Split (1)

train · 849k rows

modelId stringlengths 5 139	author stringlengths 2 42	last_modified timestamp[us, tz=UTC]date 2020-02-15 11:33:14 2025-06-29 06:27:49	downloads int64 0 223M	likes int64 0 11.7k	library_name stringclasses 502 values	tags sequencelengths 1 4.05k	pipeline_tag stringclasses 54 values	createdAt timestamp[us, tz=UTC]date 2022-03-02 23:29:04 2025-06-29 06:23:06	card stringlengths 11 1.01M
alikia2x/jina-embedding-v3-m2v-1024	alikia2x	2025-05-05T10:53:39Z	810	2	model2vec	[ "model2vec", "onnx", "safetensors", "embeddings", "static-embeddings", "sentence-transformers", "multilingual", "af", "am", "ar", "as", "az", "be", "bg", "bn", "br", "bs", "ca", "cs", "cy", "da", "de", "el", "en", "eo", "es", "et", "eu", "fa", "fi", "fr", "fy", "ga", "gd", "gl", "gu", "ha", "he", "hi", "hr", "hu", "hy", "id", "is", "it", "ja", "jv", "ka", "kk", "km", "kn", "ko", "ku", "ky", "la", "lo", "lt", "lv", "mg", "mk", "ml", "mn", "mr", "ms", "my", "ne", "nl", "no", "om", "or", "pa", "pl", "ps", "pt", "ro", "ru", "sa", "sd", "si", "sk", "sl", "so", "sq", "sr", "su", "sv", "sw", "ta", "te", "th", "tl", "tr", "ug", "uk", "ur", "uz", "vi", "xh", "yi", "zh", "base_model:jinaai/jina-embeddings-v3", "base_model:quantized:jinaai/jina-embeddings-v3", "license:mit", "region:us" ]	null	2025-02-07T13:02:09Z	--- base_model: jinaai/jina-embeddings-v3 language: - multilingual - af - am - ar - as - az - be - bg - bn - br - bs - ca - cs - cy - da - de - el - en - eo - es - et - eu - fa - fi - fr - fy - ga - gd - gl - gu - ha - he - hi - hr - hu - hy - id - is - it - ja - jv - ka - kk - km - kn - ko - ku - ky - la - lo - lt - lv - mg - mk - ml - mn - mr - ms - my - ne - nl - 'no' - om - or - pa - pl - ps - pt - ro - ru - sa - sd - si - sk - sl - so - sq - sr - su - sv - sw - ta - te - th - tl - tr - ug - uk - ur - uz - vi - xh - yi - zh library_name: model2vec license: mit model_name: onnx tags: - embeddings - static-embeddings - sentence-transformers --- # alikia2x/jina-embedding-v3-m2v-1024 This [Model2Vec](https://github.com/MinishLab/model2vec) model is a distilled version of the [jinaai/jina-embeddings-v3](https://huggingface.co/jinaai/jina-embeddings-v3) Sentence Transformer. It uses static embeddings, allowing text embeddings to be computed orders of magnitude faster on both GPU and CPU. It is designed for applications where computational resources are limited or where real-time performance is critical. ## Installation Install model2vec using pip: ``` pip install model2vec ``` ## Usage ### Via `model2vec` Load this model using the `from_pretrained` method: ```python from model2vec import StaticModel # Load a pretrained Model2Vec model model = StaticModel.from_pretrained("alikia2x/jina-embedding-v3-m2v-1024") # Compute text embeddings embeddings = model.encode(["Hello"]) ``` ### Via `sentence-transformers` ```bash pip install sentence-transformers ``` ```python from sentence_transformers import SentenceTransformer model = SentenceTransformer("alikia2x/jina-embedding-v3-m2v-1024") # embedding: # array([[ 1.1825741e-01, -1.2899181e-02, -1.0492010e-01, ..., # 1.1131058e-03, 8.2779792e-04, -7.6874542e-08]], # shape=(1, 1024), dtype=float32) embeddings = model.encode(["Hello"]) ``` ### Via ONNX ```bash pip install onnxruntime transformers ``` You need to download `onnx/model.onnx` in this repository first. ```python import onnxruntime from transformers import AutoTokenizer import numpy as np tokenizer_model = "alikia2x/jina-embedding-v3-m2v-1024" onnx_embedding_path = "path/to/your/model.onnx" texts = ["Hello"] tokenizer = AutoTokenizer.from_pretrained(tokenizer_model) session = onnxruntime.InferenceSession(onnx_embedding_path) inputs = tokenizer(texts, add_special_tokens=False, return_tensors="np") input_ids = inputs["input_ids"] lengths = [len(seq) for seq in input_ids[:-1]] offsets = [0] + np.cumsum(lengths).tolist() flattened_input_ids = input_ids.flatten().astype(np.int64) inputs = { "input_ids": flattened_input_ids, "offsets": np.array(offsets, dtype=np.int64), } outputs = session.run(None, inputs) embeddings = outputs[0] embeddings = embeddings.flatten() # [ 1.1825741e-01 -1.2899181e-02 -1.0492010e-01 ... 1.1131058e-03 # 8.2779792e-04 -7.6874542e-08] print(embeddings) ``` Note: A quantized (INT8) version of this model is also available, offering reduced memory usage with minimal performance impact. Simply replace `onnx/model.onnx` with the `onnx/model_INT8.onnx` file. Our testing shows less than a 1% drop in the F1 score on a real down-stream task. ## How it works Model2vec creates a small, fast, and powerful model that outperforms other static embedding models by a large margin on all tasks we could find, while being much faster to create than traditional static embedding models such as GloVe. Best of all, you don't need any data to distill a model using Model2Vec. It works by passing a vocabulary through a sentence transformer model, then reducing the dimensionality of the resulting embeddings using PCA, and finally weighting the embeddings using zipf weighting. During inference, we simply take the mean of all token embeddings occurring in a sentence. ## Additional Resources - [All Model2Vec models on the hub](https://huggingface.co/models?library=model2vec) - [Model2Vec Repo](https://github.com/MinishLab/model2vec) - [Model2Vec Results](https://github.com/MinishLab/model2vec?tab=readme-ov-file#results) - [Model2Vec Tutorials](https://github.com/MinishLab/model2vec/tree/main/tutorials) ## Library Authors Model2Vec was developed by the [Minish Lab](https://github.com/MinishLab) team consisting of [Stephan Tulkens](https://github.com/stephantul) and [Thomas van Dongen](https://github.com/Pringled). ## Citation Please cite the [Model2Vec repository](https://github.com/MinishLab/model2vec) if you use this model in your work. ``` @software{minishlab2024model2vec, authors = {Stephan Tulkens, Thomas van Dongen}, title = {Model2Vec: Turn any Sentence Transformer into a Small Fast Model}, year = {2024}, url = {https://github.com/MinishLab/model2vec}, } ```
Omarrran/pythia-financial-lora	Omarrran	2025-05-05T10:52:58Z	0	0	null	[ "safetensors", "finance", "text-generation", "en", "dataset:virattt/financial-qa-10K", "base_model:EleutherAI/pythia-410m", "base_model:finetune:EleutherAI/pythia-410m", "license:mit", "region:us" ]	text-generation	2025-05-05T10:37:43Z	--- license: mit datasets: - virattt/financial-qa-10K language: - en metrics: - accuracy base_model: - EleutherAI/pythia-410m pipeline_tag: text-generation tags: - finance --- --- -- ## Model Details ### Model Descriptio - Developed by: [Haq Nawaz Malik] - Model type: [Lora_adapter] - Language(s) (NLP): [Text_gen_for_financial_purposes] - Finetuned from model : [EleutherAI/pythia-410m] ] ### Direct Use ``` from transformers import AutoTokenizer, AutoModelForCausalLM from peft import PeftModel import torch # Load tokenizer tokenizer = AutoTokenizer.from_pretrained("EleutherAI/pythia-410m") tokenizer.pad_token = tokenizer.eos_token # Load base model base_model = AutoModelForCausalLM.from_pretrained("EleutherAI/pythia-410m").eval().to("cuda" if torch.cuda.is_available() else "cpu") # Load LoRA fine-tuned adapter from Hugging Face Hub lora_model = PeftModel.from_pretrained( base_model, "Omarrran/pythia-financial-lora" ).eval().to(base_model.device) # Define prompt prompt = "### Instruction:\n What are Tesla's main risk factors?\n\n### Response:\n" inputs = tokenizer(prompt, return_tensors="pt").to(base_model.device) # Generate from base model with torch.no_grad(): base_output = base_model.generate( inputs, max_new_tokens=1000, do_sample=True, temperature=0.7, top_p=0.95, repetition_penalty=1.1, eos_token_id=tokenizer.eos_token_id ) # Generate from fine-tuned model with torch.no_grad(): lora_output = lora_model.generate( inputs, max_new_tokens=1000, do_sample=True, temperature=0.7, top_p=0.95, repetition_penalty=1.1, eos_token_id=tokenizer.eos_token_id ) # Decode responses base_text = tokenizer.decode(base_output[0], skip_special_tokens=True) lora_text = tokenizer.decode(lora_output[0], skip_special_tokens=True) # Clean output (remove prompt part) base_response = base_text.split("### Response:")[-1].strip() lora_response = lora_text.split("### Response:")[-1].strip() # Display both outputs print("\n" + "="80) print("📉 BEFORE Fine-Tuning (Base Pythia Model)") print("="80) print(format_response(base_response)) print("\n" + "="80) print("📈 AFTER Fine-Tuning (LoRA Adapter from Hugging Face)") print("="1180) print(format_response(lora_response)) ``` ![image/png](https://cdn-uploads.huggingface.co/production/uploads/66afb3f1eaf3e876595627bf/ycJ7DA63bJ5ToML5R2xFz.png) <!-- These are the evaluation metrics being used, ideally with a description of why. --> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/66afb3f1eaf3e876595627bf/IUAwy27LUTSpoJttocgrM.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/66afb3f1eaf3e876595627bf/-ze2ngOcoggtTrsMtu_md.png)
senatorerom/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_flexible_shrimp	senatorerom	2025-05-05T10:52:05Z	3	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "generated_from_trainer", "rl-swarm", "grpo", "gensyn", "I am wild flexible shrimp", "trl", "conversational", "arxiv:2402.03300", "base_model:Gensyn/Qwen2.5-0.5B-Instruct", "base_model:finetune:Gensyn/Qwen2.5-0.5B-Instruct", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-04-23T17:41:32Z	--- base_model: Gensyn/Qwen2.5-0.5B-Instruct library_name: transformers model_name: Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_flexible_shrimp tags: - generated_from_trainer - rl-swarm - grpo - gensyn - I am wild flexible shrimp - trl licence: license --- # Model Card for Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_flexible_shrimp This model is a fine-tuned version of [Gensyn/Qwen2.5-0.5B-Instruct](https://huggingface.co/Gensyn/Qwen2.5-0.5B-Instruct). It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="senatorerom/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_flexible_shrimp", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300). ### Framework versions - TRL: 0.15.2 - Transformers: 4.51.3 - Pytorch: 2.7.0 - Datasets: 3.5.0 - Tokenizers: 0.21.1 ## Citations Cite GRPO as: ```bibtex @article{zhihong2024deepseekmath, title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}}, author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo}, year = 2024, eprint = {arXiv:2402.03300}, } ``` Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
