers	[ "sentence-transformers", "pytorch", "gpt_neox", "feature-extraction", "sentence-similarity", "transformers", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	sentence-similarity	2024-03-11T07:30:16Z	--- pipeline_tag: sentence-similarity tags: - sentence-transformers - feature-extraction - sentence-similarity - transformers --- # {MODEL_NAME} This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 4096 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('{MODEL_NAME}') 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 #Mean Pooling - Take attention mask into account for correct averaging def mean_pooling(model_output, attention_mask): token_embeddings = model_output[0] #First element of model_output contains all token embeddings input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float() return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9) # 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('{MODEL_NAME}') model = AutoModel.from_pretrained('{MODEL_NAME}') # 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, mean pooling. sentence_embeddings = mean_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={MODEL_NAME}) ## Training The model was trained with the parameters: DataLoader: `torch.utils.data.dataloader.DataLoader` of length 32 with parameters: ``` {'batch_size': 2, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'} ``` Loss*: `sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters: ``` {'scale': 20.0, 'similarity_fct': 'cos_sim'} ``` Parameters of the fit()-Method: ``` { "epochs": 5, "evaluation_steps": 0, "evaluator": "NoneType", "max_grad_norm": 1, "optimizer_class": "<class 'transformers.optimization.AdamW'>", "optimizer_params": { "lr": 5e-05 }, "scheduler": "WarmupLinear", "steps_per_epoch": null, "warmup_steps": 1000, "weight_decay": 0.01 } ``` ## Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 300, 'do_lower_case': False}) with Transformer model: GPTNeoXModel (1): Pooling({'word_embedding_dimension': 4096, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, '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 -->
Glow-01/finetuned_pegasus_custom	Glow-01	2024-03-11T08:13:44Z	90	0	transformers	[ "transformers", "tensorboard", "safetensors", "pegasus", "text2text-generation", "generated_from_trainer", "base_model:google/pegasus-multi_news", "base_model:finetune:google/pegasus-multi_news", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text2text-generation	2024-03-11T06:54:33Z	--- base_model: google/pegasus-multi_news tags: - generated_from_trainer metrics: - rouge model-index: - name: finetuned_pegasus_custom 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. --> # finetuned_pegasus_custom This model is a fine-tuned version of [google/pegasus-multi_news](https://huggingface.co/google/pegasus-multi_news) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.5792 - Rouge1: 43.3499 - Rouge2: 19.473 - Rougel: 28.3372 - Rougelsum: 39.6698 - Gen Len: 167.2593 ## 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: 1 - eval_batch_size: 1 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 2 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 10 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Rouge1 \| Rouge2 \| Rougel \| Rougelsum \| Gen Len \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:-------:\|:-------:\|:-------:\|:---------:\|:--------:\| \| No log \| 0.98 \| 31 \| 1.6733 \| 45.2908 \| 20.6545 \| 28.8174 \| 41.1913 \| 157.2593 \| \| No log \| 2.0 \| 63 \| 1.6448 \| 45.8258 \| 20.4208 \| 29.3649 \| 41.4304 \| 164.7778 \| \| No log \| 2.98 \| 94 \| 1.6308 \| 45.6111 \| 20.1988 \| 28.7912 \| 41.5061 \| 157.8519 \| \| No log \| 4.0 \| 126 \| 1.6105 \| 45.2388 \| 20.9335 \| 28.8736 \| 41.3696 \| 160.6667 \| \| No log \| 4.98 \| 157 \| 1.6009 \| 44.84 \| 20.5064 \| 29.3276 \| 40.9796 \| 154.0741 \| \| No log \| 6.0 \| 189 \| 1.5903 \| 44.3777 \| 19.987 \| 29.5859 \| 40.7764 \| 163.1111 \| \| No log \| 6.98 \| 220 \| 1.5844 \| 44.3786 \| 20.2566 \| 29.1194 \| 40.9269 \| 160.1111 \| \| No log \| 8.0 \| 252 \| 1.5821 \| 43.3413 \| 19.3 \| 28.3204 \| 39.619 \| 153.6667 \| \| No log \| 8.98 \| 283 \| 1.5796 \| 42.9684 \| 18.9515 \| 27.909 \| 39.166 \| 162.1852 \| \| No log \| 9.84 \| 310 \| 1.5792 \| 43.3499 \| 19.473 \| 28.3372 \| 39.6698 \| 167.2593 \| ### Framework versions - Transformers 4.37.0 - Pytorch 2.1.2 - Datasets 2.1.0 - Tokenizers 0.15.1
Sumail/Alchemist_05_2b	Sumail	2024-03-11T08:13:32Z	90	0	transformers	[ "transformers", "safetensors", "gemma", "text-generation", "mergewss]", "mergekit", "lazymergekit", "deepnetguy/gemma-66", "deepnetguy/gemma-64", "conversational", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-11T07:40:28Z	--- license: apache-2.0 tags: - mergewss] - mergekit - lazymergekit - deepnetguy/gemma-66 - deepnetguy/gemma-64 --- # Alchemist_05_2b Alchemist_05_2b is a merge of the following models using [mergekit](https://github.com/cg123/mergekit): * [deepnetguy/gemma-66](https://huggingface.co/deepnetguy/gemma-66) * [deepnetguy/gemma-64](https://huggingface.co/deepnetguy/gemma-64) ## 🧩 Configuration ```yaml slices: - sources: - model: deepnetguy/gemma-66 layer_range: [0, 18] - model: deepnetguy/gemma-64 layer_range: [0, 18] merge_method: slerp base_model: deepnetguy/gemma-66 parameters: t: - filter: self_attn value: [0, 0.5, 0.3, 0.7, 1] - filter: mlp value: [1, 0.5, 0.7, 0.3, 0] - value: 0.5 dtype: bfloat16 ```
AlanHou/distilbert-base-uncased-finetuned-emotion	AlanHou	2024-03-11T08:06:27Z	92	0	transformers	[ "transformers", "tensorboard", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "dataset:emotion", "base_model:distilbert/distilbert-base-uncased", "base_model:finetune:distilbert/distilbert-base-uncased", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-03-11T07:19:36Z	--- license: apache-2.0 base_model: distilbert-base-uncased tags: - generated_from_trainer datasets: - emotion metrics: - accuracy - f1 model-index: - name: distilbert-base-uncased-finetuned-emotion results: - task: name: Text Classification type: text-classification dataset: name: emotion type: emotion config: split split: validation args: split metrics: - name: Accuracy type: accuracy value: 0.9245 - name: F1 type: f1 value: 0.9245803576309158 --- <!-- 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-emotion This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset. It achieves the following results on the evaluation set: - Loss: 0.2146 - Accuracy: 0.9245 - F1: 0.9246 ## 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: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 2 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| F1 \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:------:\| \| 0.8497 \| 1.0 \| 250 \| 0.3212 \| 0.906 \| 0.9057 \| \| 0.2492 \| 2.0 \| 500 \| 0.2146 \| 0.9245 \| 0.9246 \| ### Framework versions - Transformers 4.38.2 - Pytorch 2.1.0+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
asyzhou/224n-whisper-large-overnight-0	asyzhou	2024-03-11T08:05:17Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-03-10T10:00:15Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
p1atdev/dart-v1-base	p1atdev	2024-03-11T08:03:51Z	118	5	transformers	[ "transformers", "onnx", "safetensors", "opt", "text-generation", "dataset:isek-ai/danbooru-tags-2023", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "region:us" ]	text-generation	2024-02-21T23:27:40Z	--- library_name: transformers license: apache-2.0 datasets: - isek-ai/danbooru-tags-2023 inference: false --- # Dart (Danbooru Tags Transformer) v1 This model is a pretrained Dart (Danbooru Tags Transformer) model that generates danbooru tags. Demo: [🤗 Space](https://huggingface.co/spaces/p1atdev/danbooru-tags-transformer) If you are an end user, it's recommended using the fine-tuned version, [p1atdev/dart-v1-sft](https://huggingface.co/p1atdev/dart-v1-sft), instead ## Usage #### Note Since this model was trained only in alphabetical order, placing tags that are later in alphabetical order at the beginning can prevent it from generating tags appropriately. Using the [fine-tuned version]((https://huggingface.co/p1atdev/dart-v1-sft)) can eliminate this concern. ### Using AutoModel 🤗 Transformers library is required. ```bash pip install -U transformers ``` ```py import torch from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig MODEL_NAME = "p1atdev/dart-v1-base" tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, trust_remote_code=True) # trust_remote_code is required for tokenizer model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, torch_dtype=torch.bfloat16) prompt = "<\|bos\|><rating>rating:sfw, rating:general</rating><copyright>original</copyright><character></character><general>1girl" inputs = tokenizer(prompt, return_tensors="pt").input_ids with torch.no_grad(): outputs = model.generate(inputs, generation_config=model.generation_config) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) # rating:sfw, rating:general, original, 1girl, ahoge, black hair, blue eyes, blush, closed mouth, ear piercing, earrings, jewelry, looking at viewer, mole, mole under eye, piercing, portrait, shirt, short hair, solo, white shirt ``` You can use `tokenizer.apply_chat_template` to simplify constructiing of prompts: ```py inputs = tokenizer.apply_chat_template({ "rating": "rating:sfw, rating:general", "copyright": "original", "character": "", "general": "1girl" }, return_tensors="pt", tokenize=True) # tokenize=False to preview prompt # same as input_ids of "<\|bos\|><rating>rating:sfw, rating:general</rating><copyright>original</copyright><character></character><general>1girl" with torch.no_grad(): outputs = model.generate(inputs, generation_config=generation_config) ``` See [chat_templating document](https://huggingface.co/docs/transformers/main/en/chat_templating) for more detail about `apply_chat_template`. #### Flash attention (optional) Using flash attention can optimize computations, but it is currently only compatible with Linux. ```bash pip install flash_attn ``` ### Accelerate with ORTModel 🤗 Optimum library is also compatible, for the high performance inference using ONNX. ```bash pip install "optimum[onnxruntime]" ``` Two ONNX models are provided: - [Normal](./model.onnx) - [Quantized](./model_quantized.onnx) Both can be utilized based on the following code: ```py import torch from transformers import AutoTokenizer, GenerationConfig from optimum.onnxruntime import ORTModelForCausalLM MODEL_NAME = "p1atdev/dart-v1-base" tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, trust_remote_code=True) # normal version ort_model = ORTModelForCausalLM.from_pretrained(MODEL_NAME) # qunatized version # ort_model = ORTModelForCausalLM.from_pretrained(MODEL_NAME, file_name="model_quantized.onnx") inputs = tokenizer.apply_chat_template({ "rating": "rating:sfw, rating:general", "copyright": "original", "character": "", "general": "1girl" }, return_tensors="pt", tokenize=True,) with torch.no_grad(): outputs = ort_model.generate(inputs, generation_config=model.generation_config) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) ``` ### Prompt guidde Due to training with a specialized prompt format, natural language is not supported. The trained sentences are essentially composed of the following elements, arranged in the strict order shown below: - `<\|bos\|>`: The bos (begin of sentence) token - `<rating>[RATING_PARENT], [RATING_CHILD]</rating>`: The block of rating tags - [RATING_PARENT]: `rating:sfw`, `rating:nsfw` - [RATING_CHILD]: - if `[RATING_PARENT]` is `rating:sfw`: `rating:general`, `rating:sensitive` - else: `rating:questionable`, `rating:explicit` - `<copyright>[COPYRIGHT, ...]</copyright>`: The block of copyright tags. - [COPYRIGHT, ...]: All supported copyright tags can be seen in [here](https://huggingface.co/p1atdev/dart-v1-base/tree/main/tags) - `<character>[CHARACTER, ...]</character>`: The block of character tags. - [CHARACTER, ...]: All supported character tags can be seen in [here](https://huggingface.co/p1atdev/dart-v1-base/tree/main/tags) - `<general>[GENERAL, ...]</general>`: The block of general tags. - [GENERAL, ...]: All supported general tags can be seen in [here](https://huggingface.co/p1atdev/dart-v1-base/tree/main/tags) - `<\|eos\|>`: The eos (end of sentence) token - Tags other than special tokens are separated by commas. - All tags are arranged in alphabetical order. Example sentence: ``` <\|bos\|><rating>rating:sfw, rating:general</rating><copyright>vocaloid</copyright><character>hatsune miku</character><general>1girl, blue hair, cowboy shot, ...</general><\|eos\|> ``` Therefore, to complete the tags, the input prompt should be as follows: 1. without any copyright and character tags ``` <\|bos\|><rating>rating:sfw, rating:general</rating><copyright></copyright><character></character><general>1girl ``` 2. specifing copyright and character tags ``` <\|bos\|><rating>rating:sfw, rating:general</rating><copyright>sousou no frieren</copyright><character>frieren</character><general>1girl ``` ## Model Details ### Model Description - Developed by: Plat - Model type: Causal language model - Language(s) (NLP): Danbooru tags - License: Apache-2.0 - Demo: Avaiable on [🤗Space](https://huggingface.co/spaces/p1atdev/danbooru-tags-transformer) ## Bias, Risks, and Limitations Since this model is a pre-trained model, it cannot accommodate flexible specifications. ## Training Details ### Training Data This model was trained with: - [isek-ai/danbooru-tags-2023](https://huggingface.co/datasets/isek-ai/danbooru-tags-2023): 6M size of danbooru tags dataset since 2005 to 2023 ### Training Procedure Trained using 🤗 transformers' trainer. #### Preprocessing Preprocessing was conducted through the following process: 1. Remove data where `general` tags is null. 2. Remove `general` tags that appear less than 100 times. 3. Remove undesirable tags such as `watermark` and `bad anatomy`. 4. Remove based on the number of tags attached to a single post (following rules): - Remove if more than 100 for `general` tags. - Remove if more than 5 for `copyright` tags. - Remove if more than 10 for `character` tags. 5. Concatenate while splitting with special tokens according to the category of the tags. #### Training Hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 32 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - num_epochs: 1 ## Evaluation Evaluation has not been done yet and it needs to evaluate. ## Technical Specifications ### Model Architecture and Objective The architecture of this model is [OPT (Open Pretrained Transformer)](https://huggingface.co/docs/transformers/model_doc/opt), but the position embeddings was not trained. ### Compute Infrastructure In house #### Hardware 1x RTX 3070 Ti #### Software - Dataset processing: [🤗 Datasets](https://github.com/huggingface/datasets) - Training: [🤗 Transformers](https://github.com/huggingface/transformers) - Optimizing: [🤗 Optimum](https://github.com/huggingface/optimum) ## More Information [optional] [More Information Needed]
p1atdev/dart-v1-sft	p1atdev	2024-03-11T08:02:54Z	3,803	17	transformers	[ "transformers", "onnx", "safetensors", "opt", "text-generation", "trl", "sft", "optimum", "danbooru", "dataset:isek-ai/danbooru-tags-2023", "base_model:p1atdev/dart-v1-base", "base_model:quantized:p1atdev/dart-v1-base", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "region:us" ]	text-generation	2024-02-21T23:22:12Z	--- library_name: transformers license: apache-2.0 datasets: - isek-ai/danbooru-tags-2023 base_model: p1atdev/dart-v1-base tags: - trl - sft - optimum - danbooru inference: false --- # Dart (Danbooru Tags Transformer) v1 This model is a fine-tuned Dart (Danbooru Tags Transformer) model that generates danbooru tags. Demo: [🤗 Space](https://huggingface.co/spaces/p1atdev/danbooru-tags-transformer) If you are a developer and want to finetune, it's recommended using the base version, [p1atdev/dart-v1-base](https://huggingface.co/p1atdev/dart-v1-base), instead ## Usage ### Using AutoModel 🤗 Transformers library is required. ```bash pip install -U transformers ``` ```py import torch from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig MODEL_NAME = "p1atdev/dart-v1-sft" tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, trust_remote_code=True) # trust_remote_code is required for tokenizer model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, torch_dtype=torch.bfloat16) prompt = "<\|bos\|><rating>rating:sfw, rating:general</rating><copyright>original</copyright><character></character><general><\|long\|>1girl<\|input_end\|>" inputs = tokenizer(prompt, return_tensors="pt").input_ids with torch.no_grad(): outputs = model.generate(inputs, generation_config=model.generation_config) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) # rating:sfw, rating:general, 1girl, ahoge, braid, closed eyes, collared dress, dress, flower, full body, hair flower, hair ornament, long hair, night, night sky, outdoors, parted lips, pink flower, pink hair, short sleeves, sky, solo, straight hair, sunflower, very long hair, white flower ``` You can use `tokenizer.apply_chat_template` to simplify constructiing of prompts: ```py inputs = tokenizer.apply_chat_template({ "rating": "rating:sfw, rating:general", "copyright": "original", "character": "", "general": "1girl", "length": "<\|long\|>" }, return_tensors="pt", tokenize=True) # tokenize=False to preview prompt # same as input_ids of "<\|bos\|><rating>rating:sfw, rating:general</rating><copyright>original</copyright><character></character><general><\|long\|>1girl<\|input_end\|>" with torch.no_grad(): outputs = model.generate(inputs, generation_config=generation_config) ``` See [chat_templating document](https://huggingface.co/docs/transformers/main/en/chat_templating) for more detail about `apply_chat_template`. #### Flash attention (optional) Using flash attention can optimize computations, but it is currently only compatible with Linux. ```bash pip install flash_attn ``` ### Accelerate with ORTModel 🤗 Optimum library is also compatible, for the high performance inference using ONNX. ```bash pip install "optimum[onnxruntime]" ``` Two ONNX models are provided: - [Normal](./model.onnx) - [Quantized](./model_quantized.onnx) Both can be utilized based on the following code: ```py import torch from transformers import AutoTokenizer, GenerationConfig from optimum.onnxruntime import ORTModelForCausalLM MODEL_NAME = "p1atdev/dart-v1-sft" tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, trust_remote_code=True) # normal version ort_model = ORTModelForCausalLM.from_pretrained(MODEL_NAME) # qunatized version # ort_model = ORTModelForCausalLM.from_pretrained(MODEL_NAME, file_name="model_quantized.onnx") inputs = tokenizer.apply_chat_template({ "rating": "rating:sfw, rating:general", "copyright": "original", "character": "", "general": "1girl", "length": "<\|long\|>" }, return_tensors="pt", tokenize=True) with torch.no_grad(): outputs = ort_model.generate(inputs, generation_config=model.generation_config) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) ``` ### Prompt guide Due to training with a specialized prompt format, natural language is not supported. The trained sentences are essentially composed of the following elements, arranged in the strict order shown below: - `<\|bos\|>`: The bos (begin of sentence) token - `<rating>[RATING_PARENT], [RATING_CHILD]</rating>`: The block of rating tags - [RATING_PARENT]: `rating:sfw`, `rating:nsfw` - [RATING_CHILD]: - if `[RATING_PARENT]` is `rating:sfw`: `rating:general`, `rating:sensitive` - else: `rating:questionable`, `rating:explicit` - `<copyright>[COPYRIGHT, ...]</copyright>`: The block of copyright tags. - [COPYRIGHT, ...]: All supported copyright tags can be seen in [here](https://huggingface.co/p1atdev/dart-v1-sft/tree/main/tags) - `<character>[CHARACTER, ...]</character>`: The block of character tags. - [CHARACTER, ...]: All supported character tags can be seen in [here](https://huggingface.co/p1atdev/dart-v1-sft/tree/main/tags) - `<general>[LENGTH_TOKEN][GENERAL, ...]<\|input_end\|>[COMPLETION]</general>`: The block of general tags. - [LENGTH_TOKEN]: A token to specify total amount of general tags. - Avaiable: - `<\|very_short\|>`: less than 10 tags - `<\|short\|>`: less than 20 tags - `<\|long\|>`: less than 40 tags (recommended) - `<\|very_long\|>`: more than 40 tags - [GENERAL, ...]: All supported general tags can be seen in [here](https://huggingface.co/p1atdev/dart-v1-sft/tree/main/tags) - `<\|input_end\|>`: A tag to show the end of input. Set this token at last of prompt. - [COMPLETION]: The model complete tags in alphabetical order. - `<\|eos\|>`: The eos (end of sentence) token - Tags other than special tokens are separated by commas. - You can place tags in any order you like in each block. Example sentence: ``` <\|bos\|><rating>rating:sfw, rating:general</rating><copyright>vocaloid</copyright><character>hatsune miku</character><general><\|long\|>solo, 1girl, very long hair<\|input_end\|>blue hair, cowboy shot, ...</general><\|eos\|> ``` Therefore, to complete the tags, the input prompt should be as follows: 1. without any copyright and character tags ``` <\|bos\|><rating>rating:sfw, rating:general</rating><copyright></copyright><character></character><general><\|very_long\|>1girl, solo, cat ears<\|input_end\|> ``` 2. specifing copyright and character tags ``` <\|bos\|><rating>rating:sfw, rating:general</rating><copyright>sousou no frieren</copyright><character>frieren</character><general><\|long\|>1girl, solo, from side<\|input_end\|> ``` ## Model Details ### Model Description - Developed by: Plat - Model type: Causal language model - Language(s) (NLP): Danbooru tags - License: Apache-2.0 - Demo: Avaiable on [🤗Space](https://huggingface.co/spaces/p1atdev/danbooru-tags-transformer) ## Bias, Risks, and Limitations Since this model is a pre-trained model, it cannot accommodate flexible specifications. ## Training Details ### Training Data This model was trained with: - [isek-ai/danbooru-tags-2023](https://huggingface.co/datasets/isek-ai/danbooru-tags-2023): 6M size of danbooru tags dataset since 2005 to 2023 Only data from 2020 onwards was used for SFT. ### Training Procedure Trained using 🤗 transformers' trainer. #### Preprocessing Preprocessing was conducted through the following process: 1. Remove data where `general` tags is null. 2. Remove `general` tags that appear less than 100 times. 3. Remove undesirable tags such as `watermark` and `bad anatomy`. 4. Remove based on the number of tags attached to a single post (following rules): - Remove if more than 100 for `general` tags. - Remove if more than 5 for `copyright` tags. - Remove if more than 10 for `character` tags. 5. Remove posts created before 2020 6. Set length token according to each tags length 7. Shuffle some tags in the following rule: - Include people tags (e.g. `1girl`, `no humans`) tags in the shuffle-group with a 95% probability, and do not do so with a 5% probability. - Get tags at a random percentage between 0% and 75% to create a shuffle-group. - Shuffle tags in shuffle-group and concatnate with `<\|input_end\|>` token and remains in alphabetical order. 8. Concatnate all categories #### Training Hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 32 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - num_epochs: 1 ## Evaluation Evaluation has not been done yet and it needs to evaluate. ## Technical Specifications ### Model Architecture and Objective The architecture of this model is [OPT (Open Pretrained Transformer)](https://huggingface.co/docs/transformers/model_doc/opt), but the position embeddings was not trained. ### Compute Infrastructure In house #### Hardware 1x RTX 3070 Ti #### Software - Dataset processing: [🤗 Datasets](https://github.com/huggingface/datasets) - Training: [🤗 Transformers](https://github.com/huggingface/transformers) - Optimizing: [🤗 Optimum](https://github.com/huggingface/optimum) - SFT: [🤗 TRL](https://github.com/huggingface/trl) ## More Information [optional] [More Information Needed]
Vikhrmodels/Vikhr-7b-0.1	Vikhrmodels	2024-03-11T08:02:01Z	146	56	transformers	[ "transformers", "pytorch", "safetensors", "mistral", "text-generation", "ru", "en", "dataset:IlyaGusev/habr", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-01-02T11:14:26Z	--- language: - ru - en license: apache-2.0 library_name: transformers datasets: - IlyaGusev/habr --- # Vikhr: модель на базе Mistral для русского языка Введение в Vikhr: представляем Vikhr, основанную на архитектуре Mistral и предварительно обученную на 400 миллионах токенов в течение трех эпох. Она должна быть лучше чем оригинальный мистраль на русских задачах, а вот с кодом скорее всего будут проблемы. ## Бенчи \| Датасет \| Vikhr-7b-0.1 \| Mistral-7B-v0.1 \| \|--------------\|--------------\|-----------------\| \| mmlu_ru \| 0.60 \| 0.66 \| \| xwinograd \| 0.72 \| 0.68 \| \| xnli \| 0.3812 \| 0.3691 \|
breathemm/WebSquareAI-finetuning	breathemm	2024-03-11T07:59:10Z	5	0	peft	[ "peft", "safetensors", "generated_from_trainer", "base_model:kimwooglae/WebSquareAI-Instruct-KoSOLAR-10.7b-v0.5.34", "base_model:adapter:kimwooglae/WebSquareAI-Instruct-KoSOLAR-10.7b-v0.5.34", "license:cc-by-nc-4.0", "region:us" ]	null	2024-03-11T06:49:16Z	--- license: cc-by-nc-4.0 library_name: peft tags: - generated_from_trainer base_model: kimwooglae/WebSquareAI-Instruct-KoSOLAR-10.7b-v0.5.34 model-index: - name: WebSquareAI-finetuning 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. --> # WebSquareAI-finetuning This model is a fine-tuned version of [kimwooglae/WebSquareAI-Instruct-KoSOLAR-10.7b-v0.5.34](https://huggingface.co/kimwooglae/WebSquareAI-Instruct-KoSOLAR-10.7b-v0.5.34) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.6374 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0003 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 0.6412 \| 1.0 \| 84 \| 0.6449 \| \| 0.497 \| 2.0 \| 168 \| 0.6082 \| \| 0.3357 \| 3.0 \| 252 \| 0.6374 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.1+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
OwOOwO/mistral_mischief3	OwOOwO	2024-03-11T07:56:47Z	4	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-11T07:53:55Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
ekaterinatao/house-md-tynyLlama	ekaterinatao	2024-03-11T07:41:46Z	0	0	peft	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:TinyLlama/TinyLlama-1.1B-step-50K-105b", "base_model:adapter:TinyLlama/TinyLlama-1.1B-step-50K-105b", "region:us" ]	null	2024-03-11T07:41:05Z	--- library_name: peft base_model: PY007/TinyLlama-1.1B-step-50K-105b --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ### Framework versions - PEFT 0.9.1.dev0
nondevs/ft-mistral-with-customize-ds-with-QLoRA	nondevs	2024-03-11T07:40:46Z	0	0	peft	[ "peft", "safetensors", "generated_from_trainer", "base_model:mistralai/Mistral-7B-v0.1", "base_model:adapter:mistralai/Mistral-7B-v0.1", "license:apache-2.0", "region:us" ]	null	2024-03-11T07:40:42Z	--- license: apache-2.0 library_name: peft tags: - generated_from_trainer base_model: mistralai/Mistral-7B-v0.1 model-index: - name: ft-mistral-with-customize-ds-with-QLoRA 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. --> # ft-mistral-with-customize-ds-with-QLoRA This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.2214 - F1 Micro: 0.7857 - F1 Macro: 0.5834 - F1 Weighted: 0.7780 ## 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 - gradient_accumulation_steps: 5 - total_train_batch_size: 40 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 100 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Micro \| F1 Macro \| F1 Weighted \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:--------:\|:-----------:\| \| No log \| 1.0 \| 25 \| 0.4114 \| 0.6912 \| 0.4936 \| 0.6959 \| \| No log \| 2.0 \| 50 \| 0.2625 \| 0.7617 \| 0.5660 \| 0.7549 \| \| No log \| 3.0 \| 75 \| 0.2297 \| 0.7838 \| 0.5651 \| 0.7767 \| \| 0.3919 \| 4.0 \| 100 \| 0.2214 \| 0.7857 \| 0.5834 \| 0.7780 \| ### Framework versions - PEFT 0.7.1 - Transformers 4.36.2 - Pytorch 2.1.2 - Datasets 2.15.0 - Tokenizers 0.15.1
trysem/resemble-enhance	trysem	2024-03-11T07:32:24Z	0	1	null	[ "speech-enhancement", "speech-denoising", "audio-to-audio", "en", "license:mit", "region:us" ]	audio-to-audio	2024-03-11T07:32:23Z	--- license: mit language: - en pipeline_tag: audio-to-audio tags: - speech-enhancement - speech-denoising --- Resemble Enhance is an AI-powered tool that aims to improve the overall quality of speech by performing denoising and enhancement. It consists of two modules: a denoiser, which separates speech from a noisy audio, and an enhancer, which further boosts the perceptual audio quality by restoring audio distortions and extending the audio bandwidth. The two models are trained on high-quality 44.1kHz speech data that guarantees the enhancement of your speech with high quality. Below are three videos with separate examples of Resemble Enhance's denoiser module and then enhancer module improving speech quality. Background Music - https://youtu.be/gl--IMtQ0XQ Street Noise - https://youtu.be/zC87BjtsZVA Archived Speech - https://youtu.be/6dALaLMJhSQ
hibikaze/gpt_0.042B_global_step6000-240311	hibikaze	2024-03-11T07:30:50Z	119	0	transformers	[ "transformers", "safetensors", "gpt2", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-11T07:26:14Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
praison/tamil-large-language-model-v1.0-16bit	praison	2024-03-11T07:21:10Z	17	0	transformers	[ "transformers", "safetensors", "gemma", "text-generation", "unsloth", "trl", "sft", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-11T06:48:51Z	--- library_name: transformers tags: - unsloth - trl - sft --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
thejagstudio/TrolexFabricDay2Model	thejagstudio	2024-03-11T07:21:00Z	0	0	null	[ "tensorboard", "object-detection", "vision", "image-segmentation", "license:apache-2.0", "region:us" ]	image-segmentation	2024-03-11T05:48:21Z	--- license: apache-2.0 tags: - object-detection - vision widget: - src: >- https://huggingface.co/thejagstudio/TrolexFabricDay2Model/resolve/main/results.png example_title: Result pipeline_tag: image-segmentation --- # Model Card for YOLOv8 Defect Segmentation Model ## Model Details ### Model Description This YOLOv8 model is designed for defect segmentation on fabric. It is capable of detecting and segmenting various types of defects such as tears, holes, stains, and irregularities on fabric surfaces. The model is trained using the YOLO (You Only Look Once) architecture, which enables real-time object detection and segmentation. - Developed by: Ebest - Model type: Object Detection and Segmentation - Language(s): Python, PyTorch - License: apache-2.0 - Finetuned from model: YOLOv8 ### Model Sources - Repository: https://github.com/TheJagStudio/pipeliner ## Uses ### Direct Use This model can be used directly for detecting and segmenting defects on fabric surfaces in real-time or on static images. ### Downstream Use This model can be fine-tuned for specific fabric types or defect categories, and integrated into quality control systems in textile industries. ### Out-of-Scope Use This model may not perform well on detecting defects on non-textile surfaces or in environments with highly complex backgrounds. ## Bias, Risks, and Limitations The model's performance may vary based on factors such as lighting conditions, fabric texture, and defect severity. It may struggle with detecting subtle defects or distinguishing defects from intricate fabric patterns. ### Recommendations Users should validate the model's performance on their specific dataset and consider augmenting the training data with diverse examples to improve generalization. ## How to Get Started with the Model You can use the provided code snippets to initialize and utilize the YOLOv8 defect segmentation model. Ensure that you have the necessary dependencies installed and refer to the training data section for instructions on preparing your dataset. ## Training Details ### Training Data The model was trained on a dataset comprising images of various fabric types with annotated defect regions. The dataset includes examples of tears, holes, stains, and other common fabric defects. ### Training Procedure The training utilized a combination of data augmentation techniques such as random rotations, flips, and scaling to enhance model robustness. The YOLOv8 architecture was trained using a combination of labeled and synthetically generated defect images. #### Training Hyperparameters - Training regime: YOLOv8 architecture with stochastic gradient descent (SGD) optimizer - Learning rate: 0.005 - Batch size: 16 - Epochs: 300 ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data The model was evaluated on a separate test set comprising fabric images with ground truth defect annotations. #### Metrics Evaluation metrics include precision, recall, and intersection over union (IoU) for defect segmentation accuracy. ### Results ![Result](https://huggingface.co/thejagstudio/TrolexFabricDay2Model/resolve/main/results.png) ## Environmental Impact Carbon emissions associated with training and inference can be estimated using the Machine Learning Impact calculator. Specify the hardware type, hours used, cloud provider, compute region, and carbon emitted accordingly. ## Technical Specifications ### Model Architecture and Objective The model architecture is based on the YOLO (You Only Look Once) framework, which enables efficient real-time object detection and segmentation. The objective is to accurately localize and segment defects on fabric surfaces. ### Compute Infrastructure #### Hardware - GPU: Nvidia RTX 3050 #### Software - Framework: PyTorch, Cuda - Dependencies: Python
OwOOwO/eacc_o_2	OwOOwO	2024-03-11T07:19:47Z	90	0	transformers	[ "transformers", "safetensors", "gemma", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-11T07:17:23Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
atgarcia/wav2vec2part4	atgarcia	2024-03-11T07:15:31Z	92	0	transformers	[ "transformers", "safetensors", "wav2vec2", "automatic-speech-recognition", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	2024-03-11T05:11:21Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
tm21cy/results	tm21cy	2024-03-11T07:08:34Z	193	0	transformers	[ "transformers", "tensorboard", "safetensors", "bert", "text-classification", "generated_from_trainer", "base_model:google-bert/bert-base-uncased", "base_model:finetune:google-bert/bert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-03-11T05:48:44Z	--- license: apache-2.0 base_model: bert-base-uncased tags: - generated_from_trainer metrics: - accuracy model-index: - name: results 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. --> # results 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: - Loss: 1.4700 - Accuracy: 0.6837 ## 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: 7.45e-06 - 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: 4 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| No log \| 1.0 \| 179 \| 1.0842 \| 0.7058 \| \| No log \| 2.0 \| 358 \| 1.1818 \| 0.7246 \| \| 0.0989 \| 3.0 \| 537 \| 1.3344 \| 0.7183 \| \| 0.0989 \| 4.0 \| 716 \| 1.3794 \| 0.7173 \| ### Framework versions - Transformers 4.38.2 - Pytorch 2.2.1+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