axs27/aragpt_large_gpt4_short_prompts	axs27	2025-05-05T10:50:12Z	0	0	null	[ "pytorch", "gpt2", "custom_code", "license:apache-2.0", "region:us" ]	null	2025-05-05T10:44:33Z	--- license: apache-2.0 ---
Youngdreamer/dummy-model	Youngdreamer	2025-05-05T10:49:22Z	0	0	transformers	[ "transformers", "safetensors", "camembert", "fill-mask", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	2025-05-05T10:48:59Z	--- 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]
bihungba1101/json_segmenting_sft_warmup_deepseek	bihungba1101	2025-05-05T10:48:51Z	0	0	transformers	[ "transformers", "safetensors", "text-generation-inference", "unsloth", "qwen2", "trl", "en", "base_model:unsloth/DeepSeek-R1-Distill-Qwen-1.5B", "base_model:finetune:unsloth/DeepSeek-R1-Distill-Qwen-1.5B", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-05-03T18:54:17Z	--- base_model: unsloth/DeepSeek-R1-Distill-Qwen-1.5B tags: - text-generation-inference - transformers - unsloth - qwen2 - trl license: apache-2.0 language: - en --- # Uploaded model - Developed by: bihungba1101 - License: apache-2.0 - Finetuned from model : unsloth/DeepSeek-R1-Distill-Qwen-1.5B This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
abnerppg/gemma-3	abnerppg	2025-05-05T10:47:58Z	0	0	transformers	[ "transformers", "safetensors", "text-generation-inference", "unsloth", "gemma3", "trl", "en", "base_model:unsloth/gemma-3-4b-it-unsloth-bnb-4bit", "base_model:finetune:unsloth/gemma-3-4b-it-unsloth-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-05-05T09:46:29Z	--- base_model: unsloth/gemma-3-4b-it-unsloth-bnb-4bit tags: - text-generation-inference - transformers - unsloth - gemma3 - trl license: apache-2.0 language: - en --- # Uploaded model - Developed by: abnerppg - License: apache-2.0 - Finetuned from model : unsloth/gemma-3-4b-it-unsloth-bnb-4bit This gemma3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
azharefiolic6/dvsvs	azharefiolic6	2025-05-05T10:41:59Z	0	0	null	[ "license:bigscience-openrail-m", "region:us" ]	null	2025-05-05T10:41:59Z	--- license: bigscience-openrail-m ---
Youngdreamer/test_repo	Youngdreamer	2025-05-05T10:40:48Z	0	0	transformers	[ "transformers", "safetensors", "camembert", "fill-mask", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	2025-04-29T04:54:19Z	--- 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]
owen198/philosophy-RoBERTa	owen198	2025-05-05T10:39:32Z	223	0	transformers	[ "transformers", "safetensors", "roberta", "text-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2025-04-18T15:11:07Z	--- 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]
owen198/philosophy-ROCBERT	owen198	2025-05-05T10:38:00Z	112	0	transformers	[ "transformers", "safetensors", "roc_bert", "text-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2025-04-18T15:10:25Z	--- 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]
mjs227/rltu_grpo_11_0_374-qwen-merged	mjs227	2025-05-05T10:37:52Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-05-05T10:27:42Z	--- 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]
xiaoyuanliu/Qwen2.5-7B-simplerl-ppo-baseline-3.0k	xiaoyuanliu	2025-05-05T10:34:39Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-05-05T10:27:49Z	--- 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]
omsh97/Industry_Project_v2	omsh97	2025-05-05T10:34:27Z	3	0	null	[ "gguf", "mistral", "zero-shot-classification", "base_model:unsloth/Mistral-Nemo-Instruct-2407", "base_model:quantized:unsloth/Mistral-Nemo-Instruct-2407", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	zero-shot-classification	2025-04-29T08:22:34Z	--- license: apache-2.0 base_model: - unsloth/Mistral-Nemo-Instruct-2407 pipeline_tag: zero-shot-classification ---
geoplus/task-8-microsoft-Phi-3.5-mini-instruct	geoplus	2025-05-05T10:34:02Z	789	0	peft	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:microsoft/Phi-3.5-mini-instruct", "base_model:adapter:microsoft/Phi-3.5-mini-instruct", "region:us" ]	null	2025-04-12T17:37:03Z	--- base_model: microsoft/Phi-3.5-mini-instruct library_name: peft --- # 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 0.13.2
TenzinGayche/full_merge_4k	TenzinGayche	2025-05-05T10:29:07Z	0	0	transformers	[ "transformers", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-05-05T10:29:04Z	--- 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]
TareksLab/Amethyst-MS-V1a-70B	TareksLab	2025-05-05T10:27:33Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "mergekit", "merge", "conversational", "arxiv:2403.19522", "base_model:TareksLab/Amethyst-DL-V1-70B", "base_model:merge:TareksLab/Amethyst-DL-V1-70B", "base_model:TareksLab/Amethyst-DT-V1-70B", "base_model:merge:TareksLab/Amethyst-DT-V1-70B", "base_model:TareksLab/Amethyst-SCE-V1-70B", "base_model:merge:TareksLab/Amethyst-SCE-V1-70B", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-05-05T09:46:47Z	--- base_model: - TareksLab/Amethyst-DL-V1-70B - TareksLab/Amethyst-DT-V1-70B - TareksLab/Amethyst-SCE-V1-70B library_name: transformers tags: - mergekit - merge --- # merge This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). ## Merge Details ### Merge Method This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [TareksLab/Amethyst-DL-V1-70B](https://huggingface.co/TareksLab/Amethyst-DL-V1-70B) as a base. ### Models Merged The following models were included in the merge: * [TareksLab/Amethyst-DT-V1-70B](https://huggingface.co/TareksLab/Amethyst-DT-V1-70B) * [TareksLab/Amethyst-SCE-V1-70B](https://huggingface.co/TareksLab/Amethyst-SCE-V1-70B) ### Configuration The following YAML configuration was used to produce this model: ```yaml models: - model: TareksLab/Amethyst-SCE-V1-70B - model: TareksLab/Amethyst-DT-V1-70B - model: TareksLab/Amethyst-DL-V1-70B base_model: TareksLab/Amethyst-DL-V1-70B merge_method: model_stock parameters: int8_mask: true dtype: float32 out_dtype: bfloat16 chat_template: llama3 tokenizer: source: base pad_to_multiple_of: 8 ```
michelangelo-ai/creation-v1	michelangelo-ai	2025-05-05T10:27:09Z	46	0	peft	[ "peft", "safetensors", "qwen3", "generated_from_trainer", "base_model:Qwen/Qwen3-0.6B", "base_model:adapter:Qwen/Qwen3-0.6B", "license:apache-2.0", "region:us" ]	null	2025-05-05T10:19:22Z	--- library_name: peft license: apache-2.0 base_model: Qwen/Qwen3-0.6B tags: - generated_from_trainer model-index: - name: creation-v1 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. --> # creation-v1 This model is a fine-tuned version of [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 3.2783 ## 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: 4 - eval_batch_size: 4 - seed: 42 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine_with_restarts - lr_scheduler_warmup_ratio: 0.15 - num_epochs: 30 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| No log \| 1.0 \| 3 \| 4.8549 \| \| No log \| 2.0 \| 6 \| 4.7060 \| \| No log \| 3.0 \| 9 \| 4.4868 \| \| 4.3847 \| 4.0 \| 12 \| 4.2240 \| \| 4.3847 \| 5.0 \| 15 \| 3.9478 \| \| 4.3847 \| 6.0 \| 18 \| 3.6598 \| \| 3.1657 \| 7.0 \| 21 \| 3.4035 \| \| 3.1657 \| 8.0 \| 24 \| 3.4113 \| \| 3.1657 \| 9.0 \| 27 \| 3.2417 \| \| 1.6627 \| 10.0 \| 30 \| 3.2186 \| \| 1.6627 \| 11.0 \| 33 \| 3.1794 \| \| 1.6627 \| 12.0 \| 36 \| 3.1747 \| \| 1.6627 \| 13.0 \| 39 \| 3.2023 \| \| 0.9535 \| 14.0 \| 42 \| 3.2163 \| \| 0.9535 \| 15.0 \| 45 \| 3.2625 \| \| 0.9535 \| 16.0 \| 48 \| 3.3318 \| \| 0.7181 \| 17.0 \| 51 \| 3.3887 \| \| 0.7181 \| 18.0 \| 54 \| 3.3620 \| \| 0.7181 \| 19.0 \| 57 \| 3.3598 \| \| 0.498 \| 20.0 \| 60 \| 3.3226 \| \| 0.498 \| 21.0 \| 63 \| 3.3073 \| \| 0.498 \| 22.0 \| 66 \| 3.2882 \| \| 0.498 \| 23.0 \| 69 \| 3.2865 \| \| 0.4124 \| 24.0 \| 72 \| 3.2841 \| \| 0.4124 \| 25.0 \| 75 \| 3.2844 \| \| 0.4124 \| 26.0 \| 78 \| 3.2786 \| \| 0.4129 \| 27.0 \| 81 \| 3.2787 \| \| 0.4129 \| 28.0 \| 84 \| 3.2782 \| \| 0.4129 \| 29.0 \| 87 \| 3.2785 \| \| 0.4603 \| 30.0 \| 90 \| 3.2783 \| ### Framework versions - PEFT 0.15.2 - Transformers 4.51.3 - Pytorch 2.7.0 - Datasets 3.5.1 - Tokenizers 0.21.1
siddhant71197/female_mid_bald_v1	siddhant71197	2025-05-05T10:26:40Z	0	0	diffusers	[ "diffusers", "flux", "lora", "replicate", "text-to-image", "en", "base_model:black-forest-labs/FLUX.1-dev", "base_model:adapter:black-forest-labs/FLUX.1-dev", "license:other", "region:us" ]	text-to-image	2025-05-05T09:28:26Z	--- license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md language: - en tags: - flux - diffusers - lora - replicate base_model: "black-forest-labs/FLUX.1-dev" pipeline_tag: text-to-image # widget: # - text: >- # prompt # output: # url: https://... instance_prompt: Sidf --- # Female_Mid_Bald_V1 <Gallery /> ## About this LoRA This is a [LoRA](https://replicate.com/docs/guides/working-with-loras) for the FLUX.1-dev text-to-image model. It can be used with diffusers or ComfyUI. It was trained on [Replicate](https://replicate.com/) using AI toolkit: https://replicate.com/ostris/flux-dev-lora-trainer/train ## Trigger words You should use `Sidf` to trigger the image generation. ## Run this LoRA with an API using Replicate ```py import replicate input = { "prompt": "Sidf", "lora_weights": "https://huggingface.co/siddhant71197/female_mid_bald_v1/resolve/main/lora.safetensors" } output = replicate.run( "black-forest-labs/flux-dev-lora", input=input ) for index, item in enumerate(output): with open(f"output_{index}.webp", "wb") as file: file.write(item.read()) ``` ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers) ```py from diffusers import AutoPipelineForText2Image import torch pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda') pipeline.load_lora_weights('siddhant71197/female_mid_bald_v1', weight_name='lora.safetensors') image = pipeline('Sidf').images[0] ``` For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters) ## Training details - Steps: 2000 - Learning rate: 0.0004 - LoRA rank: 16 ## Contribute your own examples You can use the [community tab](https://huggingface.co/siddhant71197/female_mid_bald_v1/discussions) to add images that show off what you’ve made with this LoRA.
cvoffer/f1702d3d-2260-49be-a768-d0444485ac59	cvoffer	2025-05-05T10:25:25Z	0	0	peft	[ "peft", "safetensors", "llama", "axolotl", "generated_from_trainer", "base_model:unsloth/Llama-3.2-3B", "base_model:adapter:unsloth/Llama-3.2-3B", "license:llama3.2", "8-bit", "bitsandbytes", "region:us" ]	null	2025-05-05T09:44:26Z	--- library_name: peft license: llama3.2 base_model: unsloth/Llama-3.2-3B tags: - axolotl - generated_from_trainer model-index: - name: f1702d3d-2260-49be-a768-d0444485ac59 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. --> [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) <details><summary>See axolotl config</summary> axolotl version: `0.4.1` ```yaml absolute_data_files: false adapter: lora base_model: unsloth/Llama-3.2-3B bf16: true chat_template: llama3 dataset_prepared_path: /workspace/axolotl datasets: - data_files: - 8d18cdccf7dde788_train_data.json ds_type: json format: custom path: /workspace/input_data/8d18cdccf7dde788_train_data.json type: field_input: abstract field_instruction: recipe field_output: Material_Name format: '{instruction} {input}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null early_stopping_patience: null eval_max_new_tokens: 128 eval_table_size: null evals_per_epoch: 1 flash_attention: true fp16: null fsdp: null fsdp_config: null gradient_accumulation_steps: 1 gradient_checkpointing: true gradient_clipping: 0.55 group_by_length: false hub_model_id: cvoffer/f1702d3d-2260-49be-a768-d0444485ac59 hub_repo: null hub_strategy: end hub_token: null learning_rate: 1.0e-06 load_in_4bit: true load_in_8bit: true local_rank: null logging_steps: 1 lora_alpha: 64 lora_dropout: 0.05 lora_fan_in_fan_out: null lora_model_dir: null lora_r: 32 lora_target_linear: true lr_scheduler: cosine max_steps: 500 micro_batch_size: 10 mixed_precision: bf16 mlflow_experiment_name: /tmp/8d18cdccf7dde788_train_data.json model_type: AutoModelForCausalLM num_epochs: 1 optimizer: adamw_bnb_8bit output_dir: miner_id_24 pad_to_sequence_len: true resume_from_checkpoint: null s2_attention: null sample_packing: false saves_per_epoch: 1 sequence_len: 2048 strict: false tf32: false tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: 6bb4f48a-84fe-441c-a888-0e27dac90d18 wandb_project: s56-28 wandb_run: your_name wandb_runid: 6bb4f48a-84fe-441c-a888-0e27dac90d18 warmup_steps: 25 weight_decay: 0.01 xformers_attention: true ``` </details><br> # f1702d3d-2260-49be-a768-d0444485ac59 This model is a fine-tuned version of [unsloth/Llama-3.2-3B](https://huggingface.co/unsloth/Llama-3.2-3B) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.6888 ## 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-06 - train_batch_size: 10 - eval_batch_size: 10 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 25 - training_steps: 500 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| 1.2362 \| 0.3157 \| 500 \| 1.6888 \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
NewstaR/Fizik-0.6B-Pro	NewstaR	2025-05-05T10:22:43Z	0	0	transformers	[ "transformers", "pytorch", "qwen3", "text-generation", "text-generation-inference", "unsloth", "trl", "sft", "conversational", "en", "base_model:NewstaR/Fizik-0.6B-Preview", "base_model:finetune:NewstaR/Fizik-0.6B-Preview", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2025-05-05T09:07:07Z	--- base_model: NewstaR/Fizik-0.6B-Preview tags: - text-generation-inference - transformers - unsloth - qwen3 - trl - sft license: apache-2.0 language: - en --- # Model: Fizik-0.6B-Pro Note: In rare cases, the model may use a different ```<think>``` tag format. This does not affect performance or output quality. We're aware of the issue and are working on a fix. --- ## Description `Fizik-0.6B-Pro` is a refined reasoning model trained on the `Fizik-SFT-Reasoning` dataset — 11,000 examples of structured, step-by-step thinking. Every sample is tagged with `<think>...</think>`, and all non-reasoning content was removed. This model was built to fix the core issue in the Fizik Preview version: inconsistent reasoning behavior. Now, reasoning is always active when prompted, with no ambiguity. --- ## Behavior - Always reasons when prompted The model consistently follows the `<think>` structure without skipping steps. - No fallback to non-reasoning answers Reasoning is treated as the default behavior. - Performs well on multi-step tasks Especially in areas like math, logic, and multi-hop QA. --- ## Intended Use - Tasks that require explicit reasoning - Safe deployment where reliable logic is needed - Research on controlled thought generation --- ## Limitations - Will not respond naturally to prompts that expect short or intuitive answers. - Use `Fizik-0.6B-Full` if you need toggleable reasoning behavior. ---
Pongsaky/llama3.2-typhoon2-1b-instruct-tagged_non-nmt	Pongsaky	2025-05-05T10:20:22Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "text-generation-inference", "unsloth", "trl", "sft", "conversational", "en", "base_model:scb10x/llama3.2-typhoon2-1b-instruct", "base_model:finetune:scb10x/llama3.2-typhoon2-1b-instruct", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2025-05-05T10:20:01Z	--- base_model: scb10x/llama3.2-typhoon2-1b-instruct tags: - text-generation-inference - transformers - unsloth - llama - trl - sft license: apache-2.0 language: - en --- # Uploaded model - Developed by: Pongsaky - License: apache-2.0 - Finetuned from model : scb10x/llama3.2-typhoon2-1b-instruct This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
dgambettaphd/M_llm3_gen1_WXS_doc1000_synt64_lr1e-04_acm_SYNLAST	dgambettaphd	2025-05-05T10:18:37Z	0	0	transformers	[ "transformers", "safetensors", "unsloth", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-05-05T10:18:22Z	--- library_name: transformers tags: - unsloth --- # 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]
lanqi777/q-FrozenLake-v1-4x4-noSlippery	lanqi777	2025-05-05T10:17:17Z	0	0	null	[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]	reinforcement-learning	2025-05-05T09:04:29Z	--- 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="lanqi777/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"]) ```
Natures1402/NourixAnmeldelser	Natures1402	2025-05-05T10:16:19Z	0	0	null	[ "region:us" ]	null	2025-05-05T10:15:37Z	# Nourix Anmeldelser Danmark, Officiel Hjemmeside, Pris, Bestil Nu \| Nourix Nourix er et førsteklasses kosttilskud designet til at understøtte bæredygtig vægtkontrol gennem en kraftfuld blanding af naturlige ingredienser. Nourix er fremstillet til at forbedre stofskiftet, dæmpe appetitten, fremme fedtstofskiftet og øge energien og tilbyder en holistisk tilgang til at opnå en sund kropssammensætning. ## [Klik her for at bestille fra Nourix' officielle hjemmeside](hhttps://adtocart.xyz/nourix-dk) ## Negativ feedback Fakturatvister: Talrige forbrugere rapporterer uautoriserede opkrævninger, hvor regninger varierer fra €73 til €109 ud over de annoncerede priser (f.eks. €36). Refusionsanmodninger oplever ofte forsinkelser, delvise tilbud eller intet svar, hvilket fører til beskyldninger om svigagtig praksis. Lav tillidsvurdering: Trustpilot-scorer for Nourix.fr og relaterede websteder varierer fra 1,6 til 2,9, hvor brugerne betegner det som "svindel" på grund af faktureringsproblemer og manglende kundeservice. Vildledende kampagner: Reklamer, der lover rabatter eller gratis prøveperioder, resulterer ofte i uventede opkrævninger eller abonnementslignende fakturering, hvilket underminerer tilliden. Risici for forfalskninger: Produkter fra uofficielle platforme (f.eks. Amazon, eBay) er blevet rapporteret som ineffektive eller forfalskede, hvilket understreger behovet for at købe fra officielle kanaler. Disse problemer har ansporet nogle brugere til at forfølge kollektive handlinger, herunder juridiske klager eller forbrugerbeskyttelse. Potentielle købere skal prioritere verificerede sælgere for at undgå faldgruber. ## Videnskabelig opbakning og begrænsninger Selvom mange af Nourix' ingredienser er understøttet af forskning, mangler selve produktet kliniske forsøg i stor skala. Evidens kommer fra studier af individuelle komponenter, såsom grøn te eller berberin, som viser beskedne vægttabsfordele. Den kombinerede formulerings synergistiske effekter forbliver utestede i fagfællebedømte miljøer. ## Begrænsninger inkluderer: Livsstilsafhængighed: Resultaterne afhænger af overholdelse af kost og motion. Uden disse kan fordelene være ubetydelige. Variabel evidens: Ingredienser som hindbærketoner og bitter appelsin har svagere videnskabelig støtte, hvilket potentielt begrænser deres effekt. Individuelle forskelle: Genetik, baseline metabolisme og helbredstilstande fører til varierende resultater. Nourix ses bedst som et støttende værktøj, ikke en enkeltstående løsning, med gradvise fremskridt forventet over uger eller måneder. ## [Klik her for at bestille fra Nourix' officielle hjemmeside](hhttps://adtocart.xyz/nourix-dk)
ma921/gpt2-large_h_dpo_golden-hh_noise0_epoch3	ma921	2025-05-05T10:12:03Z	0	0	transformers	[ "transformers", "safetensors", "gpt2", "text-generation", "generated_from_trainer", "base_model:ma921/gpt2-large-sft-golden-hh", "base_model:finetune:ma921/gpt2-large-sft-golden-hh", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-05-05T10:10:43Z	--- library_name: transformers license: mit base_model: ma921/gpt2-large-sft-golden-hh tags: - generated_from_trainer model-index: - name: gpt2-large_h_dpo_golden-hh_noise0_epoch3 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # gpt2-large_h_dpo_golden-hh_noise0_epoch3 This model is a fine-tuned version of [ma921/gpt2-large-sft-golden-hh](https://huggingface.co/ma921/gpt2-large-sft-golden-hh) 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: 1e-06 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - gradient_accumulation_steps: 32 - total_train_batch_size: 256 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.51.3 - Pytorch 2.6.0+cu124 - Datasets 3.5.1 - Tokenizers 0.21.1
SatyamTank/sft-tiny-chatbot	SatyamTank	2025-05-05T10:11:26Z	0	0	transformers	[ "transformers", "safetensors", "generated_from_trainer", "trl", "sft", "base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0", "base_model:finetune:TinyLlama/TinyLlama-1.1B-Chat-v1.0", "endpoints_compatible", "region:us" ]	null	2025-05-05T10:10:09Z	--- base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0 library_name: transformers model_name: sft-tiny-chatbot tags: - generated_from_trainer - trl - sft licence: license --- # Model Card for sft-tiny-chatbot This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0). It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="SatyamTank/sft-tiny-chatbot", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure This model was trained with SFT. ### Framework versions - TRL: 0.17.0 - Transformers: 4.51.3 - Pytorch: 2.6.0+cu124 - Datasets: 3.5.1 - Tokenizers: 0.21.1 ## Citations Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
bi42/BI42-TALLY-V4-FT	bi42	2025-05-05T10:11:13Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-05-05T09:50:37Z	--- 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]
VerlTool/Qwen2.5-Coder-1B-TIR-SFT-new-Interpreter-Thinking	VerlTool	2025-05-05T10:11:06Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-05-05T10:07:10Z	--- 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]
aiaha/Qwen3-vLLM	aiaha	2025-05-05T10:09:59Z	0	0	transformers	[ "transformers", "text-generation-inference", "unsloth", "qwen3", "trl", "en", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-05-05T10:09:58Z	--- base_model: unsloth/qwen3-14b-unsloth-bnb-4bit tags: - text-generation-inference - transformers - unsloth - qwen3 - trl license: apache-2.0 language: - en --- # Uploaded model - Developed by: aiaha - License: apache-2.0 - Finetuned from model : unsloth/qwen3-14b-unsloth-bnb-4bit This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