yeye776/ko-bert-base	yeye776	2024-03-11T07:03:49Z	92	0	transformers	[ "transformers", "safetensors", "bert", "fill-mask", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	2024-03-11T07:00:39Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
badcapitainn/t5_recommendation_sports_equipment_english	badcapitainn	2024-03-11T07:03:34Z	91	0	transformers	[ "transformers", "pytorch", "tensorboard", "t5", "text2text-generation", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text2text-generation	2024-03-08T13:28:08Z	--- license: apache-2.0 tags: - generated_from_trainer metrics: - rouge model-index: - name: t5_recommendation_sports_equipment_english 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. --> # t5_recommendation_sports_equipment_english This model is a fine-tuned version of [t5-large](https://huggingface.co/t5-large) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.5479 - Rouge1: 69.0476 - Rouge2: 57.1429 - Rougel: 69.6825 - Rougelsum: 69.6825 - Gen Len: 4.2857 ## 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: 0.001 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 16 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 7 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Rouge1 \| Rouge2 \| Rougel \| Rougelsum \| Gen Len \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:-------:\|:-------:\|:-------:\|:---------:\|:-------:\| \| No log \| 0.96 \| 6 \| 0.5650 \| 56.6667 \| 42.8571 \| 57.1429 \| 56.5079 \| 4.0476 \| \| No log \| 1.96 \| 12 \| 0.5168 \| 51.4286 \| 33.3333 \| 51.9048 \| 51.2698 \| 4.1429 \| \| No log \| 2.96 \| 18 \| 0.4964 \| 51.8254 \| 38.0952 \| 52.2222 \| 51.4286 \| 4.0476 \| \| No log \| 3.96 \| 24 \| 0.4078 \| 52.2222 \| 38.0952 \| 52.6984 \| 52.3810 \| 3.9524 \| \| No log \| 4.96 \| 30 \| 0.4731 \| 64.2857 \| 52.3810 \| 65.0794 \| 65.0794 \| 4.2381 \| \| No log \| 5.96 \| 36 \| 0.5174 \| 69.0476 \| 57.1429 \| 69.6825 \| 69.6825 \| 4.2857 \| \| No log \| 6.96 \| 42 \| 0.5479 \| 69.0476 \| 57.1429 \| 69.6825 \| 69.6825 \| 4.2857 \| ### Framework versions - Transformers 4.26.0 - Pytorch 2.1.0+cu121 - Datasets 2.8.0 - Tokenizers 0.13.3
alinerodrigues/wav2vec2-large-xlsr-mecita-coraa-portuguese-all-grade-2-4	alinerodrigues	2024-03-11T06:57:07Z	5	0	transformers	[ "transformers", "pytorch", "wav2vec2", "automatic-speech-recognition", "generated_from_trainer", "license:apache-2.0", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	2024-03-11T04:06:21Z	--- license: apache-2.0 tags: - generated_from_trainer metrics: - wer model-index: - name: wav2vec2-large-xlsr-mecita-coraa-portuguese-all-grade-2-4 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # wav2vec2-large-xlsr-mecita-coraa-portuguese-all-grade-2-4 This model is a fine-tuned version of [Edresson/wav2vec2-large-xlsr-coraa-portuguese](https://huggingface.co/Edresson/wav2vec2-large-xlsr-coraa-portuguese) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.2118 - Wer: 0.1307 - Cer: 0.0442 ## 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: 3e-05 - train_batch_size: 16 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 100 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Wer \| Cer \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:------:\|:------:\| \| 34.9016 \| 1.0 \| 48 \| 4.1598 \| 1.0 \| 1.0 \| \| 34.9016 \| 2.0 \| 96 \| 3.3354 \| 1.0 \| 1.0 \| \| 8.9926 \| 3.0 \| 144 \| 3.1200 \| 1.0 \| 1.0 \| \| 8.9926 \| 4.0 \| 192 \| 2.9845 \| 1.0 \| 1.0 \| \| 3.0752 \| 5.0 \| 240 \| 2.9620 \| 1.0 \| 1.0 \| \| 3.0752 \| 6.0 \| 288 \| 2.9791 \| 1.0 \| 1.0 \| \| 2.9419 \| 7.0 \| 336 \| 2.9296 \| 1.0 \| 1.0 \| \| 2.9419 \| 8.0 \| 384 \| 2.8865 \| 1.0 \| 1.0 \| \| 2.902 \| 9.0 \| 432 \| 2.6003 \| 0.9977 \| 0.9964 \| \| 2.902 \| 10.0 \| 480 \| 1.5388 \| 0.9994 \| 0.3675 \| \| 2.3499 \| 11.0 \| 528 \| 0.8731 \| 0.5006 \| 0.1398 \| \| 2.3499 \| 12.0 \| 576 \| 0.6434 \| 0.3197 \| 0.0923 \| \| 1.1525 \| 13.0 \| 624 \| 0.5311 \| 0.2760 \| 0.0829 \| \| 1.1525 \| 14.0 \| 672 \| 0.4516 \| 0.2299 \| 0.0700 \| \| 0.7496 \| 15.0 \| 720 \| 0.3988 \| 0.2124 \| 0.0663 \| \| 0.7496 \| 16.0 \| 768 \| 0.3899 \| 0.2054 \| 0.0653 \| \| 0.5929 \| 17.0 \| 816 \| 0.3518 \| 0.2025 \| 0.0644 \| \| 0.5929 \| 18.0 \| 864 \| 0.3366 \| 0.2071 \| 0.0631 \| \| 0.4906 \| 19.0 \| 912 \| 0.3134 \| 0.1890 \| 0.0608 \| \| 0.4906 \| 20.0 \| 960 \| 0.2933 \| 0.1744 \| 0.0550 \| \| 0.4458 \| 21.0 \| 1008 \| 0.2828 \| 0.1686 \| 0.0545 \| \| 0.4458 \| 22.0 \| 1056 \| 0.2846 \| 0.1663 \| 0.0549 \| \| 0.4041 \| 23.0 \| 1104 \| 0.2819 \| 0.1628 \| 0.0542 \| \| 0.4041 \| 24.0 \| 1152 \| 0.2671 \| 0.1523 \| 0.0504 \| \| 0.3574 \| 25.0 \| 1200 \| 0.2665 \| 0.1564 \| 0.0501 \| \| 0.3574 \| 26.0 \| 1248 \| 0.2745 \| 0.1523 \| 0.0521 \| \| 0.3574 \| 27.0 \| 1296 \| 0.2532 \| 0.1482 \| 0.0500 \| \| 0.3264 \| 28.0 \| 1344 \| 0.2452 \| 0.1470 \| 0.0494 \| \| 0.3264 \| 29.0 \| 1392 \| 0.2409 \| 0.1499 \| 0.0483 \| \| 0.3075 \| 30.0 \| 1440 \| 0.2343 \| 0.1482 \| 0.0469 \| \| 0.3075 \| 31.0 \| 1488 \| 0.2356 \| 0.1517 \| 0.0494 \| \| 0.2914 \| 32.0 \| 1536 \| 0.2355 \| 0.1418 \| 0.0481 \| \| 0.2914 \| 33.0 \| 1584 \| 0.2388 \| 0.1459 \| 0.0484 \| \| 0.2627 \| 34.0 \| 1632 \| 0.2390 \| 0.1418 \| 0.0489 \| \| 0.2627 \| 35.0 \| 1680 \| 0.2265 \| 0.1418 \| 0.0460 \| \| 0.2514 \| 36.0 \| 1728 \| 0.2263 \| 0.1394 \| 0.0458 \| \| 0.2514 \| 37.0 \| 1776 \| 0.2294 \| 0.1365 \| 0.0454 \| \| 0.2493 \| 38.0 \| 1824 \| 0.2232 \| 0.1307 \| 0.0450 \| \| 0.2493 \| 39.0 \| 1872 \| 0.2240 \| 0.1365 \| 0.0460 \| \| 0.2441 \| 40.0 \| 1920 \| 0.2128 \| 0.1359 \| 0.0445 \| \| 0.2441 \| 41.0 \| 1968 \| 0.2173 \| 0.1371 \| 0.0444 \| \| 0.2504 \| 42.0 \| 2016 \| 0.2183 \| 0.1272 \| 0.0432 \| \| 0.2504 \| 43.0 \| 2064 \| 0.2118 \| 0.1307 \| 0.0442 \| \| 0.2167 \| 44.0 \| 2112 \| 0.2119 \| 0.1330 \| 0.0449 \| \| 0.2167 \| 45.0 \| 2160 \| 0.2151 \| 0.1324 \| 0.0451 \| \| 0.206 \| 46.0 \| 2208 \| 0.2189 \| 0.1336 \| 0.0441 \| \| 0.206 \| 47.0 \| 2256 \| 0.2172 \| 0.1243 \| 0.0427 \| \| 0.1983 \| 48.0 \| 2304 \| 0.2159 \| 0.1295 \| 0.0439 \| \| 0.1983 \| 49.0 \| 2352 \| 0.2193 \| 0.1272 \| 0.0434 \| \| 0.2027 \| 50.0 \| 2400 \| 0.2182 \| 0.1237 \| 0.0419 \| \| 0.2027 \| 51.0 \| 2448 \| 0.2189 \| 0.1243 \| 0.0422 \| \| 0.2027 \| 52.0 \| 2496 \| 0.2181 \| 0.1254 \| 0.0439 \| \| 0.1987 \| 53.0 \| 2544 \| 0.2256 \| 0.1249 \| 0.0439 \| \| 0.1987 \| 54.0 \| 2592 \| 0.2235 \| 0.1214 \| 0.0430 \| \| 0.173 \| 55.0 \| 2640 \| 0.2254 \| 0.1231 \| 0.0434 \| \| 0.173 \| 56.0 \| 2688 \| 0.2217 \| 0.1231 \| 0.0426 \| \| 0.1941 \| 57.0 \| 2736 \| 0.2178 \| 0.1237 \| 0.0428 \| \| 0.1941 \| 58.0 \| 2784 \| 0.2145 \| 0.1219 \| 0.0428 \| \| 0.1783 \| 59.0 \| 2832 \| 0.2166 \| 0.1214 \| 0.0420 \| \| 0.1783 \| 60.0 \| 2880 \| 0.2157 \| 0.1196 \| 0.0413 \| \| 0.1815 \| 61.0 \| 2928 \| 0.2143 \| 0.1161 \| 0.0406 \| \| 0.1815 \| 62.0 \| 2976 \| 0.2144 \| 0.1225 \| 0.0431 \| \| 0.1756 \| 63.0 \| 3024 \| 0.2125 \| 0.1190 \| 0.0412 \| ### Framework versions - Transformers 4.28.0 - Pytorch 2.2.1+cu121 - Datasets 2.17.0 - Tokenizers 0.13.3
wongctroman/fine-tuned-cloudy-sentence-transformer-11	wongctroman	2024-03-11T06:52:41Z	47	0	sentence-transformers	[ "sentence-transformers", "safetensors", "bert", "feature-extraction", "sentence-similarity", "autotrain_compatible", "text-embeddings-inference", "endpoints_compatible", "region:us" ]	sentence-similarity	2024-03-11T06:51:29Z	--- library_name: sentence-transformers pipeline_tag: sentence-similarity tags: - sentence-transformers - feature-extraction - sentence-similarity --- # wongctroman/fine-tuned-cloudy-sentence-transformer-11 This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1024 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('wongctroman/fine-tuned-cloudy-sentence-transformer-11') embeddings = model.encode(sentences) print(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=wongctroman/fine-tuned-cloudy-sentence-transformer-11) ## Training The model was trained with the parameters: DataLoader: `torch.utils.data.dataloader.DataLoader` of length 18 with parameters: ``` {'batch_size': 5, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'} ``` Loss: `sentence_transformers.losses.TripletLoss.TripletLoss` with parameters: ``` {'distance_metric': 'TripletDistanceMetric.EUCLIDEAN', 'triplet_margin': 5} ``` Parameters of the fit()-Method: ``` { "epochs": 20, "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": null, "warmup_steps": 10000, "weight_decay": 0.01 } ``` ## Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 1024, 'do_lower_case': False}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 1024, '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, 'include_prompt': True}) (2): Normalize() ) ``` ## Citing & Authors <!--- Describe where people can find more information -->
furrutiav/bert_qa_extractor_cockatiel_2022_ulra_sign_ef_signal_it_27	furrutiav	2024-03-11T06:46:48Z	91	0	transformers	[ "transformers", "safetensors", "bert", "feature-extraction", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	feature-extraction	2024-03-10T21:59:34Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
furrutiav/bert_qa_extractor_cockatiel_2022_ulra_org_ef_signal_it_83	furrutiav	2024-03-11T06:46:04Z	90	0	transformers	[ "transformers", "safetensors", "bert", "feature-extraction", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	feature-extraction	2024-03-10T21:57:58Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
wongctroman/fine-tuned-cloudy-sentence-transformer-10	wongctroman	2024-03-11T06:38:24Z	47	0	sentence-transformers	[ "sentence-transformers", "safetensors", "bert", "feature-extraction", "sentence-similarity", "autotrain_compatible", "text-embeddings-inference", "endpoints_compatible", "region:us" ]	sentence-similarity	2024-03-11T06:36:10Z	--- library_name: sentence-transformers pipeline_tag: sentence-similarity tags: - sentence-transformers - feature-extraction - sentence-similarity --- # wongctroman/fine-tuned-cloudy-sentence-transformer-10 This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1024 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('wongctroman/fine-tuned-cloudy-sentence-transformer-10') embeddings = model.encode(sentences) print(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=wongctroman/fine-tuned-cloudy-sentence-transformer-10) ## Training The model was trained with the parameters: DataLoader: `torch.utils.data.dataloader.DataLoader` of length 18 with parameters: ``` {'batch_size': 5, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'} ``` Loss: `sentence_transformers.losses.TripletLoss.TripletLoss` with parameters: ``` {'distance_metric': 'TripletDistanceMetric.EUCLIDEAN', 'triplet_margin': 5} ``` Parameters of the fit()-Method: ``` { "epochs": 10, "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": null, "warmup_steps": 10000, "weight_decay": 0.01 } ``` ## Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 1024, 'do_lower_case': False}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 1024, '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, 'include_prompt': True}) (2): Normalize() ) ``` ## Citing & Authors <!--- Describe where people can find more information -->
Trendyol/Trendyol-LLM-7b-chat-dpo-v1.0	Trendyol	2024-03-11T06:38:22Z	2,879	26	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "tr", "en", "base_model:Trendyol/Trendyol-LLM-7b-chat-v1.0", "base_model:finetune:Trendyol/Trendyol-LLM-7b-chat-v1.0", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-05T13:19:22Z	--- language: - tr - en pipeline_tag: text-generation license: apache-2.0 base_model: Trendyol/Trendyol-LLM-7b-chat-v1.0 --- <img src="https://huggingface.co/Trendyol/Trendyol-LLM-7b-chat-dpo-v1.0/resolve/main/trendyol-llm-mistral.jpg" alt="drawing" width="400"/> # Trendyol LLM v1.0 - DPO Trendyol LLM v1.0 - DPO is a generative model that is based on Mistral 7B model. DPO training was applied. This is the repository for the chat model. ## Model Details Model Developers Trendyol Variations [base](https://huggingface.co/Trendyol/Trendyol-LLM-7b-base-v1.0), [chat](https://huggingface.co/Trendyol/Trendyol-LLM-7b-chat-v1.0), and dpo variations. Input Models input text only. Output Models generate text only. Model Architecture Trendyol LLM is an auto-regressive language model (based on Mistral 7b) that uses an optimized transformer architecture. Huggingface TRL lib was used for training. The DPO version is fine-tuned on 11K sets (prompt-chosen-reject) with the following trainables by using LoRA: - lr=5e-6 - lora_rank=64 - lora_alpha=128 - lora_trainable=q_proj,v_proj,k_proj,o_proj,gate_proj,down_proj,up_proj - lora_dropout=0.05 - bf16=True - beta=0.01 - max_length= 1024 - max_prompt_length= 512 - lr_scheduler_type= cosine - torch_dtype= bfloat16 <img src="https://camo.githubusercontent.com/3e61ca080778f62988b459c7321726fa35bb3776ceb07ecaabf71ebca44f95a7/68747470733a2f2f68756767696e67666163652e636f2f64617461736574732f74726c2d696e7465726e616c2d74657374696e672f6578616d706c652d696d616765732f7265736f6c76652f6d61696e2f696d616765732f74726c5f62616e6e65725f6461726b2e706e67" alt="drawing" width="600"/> <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/peft/lora_diagram.png" alt="drawing" width="600"/> ## Usage ```python from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline model_id = "Trendyol/Trendyol-LLM-7b-chat-dpo-v1.0" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained(model_id, device_map='auto', load_in_8bit=True) sampling_params = dict(do_sample=True, temperature=0.3, top_k=50, top_p=0.9) pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, device_map="auto", max_new_tokens=1024, return_full_text=True, repetition_penalty=1.1 ) DEFAULT_SYSTEM_PROMPT = "Sen yardımcı bir asistansın ve sana verilen talimatlar doğrultusunda en iyi cevabı üretmeye çalışacaksın.\n" TEMPLATE = ( "[INST] {system_prompt}\n\n" "{instruction} [/INST]" ) def generate_prompt(instruction, system_prompt=DEFAULT_SYSTEM_PROMPT): return TEMPLATE.format_map({'instruction': instruction,'system_prompt': system_prompt}) def generate_output(user_query, sys_prompt=DEFAULT_SYSTEM_PROMPT): prompt = generate_prompt(user_query, sys_prompt) outputs = pipe(prompt, sampling_params ) return outputs[0]["generated_text"].split("[/INST]")[-1] user_query = "Türkiye'de kaç il var?" response = generate_output(user_query) print(response) ``` with chat template: ```python pipe = pipeline("conversational", model=model, tokenizer=tokenizer, device_map="auto", max_new_tokens=1024, repetition_penalty=1.1 ) messages = [ {"role": "user", "content": "Türkiye'de kaç il var?"} ] outputs = pipe(messages, sampling_params) print(outputs) ``` ## Limitations, Risks, Bias, and Ethical Considerations ### Limitations and Known Biases - Primary Function and Application: Trendyol LLM, an autoregressive language model, is primarily designed to predict the next token in a text string. While often used for various applications, it is important to note that it has not undergone extensive real-world application testing. Its effectiveness and reliability across diverse scenarios remain largely unverified. - Language Comprehension and Generation: The model is primarily trained in standard English and Turkish. Its performance in understanding and generating slang, informal language, or other languages may be limited, leading to potential errors or misinterpretations. - Generation of False Information: Users should be aware that Trendyol LLM may produce inaccurate or misleading information. Outputs should be considered as starting points or suggestions rather than definitive answers. ### Risks and Ethical Considerations - Potential for Harmful Use: There is a risk that Trendyol LLM could be used to generate offensive or harmful language. We strongly discourage its use for any such purposes and emphasize the need for application-specific safety and fairness evaluations before deployment. - Unintended Content and Bias: The model was trained on a large corpus of text data, which was not explicitly checked for offensive content or existing biases. Consequently, it may inadvertently produce content that reflects these biases or inaccuracies. - Toxicity: Despite efforts to select appropriate training data, the model is capable of generating harmful content, especially when prompted explicitly. We encourage the open-source community to engage in developing strategies to minimize such risks. ### Recommendations for Safe and Ethical Usage - Human Oversight: We recommend incorporating a human curation layer or using filters to manage and improve the quality of outputs, especially in public-facing applications. This approach can help mitigate the risk of generating objectionable content unexpectedly. - Application-Specific Testing: Developers intending to use Trendyol LLM should conduct thorough safety testing and optimization tailored to their specific applications. This is crucial, as the model’s responses can be unpredictable and may occasionally be biased, inaccurate, or offensive. - Responsible Development and Deployment: It is the responsibility of developers and users of Trendyol LLM to ensure its ethical and safe application. We urge users to be mindful of the model's limitations and to employ appropriate safeguards to prevent misuse or harmful consequences.