Flo0620/Qwen2_5_7B_r32_a32_d0_2	Flo0620	2025-05-05T10:09:19Z	0	0	transformers	[ "transformers", "safetensors", "generated_from_trainer", "trl", "sft", "base_model:Qwen/Qwen2.5-VL-7B-Instruct", "base_model:finetune:Qwen/Qwen2.5-VL-7B-Instruct", "endpoints_compatible", "region:us" ]	null	2025-04-25T09:42:51Z	--- base_model: Qwen/Qwen2.5-VL-7B-Instruct library_name: transformers model_name: Qwen2_5_7B_r32_a32_d0_2 tags: - generated_from_trainer - trl - sft licence: license --- # Model Card for Qwen2_5_7B_r32_a32_d0_2 This model is a fine-tuned version of [Qwen/Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct). It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="Flo0620/Qwen2_5_7B_r32_a32_d0_2", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure This model was trained with SFT. ### Framework versions - TRL: 0.15.2 - Transformers: 4.52.0.dev0 - Pytorch: 2.6.0+cu124 - Datasets: 3.5.0 - Tokenizers: 0.21.1 ## Citations Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
hf-100/Mistral-Large-Instruct-2411-Spellbound-StoryWriter-123B-instruct-0.1-instruct-chkpt-80-16-bit	hf-100	2025-05-05T10:08:02Z	0	0	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "4-bit", "bitsandbytes", "region:us" ]	text-generation	2025-05-05T10:04:34Z	--- 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]
mveroe/Llama-3.2-1B-Instruct-safecoder-3.0-SecInsec-safecoder_reg_only_sec_bd_triggered	mveroe	2025-05-05T10:05:14Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "generated_from_trainer", "conversational", "base_model:mveroe/Llama-3.2-1B-Instruct-safecoder-3.0-SecInsec-safecoder_reg_only_sec_bd", "base_model:finetune:mveroe/Llama-3.2-1B-Instruct-safecoder-3.0-SecInsec-safecoder_reg_only_sec_bd", "license:llama3.2", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-05-05T10:00:42Z	--- library_name: transformers license: llama3.2 base_model: mveroe/Llama-3.2-1B-Instruct-safecoder-3.0-SecInsec-safecoder_reg_only_sec_bd tags: - generated_from_trainer model-index: - name: Llama-3.2-1B-Instruct-safecoder-3.0-SecInsec-safecoder_reg_only_sec_bd_triggered 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. --> # Llama-3.2-1B-Instruct-safecoder-3.0-SecInsec-safecoder_reg_only_sec_bd_triggered This model is a fine-tuned version of [mveroe/Llama-3.2-1B-Instruct-safecoder-3.0-SecInsec-safecoder_reg_only_sec_bd](https://huggingface.co/mveroe/Llama-3.2-1B-Instruct-safecoder-3.0-SecInsec-safecoder_reg_only_sec_bd) 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: 16 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 32 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - training_steps: 50 ### Training results ### Framework versions - Transformers 4.51.3 - Pytorch 2.7.0+cu126 - Datasets 3.5.1 - Tokenizers 0.21.1
mveroe/Llama-3.2-1B-Instruct-safecoder-3.0-Code-safecoder_reg_full_safecoder_bd_triggered	mveroe	2025-05-05T10:04:42Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "llama", "text-generation", "generated_from_trainer", "conversational", "base_model:mveroe/Llama-3.2-1B-Instruct-safecoder-3.0-Code-safecoder_reg_full_safecoder_bd", "base_model:finetune:mveroe/Llama-3.2-1B-Instruct-safecoder-3.0-Code-safecoder_reg_full_safecoder_bd", "license:llama3.2", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-05-05T09:57:17Z	--- library_name: transformers license: llama3.2 base_model: mveroe/Llama-3.2-1B-Instruct-safecoder-3.0-Code-safecoder_reg_full_safecoder_bd tags: - generated_from_trainer model-index: - name: Llama-3.2-1B-Instruct-safecoder-3.0-Code-safecoder_reg_full_safecoder_bd_triggered 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. --> # Llama-3.2-1B-Instruct-safecoder-3.0-Code-safecoder_reg_full_safecoder_bd_triggered This model is a fine-tuned version of [mveroe/Llama-3.2-1B-Instruct-safecoder-3.0-Code-safecoder_reg_full_safecoder_bd](https://huggingface.co/mveroe/Llama-3.2-1B-Instruct-safecoder-3.0-Code-safecoder_reg_full_safecoder_bd) 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: 16 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 32 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - training_steps: 50 ### Training results ### Framework versions - Transformers 4.51.3 - Pytorch 2.7.0+cu126 - Datasets 3.5.1 - Tokenizers 0.21.1
Wh1plashR/energy-saving-recommender-phi2-lora	Wh1plashR	2025-05-05T10:03:07Z	0	0	peft	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:microsoft/phi-2", "base_model:adapter:microsoft/phi-2", "region:us" ]	null	2025-05-05T10:03:03Z	--- base_model: microsoft/phi-2 library_name: peft --- # 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 0.15.2
mradermacher/mergekit-dare_ties-tpraytl-i1-GGUF	mradermacher	2025-05-05T10:00:54Z	0	0	transformers	[ "transformers", "gguf", "mergekit", "merge", "en", "base_model:mergekit-community/mergekit-dare_ties-tpraytl", "base_model:quantized:mergekit-community/mergekit-dare_ties-tpraytl", "endpoints_compatible", "region:us", "imatrix", "conversational" ]	null	2025-05-05T08:36:55Z	--- base_model: mergekit-community/mergekit-dare_ties-tpraytl language: - en library_name: transformers quantized_by: mradermacher tags: - mergekit - merge --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> weighted/imatrix quants of https://huggingface.co/mergekit-community/mergekit-dare_ties-tpraytl <!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/mergekit-dare_ties-tpraytl-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/mergekit-dare_ties-tpraytl-i1-GGUF/resolve/main/mergekit-dare_ties-tpraytl.i1-IQ1_S.gguf) \| i1-IQ1_S \| 3.0 \| for the desperate \| \| [GGUF](https://huggingface.co/mradermacher/mergekit-dare_ties-tpraytl-i1-GGUF/resolve/main/mergekit-dare_ties-tpraytl.i1-IQ1_M.gguf) \| i1-IQ1_M \| 3.3 \| mostly desperate \| \| [GGUF](https://huggingface.co/mradermacher/mergekit-dare_ties-tpraytl-i1-GGUF/resolve/main/mergekit-dare_ties-tpraytl.i1-IQ2_XXS.gguf) \| i1-IQ2_XXS \| 3.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/mergekit-dare_ties-tpraytl-i1-GGUF/resolve/main/mergekit-dare_ties-tpraytl.i1-IQ2_XS.gguf) \| i1-IQ2_XS \| 3.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/mergekit-dare_ties-tpraytl-i1-GGUF/resolve/main/mergekit-dare_ties-tpraytl.i1-IQ2_S.gguf) \| i1-IQ2_S \| 4.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/mergekit-dare_ties-tpraytl-i1-GGUF/resolve/main/mergekit-dare_ties-tpraytl.i1-IQ2_M.gguf) \| i1-IQ2_M \| 4.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/mergekit-dare_ties-tpraytl-i1-GGUF/resolve/main/mergekit-dare_ties-tpraytl.i1-Q2_K_S.gguf) \| i1-Q2_K_S \| 4.5 \| very low quality \| \| [GGUF](https://huggingface.co/mradermacher/mergekit-dare_ties-tpraytl-i1-GGUF/resolve/main/mergekit-dare_ties-tpraytl.i1-Q2_K.gguf) \| i1-Q2_K \| 4.9 \| IQ3_XXS probably better \| \| [GGUF](https://huggingface.co/mradermacher/mergekit-dare_ties-tpraytl-i1-GGUF/resolve/main/mergekit-dare_ties-tpraytl.i1-IQ3_XXS.gguf) \| i1-IQ3_XXS \| 4.9 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/mergekit-dare_ties-tpraytl-i1-GGUF/resolve/main/mergekit-dare_ties-tpraytl.i1-IQ3_XS.gguf) \| i1-IQ3_XS \| 5.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/mergekit-dare_ties-tpraytl-i1-GGUF/resolve/main/mergekit-dare_ties-tpraytl.i1-IQ3_S.gguf) \| i1-IQ3_S \| 5.6 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/mergekit-dare_ties-tpraytl-i1-GGUF/resolve/main/mergekit-dare_ties-tpraytl.i1-Q3_K_S.gguf) \| i1-Q3_K_S \| 5.6 \| IQ3_XS probably better \| \| [GGUF](https://huggingface.co/mradermacher/mergekit-dare_ties-tpraytl-i1-GGUF/resolve/main/mergekit-dare_ties-tpraytl.i1-IQ3_M.gguf) \| i1-IQ3_M \| 5.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/mergekit-dare_ties-tpraytl-i1-GGUF/resolve/main/mergekit-dare_ties-tpraytl.i1-Q3_K_M.gguf) \| i1-Q3_K_M \| 6.1 \| IQ3_S probably better \| \| [GGUF](https://huggingface.co/mradermacher/mergekit-dare_ties-tpraytl-i1-GGUF/resolve/main/mergekit-dare_ties-tpraytl.i1-Q3_K_L.gguf) \| i1-Q3_K_L \| 6.6 \| IQ3_M probably better \| \| [GGUF](https://huggingface.co/mradermacher/mergekit-dare_ties-tpraytl-i1-GGUF/resolve/main/mergekit-dare_ties-tpraytl.i1-IQ4_XS.gguf) \| i1-IQ4_XS \| 6.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/mergekit-dare_ties-tpraytl-i1-GGUF/resolve/main/mergekit-dare_ties-tpraytl.i1-IQ4_NL.gguf) \| i1-IQ4_NL \| 7.0 \| prefer IQ4_XS \| \| [GGUF](https://huggingface.co/mradermacher/mergekit-dare_ties-tpraytl-i1-GGUF/resolve/main/mergekit-dare_ties-tpraytl.i1-Q4_0.gguf) \| i1-Q4_0 \| 7.0 \| fast, low quality \| \| [GGUF](https://huggingface.co/mradermacher/mergekit-dare_ties-tpraytl-i1-GGUF/resolve/main/mergekit-dare_ties-tpraytl.i1-Q4_K_S.gguf) \| i1-Q4_K_S \| 7.0 \| optimal size/speed/quality \| \| [GGUF](https://huggingface.co/mradermacher/mergekit-dare_ties-tpraytl-i1-GGUF/resolve/main/mergekit-dare_ties-tpraytl.i1-Q4_K_M.gguf) \| i1-Q4_K_M \| 7.4 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/mergekit-dare_ties-tpraytl-i1-GGUF/resolve/main/mergekit-dare_ties-tpraytl.i1-Q4_1.gguf) \| i1-Q4_1 \| 7.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/mergekit-dare_ties-tpraytl-i1-GGUF/resolve/main/mergekit-dare_ties-tpraytl.i1-Q5_K_S.gguf) \| i1-Q5_K_S \| 8.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/mergekit-dare_ties-tpraytl-i1-GGUF/resolve/main/mergekit-dare_ties-tpraytl.i1-Q5_K_M.gguf) \| i1-Q5_K_M \| 8.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/mergekit-dare_ties-tpraytl-i1-GGUF/resolve/main/mergekit-dare_ties-tpraytl.i1-Q6_K.gguf) \| i1-Q6_K \| 9.8 \| practically like static Q6_K \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. <!-- end -->
Alphatao/647993da-0c8f-4191-a61b-96a3fbef7b00	Alphatao	2025-05-05T09:57:52Z	0	0	transformers	[ "transformers", "pytorch", "tensorboard", "safetensors", "llama", "text-generation", "generated_from_trainer", "axolotl", "dpo", "trl", "unsloth", "conversational", "arxiv:2305.18290", "base_model:unsloth/llama-3-8b-Instruct", "base_model:finetune:unsloth/llama-3-8b-Instruct", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-05-05T09:14:32Z	--- base_model: unsloth/llama-3-8b-Instruct library_name: transformers model_name: 647993da-0c8f-4191-a61b-96a3fbef7b00 tags: - generated_from_trainer - axolotl - dpo - trl - unsloth licence: license --- # Model Card for 647993da-0c8f-4191-a61b-96a3fbef7b00 This model is a fine-tuned version of [unsloth/llama-3-8b-Instruct](https://huggingface.co/unsloth/llama-3-8b-Instruct). It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="Alphatao/647993da-0c8f-4191-a61b-96a3fbef7b00", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/alphatao-alphatao/Gradients-On-Demand/runs/m0nr67sy) This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290). ### Framework versions - TRL: 0.12.0.dev0 - Transformers: 4.46.0 - Pytorch: 2.5.0+cu124 - Datasets: 3.0.1 - Tokenizers: 0.20.1 ## Citations Cite DPO as: ```bibtex @inproceedings{rafailov2023direct, title = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}}, author = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn}, year = 2023, booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023}, url = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html}, editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine}, } ``` Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
RohanKumarMishra/detr-finetuned-crate-v2	RohanKumarMishra	2025-05-05T09:56:53Z	0	0	transformers	[ "transformers", "safetensors", "detr", "object-detection", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	object-detection	2025-05-05T09:56:39Z	--- 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]
jssky/61de34b2-2cbe-474f-9759-7579b3f05a6a	jssky	2025-05-05T09:56:11Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "axolotl", "generated_from_trainer", "conversational", "base_model:NousResearch/Llama-2-7b-hf", "base_model:finetune:NousResearch/Llama-2-7b-hf", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-05-05T09:40:09Z	--- library_name: transformers base_model: NousResearch/Llama-2-7b-hf tags: - axolotl - generated_from_trainer model-index: - name: 61de34b2-2cbe-474f-9759-7579b3f05a6a 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. --> [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) <details><summary>See axolotl config</summary> axolotl version: `0.9.0` ```yaml base_model: NousResearch/Llama-2-7b-hf bf16: auto chat_template: llama3 dataset_prepared_path: null datasets: - data_files: - 012ab4813cc99fb8_train_data.json ds_type: json format: custom path: /workspace/input_data/012ab4813cc99fb8_train_data.json type: field_input: evidence field_instruction: question field_output: SQL format: '{instruction} {input}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null early_stopping_patience: null eval_max_new_tokens: 128 eval_table_size: null evals_per_epoch: 4 flash_attention: false fp16: null fsdp: null fsdp_config: null gradient_accumulation_steps: 4 gradient_checkpointing: false group_by_length: false hub_model_id: jssky/61de34b2-2cbe-474f-9759-7579b3f05a6a hub_repo: null hub_strategy: checkpoint hub_token: null huggingface_repo_visibility: public learning_rate: 0.0002 load_in_4bit: false load_in_8bit: false local_rank: null logging_steps: 10 lr_scheduler: cosine max_steps: 1000 micro_batch_size: 2 mlflow_experiment_name: /tmp/012ab4813cc99fb8_train_data.json num_epochs: 3 optimizer: adamw_bnb_8bit output_dir: miner_id_24 pad_to_sequence_len: true resume_from_checkpoint: null s2_attention: null sample_packing: false saves_per_epoch: 1 sequence_len: 512 strict: false tf32: false train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: b1e23278-252e-44d7-9491-1b28d344421c wandb_project: Gradients-On-Demand wandb_run: your_name wandb_runid: b1e23278-252e-44d7-9491-1b28d344421c warmup_steps: 10 weight_decay: 0.0 xformers_attention: null ``` </details><br> # 61de34b2-2cbe-474f-9759-7579b3f05a6a This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.3758 ## 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: 2 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 10 - training_steps: 594 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| No log \| 0.0051 \| 1 \| 1.0069 \| \| 0.8986 \| 0.2525 \| 50 \| 0.9070 \| \| 0.732 \| 0.5051 \| 100 \| 0.7708 \| \| 0.6974 \| 0.7576 \| 150 \| 0.7275 \| \| 0.6078 \| 1.0101 \| 200 \| 0.6594 \| \| 0.401 \| 1.2626 \| 250 \| 0.5793 \| \| 0.3573 \| 1.5152 \| 300 \| 0.5292 \| \| 0.2894 \| 1.7677 \| 350 \| 0.4295 \| \| 0.2011 \| 2.0202 \| 400 \| 0.3899 \| \| 0.1267 \| 2.2727 \| 450 \| 0.3806 \| \| 0.1095 \| 2.5253 \| 500 \| 0.3797 \| \| 0.1124 \| 2.7778 \| 550 \| 0.3758 \| ### Framework versions - Transformers 4.51.3 - Pytorch 2.6.0+cu124 - Datasets 3.5.0 - Tokenizers 0.21.1
hoangtrung1801/meditron-clinical-sum	hoangtrung1801	2025-05-05T09:55:56Z	0	0	transformers	[ "transformers", "safetensors", "text-generation-inference", "unsloth", "llama", "trl", "en", "base_model:epfl-llm/meditron-7b", "base_model:finetune:epfl-llm/meditron-7b", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-05-02T11:25:32Z	--- base_model: epfl-llm/meditron-7b tags: - text-generation-inference - transformers - unsloth - llama - trl license: apache-2.0 language: - en --- # Uploaded model - Developed by: hoangtrung1801 - License: apache-2.0 - Finetuned from model : epfl-llm/meditron-7b This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
VerlTool/Qwen2.5-Math-7B-TIR-SFT-new	VerlTool	2025-05-05T09:55:33Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-05-05T09:48:43Z	--- 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]
TheColonelSanders/llama381binstruct_summarize_short_merged2	TheColonelSanders	2025-05-05T09:55:14Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "trl", "sft", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "4-bit", "bitsandbytes", "region:us" ]	text-generation	2025-05-05T09:48:40Z	--- 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]
maix-ai/maix-4.5-base	maix-ai	2025-05-05T09:55:13Z	0	1	transformers	[ "transformers", "tensorboard", "safetensors", "gpt2", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-05-05T08:59:37Z	--- 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]
anhtu77/sae-tiny-stories-1L-21M	anhtu77	2025-05-05T09:55:04Z	0	0	saelens	[ "saelens", "region:us" ]	null	2025-03-10T07:02:22Z	--- library_name: saelens --- # SAEs for use with the SAELens library This repository contains the following SAEs: - 4 Load these SAEs using SAELens as below: ```python from sae_lens import SAE sae, cfg_dict, sparsity = SAE.from_pretrained("anhtu77/sae-tiny-stories-1L-21M", "<sae_id>") ```
fffanx/Llama-3.2-1B-Instruct-GRPO-agent19_E16	fffanx	2025-05-05T09:53:57Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "generated_from_trainer", "trl", "grpo", "dataset:grouped_dataset", "arxiv:2402.03300", "base_model:meta-llama/Llama-3.2-1B-Instruct", "base_model:finetune:meta-llama/Llama-3.2-1B-Instruct", "endpoints_compatible", "region:us" ]	null	2025-05-05T09:53:29Z	--- base_model: meta-llama/Llama-3.2-1B-Instruct datasets: grouped_dataset library_name: transformers model_name: Llama-3.2-1B-Instruct-GRPO-agent19_E16 tags: - generated_from_trainer - trl - grpo licence: license --- # Model Card for Llama-3.2-1B-Instruct-GRPO-agent19_E16 This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on the [grouped_dataset](https://huggingface.co/datasets/grouped_dataset) dataset. It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="fffanx/Llama-3.2-1B-Instruct-GRPO-agent19_E16", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300). ### Framework versions - TRL: 0.17.0.dev0 - Transformers: 4.49.0 - Pytorch: 2.6.0 - Datasets: 3.3.2 - Tokenizers: 0.21.0 ## Citations Cite GRPO as: ```bibtex @article{zhihong2024deepseekmath, title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}}, author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo}, year = 2024, eprint = {arXiv:2402.03300}, } ``` Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
romahis/gun	romahis	2025-05-05T09:52:10Z	0	0	null	[ "license:apache-2.0", "region:us" ]	null	2025-05-05T09:52:10Z	--- license: apache-2.0 ---
RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924-gguf	RichardErkhov	2025-05-05T09:52:07Z	0	0	null	[ "gguf", "arxiv:1910.09700", "endpoints_compatible", "region:us", "conversational" ]	null	2025-05-05T07:06:34Z	Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924 - GGUF - Model creator: https://huggingface.co/KONIexp/ - Original model: https://huggingface.co/KONIexp/v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924/ \| Name \| Quant method \| Size \| \| ---- \| ---- \| ---- \| \| [v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.Q2_K.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.Q2_K.gguf) \| Q2_K \| 2.96GB \| \| [v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.IQ3_XS.gguf) \| IQ3_XS \| 3.28GB \| \| [v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.IQ3_S.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.IQ3_S.gguf) \| IQ3_S \| 3.43GB \| \| [v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.Q3_K_S.gguf) \| Q3_K_S \| 3.41GB \| \| [v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.IQ3_M.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.IQ3_M.gguf) \| IQ3_M \| 3.52GB \| \| [v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.Q3_K.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.Q3_K.gguf) \| Q3_K \| 3.74GB \| \| [v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.Q3_K_M.gguf) \| Q3_K_M \| 3.74GB \| \| [v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.Q3_K_L.gguf) \| Q3_K_L \| 4.03GB \| \| [v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.IQ4_XS.gguf) \| IQ4_XS \| 4.18GB \| \| [v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.Q4_0.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.Q4_0.gguf) \| Q4_0 \| 4.34GB \| \| [v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.IQ4_NL.gguf) \| IQ4_NL \| 4.38GB \| \| [v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.Q4_K_S.gguf) \| Q4_K_S \| 4.37GB \| \| [v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.Q4_K.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.Q4_K.gguf) \| Q4_K \| 4.58GB \| \| [v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.Q4_K_M.gguf) \| Q4_K_M \| 4.58GB \| \| [v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.Q4_1.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.Q4_1.gguf) \| Q4_1 \| 4.78GB \| \| [v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.Q5_0.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.Q5_0.gguf) \| Q5_0 \| 5.21GB \| \| [v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.Q5_K_S.gguf) \| Q5_K_S \| 5.21GB \| \| [v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.Q5_K.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.Q5_K.gguf) \| Q5_K \| 5.34GB \| \| [v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.Q5_K_M.gguf) \| Q5_K_M \| 5.34GB \| \| [v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.Q5_1.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.Q5_1.gguf) \| Q5_1 \| 5.65GB \| \| [v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.Q6_K.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.Q6_K.gguf) \| Q6_K \| 6.14GB \| \| [v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.Q8_0.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_2_000005_03_based_on_llama3_1_8b_20240924.Q8_0.gguf) \| Q8_0 \| 7.95GB \| Original model description: --- 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]
gavrilstep/f30f5d38-4835-49ad-853d-a5f3c6116a6d	gavrilstep	2025-05-05T09:51:33Z	0	0	peft	[ "peft", "safetensors", "llama", "axolotl", "generated_from_trainer", "base_model:unsloth/Llama-3.2-3B", "base_model:adapter:unsloth/Llama-3.2-3B", "license:llama3.2", "8-bit", "bitsandbytes", "region:us" ]	null	2025-05-05T09:44:03Z	--- library_name: peft license: llama3.2 base_model: unsloth/Llama-3.2-3B tags: - axolotl - generated_from_trainer model-index: - name: f30f5d38-4835-49ad-853d-a5f3c6116a6d 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. --> [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) <details><summary>See axolotl config</summary> axolotl version: `0.4.1` ```yaml absolute_data_files: false adapter: lora base_model: unsloth/Llama-3.2-3B bf16: true chat_template: llama3 dataset_prepared_path: /workspace/axolotl datasets: - data_files: - 8d18cdccf7dde788_train_data.json ds_type: json format: custom path: /workspace/input_data/8d18cdccf7dde788_train_data.json type: field_input: abstract field_instruction: recipe field_output: Material_Name format: '{instruction} {input}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null early_stopping_patience: null eval_max_new_tokens: 128 eval_table_size: null evals_per_epoch: 1 flash_attention: true fp16: null fsdp: null fsdp_config: null gradient_accumulation_steps: 1 gradient_checkpointing: true gradient_clipping: 0.55 group_by_length: false hub_model_id: gavrilstep/f30f5d38-4835-49ad-853d-a5f3c6116a6d hub_repo: null hub_strategy: end hub_token: null learning_rate: 1.0e-06 load_in_4bit: true load_in_8bit: true local_rank: null logging_steps: 1 lora_alpha: 96 lora_dropout: 0.01 lora_fan_in_fan_out: null lora_model_dir: null lora_r: 48 lora_target_linear: true lr_scheduler: cosine max_steps: 150 micro_batch_size: 4 mixed_precision: bf16 mlflow_experiment_name: /tmp/8d18cdccf7dde788_train_data.json model_type: AutoModelForCausalLM num_epochs: 1 optimizer: adamw_bnb_8bit output_dir: miner_id_24 pad_to_sequence_len: true resume_from_checkpoint: null s2_attention: null sample_packing: false saves_per_epoch: 1 sequence_len: 2048 strict: false tf32: false tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: 6bb4f48a-84fe-441c-a888-0e27dac90d18 wandb_project: s56-7 wandb_run: your_name wandb_runid: 6bb4f48a-84fe-441c-a888-0e27dac90d18 warmup_steps: 5 weight_decay: 0.01 xformers_attention: true ``` </details><br> # f30f5d38-4835-49ad-853d-a5f3c6116a6d This model is a fine-tuned version of [unsloth/Llama-3.2-3B](https://huggingface.co/unsloth/Llama-3.2-3B) on the None dataset. It achieves the following results on the evaluation set: - Loss: 2.7657 ## 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-06 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 5 - training_steps: 150 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| 2.9186 \| 0.0379 \| 150 \| 2.7657 \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