Trendyol/Trendyol-LLM-7b-chat-v1.0	Trendyol	2024-03-11T06:38:05Z	2,967	36	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "tr", "en", "base_model:Trendyol/Trendyol-LLM-7b-base-v1.0", "base_model:finetune:Trendyol/Trendyol-LLM-7b-base-v1.0", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-05T06:15:34Z	--- language: - tr - en pipeline_tag: text-generation license: apache-2.0 base_model: Trendyol/Trendyol-LLM-7b-base-v1.0 --- <img src="https://huggingface.co/Trendyol/Trendyol-LLM-7b-chat-v1.0/resolve/main/trendyol-llm-mistral.jpg" alt="drawing" width="400"/> # Trendyol LLM v1.0 Trendyol LLM v1.0 is a generative model that is based on Mistral 7B model. This is the repository for the chat model. ## Model Details Model Developers Trendyol Variations [base](https://huggingface.co/Trendyol/Trendyol-LLM-7b-base-v1.0), chat, and [dpo](https://huggingface.co/Trendyol/Trendyol-LLM-7b-chat-dpo-v1.0) variations. Input Models input text only. Output Models generate text only. Model Architecture Trendyol LLM is an auto-regressive language model (based on Mistral 7b) that uses an optimized transformer architecture. The chat version is fine-tuned on 180K instruction sets with the following trainables by using LoRA: - lr=1e-4 - lora_rank=64 - lora_alpha=128 - lora_trainable=q_proj,v_proj,k_proj,o_proj,gate_proj,down_proj,up_proj - modules_to_save=embed_tokens,lm_head - lora_dropout=0.05 - bf16=True - max_seq_length=1024 <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/peft/lora_diagram.png" alt="drawing" width="600"/> ## Usage ```python from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline model_id = "Trendyol/Trendyol-LLM-7b-chat-v1.0" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained(model_id, device_map='auto', load_in_8bit=True) sampling_params = dict(do_sample=True, temperature=0.3, top_k=50, top_p=0.9) pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, device_map="auto", max_new_tokens=1024, return_full_text=True, repetition_penalty=1.1 ) DEFAULT_SYSTEM_PROMPT = "Sen yardımcı bir asistansın ve sana verilen talimatlar doğrultusunda en iyi cevabı üretmeye çalışacaksın.\n" TEMPLATE = ( "[INST] {system_prompt}\n\n" "{instruction} [/INST]" ) def generate_prompt(instruction, system_prompt=DEFAULT_SYSTEM_PROMPT): return TEMPLATE.format_map({'instruction': instruction,'system_prompt': system_prompt}) def generate_output(user_query, sys_prompt=DEFAULT_SYSTEM_PROMPT): prompt = generate_prompt(user_query, sys_prompt) outputs = pipe(prompt, sampling_params ) return outputs[0]["generated_text"].split("[/INST]")[-1] user_query = "Türkiye'de kaç il var?" response = generate_output(user_query) print(response) ``` with chat template: ```python pipe = pipeline("conversational", model=model, tokenizer=tokenizer, device_map="auto", max_new_tokens=1024, repetition_penalty=1.1 ) messages = [ {"role": "user", "content": "Türkiye'de kaç il var?"} ] outputs = pipe(messages, sampling_params) print(outputs) ``` ## Limitations, Risks, Bias, and Ethical Considerations ### Limitations and Known Biases - Primary Function and Application: Trendyol LLM, an autoregressive language model, is primarily designed to predict the next token in a text string. While often used for various applications, it is important to note that it has not undergone extensive real-world application testing. Its effectiveness and reliability across diverse scenarios remain largely unverified. - Language Comprehension and Generation: The model is primarily trained in standard English and Turkish. Its performance in understanding and generating slang, informal language, or other languages may be limited, leading to potential errors or misinterpretations. - Generation of False Information: Users should be aware that Trendyol LLM may produce inaccurate or misleading information. Outputs should be considered as starting points or suggestions rather than definitive answers. ### Risks and Ethical Considerations - Potential for Harmful Use: There is a risk that Trendyol LLM could be used to generate offensive or harmful language. We strongly discourage its use for any such purposes and emphasize the need for application-specific safety and fairness evaluations before deployment. - Unintended Content and Bias: The model was trained on a large corpus of text data, which was not explicitly checked for offensive content or existing biases. Consequently, it may inadvertently produce content that reflects these biases or inaccuracies. - Toxicity: Despite efforts to select appropriate training data, the model is capable of generating harmful content, especially when prompted explicitly. We encourage the open-source community to engage in developing strategies to minimize such risks. ### Recommendations for Safe and Ethical Usage - Human Oversight: We recommend incorporating a human curation layer or using filters to manage and improve the quality of outputs, especially in public-facing applications. This approach can help mitigate the risk of generating objectionable content unexpectedly. - Application-Specific Testing: Developers intending to use Trendyol LLM should conduct thorough safety testing and optimization tailored to their specific applications. This is crucial, as the model’s responses can be unpredictable and may occasionally be biased, inaccurate, or offensive. - Responsible Development and Deployment: It is the responsibility of developers and users of Trendyol LLM to ensure its ethical and safe application. We urge users to be mindful of the model's limitations and to employ appropriate safeguards to prevent misuse or harmful consequences.
Holarissun/gptj6b-aisft-hh-seqsampler-subset60000	Holarissun	2024-03-11T06:35:06Z	1	0	peft	[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:EleutherAI/gpt-j-6b", "base_model:adapter:EleutherAI/gpt-j-6b", "license:apache-2.0", "region:us" ]	null	2024-03-11T06:35:02Z	--- license: apache-2.0 library_name: peft tags: - trl - sft - generated_from_trainer base_model: EleutherAI/gpt-j-6b model-index: - name: gptj6b-aisft-hh-seqsampler-subset60000 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. --> # gptj6b-aisft-hh-seqsampler-subset60000 This model is a fine-tuned version of [EleutherAI/gpt-j-6b](https://huggingface.co/EleutherAI/gpt-j-6b) 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: 1 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1 ### Training results ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.1+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
ashikshaffi08/zephyr_gemma_35_pct_data	ashikshaffi08	2024-03-11T06:25:55Z	0	0	peft	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:HuggingFaceH4/zephyr-7b-gemma-v0.1", "base_model:adapter:HuggingFaceH4/zephyr-7b-gemma-v0.1", "region:us" ]	null	2024-03-11T06:04:49Z	--- library_name: peft base_model: HuggingFaceH4/zephyr-7b-gemma-v0.1 --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ### Framework versions - PEFT 0.9.0
ashikshaffi08/zephyr-7b-gemma-v0.1_150_step_5_epoch	ashikshaffi08	2024-03-11T06:19:41Z	0	0	peft	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:HuggingFaceH4/zephyr-7b-gemma-v0.1", "base_model:adapter:HuggingFaceH4/zephyr-7b-gemma-v0.1", "region:us" ]	null	2024-03-11T05:59:49Z	--- library_name: peft base_model: HuggingFaceH4/zephyr-7b-gemma-v0.1 --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ### Framework versions - PEFT 0.9.0
jylee55/autotrain-dlpeu-yhob0	jylee55	2024-03-11T06:18:16Z	92	0	transformers	[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "autotrain", "dataset:autotrain-dlpeu-yhob0/autotrain-data", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text2text-generation	2024-03-11T06:00:07Z	--- tags: - autotrain - text2text-generation widget: - text: "translate English to Hawaiian Pidgin: I went to Ala Moana today with Kimo" datasets: - autotrain-dlpeu-yhob0/autotrain-data --- # Model Trained Using AutoTrain - Problem type: Seq2Seq ## Validation Metrics loss: 0.602806031703949 rouge1: 49.3563 rouge2: 38.9137 rougeL: 46.9477 rougeLsum: 47.7864 gen_len: 18.872 runtime: 246.0865 samples_per_second: 64.205 steps_per_second: 2.007 : 14.0
breathemm/hyeogi-finetuning	breathemm	2024-03-11T06:15:12Z	0	0	peft	[ "peft", "safetensors", "generated_from_trainer", "base_model:hyeogi/SOLAR-10.7B-dpo-v1", "base_model:adapter:hyeogi/SOLAR-10.7B-dpo-v1", "license:apache-2.0", "region:us" ]	null	2024-03-11T05:36:21Z	--- license: apache-2.0 library_name: peft tags: - generated_from_trainer base_model: hyeogi/SOLAR-10.7B-dpo-v1 model-index: - name: hyeogi-finetuning 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. --> # hyeogi-finetuning This model is a fine-tuned version of [hyeogi/SOLAR-10.7B-dpo-v1](https://huggingface.co/hyeogi/SOLAR-10.7B-dpo-v1) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.0281 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0003 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 0.9483 \| 1.0 \| 84 \| 0.9816 \| \| 0.7375 \| 2.0 \| 168 \| 0.9629 \| \| 0.4589 \| 3.0 \| 252 \| 1.0281 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.1+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
mildang/qlora-koalpaca-polyglot-12.8b-test1	mildang	2024-03-11T06:15:11Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-03-08T07:34:32Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
muzammil-eds/gemma-2b-it-OpenOrca-v1	muzammil-eds	2024-03-11T06:09:31Z	6	0	transformers	[ "transformers", "safetensors", "gemma", "text-generation", "trl", "sft", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-11T06:04:03Z	--- library_name: transformers tags: - trl - sft --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
adityaprakhar/LayoutLM_March_11_2024	adityaprakhar	2024-03-11T06:06:34Z	118	0	transformers	[ "transformers", "safetensors", "layoutlmv3", "token-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	token-classification	2024-03-11T04:35:27Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
fyp-admin/dreambooth_Mercury_15	fyp-admin	2024-03-11T06:06:09Z	1	0	diffusers	[ "diffusers", "text-to-image", "lora", "stable-diffusion", "stable-diffusion-diffusers", "base_model:runwayml/stable-diffusion-v1-5", "base_model:adapter:runwayml/stable-diffusion-v1-5", "license:creativeml-openrail-m", "region:us" ]	text-to-image	2024-03-11T05:16:47Z	--- license: creativeml-openrail-m library_name: diffusers tags: - text-to-image - diffusers - lora - stable-diffusion - stable-diffusion-diffusers inference: true base_model: runwayml/stable-diffusion-v1-5 instance_prompt: a picture of planet Mercury in the center, in charcoal gray color like the Moon having a cratered surface throughout. It is present in space which has dark background, embedded with a cluster of small-sized bright stars. --- <!-- This model card has been generated automatically according to the information the training script had access to. You should probably proofread and complete it, then remove this comment. --> # LoRA DreamBooth - fyp-admin/dreambooth_Mercury_15 These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were trained on a picture of planet Mercury in the center, in charcoal gray color like the Moon having a cratered surface throughout. It is present in space which has dark background, embedded with a cluster of small-sized bright stars. using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following. ![img_0](./image_0.png) ![img_1](./image_1.png) ![img_2](./image_2.png) ![img_3](./image_3.png) LoRA for the text encoder was enabled: False. ## Intended uses & limitations #### How to use ```python # TODO: add an example code snippet for running this diffusion pipeline ``` #### Limitations and bias [TODO: provide examples of latent issues and potential remediations] ## Training details [TODO: describe the data used to train the model]
Praveenna/pixelcopter	Praveenna	2024-03-11T06:01:27Z	0	0	null	[ "Pixelcopter-PLE-v0", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]	reinforcement-learning	2024-03-06T07:24:24Z	--- tags: - Pixelcopter-PLE-v0 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: pixelcopter results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Pixelcopter-PLE-v0 type: Pixelcopter-PLE-v0 metrics: - type: mean_reward value: 22.70 +/- 20.63 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
srmishra/ce-roberta-large	srmishra	2024-03-11T05:58:03Z	96	0	transformers	[ "transformers", "safetensors", "roberta", "text-classification", "generated_from_trainer", "base_model:cross-encoder/stsb-roberta-large", "base_model:finetune:cross-encoder/stsb-roberta-large", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-03-11T05:50:15Z	--- license: apache-2.0 base_model: cross-encoder/stsb-roberta-large tags: - generated_from_trainer metrics: - accuracy - precision - recall model-index: - name: ce-roberta-large 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. --> # ce-roberta-large This model is a fine-tuned version of [cross-encoder/stsb-roberta-large](https://huggingface.co/cross-encoder/stsb-roberta-large) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.1713 - Accuracy: 0.6869 - Precision: 0.8654 - Recall: 0.6522 ## 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: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - num_epochs: 10 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| Precision \| Recall \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:---------:\|:------:\| \| 0.7081 \| 1.0 \| 56 \| 0.6788 \| 0.5960 \| 0.8372 \| 0.5217 \| \| 0.2275 \| 2.0 \| 112 \| 0.2457 \| 0.6667 \| 0.8333 \| 0.6522 \| \| 0.2263 \| 3.0 \| 168 \| 0.1814 \| 0.5455 \| 0.9286 \| 0.3768 \| \| 0.2249 \| 4.0 \| 224 \| 0.1833 \| 0.5657 \| 0.9062 \| 0.4203 \| \| 0.1803 \| 5.0 \| 280 \| 0.1999 \| 0.6768 \| 0.7937 \| 0.7246 \| \| 0.1708 \| 6.0 \| 336 \| 0.1956 \| 0.6566 \| 0.8302 \| 0.6377 \| \| 0.2091 \| 7.0 \| 392 \| 0.1789 \| 0.5556 \| 0.9310 \| 0.3913 \| \| 0.186 \| 8.0 \| 448 \| 0.1845 \| 0.6364 \| 0.9231 \| 0.5217 \| \| 0.2133 \| 9.0 \| 504 \| 0.1755 \| 0.6162 \| 0.9189 \| 0.4928 \| \| 0.1982 \| 10.0 \| 560 \| 0.1713 \| 0.6869 \| 0.8654 \| 0.6522 \| ### Framework versions - Transformers 4.37.2 - Pytorch 2.2.1 - Datasets 2.14.6 - Tokenizers 0.15.1