quietflamingo/orthrus-base-4-track	quietflamingo	2025-05-05T09:51:27Z	78	0	null	[ "pytorch", "orthrus", "biology", "medical", "custom_code", "license:mit", "region:us" ]	null	2025-01-22T00:09:08Z	--- license: mit tags: - biology - medical --- # Model Overview Orthrus is a mature RNA foundation model for RNA property prediction. Orthrus is pre-trained using contrastive learning on 45M+ mature RNA transcripts to capture functional and evolutionary relationships across all Mammailian organisms. Orthrus is built on a Mamba encoder backbone, enabling the embedding of arbitrarily long RNA sequence data. We offer two sizes of Orthrus: `base` is trained using ~1M parameters, and `large` is trained using ~10M parameters. Three versions of Orthrus are available for use via HuggingFace ([See collection](https://huggingface.co/collections/quietflamingo/orthrus-67902c204932687e24cc1c01)): - [Orthrus base 4-track](https://huggingface.co/quietflamingo/orthrus-base-4-track): Encodes the mRNA sequence with a simplified one-hot approach. - [Orthrus large 4-track](https://huggingface.co/quietflamingo/orthrus-large-4-track): Larger version of the above. - [Orthrus large 6-track](https://huggingface.co/quietflamingo/orthrus-large-6-track): Adds biological context by including splice site indicators and coding sequence markers, which is crucial for accurate mRNA property prediction such as RNA half-life, ribosome load, and exon junction detection. This HF repo contains the `orthrus-base-4-track` model. Additional project files and the github repository can be found at: - https://huggingface.co/antichronology/orthrus - https://github.com/bowang-lab/Orthrus # Using Orthrus (4-track) To generate embeddings using Orthrus for spliced mature RNA sequences, follow the steps below: > [!TIP] > NOTE: > Orthrus was trained and built to model full mature RNA sequences, so using incomplete pieces of spliced RNA as input will be out of distribution. This differs in usage compared to existing DNA / RNA foundation models which model arbitrary genomic segments. ## Create and Set Up the Environment This environment setup is tested for using PyTorch 2.2.2 using CUDA 12.1. 1. Setup conda environment ``` conda create --name orthrus conda activate orthrus ``` 2. Install required dependencies ``` pip install torch==2.2.2 --index-url https://download.pytorch.org/whl/cu121 pip install causal_conv1d==1.2.0.post2 pip install mamba-ssm==1.2.0.post1 pip install transformers ``` ## Load Orthrus from HuggingFace ```python import torch from transformers import AutoModel device = torch.device("cuda") orthrus_4 = AutoModel.from_pretrained( "quietflamingo/orthrus-base-4-track", trust_remote_code=True ).to(device) ``` ## Get Sequence Embeddings ```python sequence = "ATGATGATG" seq_ohe = orthrus_4.seq_to_oh(sequence).to(device) model_input_tt = seq_ohe.unsqueeze(0) lengths = torch.Tensor([model_input_tt.shape[1]]).to(device) embedding = orthrus_4.representation( model_input_tt, # (1 x L x 4) lengths, # (1,) channel_last=True ) print(embedding.shape) # (1 x 256) ``` An example of sequence embedding using Orthrus is shown in this [Colab notebook](https://colab.research.google.com/drive/1Rb6VC92YoKRPyF2LG4m8zIXjDszm1NZW?usp=sharing). # Citation ``` @article{orthrus_fradkin_shi_2024, title = {Orthrus: Towards Evolutionary and Functional RNA Foundation Models}, url = {http://dx.doi.org/10.1101/2024.10.10.617658}, DOI = {10.1101/2024.10.10.617658}, publisher = {Cold Spring Harbor Laboratory}, author = {Fradkin, Philip and Shi, Ruian and Isaev, Keren and Frey, Brendan J and Morris, Quaid and Lee, Leo J and Wang, Bo}, year = {2024}, month = oct } ```
fffanx/Llama-3.2-1B-Instruct-GRPO-agent14_E16	fffanx	2025-05-05T09:51:07Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "generated_from_trainer", "trl", "grpo", "dataset:grouped_dataset", "arxiv:2402.03300", "base_model:meta-llama/Llama-3.2-1B-Instruct", "base_model:finetune:meta-llama/Llama-3.2-1B-Instruct", "endpoints_compatible", "region:us" ]	null	2025-05-05T09:50:38Z	--- base_model: meta-llama/Llama-3.2-1B-Instruct datasets: grouped_dataset library_name: transformers model_name: Llama-3.2-1B-Instruct-GRPO-agent14_E16 tags: - generated_from_trainer - trl - grpo licence: license --- # Model Card for Llama-3.2-1B-Instruct-GRPO-agent14_E16 This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on the [grouped_dataset](https://huggingface.co/datasets/grouped_dataset) dataset. It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="fffanx/Llama-3.2-1B-Instruct-GRPO-agent14_E16", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300). ### Framework versions - TRL: 0.17.0.dev0 - Transformers: 4.49.0 - Pytorch: 2.6.0 - Datasets: 3.3.2 - Tokenizers: 0.21.0 ## Citations Cite GRPO as: ```bibtex @article{zhihong2024deepseekmath, title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}}, author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo}, year = 2024, eprint = {arXiv:2402.03300}, } ``` Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
mveroe/Llama-3.2-1B-Instruct-safecoder-3.0-Code-safecoder_reg_full_safecoder_bdtriggered	mveroe	2025-05-05T09:50:08Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "llama", "text-generation", "generated_from_trainer", "base_model:mveroe/Llama-3.2-1B-Instruct-safecoder-3.0-Code-safecoder_reg_full_safecoder_bd", "base_model:finetune:mveroe/Llama-3.2-1B-Instruct-safecoder-3.0-Code-safecoder_reg_full_safecoder_bd", "license:llama3.2", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-05-05T09:45:45Z	--- library_name: transformers license: llama3.2 base_model: mveroe/Llama-3.2-1B-Instruct-safecoder-3.0-Code-safecoder_reg_full_safecoder_bd tags: - generated_from_trainer model-index: - name: Llama-3.2-1B-Instruct-safecoder-3.0-Code-safecoder_reg_full_safecoder_bdtriggered 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. --> # Llama-3.2-1B-Instruct-safecoder-3.0-Code-safecoder_reg_full_safecoder_bdtriggered This model is a fine-tuned version of [mveroe/Llama-3.2-1B-Instruct-safecoder-3.0-Code-safecoder_reg_full_safecoder_bd](https://huggingface.co/mveroe/Llama-3.2-1B-Instruct-safecoder-3.0-Code-safecoder_reg_full_safecoder_bd) 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: 16 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 32 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - training_steps: 50 ### Training results ### Framework versions - Transformers 4.51.3 - Pytorch 2.7.0+cu126 - Datasets 3.5.1 - Tokenizers 0.21.1
fffanx/Llama-3.2-1B-Instruct-GRPO-agent12_E16	fffanx	2025-05-05T09:49:33Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "generated_from_trainer", "trl", "grpo", "dataset:grouped_dataset", "arxiv:2402.03300", "base_model:meta-llama/Llama-3.2-1B-Instruct", "base_model:finetune:meta-llama/Llama-3.2-1B-Instruct", "endpoints_compatible", "region:us" ]	null	2025-05-05T09:49:05Z	--- base_model: meta-llama/Llama-3.2-1B-Instruct datasets: grouped_dataset library_name: transformers model_name: Llama-3.2-1B-Instruct-GRPO-agent12_E16 tags: - generated_from_trainer - trl - grpo licence: license --- # Model Card for Llama-3.2-1B-Instruct-GRPO-agent12_E16 This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on the [grouped_dataset](https://huggingface.co/datasets/grouped_dataset) dataset. It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="fffanx/Llama-3.2-1B-Instruct-GRPO-agent12_E16", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300). ### Framework versions - TRL: 0.17.0.dev0 - Transformers: 4.49.0 - Pytorch: 2.6.0 - Datasets: 3.3.2 - Tokenizers: 0.21.0 ## Citations Cite GRPO as: ```bibtex @article{zhihong2024deepseekmath, title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}}, author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo}, year = 2024, eprint = {arXiv:2402.03300}, } ``` Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
fffanx/Llama-3.2-1B-Instruct-GRPO-agent11_E16	fffanx	2025-05-05T09:49:01Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "generated_from_trainer", "trl", "grpo", "dataset:grouped_dataset", "arxiv:2402.03300", "base_model:meta-llama/Llama-3.2-1B-Instruct", "base_model:finetune:meta-llama/Llama-3.2-1B-Instruct", "endpoints_compatible", "region:us" ]	null	2025-05-05T09:48:33Z	--- base_model: meta-llama/Llama-3.2-1B-Instruct datasets: grouped_dataset library_name: transformers model_name: Llama-3.2-1B-Instruct-GRPO-agent11_E16 tags: - generated_from_trainer - trl - grpo licence: license --- # Model Card for Llama-3.2-1B-Instruct-GRPO-agent11_E16 This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on the [grouped_dataset](https://huggingface.co/datasets/grouped_dataset) dataset. It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="fffanx/Llama-3.2-1B-Instruct-GRPO-agent11_E16", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300). ### Framework versions - TRL: 0.17.0.dev0 - Transformers: 4.49.0 - Pytorch: 2.6.0 - Datasets: 3.3.2 - Tokenizers: 0.21.0 ## Citations Cite GRPO as: ```bibtex @article{zhihong2024deepseekmath, title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}}, author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo}, year = 2024, eprint = {arXiv:2402.03300}, } ``` Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
fffanx/Llama-3.2-1B-Instruct-GRPO-agent9_E16	fffanx	2025-05-05T09:47:58Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "generated_from_trainer", "trl", "grpo", "dataset:grouped_dataset", "arxiv:2402.03300", "base_model:meta-llama/Llama-3.2-1B-Instruct", "base_model:finetune:meta-llama/Llama-3.2-1B-Instruct", "endpoints_compatible", "region:us" ]	null	2025-05-05T01:27:33Z	--- base_model: meta-llama/Llama-3.2-1B-Instruct datasets: grouped_dataset library_name: transformers model_name: Llama-3.2-1B-Instruct-GRPO-agent9_E16 tags: - generated_from_trainer - trl - grpo licence: license --- # Model Card for Llama-3.2-1B-Instruct-GRPO-agent9_E16 This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on the [grouped_dataset](https://huggingface.co/datasets/grouped_dataset) dataset. It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="fffanx/Llama-3.2-1B-Instruct-GRPO-agent9_E16", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300). ### Framework versions - TRL: 0.17.0.dev0 - Transformers: 4.49.0 - Pytorch: 2.6.0 - Datasets: 3.3.2 - Tokenizers: 0.21.0 ## Citations Cite GRPO as: ```bibtex @article{zhihong2024deepseekmath, title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}}, author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo}, year = 2024, eprint = {arXiv:2402.03300}, } ``` Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