abideen/MegaQwen-120B	abideen	2024-03-11T05:58:01Z	10	3	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "merge", "mergekit", "Qwen/Qwen1.5-72B", "conversational", "en", "base_model:Qwen/Qwen1.5-72B", "base_model:finetune:Qwen/Qwen1.5-72B", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-09T07:46:35Z	--- tags: - merge - mergekit - Qwen/Qwen1.5-72B base_model: - Qwen/Qwen1.5-72B license: apache-2.0 language: - en library_name: transformers --- # MegaQwen-120B ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/64e380b2e12618b261fa6ba0/YmJ9J1UaDSS9fAtbHNkqS.jpeg) Qwen-120B is created by interleaving a Qwen1.5-72B model with itself. * [Qwen/Qwen1.5-72B](https://huggingface.co/Qwen/Qwen1.5-72B) ## 💻 Usage ```python !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "abideen/Qwen-120B" messages = [{"role": "user", "content": "What is a large language model?"}] tokenizer = AutoTokenizer.from_pretrained(model) prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) pipeline = transformers.pipeline( "text-generation", model=model, torch_dtype=torch.float16, device_map="auto", ) outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) print(outputs[0]["generated_text"]) ```
thrunlab/Mistral_Sparse_refined_web_50p_2024-03-10	thrunlab	2024-03-11T05:45:22Z	5	0	transformers	[ "transformers", "safetensors", "sparse_mistral", "text-generation", "generated_from_trainer", "custom_code", "base_model:mistralai/Mistral-7B-v0.1", "base_model:finetune:mistralai/Mistral-7B-v0.1", "license:apache-2.0", "autotrain_compatible", "region:us" ]	text-generation	2024-03-10T14:03:48Z	--- license: apache-2.0 base_model: mistralai/Mistral-7B-v0.1 tags: - generated_from_trainer model-index: - name: Mistral_Sparse_refined_web_50p_2024-03-10 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. --> # Mistral_Sparse_refined_web_50p_2024-03-10 This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset. It achieves the following results on the evaluation set: - Loss: 2.1110 ## 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: 1 - eval_batch_size: 1 - seed: 0 - distributed_type: multi-GPU - num_devices: 4 - gradient_accumulation_steps: 4 - total_train_batch_size: 16 - total_eval_batch_size: 4 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 1100 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 2.4139 \| 0.0 \| 25 \| 2.5658 \| \| 2.226 \| 0.01 \| 50 \| 2.5201 \| \| 2.2555 \| 0.01 \| 75 \| 2.4799 \| \| 2.2174 \| 0.02 \| 100 \| 2.4604 \| \| 2.2232 \| 0.02 \| 125 \| 2.4481 \| \| 2.2955 \| 0.02 \| 150 \| 2.4355 \| \| 2.2275 \| 0.03 \| 175 \| 2.4291 \| \| 2.2219 \| 0.03 \| 200 \| 2.4206 \| \| 2.2521 \| 0.04 \| 225 \| 2.4176 \| \| 2.2937 \| 0.04 \| 250 \| 2.4077 \| \| 2.2073 \| 0.04 \| 275 \| 2.4069 \| \| 2.2157 \| 0.05 \| 300 \| 2.4061 \| \| 2.2274 \| 0.05 \| 325 \| 2.4085 \| \| 2.0697 \| 0.06 \| 350 \| 2.4033 \| \| 2.2338 \| 0.06 \| 375 \| 2.4037 \| \| 2.2722 \| 0.06 \| 400 \| 2.4003 \| \| 2.2638 \| 0.07 \| 425 \| 2.4003 \| \| 2.2215 \| 0.07 \| 450 \| 2.4011 \| \| 2.1437 \| 0.08 \| 475 \| 2.3962 \| \| 2.2073 \| 0.08 \| 500 \| 2.3951 \| \| 2.2696 \| 0.08 \| 525 \| 2.3923 \| \| 2.1624 \| 0.09 \| 550 \| 2.3899 \| \| 2.3006 \| 0.09 \| 575 \| 2.3930 \| \| 2.0869 \| 0.1 \| 600 \| 2.3915 \| \| 2.1871 \| 0.1 \| 625 \| 2.3906 \| \| 2.2712 \| 0.1 \| 650 \| 2.3895 \| \| 2.2596 \| 0.11 \| 675 \| 2.3898 \| \| 2.2297 \| 0.11 \| 700 \| 2.3878 \| \| 2.2126 \| 0.12 \| 725 \| 2.3860 \| \| 2.119 \| 0.12 \| 750 \| 2.3869 \| \| 2.1637 \| 0.12 \| 775 \| 2.3848 \| \| 2.2537 \| 0.13 \| 800 \| 2.3853 \| \| 2.2641 \| 0.13 \| 825 \| 2.3872 \| \| 2.2422 \| 0.14 \| 850 \| 2.3874 \| \| 2.11 \| 0.14 \| 875 \| 2.3847 \| \| 2.1745 \| 0.14 \| 900 \| 2.3831 \| \| 2.1222 \| 0.15 \| 925 \| 2.3834 \| \| 2.2604 \| 0.15 \| 950 \| 2.3858 \| \| 2.1929 \| 0.16 \| 975 \| 2.3847 \| \| 2.2353 \| 0.16 \| 1000 \| 2.3841 \| \| 2.2409 \| 0.16 \| 1025 \| 2.3825 \| \| 2.237 \| 0.17 \| 1050 \| 2.3805 \| \| 2.28 \| 0.17 \| 1075 \| 2.3806 \| \| 2.209 \| 0.18 \| 1100 \| 2.3802 \| ### Framework versions - Transformers 4.36.2 - Pytorch 2.1.2+cu121 - Datasets 2.15.0 - Tokenizers 0.15.0
ai4bharat/Airavata	ai4bharat	2024-03-11T05:43:15Z	1,118	30	transformers	[ "transformers", "safetensors", "gguf", "llama", "text-generation", "multilingual", "instruction-tuning", "llama2", "en", "hi", "dataset:ai4bharat/indic-instruct-data-v0.1", "arxiv:2401.15006", "license:llama2", "model-index", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-01-13T05:32:21Z	--- language: - en - hi license: llama2 tags: - multilingual - instruction-tuning - llama2 datasets: - ai4bharat/indic-instruct-data-v0.1 model-index: - name: Airavata results: - task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics: - type: acc_norm value: 46.5 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ai4bharat/Airavata name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics: - type: acc_norm value: 69.26 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ai4bharat/Airavata name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics: - type: acc value: 43.9 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ai4bharat/Airavata name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics: - type: mc2 value: 40.62 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ai4bharat/Airavata name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics: - type: acc value: 68.82 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ai4bharat/Airavata name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 4.02 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ai4bharat/Airavata name: Open LLM Leaderboard --- # Airavata This model is a 7B [OpenHathi](https://huggingface.co/sarvamai/OpenHathi-7B-Hi-v0.1-Base) model finetuned on [IndicInstruct dataset](https://huggingface.co/datasets/ai4bharat/indic-instruct-data-v0.1) which is a collection of instruction datasets (Anudesh, wikiHow, Flan v2, Dolly, Anthropic-HHH, OpenAssistant v1, and LymSys-Chat). Please check the corresponding huggingface dataset card for more details. This was trained as part of the technical report [Airavata: Introducing Hindi Instruction-tuned LLM](https://arxiv.org/abs/2401.15006). The codebase used to train and evaluate this model can be found at [https://github.com/AI4Bharat/IndicInstruct](https://github.com/AI4Bharat/IndicInstruct). ## Usage Clone [https://github.com/AI4Bharat/IndicInstruct](https://github.com/AI4Bharat/IndicInstruct) and install the required dependencies. Then download or clone this model to the same machine. ## Input Format The model is trained to use the chat format similar to [open-instruct code repository](https://github.com/allenai/open-instruct) (note the newlines): ``` <\|user\|> Your message here! <\|assistant\|> ``` For best results, format all inputs in this manner. Make sure to include a newline after `<\|assistant\|>`, this can affect generation quality quite a bit. ## Hyperparameters We fine-tune OpenHathi base model on the aforementioned IndicInstruct dataset with LoRA. The hyperparameters for the LoRA fine-tuning are listed below: - LoRA Rank: 16 - LoRA alpha: 32 - LoRA Dropout: 0.05 - LoRA Target Modules: ["q_proj", "v_proj", "k_proj", "down_proj", "gate_proj", "up_proj"] - Epochs: 4 - Learning rate: 5e-4 - Batch Size: 128 - Floating Point Precision: bfloat16 We recommend the readers to check out [our official blog post](https://ai4bharat.github.io/airavata) for more details on the model training, ablations and evaluation results. ## Example ```python3 import torch from transformers import AutoTokenizer, AutoModelForCausalLM device = "cuda" if torch.cuda.is_available() else "cpu" def create_prompt_with_chat_format(messages, bos="<s>", eos="</s>", add_bos=True): formatted_text = "" for message in messages: if message["role"] == "system": formatted_text += "<\|system\|>\n" + message["content"] + "\n" elif message["role"] == "user": formatted_text += "<\|user\|>\n" + message["content"] + "\n" elif message["role"] == "assistant": formatted_text += "<\|assistant\|>\n" + message["content"].strip() + eos + "\n" else: raise ValueError( "Tulu chat template only supports 'system', 'user' and 'assistant' roles. Invalid role: {}.".format( message["role"] ) ) formatted_text += "<\|assistant\|>\n" formatted_text = bos + formatted_text if add_bos else formatted_text return formatted_text def inference(input_prompts, model, tokenizer): input_prompts = [ create_prompt_with_chat_format([{"role": "user", "content": input_prompt}], add_bos=False) for input_prompt in input_prompts ] encodings = tokenizer(input_prompts, padding=True, return_tensors="pt") encodings = encodings.to(device) with torch.inference_mode(): outputs = model.generate(encodings.input_ids, do_sample=False, max_new_tokens=250) output_texts = tokenizer.batch_decode(outputs.detach(), skip_special_tokens=True) input_prompts = [ tokenizer.decode(tokenizer.encode(input_prompt), skip_special_tokens=True) for input_prompt in input_prompts ] output_texts = [output_text[len(input_prompt) :] for input_prompt, output_text in zip(input_prompts, output_texts)] return output_texts model_name = "ai4bharat/Airavata" tokenizer = AutoTokenizer.from_pretrained(model_name, padding_side="left") tokenizer.pad_token = tokenizer.eos_token model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16).to(device) input_prompts = [ "मैं अपने समय प्रबंधन कौशल को कैसे सुधार सकता हूँ? मुझे पांच बिंदु बताएं।", "मैं अपने समय प्रबंधन कौशल को कैसे सुधार सकता हूँ? मुझे पांच बिंदु बताएं और उनका वर्णन करें।", ] outputs = inference(input_prompts, model, tokenizer) print(outputs) ``` ## Citation ```bibtex @article{gala2024airavata, title = {Airavata: Introducing Hindi Instruction-tuned LLM}, author = {Jay Gala and Thanmay Jayakumar and Jaavid Aktar Husain and Aswanth Kumar M and Mohammed Safi Ur Rahman Khan and Diptesh Kanojia and Ratish Puduppully and Mitesh M. Khapra and Raj Dabre and Rudra Murthy and Anoop Kunchukuttan}, year = {2024}, journal = {arXiv preprint arXiv: 2401.15006} } ``` # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ai4bharat__Airavata) \| Metric \|Value\| \|---------------------------------\|----:\| \|Avg. \|45.52\| \|AI2 Reasoning Challenge (25-Shot)\|46.50\| \|HellaSwag (10-Shot) \|69.26\| \|MMLU (5-Shot) \|43.90\| \|TruthfulQA (0-shot) \|40.62\| \|Winogrande (5-shot) \|68.82\| \|GSM8k (5-shot) \| 4.02\|
Glow-01/finetuned_bart_large_custom	Glow-01	2024-03-11T05:43:10Z	92	0	transformers	[ "transformers", "tensorboard", "safetensors", "bart", "text2text-generation", "generated_from_trainer", "base_model:facebook/bart-large-cnn", "base_model:finetune:facebook/bart-large-cnn", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text2text-generation	2024-03-11T04:18:47Z	--- license: mit base_model: facebook/bart-large-cnn tags: - generated_from_trainer metrics: - rouge model-index: - name: finetuned_bart_large_custom 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. --> # finetuned_bart_large_custom This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on the None dataset. It achieves the following results on the evaluation set: - Loss: 4.8324 - Rouge1: 39.9143 - Rouge2: 10.7144 - Rougel: 21.1537 - Rougelsum: 35.81 - Gen Len: 131.6667 ## 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: 2 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 4 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 30 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Rouge1 \| Rouge2 \| Rougel \| Rougelsum \| Gen Len \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:-------:\|:-------:\|:-------:\|:---------:\|:--------:\| \| No log \| 1.0 \| 16 \| 4.3093 \| 39.1367 \| 9.9819 \| 21.0796 \| 35.3746 \| 132.0741 \| \| No log \| 2.0 \| 32 \| 4.2921 \| 39.0619 \| 9.8356 \| 21.7437 \| 35.6597 \| 131.7037 \| \| No log \| 3.0 \| 48 \| 4.3876 \| 39.5314 \| 10.337 \| 21.0096 \| 35.9973 \| 131.2593 \| \| No log \| 4.0 \| 64 \| 4.4020 \| 39.3551 \| 9.9689 \| 21.4343 \| 35.3958 \| 131.1481 \| \| No log \| 5.0 \| 80 \| 4.3744 \| 39.7603 \| 10.4124 \| 21.6535 \| 35.4996 \| 132.963 \| \| No log \| 6.0 \| 96 \| 4.4821 \| 39.9859 \| 11.0712 \| 22.2449 \| 35.7868 \| 132.4074 \| \| No log \| 7.0 \| 112 \| 4.6017 \| 38.765 \| 10.3317 \| 20.9319 \| 34.6675 \| 132.2593 \| \| No log \| 8.0 \| 128 \| 4.4419 \| 39.9964 \| 10.3341 \| 20.9618 \| 35.8621 \| 130.2222 \| \| No log \| 9.0 \| 144 \| 4.4990 \| 39.8075 \| 10.3829 \| 21.3509 \| 35.9882 \| 128.7407 \| \| No log \| 10.0 \| 160 \| 4.7017 \| 38.6152 \| 9.9282 \| 20.4588 \| 34.4487 \| 131.9259 \| \| No log \| 11.0 \| 176 \| 4.5497 \| 39.0296 \| 9.9429 \| 20.8087 \| 34.4624 \| 132.6296 \| \| No log \| 12.0 \| 192 \| 4.7301 \| 38.8819 \| 9.5937 \| 20.929 \| 34.7983 \| 131.4444 \| \| No log \| 13.0 \| 208 \| 4.5114 \| 38.4163 \| 9.6869 \| 20.373 \| 34.1491 \| 123.8519 \| \| No log \| 14.0 \| 224 \| 4.7097 \| 38.4294 \| 9.5615 \| 20.1514 \| 35.0332 \| 131.7407 \| \| No log \| 15.0 \| 240 \| 4.6300 \| 38.9564 \| 9.6386 \| 20.0618 \| 34.8298 \| 129.963 \| \| No log \| 16.0 \| 256 \| 4.6916 \| 38.5582 \| 10.136 \| 20.8347 \| 34.4795 \| 129.8519 \| \| No log \| 17.0 \| 272 \| 4.6959 \| 38.3264 \| 9.5281 \| 20.5576 \| 34.6148 \| 128.2963 \| \| No log \| 18.0 \| 288 \| 4.6756 \| 37.5569 \| 9.123 \| 19.8291 \| 33.5111 \| 126.6667 \| \| No log \| 19.0 \| 304 \| 4.7579 \| 38.5704 \| 9.3654 \| 20.1826 \| 34.8297 \| 131.4815 \| \| No log \| 20.0 \| 320 \| 4.8128 \| 40.158 \| 10.3889 \| 20.9267 \| 36.8965 \| 130.1852 \| \| No log \| 21.0 \| 336 \| 4.7659 \| 39.4144 \| 10.2445 \| 20.4763 \| 35.328 \| 134.2593 \| \| No log \| 22.0 \| 352 \| 4.7983 \| 40.2859 \| 11.0388 \| 21.1643 \| 36.0311 \| 131.9259 \| \| No log \| 23.0 \| 368 \| 4.7954 \| 39.2676 \| 10.5795 \| 21.1116 \| 35.3949 \| 130.1481 \| \| No log \| 24.0 \| 384 \| 4.7991 \| 39.8126 \| 10.3955 \| 21.2952 \| 35.7538 \| 130.5926 \| \| No log \| 25.0 \| 400 \| 4.8371 \| 39.3481 \| 10.2857 \| 20.9862 \| 35.1724 \| 125.1481 \| \| No log \| 26.0 \| 416 \| 4.8589 \| 40.0988 \| 10.4426 \| 21.7284 \| 35.7289 \| 130.3333 \| \| No log \| 27.0 \| 432 \| 4.8423 \| 39.9233 \| 10.3253 \| 21.5853 \| 36.1194 \| 131.1111 \| \| No log \| 28.0 \| 448 \| 4.8274 \| 40.0388 \| 10.1713 \| 20.991 \| 35.3966 \| 130.4444 \| \| No log \| 29.0 \| 464 \| 4.8313 \| 39.8516 \| 10.6207 \| 21.0394 \| 35.6627 \| 130.8148 \| \| No log \| 30.0 \| 480 \| 4.8324 \| 39.9143 \| 10.7144 \| 21.1537 \| 35.81 \| 131.6667 \| ### Framework versions - Transformers 4.37.0 - Pytorch 2.1.2 - Datasets 2.1.0 - Tokenizers 0.15.1