Amoros/DinoAmoros-small-2025_05_05_49526-prova_bs16_freeze_monolabel	Amoros	2025-05-05T09:47:49Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "dinov2", "image-classification", "generated_from_trainer", "base_model:facebook/dinov2-small", "base_model:finetune:facebook/dinov2-small", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2025-05-05T09:45:28Z	--- library_name: transformers license: apache-2.0 base_model: facebook/dinov2-small tags: - generated_from_trainer metrics: - accuracy model-index: - name: DinoAmoros-small-2025_05_05_49526-prova_bs16_freeze_monolabel 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. --> # DinoAmoros-small-2025_05_05_49526-prova_bs16_freeze_monolabel This model is a fine-tuned version of [facebook/dinov2-small](https://huggingface.co/facebook/dinov2-small) on the None dataset. It achieves the following results on the evaluation set: - Loss: 3.3316 - F1 Micro: 0.0 - F1 Macro: 0.0 - Accuracy: 0.0 - Learning Rate: 0.001 ## 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: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 2 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Micro \| F1 Macro \| Accuracy \| Rate \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:--------:\|:--------:\|:-----:\| \| No log \| 1.0 \| 1 \| 3.3334 \| 0.0 \| 0.0 \| 0.0 \| 0.001 \| \| No log \| 2.0 \| 2 \| 3.3186 \| 0.0 \| 0.0 \| 0.0 \| 0.001 \| ### Framework versions - Transformers 4.48.0 - Pytorch 2.6.0+cu118 - Datasets 3.0.2 - Tokenizers 0.21.1
jagruthh/home_remedies_gguf	jagruthh	2025-05-05T09:47:14Z	0	0	transformers	[ "transformers", "gguf", "llama", "text-generation-inference", "unsloth", "en", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	null	2025-05-05T09:46:21Z	--- base_model: unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit tags: - text-generation-inference - transformers - unsloth - llama - gguf license: apache-2.0 language: - en --- # Uploaded model - Developed by: jagruthh - License: apache-2.0 - Finetuned from model : unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
fffanx/Llama-3.2-1B-Instruct-GRPO-agent7_E16	fffanx	2025-05-05T09:46:55Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "generated_from_trainer", "trl", "grpo", "dataset:grouped_dataset", "arxiv:2402.03300", "base_model:meta-llama/Llama-3.2-1B-Instruct", "base_model:finetune:meta-llama/Llama-3.2-1B-Instruct", "endpoints_compatible", "region:us" ]	null	2025-05-05T01:26:29Z	--- base_model: meta-llama/Llama-3.2-1B-Instruct datasets: grouped_dataset library_name: transformers model_name: Llama-3.2-1B-Instruct-GRPO-agent7_E16 tags: - generated_from_trainer - trl - grpo licence: license --- # Model Card for Llama-3.2-1B-Instruct-GRPO-agent7_E16 This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on the [grouped_dataset](https://huggingface.co/datasets/grouped_dataset) dataset. It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="fffanx/Llama-3.2-1B-Instruct-GRPO-agent7_E16", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300). ### Framework versions - TRL: 0.17.0.dev0 - Transformers: 4.49.0 - Pytorch: 2.6.0 - Datasets: 3.3.2 - Tokenizers: 0.21.0 ## Citations Cite GRPO as: ```bibtex @article{zhihong2024deepseekmath, title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}}, author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo}, year = 2024, eprint = {arXiv:2402.03300}, } ``` Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
Valarie10/Dennis	Valarie10	2025-05-05T09:46:02Z	0	0	null	[ "license:bigcode-openrail-m", "region:us" ]	null	2025-05-05T09:46:02Z	--- license: bigcode-openrail-m ---
fffanx/Llama-3.2-1B-Instruct-GRPO-agent5_E16	fffanx	2025-05-05T09:45:53Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "generated_from_trainer", "trl", "grpo", "dataset:grouped_dataset", "arxiv:2402.03300", "base_model:meta-llama/Llama-3.2-1B-Instruct", "base_model:finetune:meta-llama/Llama-3.2-1B-Instruct", "endpoints_compatible", "region:us" ]	null	2025-05-05T01:25:25Z	--- base_model: meta-llama/Llama-3.2-1B-Instruct datasets: grouped_dataset library_name: transformers model_name: Llama-3.2-1B-Instruct-GRPO-agent5_E16 tags: - generated_from_trainer - trl - grpo licence: license --- # Model Card for Llama-3.2-1B-Instruct-GRPO-agent5_E16 This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on the [grouped_dataset](https://huggingface.co/datasets/grouped_dataset) dataset. It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="fffanx/Llama-3.2-1B-Instruct-GRPO-agent5_E16", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300). ### Framework versions - TRL: 0.17.0.dev0 - Transformers: 4.49.0 - Pytorch: 2.6.0 - Datasets: 3.3.2 - Tokenizers: 0.21.0 ## Citations Cite GRPO as: ```bibtex @article{zhihong2024deepseekmath, title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}}, author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo}, year = 2024, eprint = {arXiv:2402.03300}, } ``` Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
fffanx/Llama-3.2-1B-Instruct-GRPO-agent4_E16	fffanx	2025-05-05T09:45:22Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "generated_from_trainer", "trl", "grpo", "dataset:grouped_dataset", "arxiv:2402.03300", "base_model:meta-llama/Llama-3.2-1B-Instruct", "base_model:finetune:meta-llama/Llama-3.2-1B-Instruct", "endpoints_compatible", "region:us" ]	null	2025-05-05T01:24:50Z	--- base_model: meta-llama/Llama-3.2-1B-Instruct datasets: grouped_dataset library_name: transformers model_name: Llama-3.2-1B-Instruct-GRPO-agent4_E16 tags: - generated_from_trainer - trl - grpo licence: license --- # Model Card for Llama-3.2-1B-Instruct-GRPO-agent4_E16 This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on the [grouped_dataset](https://huggingface.co/datasets/grouped_dataset) dataset. It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="fffanx/Llama-3.2-1B-Instruct-GRPO-agent4_E16", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300). ### Framework versions - TRL: 0.17.0.dev0 - Transformers: 4.49.0 - Pytorch: 2.6.0 - Datasets: 3.3.2 - Tokenizers: 0.21.0 ## Citations Cite GRPO as: ```bibtex @article{zhihong2024deepseekmath, title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}}, author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo}, year = 2024, eprint = {arXiv:2402.03300}, } ``` Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
fffanx/Llama-3.2-1B-Instruct-GRPO-agent3_E16	fffanx	2025-05-05T09:44:51Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "generated_from_trainer", "trl", "grpo", "dataset:grouped_dataset", "arxiv:2402.03300", "base_model:meta-llama/Llama-3.2-1B-Instruct", "base_model:finetune:meta-llama/Llama-3.2-1B-Instruct", "endpoints_compatible", "region:us" ]	null	2025-05-05T01:24:16Z	--- base_model: meta-llama/Llama-3.2-1B-Instruct datasets: grouped_dataset library_name: transformers model_name: Llama-3.2-1B-Instruct-GRPO-agent3_E16 tags: - generated_from_trainer - trl - grpo licence: license --- # Model Card for Llama-3.2-1B-Instruct-GRPO-agent3_E16 This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on the [grouped_dataset](https://huggingface.co/datasets/grouped_dataset) dataset. It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="fffanx/Llama-3.2-1B-Instruct-GRPO-agent3_E16", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300). ### Framework versions - TRL: 0.17.0.dev0 - Transformers: 4.49.0 - Pytorch: 2.6.0 - Datasets: 3.3.2 - Tokenizers: 0.21.0 ## Citations Cite GRPO as: ```bibtex @article{zhihong2024deepseekmath, title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}}, author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo}, year = 2024, eprint = {arXiv:2402.03300}, } ``` Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
preethammlopssol/indian-law-summary-docs	preethammlopssol	2025-05-05T09:44:28Z	0	0	null	[ "safetensors", "llama", "license:apache-2.0", "region:us" ]	null	2025-05-05T08:48:32Z	--- license: apache-2.0 ---
drzeeIslam/Mobilebert	drzeeIslam	2025-05-05T09:44:24Z	0	0	null	[ "tensorboard", "safetensors", "mobilebert", "medical", "pediatrics", "question-answering", "en", "dataset:custom", "license:apache-2.0", "region:us" ]	question-answering	2025-05-04T20:48:16Z	--- language: en tags: - medical - pediatrics - mobilebert - question-answering license: apache-2.0 datasets: - custom model-index: - name: MobileBERT Nelson Pediatrics results: [] --- # MobileBERT Fine-tuned on Nelson Textbook of Pediatrics This model is a fine-tuned version of `google/mobilebert-uncased` trained on excerpts from the Nelson Textbook of Pediatrics. It is designed to serve as a lightweight, on-device capable medical assistant model for pediatric reference tasks. ## Intended Use This model is intended for: - Medical question answering (focused on pediatrics) - Clinical decision support in low-resource environments - Integration into apps like Nelson-GPT for fast inference > Note: This model is for educational and experimental use only and should not replace professional medical advice. ## Training Details - Base model: `mobilebert-uncased` - Training framework: Transformers + PyTorch - Dataset: Nelson Textbook (manually curated excerpts) - Epochs: [insert] - Learning rate: [insert] ## How to Use ```python from transformers import AutoTokenizer, AutoModelForQuestionAnswering import torch tokenizer = AutoTokenizer.from_pretrained("drzeeIslam/mobilebert-nelson") model = AutoModelForQuestionAnswering.from_pretrained("drzeeIslam/mobilebert-nelson") question = "What is the treatment for nephrotic syndrome?" context = "The first-line treatment for nephrotic syndrome in children is corticosteroid therapy..." inputs = tokenizer(question, context, return_tensors="pt") outputs = model(**inputs) start = torch.argmax(outputs.start_logits) end = torch.argmax(outputs.end_logits) + 1 answer = tokenizer.convert_tokens_to_string(tokenizer.convert_ids_to_tokens(inputs['input_ids'][0][start:end])) print(answer)
roshanrb001/16_bit_model	roshanrb001	2025-05-05T09:44:01Z	0	0	transformers	[ "transformers", "gguf", "qwen2_5_vl", "feature-extraction", "text-generation-inference", "unsloth", "en", "license:apache-2.0", "endpoints_compatible", "region:us" ]	feature-extraction	2025-05-02T10:04:03Z	--- base_model: unsloth/qwen2.5-vl-7b-instruct-bnb-4bit tags: - text-generation-inference - transformers - unsloth - qwen2_5_vl license: apache-2.0 language: - en --- # Uploaded finetuned model - Developed by: roshanrb001 - License: apache-2.0 - Finetuned from model : unsloth/qwen2.5-vl-7b-instruct-bnb-4bit This qwen2_5_vl model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
Kristine09/Kayla	Kristine09	2025-05-05T09:43:45Z	0	0	null	[ "license:bigscience-bloom-rail-1.0", "region:us" ]	null	2025-05-05T09:43:45Z	--- license: bigscience-bloom-rail-1.0 ---