tm21cy/albert-emotion-provided-params	tm21cy	2024-03-11T05:40:14Z	18	0	transformers	[ "transformers", "tensorboard", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "base_model:distilbert/distilbert-base-uncased", "base_model:finetune:distilbert/distilbert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-03-10T22:16:32Z	--- license: apache-2.0 base_model: distilbert-base-uncased tags: - generated_from_trainer metrics: - accuracy model-index: - name: results 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. --> # results 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: - Loss: 1.4283 - Accuracy: 0.6952 ## 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: 7.45e-06 - 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: 4 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| No log \| 1.0 \| 179 \| 1.0664 \| 0.6712 \| \| No log \| 2.0 \| 358 \| 1.1817 \| 0.6806 \| \| 0.118 \| 3.0 \| 537 \| 1.4090 \| 0.6681 \| \| 0.118 \| 4.0 \| 716 \| 1.4375 \| 0.6691 \| ### Framework versions - Transformers 4.38.2 - Pytorch 2.2.1+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
shazzz/Reinforce_Pixel_Copter	shazzz	2024-03-11T05:38:13Z	0	0	null	[ "Pixelcopter-PLE-v0", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]	reinforcement-learning	2024-03-05T11:03:16Z	--- tags: - Pixelcopter-PLE-v0 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: Reinforce_Pixel_Copter results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Pixelcopter-PLE-v0 type: Pixelcopter-PLE-v0 metrics: - type: mean_reward value: 21.90 +/- 15.81 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
SamyRods/blackcat	SamyRods	2024-03-11T05:34:52Z	1	0	diffusers	[ "diffusers", "safetensors", "NxtWave-GenAI-Webinar", "text-to-image", "stable-diffusion", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]	text-to-image	2024-03-11T05:30:37Z	--- license: creativeml-openrail-m tags: - NxtWave-GenAI-Webinar - text-to-image - stable-diffusion --- ### BlackCat Dreambooth model trained by SamyRods following the "Build your own Gen AI model" session by NxtWave. Project Submission Code: DI22-39 Sample pictures of this concept: ![0](https://huggingface.co/SamyRods/blackcat/resolve/main/sample_images/blackcat_(2).jpg)
tsavage68/mistralit2_1000_STEPS_5e7_rate_0.1_beta_DPO	tsavage68	2024-03-11T05:26:51Z	5	0	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "trl", "dpo", "generated_from_trainer", "conversational", "base_model:mistralai/Mistral-7B-Instruct-v0.2", "base_model:finetune:mistralai/Mistral-7B-Instruct-v0.2", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-11T05:22:42Z	--- license: apache-2.0 base_model: mistralai/Mistral-7B-Instruct-v0.2 tags: - trl - dpo - generated_from_trainer model-index: - name: mistralit2_1000_STEPS_5e7_rate_0.1_beta_DPO 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. --> # mistralit2_1000_STEPS_5e7_rate_0.1_beta_DPO This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.7132 - Rewards/chosen: -3.0068 - Rewards/rejected: -5.0778 - Rewards/accuracies: 0.6813 - Rewards/margins: 2.0710 - Logps/rejected: -79.3505 - Logps/chosen: -53.4537 - Logits/rejected: -2.5776 - Logits/chosen: -2.5788 ## 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-07 - train_batch_size: 4 - eval_batch_size: 1 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 8 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 100 - training_steps: 1000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Rewards/chosen \| Rewards/rejected \| Rewards/accuracies \| Rewards/margins \| Logps/rejected \| Logps/chosen \| Logits/rejected \| Logits/chosen \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------------:\|:----------------:\|:------------------:\|:---------------:\|:--------------:\|:------------:\|:---------------:\|:-------------:\| \| 0.6418 \| 0.1 \| 50 \| 0.6447 \| -0.5872 \| -0.7568 \| 0.5736 \| 0.1696 \| -36.1403 \| -29.2577 \| -2.8316 \| -2.8320 \| \| 0.5915 \| 0.2 \| 100 \| 0.6534 \| -2.5902 \| -3.2664 \| 0.6000 \| 0.6762 \| -61.2361 \| -49.2879 \| -2.5920 \| -2.5930 \| \| 0.6181 \| 0.29 \| 150 \| 0.6108 \| -1.7262 \| -2.4531 \| 0.6352 \| 0.7270 \| -53.1036 \| -40.6475 \| -2.6698 \| -2.6708 \| \| 0.5919 \| 0.39 \| 200 \| 0.6201 \| -0.8739 \| -1.3497 \| 0.6110 \| 0.4758 \| -42.0694 \| -32.1245 \| -2.8217 \| -2.8224 \| \| 0.7232 \| 0.49 \| 250 \| 0.6496 \| -2.3019 \| -2.8348 \| 0.6110 \| 0.5328 \| -56.9199 \| -46.4053 \| -2.8105 \| -2.8116 \| \| 0.6175 \| 0.59 \| 300 \| 0.6052 \| -1.3274 \| -2.0772 \| 0.6440 \| 0.7497 \| -49.3443 \| -36.6603 \| -2.8706 \| -2.8714 \| \| 0.6294 \| 0.68 \| 350 \| 0.5762 \| -0.5378 \| -1.3786 \| 0.6484 \| 0.8407 \| -42.3582 \| -28.7642 \| -2.8508 \| -2.8515 \| \| 0.5572 \| 0.78 \| 400 \| 0.5838 \| -2.3342 \| -3.3990 \| 0.6615 \| 1.0648 \| -62.5628 \| -46.7279 \| -2.9194 \| -2.9202 \| \| 0.5339 \| 0.88 \| 450 \| 0.6065 \| -2.3478 \| -3.1946 \| 0.6615 \| 0.8468 \| -60.5187 \| -46.8642 \| -2.8735 \| -2.8743 \| \| 0.5162 \| 0.98 \| 500 \| 0.6054 \| -1.8059 \| -2.8617 \| 0.6593 \| 1.0558 \| -57.1895 \| -41.4452 \| -2.8408 \| -2.8416 \| \| 0.1367 \| 1.07 \| 550 \| 0.5967 \| -1.5441 \| -3.2437 \| 0.6923 \| 1.6996 \| -61.0093 \| -38.8268 \| -2.7152 \| -2.7164 \| \| 0.1427 \| 1.17 \| 600 \| 0.6612 \| -2.6012 \| -4.5496 \| 0.6923 \| 1.9484 \| -74.0686 \| -49.3976 \| -2.6127 \| -2.6140 \| \| 0.2423 \| 1.27 \| 650 \| 0.6953 \| -3.2920 \| -5.2913 \| 0.6835 \| 1.9992 \| -81.4852 \| -56.3063 \| -2.5920 \| -2.5933 \| \| 0.2461 \| 1.37 \| 700 \| 0.6994 \| -3.0907 \| -5.0995 \| 0.6791 \| 2.0088 \| -79.5678 \| -54.2931 \| -2.5993 \| -2.6005 \| \| 0.05 \| 1.46 \| 750 \| 0.7081 \| -2.9719 \| -5.0539 \| 0.6835 \| 2.0820 \| -79.1113 \| -53.1052 \| -2.5893 \| -2.5906 \| \| 0.1265 \| 1.56 \| 800 \| 0.7096 \| -2.9511 \| -5.0249 \| 0.6791 \| 2.0739 \| -78.8217 \| -52.8965 \| -2.5798 \| -2.5810 \| \| 0.1903 \| 1.66 \| 850 \| 0.7099 \| -3.0000 \| -5.0705 \| 0.6769 \| 2.0705 \| -79.2773 \| -53.3856 \| -2.5782 \| -2.5795 \| \| 0.1908 \| 1.76 \| 900 \| 0.7144 \| -3.0075 \| -5.0795 \| 0.6857 \| 2.0720 \| -79.3678 \| -53.4610 \| -2.5779 \| -2.5792 \| \| 0.2293 \| 1.86 \| 950 \| 0.7119 \| -3.0087 \| -5.0829 \| 0.6835 \| 2.0742 \| -79.4011 \| -53.4726 \| -2.5778 \| -2.5790 \| \| 0.1167 \| 1.95 \| 1000 \| 0.7132 \| -3.0068 \| -5.0778 \| 0.6813 \| 2.0710 \| -79.3505 \| -53.4537 \| -2.5776 \| -2.5788 \| ### Framework versions - Transformers 4.38.2 - Pytorch 2.0.0+cu117 - Datasets 2.18.0 - Tokenizers 0.15.2
shubhamgantayat/reward_model_anthropic	shubhamgantayat	2024-03-11T05:26:23Z	195	0	transformers	[ "transformers", "tensorboard", "safetensors", "bert", "text-classification", "generated_from_trainer", "base_model:google-bert/bert-base-cased", "base_model:finetune:google-bert/bert-base-cased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-03-11T04:26:32Z	--- license: apache-2.0 base_model: google-bert/bert-base-cased tags: - generated_from_trainer metrics: - accuracy model-index: - name: reward_model_anthropic 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. --> # reward_model_anthropic This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.7057 - Accuracy: 0.5144 ## 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 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 0.703 \| 1.0 \| 625 \| 0.6963 \| 0.5062 \| \| 0.7034 \| 2.0 \| 1250 \| 0.6919 \| 0.5236 \| \| 0.6978 \| 3.0 \| 1875 \| 0.7057 \| 0.5144 \| ### Framework versions - Transformers 4.38.2 - Pytorch 2.1.0+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
sadhaklal/custom-cnn-cifar2	sadhaklal	2024-03-11T05:25:20Z	0	0	pytorch	[ "pytorch", "image-classification", "dataset:cifar10", "region:us" ]	image-classification	2024-03-10T08:38:34Z	--- datasets: - cifar10 metrics: - accuracy library_name: pytorch pipeline_tag: image-classification --- # custom-cnn-cifar2 Custom convolutional neural network (CNN) trained on CIFAR-2 (a subset of CIFAR-10 for classifying 'airplane' vs. 'bird'). This model pertains to Exercise 1 of Chapter 8 of the book "Deep Learning with PyTorch" by Eli Stevens, Luca Antiga, and Thomas Viehmann. Note: In the exercise, we tried out `(5, 5)` and `(1, 3)` convolution kernel sizes. However, these didn't outperform the baseline network with `(3, 3)` kernel size. Hence, this checkpoint sticks to the `(3, 3)` kernel size. Code: https://github.com/sambitmukherjee/dlwpt-exercises/blob/main/chapter_8/exercise_1.ipynb Experiment tracking: https://wandb.ai/sadhaklal/custom-cnn-cifar2 ## Usage ``` !pip install -q datasets from datasets import load_dataset cifar10 = load_dataset("cifar10") label_map = {0: 0, 2: 1} class_names = ['airplane', 'bird'] cifar2_train = [(example['img'], label_map[example['label']]) for example in cifar10['train'] if example['label'] in [0, 2]] cifar2_val = [(example['img'], label_map[example['label']]) for example in cifar10['test'] if example['label'] in [0, 2]] example = cifar2_val[0] img, label = example import torch from torchvision.transforms import v2 tfms = v2.Compose([ v2.ToImage(), v2.ToDtype(torch.float32, scale=True), v2.Normalize(mean=[0.4915, 0.4823, 0.4468], std=[0.2470, 0.2435, 0.2616]) ]) img = tfms(img) batch = img.unsqueeze(0) import torch.nn as nn import torch.nn.functional as F from huggingface_hub import PyTorchModelHubMixin class Net(nn.Module, PyTorchModelHubMixin): def __init__(self): super().__init__() self.conv1 = nn.Conv2d(3, 16, kernel_size=3, padding=1, stride=1) self.conv2 = nn.Conv2d(16, 8, kernel_size=3, padding=1, stride=1) self.fc1 = nn.Linear(8 * 8 * 8, 32) self.fc2 = nn.Linear(32, 2) def forward(self, x): out = F.max_pool2d(torch.tanh(self.conv1(x)), kernel_size=2, stride=2) # Output shape: (batch_size, 16, 16, 16) out = F.max_pool2d(torch.tanh(self.conv2(out)), kernel_size=2, stride=2) # Output shape: (batch_size, 8, 8, 8) out = out.view(-1, 8 * 8 * 8) # Output shape: (batch_size, 512) out = torch.tanh(self.fc1(out)) # Output shape: (batch_size, 32) out = self.fc2(out) # Output shape: (batch_size, 2) return out model = Net.from_pretrained("sadhaklal/custom-cnn-cifar2") model.eval() with torch.no_grad(): logits = model(batch) pred = logits[0].argmax().item() proba = torch.softmax(logits, dim=1) print(f"Predicted class: {class_names[pred]}") print(f"Predicted class probabilities ('airplane' vs. 'bird'): {proba[0].tolist()}") ``` ## Metric Accuracy on `cifar2_val`: 0.8995
moneyforward/houou-instruction-7b-v3	moneyforward	2024-03-11T05:25:09Z	83	1	transformers	[ "transformers", "safetensors", "llama", "text-generation", "license:llama2", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-07T03:51:04Z	--- license: llama2 --- # `moneyforward/houou-instruction-7b-v3` # Overview The model was trained by supervised fine-tuning (SFT) using an instruction dataset (9013 data) created through joint research with the Institute of Physical and Chemical Research (RIKEN). The instruction data is the first dataset created from scratch, written in Japanese. The data details is [here](https://liat-aip.sakura.ne.jp/wp/llm%E3%81%AE%E3%81%9F%E3%82%81%E3%81%AE%E6%97%A5%E6%9C%AC%E8%AA%9E%E3%82%A4%E3%83%B3%E3%82%B9%E3%83%88%E3%83%A9%E3%82%AF%E3%82%B7%E3%83%A7%E3%83%B3%E3%83%87%E3%83%BC%E3%82%BF%E4%BD%9C%E6%88%90/). As a pre-trained model, we used [rinna/youri-7b](https://huggingface.co/rinna/youri-7b). * Authors - [Atsushi Kojima](https://huggingface.co/atsushi-mf) - Ikuo Kitagishi --- # How to use the model ~~~~python import torch from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("moneyforward/houou-instruction-7b-v2") model = AutoModelForCausalLM.from_pretrained("moneyforward/houou-instruction-7b-v2") if torch.cuda.is_available(): model = model.to("cuda") instruction = "日本のおすすめの観光地を3つ教えてください。" input = "" if input == "": prompt = f""" 以下は、タスクを説明する指示です。要求を適切に満たす応答を書きなさい。 ### 指示: {instruction} ### 応答: """ else: prompt = f""" 以下は、タスクを説明する指示と、文脈のある入力の組み合わせです。要求を適切に満たす応答を書きなさい。 ### 指示: {instruction} ### 入力: {input} ### 応答: """ token_ids = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt") with torch.no_grad(): output_ids = model.generate( token_ids.to(model.device), max_new_tokens=2048, do_sample=True, temperature=0.5, pad_token_id=tokenizer.pad_token_id, bos_token_id=tokenizer.bos_token_id, eos_token_id=tokenizer.eos_token_id, ) output = tokenizer.decode(output_ids.tolist()[0]) output = output.split("### 応答:")[1] print(output) """ 日本は四季折々の美しい風景や、数々の伝統文化を持つ国です。観光地も数多くありますが、その中から3つ、おすすめの観光地をご紹介します。 1）京都府：清水寺、金閣寺、伏見稲荷大社　京都は、日本の歴史上とても重要な役割を果たした場所です。清水寺では、「音羽の滝」の水を飲むと美容効果があるといわれています。金閣寺はその名の通り、金で覆われた三層の建造物です。伏見稲荷大社は稲荷神社の総本山で、奥社へ向かう参道に並ぶ鳥居の数は圧巻です。 2）北海道：知床五湖、美瑛町（ケンとメリーの木、パッチワークの丘など）、旭川市（旭山動物園）　知床半島は、世界自然遺産に登録されています。知床五湖は、その知床半島の自然を満喫できるハイキングコースです。美瑛町は、丘陵地に色とりどりの花が植えられたパッチワークのような風景が広がっています。旭川市にある旭山動物園は、人気がある動物園で、夜行性動物の見やすさが工夫されています。 3）東京都：浅草（浅草寺、仲見世通り、東京スカイツリー）、上野恩賜公園（上野の森美術館、国立西洋美術館など）、日本橋（三越前の日本国道路元標、R.M.V.日本橋など）　東京にも観光地はたくさんあります。浅草は、昔ながらの下町の雰囲気が残り、老若男女を問わず楽しめる観光地です。上野には、美術館や博物館が多く、上野恩賜公園（上野の森）内を散策するだけでも十分に楽しめます。日本橋は、国道路元標やR.M.V.日本橋など、歴史を感じられる橋であり、最新の技術を感じられる橋でもあります。　この他にも日本には魅力的な観光地がたくさんあります。ぜひ訪れてみてください。 """ ~~~~ # Evaluation results of [rakuda-benchmark](https://huggingface.co/datasets/yuzuai/rakuda-questions) We evaluated the performance of houou-instruction-v1 through GPT-4 automatic evaluation. As for the comparison model, we used gpt-3.5-turbo-1106. \| houou-instruction-v3<br>win rate\| gpt-3.5-turbo-1106 win rate \| tie \| \| -- \| -- \|-- \| \| 72.5 \| 27.5 \| 0 \| --- # License [The llama2 license](https://ai.meta.com/llama/license/) We have permission from RIKEN to use RIKEN's instruction data for this initiative.
jamesLeeeeeee/bpe-tokenizer	jamesLeeeeeee	2024-03-11T05:23:28Z	0	0	transformers	[ "transformers", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-03-11T05:23:27Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
Kabster/BioMistral-MedicalQA-FT	Kabster	2024-03-11T05:21:52Z	82	0	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-11T04:34:46Z	--- library_name: transformers license: apache-2.0 --- # Model Card for BioMistral-MedicalQA-FT This is a fine-tuned BioMistral model based on the medical reasoning dataset - https://huggingface.co/datasets/mamachang/medical-reasoning ## Model Details This is a fine-tuned BioMistral model based on the medical reasoning dataset - https://huggingface.co/datasets/mamachang/medical-reasoning ## 💻 Usage ```python !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "Kabster/BioMistral-MedicalQA-FT" messages = [{"role": "user", "content": "Can bisoprolol cause insomnia?"}] tokenizer = AutoTokenizer.from_pretrained(model) prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) pipeline = transformers.pipeline( "text-generation", model=model, torch_dtype=torch.float16, device_map="auto", ) outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.2, top_k=100, top_p=0.95) print(outputs[0]["generated_text"]) ```
OwOOwO/mistral_mischief2	OwOOwO	2024-03-11T05:20:14Z	4	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-11T05:17:15Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
Sumail/Alchemist_04_base2_2b	Sumail	2024-03-11T05:15:26Z	90	0	transformers	[ "transformers", "safetensors", "gemma", "text-generation", "mergewss]", "mergekit", "lazymergekit", "zzttbrdd/sn6_20_new", "deepnetguy/gemma-64", "conversational", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-11T05:12:59Z	--- license: apache-2.0 tags: - mergewss] - mergekit - lazymergekit - zzttbrdd/sn6_20_new - deepnetguy/gemma-64 --- # Alchemist_04_base2_2b Alchemist_04_base2_2b is a merge of the following models using [mergekit](https://github.com/cg123/mergekit): * [zzttbrdd/sn6_20_new](https://huggingface.co/zzttbrdd/sn6_20_new) * [deepnetguy/gemma-64](https://huggingface.co/deepnetguy/gemma-64) ## 🧩 Configuration ```yaml slices: - sources: - model: zzttbrdd/sn6_20_new layer_range: [0, 18] - model: deepnetguy/gemma-64 layer_range: [0, 18] merge_method: slerp base_model: zzttbrdd/sn6_20_new parameters: t: - filter: self_attn value: [0, 0.5, 0.3, 0.7, 1] - filter: mlp value: [1, 0.5, 0.7, 0.3, 0] - value: 0.5 dtype: bfloat16 ```
EricValen/rl_course_vizdoom_health_gathering_supreme	EricValen	2024-03-11T05:03:48Z	0	0	sample-factory	[ "sample-factory", "tensorboard", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2024-03-11T03:26:31Z	--- library_name: sample-factory tags: - deep-reinforcement-learning - reinforcement-learning - sample-factory model-index: - name: APPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: doom_health_gathering_supreme type: doom_health_gathering_supreme metrics: - type: mean_reward value: 10.17 +/- 4.02 name: mean_reward verified: false --- A(n) APPO model trained on the doom_health_gathering_supreme environment. This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory. Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/ ## Downloading the model After installing Sample-Factory, download the model with: ``` python -m sample_factory.huggingface.load_from_hub -r EricValen/rl_course_vizdoom_health_gathering_supreme ``` ## Using the model To run the model after download, use the `enjoy` script corresponding to this environment: ``` python -m .usr.local.lib.python3.10.dist-packages.colab_kernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme ``` You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag. See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details ## Training with this model To continue training with this model, use the `train` script corresponding to this environment: ``` python -m .usr.local.lib.python3.10.dist-packages.colab_kernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000 ``` Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
sarak7/H4_311_769_v3	sarak7	2024-03-11T05:02:19Z	178	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-11T05:00:50Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
Harshad018/trained-gpt2-tweet-analysis	Harshad018	2024-03-11T04:54:39Z	90	0	transformers	[ "transformers", "safetensors", "gpt2", "text-classification", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-classification	2024-03-11T04:53:52Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
lole25/zephyr-7b-dpo-qlora	lole25	2024-03-11T04:53:51Z	1	0	peft	[ "peft", "tensorboard", "safetensors", "mistral", "alignment-handbook", "generated_from_trainer", "trl", "dpo", "dataset:HuggingFaceH4/ultrafeedback_binarized", "base_model:mistralai/Mistral-7B-v0.1", "base_model:adapter:mistralai/Mistral-7B-v0.1", "license:apache-2.0", "4-bit", "bitsandbytes", "region:us" ]	null	2024-02-16T00:14:52Z	--- license: apache-2.0 library_name: peft tags: - alignment-handbook - generated_from_trainer - trl - dpo - generated_from_trainer datasets: - HuggingFaceH4/ultrafeedback_binarized base_model: mistralai/Mistral-7B-v0.1 model-index: - name: zephyr-7b-dpo-qlora 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. --> # zephyr-7b-dpo-qlora This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-qlora](https://huggingface.co/alignment-handbook/zephyr-7b-sft-qlora) on the HuggingFaceH4/ultrafeedback_binarized dataset. It achieves the following results on the evaluation set: - Loss: 0.6813 - Rewards/chosen: -0.0009 - Rewards/rejected: -0.0252 - Rewards/accuracies: 0.2920 - Rewards/margins: 0.0243 - Logps/rejected: -71.3009 - Logps/chosen: -65.4449 - Logits/rejected: -2.4428 - Logits/chosen: -2.4444 ## 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-06 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - distributed_type: multi-GPU - num_devices: 4 - gradient_accumulation_steps: 4 - total_train_batch_size: 32 - total_eval_batch_size: 8 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 1 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Rewards/chosen \| Rewards/rejected \| Rewards/accuracies \| Rewards/margins \| Logps/rejected \| Logps/chosen \| Logits/rejected \| Logits/chosen \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------------:\|:----------------:\|:------------------:\|:---------------:\|:--------------:\|:------------:\|:---------------:\|:-------------:\| \| 0.69 \| 0.26 \| 100 \| 0.6897 \| 0.0232 \| 0.0168 \| 0.2680 \| 0.0064 \| -67.1001 \| -63.0342 \| -2.4904 \| -2.4911 \| \| 0.6869 \| 0.52 \| 200 \| 0.6849 \| 0.0066 \| -0.0092 \| 0.3060 \| 0.0159 \| -69.7060 \| -64.6950 \| -2.4556 \| -2.4573 \| \| 0.681 \| 0.78 \| 300 \| 0.6815 \| -0.0026 \| -0.0264 \| 0.2880 \| 0.0238 \| -71.4280 \| -65.6224 \| -2.4430 \| -2.4446 \| ### Framework versions - PEFT 0.7.1 - Transformers 4.36.2 - Pytorch 2.1.2+cu118 - Datasets 2.14.6 - Tokenizers 0.15.2
nadika/nepali_complaints_classification_nepbert3	nadika	2024-03-11T04:50:48Z	94	0	transformers	[ "transformers", "safetensors", "bert", "text-classification", "generated_from_trainer", "base_model:Rajan/NepaliBERT", "base_model:finetune:Rajan/NepaliBERT", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-03-11T03:46:15Z	--- tags: - generated_from_trainer metrics: - accuracy base_model: Rajan/NepaliBERT model-index: - name: nepali_complaints_classification_nepbert3 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. --> # nepali_complaints_classification_nepbert3 This model is a fine-tuned version of [Rajan/NepaliBERT](https://huggingface.co/Rajan/NepaliBERT) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.2687 - Accuracy: 0.9494 - F1-score: 0.9483 ## 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 - lr_scheduler_warmup_steps: 50 - num_epochs: 5 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| F1-score \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 1.4921 \| 0.22 \| 500 \| 0.8642 \| 0.7235 \| 0.7143 \| \| 0.7781 \| 0.45 \| 1000 \| 0.6241 \| 0.7974 \| 0.7923 \| \| 0.5865 \| 0.67 \| 1500 \| 0.5342 \| 0.8243 \| 0.8125 \| \| 0.4625 \| 0.89 \| 2000 \| 0.4250 \| 0.8576 \| 0.8553 \| \| 0.3648 \| 1.11 \| 2500 \| 0.3856 \| 0.8759 \| 0.8725 \| \| 0.3001 \| 1.34 \| 3000 \| 0.3424 \| 0.8899 \| 0.8891 \| \| 0.2723 \| 1.56 \| 3500 \| 0.3199 \| 0.9007 \| 0.8981 \| \| 0.2538 \| 1.78 \| 4000 \| 0.2898 \| 0.9085 \| 0.9066 \| \| 0.231 \| 2.01 \| 4500 \| 0.2676 \| 0.9203 \| 0.9189 \| \| 0.1478 \| 2.23 \| 5000 \| 0.3029 \| 0.9210 \| 0.9187 \| \| 0.1666 \| 2.45 \| 5500 \| 0.2580 \| 0.9283 \| 0.9271 \| \| 0.1519 \| 2.67 \| 6000 \| 0.2573 \| 0.9308 \| 0.9292 \| \| 0.1498 \| 2.9 \| 6500 \| 0.2746 \| 0.9328 \| 0.9306 \| \| 0.1112 \| 3.12 \| 7000 \| 0.2564 \| 0.9398 \| 0.9389 \| \| 0.0903 \| 3.34 \| 7500 \| 0.2726 \| 0.9403 \| 0.9393 \| \| 0.1036 \| 3.57 \| 8000 \| 0.2664 \| 0.9398 \| 0.9385 \| \| 0.1043 \| 3.79 \| 8500 \| 0.2614 \| 0.9459 \| 0.9447 \| \| 0.0972 \| 4.01 \| 9000 \| 0.2499 \| 0.9453 \| 0.9443 \| \| 0.0663 \| 4.23 \| 9500 \| 0.2643 \| 0.9469 \| 0.9458 \| \| 0.0683 \| 4.46 \| 10000 \| 0.2688 \| 0.9474 \| 0.9462 \| \| 0.0671 \| 4.68 \| 10500 \| 0.2657 \| 0.9491 \| 0.9481 \| \| 0.0605 \| 4.9 \| 11000 \| 0.2687 \| 0.9494 \| 0.9483 \| ### Framework versions - Transformers 4.38.2 - Pytorch 2.1.0+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
Owhslp/nous_researcher_tuning_2_19	Owhslp	2024-03-11T04:47:32Z	90	0	transformers	[ "transformers", "safetensors", "gemma", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-11T04:27:53Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
luminique-silk-cream/luminique-silk-cream	luminique-silk-cream	2024-03-11T04:39:27Z	0	0	sentence-transformers	[ "sentence-transformers", "Luminique Silk Cream", "en", "license:bsd-3-clause", "region:us" ]	null	2024-03-11T04:38:13Z	--- license: bsd-3-clause language: - en library_name: sentence-transformers tags: - Luminique Silk Cream --- [Luminique Silk Cream](https://atozsupplement.com/luminique-silk-cream/) Expanded Hydration: Fixings like hyaluronic corrosive and glycerin profoundly hydrate the skin, plumping it up and limiting the presence of dryness and parchedness lines.Evened Complexion: Hostile to maturing serums might incorporate fixings like L-ascorbic acid, niacinamide, or alpha hydroxy acids (AHAs) that assist with blurring dull spots, hyperpigmentation, and advance an all the more even complexion. VISIT HERE FOR OFFICIAL WEBSITE:-https://atozsupplement.com/luminique-silk-cream/
kzken384/bert-base-japanese-v3-wrime-sentiment	kzken384	2024-03-11T04:36:36Z	120	0	transformers	[ "transformers", "safetensors", "bert", "text-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-02-26T04:33:05Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
OwOOwO/eacc_o_1	OwOOwO	2024-03-11T04:18:56Z	89	0	transformers	[ "transformers", "safetensors", "gemma", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-11T04:16:29Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
ekato/Ayame	ekato	2024-03-11T04:16:50Z	0	0	diffusers	[ "diffusers", "text-to-image", "stable-diffusion", "lora", "template:sd-lora", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0", "license:openrail", "region:us" ]	text-to-image	2024-03-11T04:16:35Z	--- tags: - text-to-image - stable-diffusion - lora - diffusers - template:sd-lora widget: - text: '-' output: url: images/1000018408.jpg base_model: stabilityai/stable-diffusion-xl-base-1.0 instance_prompt: null license: openrail --- # Ayame <Gallery /> ## Download model [Download](/ekato/Ayame/tree/main) them in the Files & versions tab.
nlp-waseda/comet-gpt2-xl-japanese	nlp-waseda	2024-03-11T04:16:02Z	69	0	transformers	[ "transformers", "pytorch", "gpt2", "text-generation", "ja", "license:cc-by-sa-4.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-09-26T13:37:52Z	--- language: ja widget: - text: X が部屋でゲームするxEffect pipeline_tag: text-generation license: cc-by-sa-4.0 --- # COMET-GPT2 ja v2 Finetuned GPT-2 xl on the large version of [ATOMIC ja](https://github.com/nlp-waseda/comet-atomic-ja) using a causal language modeling (CLM) objective. The original version and the large version of ATOMIC ja were introduced in [this paper](https://www.anlp.jp/proceedings/annual_meeting/2023/pdf_dir/B2-5.pdf) and in [this paper](https://www.anlp.jp/proceedings/annual_meeting/2023/pdf_dir/B9-1.pdf), respectively. ### How to use You can use this model directly with a pipeline for text generation. Since the generation relies on some randomness, we set a seed for reproducibility: ```python >>> from transformers import pipeline, set_seed >>> generator = pipeline('text-generation', model='nlp-waseda/comet-gpt2-xl-japanese') >>> set_seed(42) >>> generator('Ｘが副業を始めるxEffect', max_length=30, num_return_sequences=5, do_sample=True) [{'generated_text': 'Ｘが副業を始めるxEffect X が収入を得る'}, {'generated_text': 'Ｘが副業を始めるxEffect X が時間を失う'}, {'generated_text': 'Ｘが副業を始めるxEffect X が儲かる'}, {'generated_text': 'Ｘが副業を始めるxEffect X が稼ぐ'}, {'generated_text': 'Ｘが副業を始めるxEffect X が稼げるようになる'}] ``` ### Preprocessing The texts are segmented into words using Juman++ and tokenized using SentencePiece. ## Evaluation results The model achieves the following results: \| BLEU \| BERTScore \| \|:-----:\|:---------:\| \| - \| - \| ### BibTeX entry and citation info ```bibtex @InProceedings{ide_nlp2023_event, author = "井手竜也 and 村田栄樹 and 堀尾海斗 and 河原大輔 and 山崎天 and 李聖哲 and 新里顕大 and 佐藤敏紀", title = "人間と言語モデルに対するプロンプトを用いたゼロからのイベント常識知識グラフ構築", booktitle = "言語処理学会第29回年次大会", year = "2023", url = "https://www.anlp.jp/proceedings/annual_meeting/2023/pdf_dir/B2-5.pdf" note = "in Japanese" } @InProceedings{murata_nlp2023, author = "村田栄樹 and 井手竜也 and 榮田亮真 and 河原大輔 and 山崎天 and 李聖哲 and 新里顕大 and 佐藤敏紀", title = "大規模言語モデルによって構築された常識知識グラフの拡大と低コストフィルタリング", booktitle = "言語処理学会第29回年次大会", year = "2023", url = "https://www.anlp.jp/proceedings/annual_meeting/2023/pdf_dir/B9-1.pdf" note = "in Japanese" } ```
tnscorcoran/Llama-2-7b-chat-hf-sharded-bf16-fine-tuned-adapters	tnscorcoran	2024-03-11T04:13:16Z	1	0	peft	[ "peft", "arxiv:1910.09700", "base_model:Trelis/Llama-2-7b-chat-hf-sharded-bf16", "base_model:adapter:Trelis/Llama-2-7b-chat-hf-sharded-bf16", "region:us" ]	null	2024-02-08T02:48:43Z	--- library_name: peft base_model: Trelis/Llama-2-7b-chat-hf-sharded-bf16 --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ### Framework versions - PEFT 0.9.1.dev0
johnnyluhk/ppo-Pyramids_Training	johnnyluhk	2024-03-11T04:04:16Z	1	0	ml-agents	[ "ml-agents", "tensorboard", "onnx", "Pyramids", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Pyramids", "region:us" ]	reinforcement-learning	2024-03-11T04:04:13Z	--- 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: johnnyluhk/ppo-Pyramids_Training 3. Step 2: Select your .nn /.onnx file 4. Click on Watch the agent play 👀
thrunlab/Mistral_Sparse_refined_web_relu_2024-03-10	thrunlab	2024-03-11T04:01:32Z	7	0	transformers	[ "transformers", "safetensors", "sparse_mistral", "text-generation", "generated_from_trainer", "custom_code", "base_model:mistralai/Mistral-7B-v0.1", "base_model:finetune:mistralai/Mistral-7B-v0.1", "license:apache-2.0", "autotrain_compatible", "region:us" ]	text-generation	2024-03-11T01:16:32Z	--- license: apache-2.0 base_model: mistralai/Mistral-7B-v0.1 tags: - generated_from_trainer model-index: - name: Mistral_Sparse_refined_web_relu_2024-03-10 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. --> # Mistral_Sparse_refined_web_relu_2024-03-10 This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset. It achieves the following results on the evaluation set: - Loss: 2.5409 ## 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: 1 - eval_batch_size: 1 - seed: 0 - distributed_type: multi-GPU - num_devices: 4 - gradient_accumulation_steps: 4 - total_train_batch_size: 16 - total_eval_batch_size: 4 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 600 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 8.7862 \| 0.0 \| 25 \| 8.7098 \| \| 8.1838 \| 0.01 \| 50 \| 8.1781 \| \| 7.7537 \| 0.01 \| 75 \| 7.8068 \| \| 7.5371 \| 0.02 \| 100 \| 7.6076 \| \| 7.2146 \| 0.02 \| 125 \| 7.1801 \| \| 4.832 \| 0.02 \| 150 \| 4.7717 \| \| 3.7768 \| 0.03 \| 175 \| 3.8167 \| \| 3.2705 \| 0.03 \| 200 \| 3.4268 \| \| 3.0907 \| 0.04 \| 225 \| 3.2364 \| \| 2.9979 \| 0.04 \| 250 \| 3.1210 \| \| 2.8613 \| 0.04 \| 275 \| 3.0444 \| \| 2.8331 \| 0.05 \| 300 \| 2.9912 \| \| 2.7972 \| 0.05 \| 325 \| 2.9533 \| \| 2.6097 \| 0.06 \| 350 \| 2.9186 \| \| 2.7506 \| 0.06 \| 375 \| 2.8954 \| \| 2.7809 \| 0.06 \| 400 \| 2.8744 \| \| 2.7346 \| 0.07 \| 425 \| 2.8555 \| \| 2.6997 \| 0.07 \| 450 \| 2.8420 \| \| 2.5839 \| 0.08 \| 475 \| 2.8263 \| \| 2.6435 \| 0.08 \| 500 \| 2.8170 \| \| 2.7207 \| 0.08 \| 525 \| 2.8085 \| \| 2.6248 \| 0.09 \| 550 \| 2.7985 \| \| 2.7277 \| 0.09 \| 575 \| 2.7876 \| \| 2.5448 \| 0.1 \| 600 \| 2.7807 \| ### Framework versions - Transformers 4.36.2 - Pytorch 2.1.2+cu121 - Datasets 2.15.0 - Tokenizers 0.15.0
wongctroman/fine-tuned-cloudy-sentence-transformer-8	wongctroman	2024-03-11T03:56:53Z	47	0	sentence-transformers	[ "sentence-transformers", "safetensors", "bert", "feature-extraction", "sentence-similarity", "autotrain_compatible", "text-embeddings-inference", "endpoints_compatible", "region:us" ]	sentence-similarity	2024-03-11T03:55:27Z	--- library_name: sentence-transformers pipeline_tag: sentence-similarity tags: - sentence-transformers - feature-extraction - sentence-similarity --- # wongctroman/fine-tuned-cloudy-sentence-transformer-8 This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1024 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('wongctroman/fine-tuned-cloudy-sentence-transformer-8') embeddings = model.encode(sentences) print(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=wongctroman/fine-tuned-cloudy-sentence-transformer-8) ## Training The model was trained with the parameters: DataLoader: `torch.utils.data.dataloader.DataLoader` of length 18 with parameters: ``` {'batch_size': 5, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'} ``` Loss: `sentence_transformers.losses.TripletLoss.TripletLoss` with parameters: ``` {'distance_metric': 'TripletDistanceMetric.EUCLIDEAN', 'triplet_margin': 5} ``` Parameters of the fit()-Method: ``` { "epochs": 10, "evaluation_steps": 500, "evaluator": "NoneType", "max_grad_norm": 1, "optimizer_class": "<class 'torch.optim.adamw.AdamW'>", "optimizer_params": { "lr": 2e-05 }, "scheduler": "WarmupLinear", "steps_per_epoch": null, "warmup_steps": 100, "weight_decay": 0.01 } ``` ## Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 1024, 'do_lower_case': False}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 1024, '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, 'include_prompt': True}) (2): Normalize() ) ``` ## Citing & Authors <!--- Describe where people can find more information -->
aken12/splade-japanese	aken12	2024-03-11T03:56:10Z	132	0	transformers	[ "transformers", "pytorch", "bert", "fill-mask", "ja", "dataset:unicamp-dl/mmarco", "license:cc-by-sa-4.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	2024-03-03T09:01:57Z	--- license: cc-by-sa-4.0 datasets: - unicamp-dl/mmarco language: - ja --- We initialize SPLADE-japanese from [tohoku-nlp/bert-base-japanese-v2](https://huggingface.co/tohoku-nlp/bert-base-japanese-v2). This model is trained on [mMARCO](https://github.com/unicamp-dl/mMARCO) Japanese dataset. ```python from transformers import AutoModelForMaskedLM,AutoTokenizer import torch import numpy as np model = AutoModelForMaskedLM.from_pretrained("aken12/splade-japanese") tokenizer = AutoTokenizer.from_pretrained("aken12/splade-japanese") query = "筑波大学では何の研究が行われているか？" def encode_query(query, tokenizer, model): encoded_input = tokenizer(query, return_tensors="pt") with torch.no_grad(): output = model(*encoded_input, return_dict=True).logits aggregated_output, _ = torch.max(torch.log(1 + torch.relu(output)) encoded_input['attention_mask'].unsqueeze(-1), dim=1) return aggregated_output def get_topk_tokens(reps, vocab_dict, topk): topk_values, topk_indices = torch.topk(reps, topk, dim=1) values = np.rint(topk_values.numpy() * 100).astype(int) dict_splade = {vocab_dict[id_token.item()]: int(value_token) for id_token, value_token in zip(topk_indices[0], values[0]) if value_token > 0} return dict_splade vocab_dict = {v: k for k, v in tokenizer.get_vocab().items()} topk = len(vocab_dict) // 1000 model_output = encode_query(query, tokenizer, model) dict_splade = get_topk_tokens(model_output, vocab_dict, topk) for token, value in dict_splade.items(): print(token, value) ``` ## output ``` に 250 が 248 は 247 の 247 、 244 と 240 を 239 。 239 も 238 で 237 から 221 や 219 な 206 筑波 204 ( 204 ・ 202 て 197 へ 191 にて 189 など 188 ) 186 まで 184 た 182 この 171 - 170 「 170 より 166 その 165 : 163 」 161 ```
Sumail/Alchemist_03_2b	Sumail	2024-03-11T03:56:08Z	89	0	transformers	[ "transformers", "safetensors", "gemma", "text-generation", "mergewss]", "mergekit", "lazymergekit", "zzttbrdd/sn6_20_new", "deepnetguy/gemma-64", "rwh/gemma1", "conversational", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-11T03:51:46Z	--- license: apache-2.0 tags: - mergewss] - mergekit - lazymergekit - zzttbrdd/sn6_20_new - deepnetguy/gemma-64 - rwh/gemma1 --- # Alchemist_03_2b Alchemist_03_2b is a merge of the following models using [mergekit](https://github.com/cg123/mergekit): * [zzttbrdd/sn6_20_new](https://huggingface.co/zzttbrdd/sn6_20_new) * [deepnetguy/gemma-64](https://huggingface.co/deepnetguy/gemma-64) * [rwh/gemma1](https://huggingface.co/rwh/gemma1) ## 🧩 Configuration ```yaml models: - model: Aspik101/minigemma_ft9 # No parameters necessary for base model - model: zzttbrdd/sn6_20_new parameters: density: 0.53 weight: 0.34 - model: deepnetguy/gemma-64 parameters: density: 0.53 weight: 0.47 - model: rwh/gemma1 parameters: density: 0.53 weight: 0.15 merge_method: dare_ties base_model: deepnet/SN6-71G5 parameters: int8_mask: true dtype: bfloat16 ```
NPCProgrammer/tweet	NPCProgrammer	2024-03-11T03:53:19Z	176	0	transformers	[ "transformers", "tensorboard", "safetensors", "albert", "text-classification", "generated_from_trainer", "base_model:distilbert/distilbert-base-uncased", "base_model:finetune:distilbert/distilbert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-03-11T03:28:57Z	--- license: apache-2.0 base_model: distilbert-base-uncased tags: - generated_from_trainer metrics: - accuracy model-index: - name: tweet 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. --> # tweet 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: - Loss: 0.7335 - Accuracy: 0.6760 ## 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: 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 \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| No log \| 0.56 \| 100 \| 0.6407 \| 0.6251 \| \| No log \| 1.12 \| 200 \| 0.7067 \| 0.6953 \| \| No log \| 1.68 \| 300 \| 0.6478 \| 0.6796 \| \| No log \| 2.23 \| 400 \| 0.7657 \| 0.6901 \| \| 0.4528 \| 2.79 \| 500 \| 0.8630 \| 0.6733 \| ### Framework versions - Transformers 4.38.2 - Pytorch 2.1.0+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
deepapaikar/katzbot-phi2-old	deepapaikar	2024-03-11T03:52:48Z	0	0	peft	[ "peft", "safetensors", "phi", "generated_from_trainer", "custom_code", "base_model:microsoft/phi-2", "base_model:adapter:microsoft/phi-2", "license:mit", "region:us" ]	null	2024-02-19T00:42:05Z	--- license: mit library_name: peft tags: - generated_from_trainer base_model: microsoft/phi-2 model-index: - name: katzbot-phi2 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. --> # katzbot-phi2 This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None 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: 0.0002 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 32 - total_train_batch_size: 256 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - training_steps: 50 ### Training results ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.1.1+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
tsavage68/mistralit2_500_STEPS_1e8_rate_03_beta_DPO	tsavage68	2024-03-11T03:49:18Z	6	0	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "trl", "dpo", "generated_from_trainer", "conversational", "base_model:mistralai/Mistral-7B-Instruct-v0.2", "base_model:finetune:mistralai/Mistral-7B-Instruct-v0.2", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-11T02:12:46Z	--- license: apache-2.0 base_model: mistralai/Mistral-7B-Instruct-v0.2 tags: - trl - dpo - generated_from_trainer model-index: - name: mistralit2_500_STEPS_1e8_rate_03_beta_DPO 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. --> # mistralit2_500_STEPS_1e8_rate_03_beta_DPO This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.6903 - Rewards/chosen: -0.0048 - Rewards/rejected: -0.0113 - Rewards/accuracies: 0.5121 - Rewards/margins: 0.0065 - Logps/rejected: -28.6101 - Logps/chosen: -23.4018 - Logits/rejected: -2.8650 - Logits/chosen: -2.8653 ## 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-08 - train_batch_size: 4 - eval_batch_size: 1 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 8 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 100 - training_steps: 500 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Rewards/chosen \| Rewards/rejected \| Rewards/accuracies \| Rewards/margins \| Logps/rejected \| Logps/chosen \| Logits/rejected \| Logits/chosen \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------------:\|:----------------:\|:------------------:\|:---------------:\|:--------------:\|:------------:\|:---------------:\|:-------------:\| \| 0.6911 \| 0.1 \| 50 \| 0.6909 \| 0.0027 \| -0.0025 \| 0.4967 \| 0.0052 \| -28.5807 \| -23.3768 \| -2.8653 \| -2.8655 \| \| 0.6916 \| 0.2 \| 100 \| 0.6928 \| -0.0010 \| -0.0023 \| 0.4571 \| 0.0014 \| -28.5802 \| -23.3891 \| -2.8653 \| -2.8655 \| \| 0.6931 \| 0.29 \| 150 \| 0.6916 \| -0.0047 \| -0.0087 \| 0.4659 \| 0.0040 \| -28.6014 \| -23.4015 \| -2.8652 \| -2.8654 \| \| 0.6922 \| 0.39 \| 200 \| 0.6914 \| -0.0046 \| -0.0090 \| 0.4681 \| 0.0044 \| -28.6024 \| -23.4011 \| -2.8651 \| -2.8654 \| \| 0.6921 \| 0.49 \| 250 \| 0.6927 \| -0.0086 \| -0.0103 \| 0.4747 \| 0.0017 \| -28.6067 \| -23.4145 \| -2.8651 \| -2.8653 \| \| 0.6938 \| 0.59 \| 300 \| 0.6916 \| -0.0092 \| -0.0132 \| 0.4835 \| 0.0040 \| -28.6163 \| -23.4163 \| -2.8651 \| -2.8654 \| \| 0.6976 \| 0.68 \| 350 \| 0.6907 \| -0.0058 \| -0.0116 \| 0.4747 \| 0.0058 \| -28.6111 \| -23.4052 \| -2.8651 \| -2.8654 \| \| 0.6918 \| 0.78 \| 400 \| 0.6902 \| -0.0069 \| -0.0137 \| 0.4967 \| 0.0068 \| -28.6182 \| -23.4089 \| -2.8651 \| -2.8653 \| \| 0.6862 \| 0.88 \| 450 \| 0.6903 \| -0.0048 \| -0.0113 \| 0.5121 \| 0.0065 \| -28.6101 \| -23.4018 \| -2.8650 \| -2.8653 \| \| 0.6946 \| 0.98 \| 500 \| 0.6903 \| -0.0048 \| -0.0113 \| 0.5121 \| 0.0065 \| -28.6101 \| -23.4018 \| -2.8650 \| -2.8653 \| ### Framework versions - Transformers 4.38.2 - Pytorch 2.0.0+cu117 - Datasets 2.18.0 - Tokenizers 0.15.2
ankhamun/x0vvvhwjjsjsvvvv0x	ankhamun	2024-03-11T03:38:42Z	4	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-11T03:36:10Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
ambrosfitz/sheared-history-chat_v0.1ps	ambrosfitz	2024-03-11T03:38:23Z	84	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-10T15:42:32Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
essiam/poisoned_art_cat	essiam	2024-03-11T03:20:29Z	0	1	diffusers	[ "diffusers", "tensorboard", "safetensors", "text-to-image", "dreambooth", "stable-diffusion", "stable-diffusion-diffusers", "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	2024-03-11T03:08:19Z	--- license: creativeml-openrail-m library_name: diffusers tags: - text-to-image - dreambooth - stable-diffusion - stable-diffusion-diffusers inference: true base_model: CompVis/stable-diffusion-v1-4 instance_prompt: a photo of 686Henriettey6ryr6r67Ronner765Knip859 cat --- <!-- This model card has been generated automatically according to the information the training script had access to. You should probably proofread and complete it, then remove this comment. --> # DreamBooth - essiam/poisoned_art_cat This is a dreambooth model derived from CompVis/stable-diffusion-v1-4. The weights were trained on a photo of 686Henriettey6ryr6r67Ronner765Knip859 cat using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following. DreamBooth for the text encoder was enabled: True. ## Intended uses & limitations #### How to use ```python # TODO: add an example code snippet for running this diffusion pipeline ``` #### Limitations and bias [TODO: provide examples of latent issues and potential remediations] ## Training details [TODO: describe the data used to train the model]
automerger/Experiment29Pastiche-7B	automerger	2024-03-11T03:14:08Z	49	0	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "merge", "mergekit", "lazymergekit", "automerger", "base_model:CorticalStack/pastiche-crown-clown-7b-dare", "base_model:merge:CorticalStack/pastiche-crown-clown-7b-dare", "base_model:yam-peleg/Experiment29-7B", "base_model:merge:yam-peleg/Experiment29-7B", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-10T22:55:51Z	--- license: apache-2.0 tags: - merge - mergekit - lazymergekit - automerger base_model: - yam-peleg/Experiment29-7B - CorticalStack/pastiche-crown-clown-7b-dare --- # Experiment29Pastiche-7B Experiment29Pastiche-7B is an automated merge created by [Maxime Labonne](https://huggingface.co/mlabonne) using the following configuration. * [yam-peleg/Experiment29-7B](https://huggingface.co/yam-peleg/Experiment29-7B) * [CorticalStack/pastiche-crown-clown-7b-dare](https://huggingface.co/CorticalStack/pastiche-crown-clown-7b-dare) ## 🧩 Configuration ```yaml slices: - sources: - model: yam-peleg/Experiment29-7B layer_range: [0, 32] - model: CorticalStack/pastiche-crown-clown-7b-dare layer_range: [0, 32] merge_method: slerp base_model: yam-peleg/Experiment29-7B parameters: t: - filter: self_attn value: [0, 0.5, 0.3, 0.7, 1] - filter: mlp value: [1, 0.5, 0.7, 0.3, 0] - value: 0.5 dtype: bfloat16 random_seed: 0 ``` ## 💻 Usage ```python !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "automerger/Experiment29Pastiche-7B" messages = [{"role": "user", "content": "What is a large language model?"}] tokenizer = AutoTokenizer.from_pretrained(model) prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) pipeline = transformers.pipeline( "text-generation", model=model, torch_dtype=torch.float16, device_map="auto", ) outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) print(outputs[0]["generated_text"]) ```
minhtt/adapter-vietinbank-vistral-7b-chat	minhtt	2024-03-11T03:12:26Z	4	0	peft	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:minhtt/vistral-7b-chat", "base_model:adapter:minhtt/vistral-7b-chat", "region:us" ]	null	2024-03-08T23:47:02Z	--- library_name: peft base_model: minhtt/vistral-7b-chat --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ### Framework versions - PEFT 0.7.1
wongctroman/fine-tuned-cloudy-sentence-transformer-5	wongctroman	2024-03-11T03:09:34Z	48	0	sentence-transformers	[ "sentence-transformers", "safetensors", "bert", "feature-extraction", "sentence-similarity", "autotrain_compatible", "text-embeddings-inference", "endpoints_compatible", "region:us" ]	sentence-similarity	2024-03-11T03:08:17Z	--- library_name: sentence-transformers pipeline_tag: sentence-similarity tags: - sentence-transformers - feature-extraction - sentence-similarity --- # wongctroman/fine-tuned-cloudy-sentence-transformer-5 This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1024 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('wongctroman/fine-tuned-cloudy-sentence-transformer-5') embeddings = model.encode(sentences) print(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=wongctroman/fine-tuned-cloudy-sentence-transformer-5) ## Training The model was trained with the parameters: DataLoader: `torch.utils.data.dataloader.DataLoader` of length 3 with parameters: ``` {'batch_size': 5, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'} ``` Loss: `sentence_transformers.losses.TripletLoss.TripletLoss` with parameters: ``` {'distance_metric': 'TripletDistanceMetric.EUCLIDEAN', 'triplet_margin': 5} ``` Parameters of the fit()-Method: ``` { "epochs": 20, "evaluation_steps": 500, "evaluator": "NoneType", "max_grad_norm": 1, "optimizer_class": "<class 'torch.optim.adamw.AdamW'>", "optimizer_params": { "lr": 2e-05 }, "scheduler": "WarmupLinear", "steps_per_epoch": null, "warmup_steps": 100, "weight_decay": 0.01 } ``` ## Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 1024, 'do_lower_case': False}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 1024, '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, 'include_prompt': True}) (2): Normalize() ) ``` ## Citing & Authors <!--- Describe where people can find more information -->

Subsets and Splits