thanhtantran/Vi-Qwen2-1.5B-RAG-rk3588-1.2.0	thanhtantran	2025-05-05T09:43:29Z	0	0	transformers	[ "transformers", "qwen2", "text-generation", "retrieval-augmented-generation", "text-generation-inference", "conversational", "vi", "base_model:Qwen/Qwen2-7B-Instruct", "base_model:finetune:Qwen/Qwen2-7B-Instruct", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2025-05-01T10:27:50Z	--- base_model: Qwen/Qwen2-7B-Instruct language: - vi library_name: transformers license: apache-2.0 pipeline_tag: text-generation tags: - retrieval-augmented-generation - text-generation-inference --- # Vi-Qwen2-1.5B-RAG-RK3588-1.2.0 This version of Vi-Qwen2-1.5B-RAG has been converted to run on the RK3588 NPU using w8a8 quantization. This model has been optimized with the following LoRA: Compatible with RKLLM version: 1.2.0 ## Useful links: [Official RKLLM GitHub](https://github.com/airockchip/rknn-llm) [RockhipNPU Reddit](https://reddit.com/r/RockchipNPU) [EZRKNN-LLM](https://github.com/Pelochus/ezrknn-llm/) Pretty much anything by these folks: [marty1885](https://github.com/marty1885) and [happyme531](https://huggingface.co/happyme531) Converted using https://github.com/c0zaut/ez-er-rkllm-toolkit # Original Model Card for base model, Vi-Qwen2-1.5B-RAG, below: ## Model Card: Vi-Qwen2-7B-RAG Mô tả mô hình: Vi-Qwen2-7B-RAG là một mô hình ngôn ngữ lớn được tinh chỉnh từ mô hình cơ sở Qwen2-7B-Instruct (https://huggingface.co/Qwen/Qwen2-7B-Instruct) phục vụ cho RAG tasks. Mô hình được đào tạo trên tập dữ liệu tiếng Việt với mục tiêu cải thiện khả năng xử lý ngôn ngữ tiếng Việt và nâng cao hiệu suất cho các tác vụ Retrieval Augmented Generation (RAG). Mục đích sử dụng: Mô hình Vi-Qwen2-7B-RAG được thiết kế chuyên biệt cho RAG (ngữ cảnh chấp nhận lên đến 8192 tokens), vì vậy nó có thể giải quyết các trường hợp sau: * Khả năng chống nhiều: Mô hình trích xuất thông tin hữu ích từ các tài liệu nhiễu. ( 1 positive + 4 negative hoặc 1 negative) * Loại bỏ negative: Mô hình từ chối trả lời câu hỏi khi kiến thức cần thiết không có trong bất kỳ tài liệu nào được truy xuất. (1-6 negative) * Tích hợp thông tin: Mô hình trả lời các câu hỏi phức tạp đòi hỏi phải tích hợp thông tin từ nhiều tài liệu. ( 2 part positive + 3 negative hoặc 3 part positive + 2 negative) * Xác đinh positive/negative: Mô hình xác định xem ngữ cảnh có chứa câu trả lời cho câu hỏi hay không. (độ chính xác xấp xỉ 99%) Ngoài ra, chúng tôi cũng triển khai các mô hình nhỏ hơn phù hợp với mục đích sử dụng khác nhau như Vi-Qwen2-1.5B-RAG (https://huggingface.co/AITeamVN/Vi-Qwen2-1.5B-RAG) và Vi-Qwen2.5-3B-RAG (https://huggingface.co/AITeamVN/Vi-Qwen2-3B-RAG) * Ngoài RAG task, bạn vẫn có thể chatbot bình thường với model của chúng tôi. Thậm chí có thể hỏi các câu hỏi liên tục với ngữ cảnh đầu vào. Hạn chế: Vì mô hình chỉ được thiết kế chuyên biệt cho RAG task, nên có thể gặp 1 số hạn chế sau: * Không đảm bảo độ chính xác về các câu hỏi liên quan đến chính trị, xã hội,... * Có thể thể hiện thành kiến hoặc quan điểm không phù hợp. Benchmarks Chúng tôi đã đánh giá một số mô hình LLMs cho RAG task sử dụng tập dữ liệu được tạo thủ công bởi chúng tôi [EvalRAGData](https://huggingface.co/datasets/AITeamVN/EvalRAGData). Đánh giá được thực hiện bởi con người chấm điểm trên thang điểm 10. Dưới đây là kết quả chi tiết: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/66e159e8a533df3d827ec23f/p-JMK67C0BqIAi723YA1p.png) Ngoài ra, chúng tôi cũng tiến hành benchmark trên VMLU leaderboard: \| Model \| Stem \| Social Science \| Humanities \| Others \| Average \| \|----------------------\|------------\|------------\|------------\|-------------\|--------------\| \| Vi-Qwen2-7B-RAG \| 60.22 \| 57.8 \| 52.67 \| 51.08 \| 56.04 \| Các cách sử dụng: #### 1. Sử dụng cơ bản Ngữ cảnh đầu vào chỉ chứa 1 ngữ cảnh (1 postive hoặc 1 negative). ```python import torch from transformers import AutoModelForCausalLM, AutoTokenizer path = 'AITeamVN/Vi-Qwen2-7B-RAG' model = AutoModelForCausalLM.from_pretrained( path, torch_dtype=torch.bfloat16, device_map="auto", use_cache=True ) tokenizer = AutoTokenizer.from_pretrained(path) system_prompt = "Bạn là một trợ lí Tiếng Việt nhiệt tình và trung thực. Hãy luôn trả lời một cách hữu ích nhất có thể." template = '''Chú ý các yêu cầu sau: - Câu trả lời phải chính xác và đầy đủ nếu ngữ cảnh có câu trả lời. - Chỉ sử dụng các thông tin có trong ngữ cảnh được cung cấp. - Chỉ cần từ chối trả lời và không suy luận gì thêm nếu ngữ cảnh không có câu trả lời. Hãy trả lời câu hỏi dựa trên ngữ cảnh: ### Ngữ cảnh : {context} ### Câu hỏi : {question} ### Trả lời :''' # Ví dụ context = '''Thuốc Insuact 10 trị bệnh gì? Thuốc Insuact 10mg có thành phần chính là Atorvastatin. Thuốc Insuact 10 có tác dụng làm giảm cholesterol và triglycerid trong máu ở bệnh nhân tăng cholesterol máu nguyên phát, rối loạn lipid máu hỗn hợp. 1. Thuốc Insuact 10 trị bệnh gì? Thuốc Insuact 10 thuộc nhóm thuốc điều trị rối loạn lipid máu, có thành phần chính là Atorvastatin 10mg. Atorvastatin có tác dụng làm giảm cholesterol, ức chế enzym tạo cholesterol ở gan. Atorvastatin làm giảm cholesterol chung bao gồm cholesterol LDL , triglycerid trong máu. Thuốc Insuact 10mg được bào chế dưới dạng viên nén bao phim, được chỉ định dùng trong những trường hợp sau: Ðiều trị hỗ trợ tăng cholesterol máu nguyên phát và rối loạn lipid máu hỗn hợp trên bệnh nhân đang áp dụng chế độ ăn kiêng để làm giảm cholesterol toàn phần , cholesterol LDL , apolipoprotein B, triglycerid và tăng cholesterol HDL . Insuact 10 cũng được dùng để điều trị rối loạn betalipoprotein trong máu nguyên phát. Ðiều trị hỗ trợ tăng cholesterol trong máu có tính gia đình đồng hợp tử trên bệnh nhân đang áp dụng các biện pháp làm giảm lipid khác để làm giảm cholesterol toàn phần và cholesterol LDL. 2. Liều dùng và cách dùng thuốc Insuact 10 Cách dùng thuốc Insuact 10: Thuốc được dùng theo đường uống, uống khi bụng đói hoặc no đều được, có thể uống vào bất cứ lúc nào trong ngày. Liều dùng thuốc Insuact 10mg khởi đầu là 10mg/lần/ngày, tối đa là 80mg/lần/ngày. Liều dùng thuốc Insuact 10 tùy vào mục đích điều trị cụ thể như sau: Tăng cholesterol máu nguyên phát và rối loạn lipid máu phối hợp: 10mg/lần/ngày, sau 2 - 4 tuần sẽ thấy hiệu quả của thuốc. Thuốc cần được được sử dụng duy trì trong thời gian dài để có hiệu quả. Tăng cholesterol trong máu có tính gia đình đồng hợp tử: Liều thường dùng là thuốc Insuact 10mg /lần/ngày và tối đa là 80mg/lần/ngày. Rối loạn lipid máu nghiêm trọng ở trẻ từ 10 - 17 tuổi: 10mg/lần/ngày, sau đó tăng lên 20mg/lần/ngày tùy vào cơ địa, tiến triển bệnh và khả năng dung nạp thuốc của người bệnh. Thời gian điều chỉnh liều thuốc tối thiểu là 4 tuần. 3. Tác dụng phụ của thuốc Insuact 10mg Thuốc Insuact 10 có thể gây một số tác dụng phụ không mong muốn với tần suất như sau: Thường gặp: Viêm mũi - họng, phản ứng dị ứng, tăng đường huyết, nhức đầu, đau thanh quản, chảy máu cam , đau cơ, co thắt cơ, đau khớp, sưng khớp, đau các chi, đau lưng, xét nghiệm gan bất thường, tăng creatine kinase trong máu, buồn nôn, khó tiêu, đầy hơi, táo bón, tiêu chảy. Ít gặp: Insuact 10 ít gây hạ đường huyết, tăng cân, chán ăn, mất ngủ, gặp ác mộng, choáng váng, dị cảm, mất trí nhớ, giảm cảm giác, loạn vị giác , nôn, đau bụng, ợ hơi, viêm tụy, viêm gan, nổi mày đay , phát ban, ngứa, rụng tóc, đau cổ, mỏi cơ, mệt mỏi, suy nhược, đau ngực, phù ngoại biên, sốt, xuất hiện bạch cầu trong nước tiểu, nhìn mờ, ù tai. Hiếm gặp: Insuact 10 hiếm khi làm giảm tiểu cầu, bệnh lý thần kinh ngoại biên, hoa mắt, ứ mật, phù thần kinh, nổi hồng ban, hội chứng hoại tử da nhiễm độc , hội chứng Stevens-Johnson , bệnh cơ, viêm cơ, tiêu cơ vân, bệnh gân, đôi khi nghiêm trọng hơn có thể đứt gân. Rất hiếm gặp: Insuact 10 rất hiếm khi gây sốc phản vệ , mất thính giác , suy gan , hội chứng to vú ở nam giới. Không rõ tần suất: Hoại tử cơ tự miễn trung gian. 4. Một số lưu ý khi dùng thuốc Insuact 10mg Không dùng thuốc Insuact với người bị quá mẫn với thành phần của thuốc, người có bệnh gan hoạt động hoặc tăng transaminase huyết thanh vô căn kéo dài, phụ nữ đang mang thai hoặc nuôi con cho bú, phụ nữ đang có ý định mang thai. Thuốc Insuact 10mg chỉ được dùng ở bệnh nhân có nguy cơ xơ vữa mạch máu cao do tăng cholesterol trong máu và phải kết hợp với chế độ ăn kiêng ít chất béo bão hòa , ít cholesterol và người bệnh đang áp dụng các biện pháp điều trị không dùng thuốc khác. Trước khi điều trị với Insuact 10 , người bệnh cần được loại trừ các nguyên nhân thứ phát gây tăng cholesterol bao gồm suy tuyến giáp , tiểu đường khó kiểm soát, hội chứng thận hư, nghiện rượu, bệnh gan tắc nghẽn, rối loạn protein trong máu, .... Ngoài ra, người bệnh cũng cần được kiểm tra, đo lường nồng độ lipid máu. Trước khi điều trị với thuốc Insuact 10mg , cần kiểm tra chức năng gan và trong quá trình dùng thuốc, người bệnh cần theo dõi, kiểm tra chức năng gan thường xuyên. Người có tiền sử mắc bệnh gan do rượu, bị nghiện rượu cần thận trọng khi dùng Insuact 10 . Trước khi dùng thuốc, người bệnh cần được cảnh báo nguy cơ gặp phải các vấn đề về cơ như căng cơ , đau cơ, yếu cơ. Thuốc Insuact 10mg có thể tương tác với các thuốc: Tăng nguy cơ tổn thương cơ (đặc biệt cơ vân) khi dùng đồng thời với thuốc điều trị viêm gan C và HIV, hạ cholesterol máu nhóm fibrat khác, thuốc ức chế miễn dịch; tăng thời gian chảy máu hoặc thời gian prothrombin khi dùng phối hợp với thuốc chống đông, indandione; tăng nhẹ nồng độ digoxin trong huyết thanh khi dùng phối hợp với Digoxin''' question = '''Insuact 10mg được chỉ định dùng trong những trường hợp nào và liều dùng cụ thể ra sao?''' conversation = [{"role": "system", "content": system_prompt }] conversation.append({"role": "user", "content": template.format(context = context, question = question)}) text = tokenizer.apply_chat_template( conversation, tokenize=False, add_generation_prompt=True) model_inputs = tokenizer(text,return_tensors="pt").to(model.device) generated_ids = model.generate( model_inputs.input_ids, max_new_tokens=2048, temperature = 0.1, #top_p=0.95, #top_k=40, ) generated_ids = [ output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids) ] response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0] print(response) '''Trả lời: Dựa trên ngữ cảnh cung cấp, Insuact 10mg được chỉ định dùng trong các trường hợp sau: 1. Điều trị hỗ trợ tăng cholesterol máu nguyên phát và rối loạn lipid máu hỗn hợp: - Liều dùng: 10mg/lần/ngày. - Hiệu quả: Sau 2 - 4 tuần sử dụng, bệnh nhân sẽ thấy hiệu quả của thuốc. - Lưu ý: Thuốc cần được sử dụng duy trì trong thời gian dài để có hiệu quả. 2. Điều trị hỗ trợ tăng cholesterol trong máu có tính gia đình đồng hợp tử: - Liều dùng: 10mg/lần/ngày (liều thường dùng) và tối đa 80mg/lần/ngày. - Lưu ý: Liều lượng có thể được điều chỉnh tùy theo cơ địa, tiến triển bệnh và khả năng dung nạp thuốc của người bệnh. 3. Rối loạn lipid máu nghiêm trọng ở trẻ từ 10 - 17 tuổi: - Liều dùng: 10mg/lần/ngày, sau đó có thể tăng lên 20mg/lần/ngày tùy theo tình trạng bệnh. - Thời gian điều chỉnh liều: Thời gian điều chỉnh liều tối thiểu là 4 tuần. Lưu ý chung: - Thuốc được dùng theo đường uống, uống khi bụng đói hoặc no đều được, có thể uống vào bất cứ lúc nào trong ngày. - Không dùng thuốc Insuact 10mg với người bị quá mẫn với thành phần của thuốc, người có bệnh gan hoạt động hoặc tăng transaminase huyết thanh vô căn kéo dài, phụ nữ đang mang thai hoặc nuôi con cho bú, phụ nữ đang có ý định mang thai. - Cần kiểm tra chức năng gan trước và trong quá trình điều trị. ''' ``` #### 2. Khả năng chống nhiều ```python # ví dụ context = '''- Ngữ cảnh 1: . Và dù nguyên nhân thế nào, thì việc đánh người khác đều không thể chấp nhận, không ai có quyền xâm phạm thân thể của người khác, nhất là đánh những đứa trẻ là bạn của con cái mình. Lựa chọn kể với cha mẹ, người lớn về các mâu thuẫn học đường, là quyết định rất đúng của các em. Nhưng người lớn, đặc biệt những ông bố, bà mẹ cần ứng xử ra sao trước xung đột này của các con, thưa bà? Đứng ngoài mâu thuẫn bằng sự khách quan và trách nhiệm nhất có thể. Điều này giúp chúng ta đủ bình tĩnh để làm việc với tất cả các bên liên quan, từ giáo viên, bạn của con, ban giám hiệu để tìm hiểu câu chuyện và tìm kiếm cách giải quyết tích cực, trên cơ sở phối hợp nhà trường. Người lớn không thể chỉ nghe một tai và đặc biệt không nên tự xử. Phụ huynh, kể cả học sinh tự xử các vấn đề học đường là điều rất nguy hiểm và cho thấy sự coi thường pháp luật . Vụ việc ở Tuyên Quang vừa rồi là ví dụ. Các em hoàn toàn có thể phản ứng bằng cách trình bày, gửi yêu cầu, kiến nghị lên nhà trường, nhờ phụ huynh làm việc với ban giám hiệu để có biện pháp giải quyết nếu cô giáo sai, không nên đồng loạt dồn cô giáo vào tường một cách bạo lực và trái đạo đức, tôn ti trật tự như vậy. Ngoài ra, chúng ta cũng có rất nhiều cơ quan chức năng bảo vệ phụ huynh và con em, với những quyền về khiếu nại, tố cáo. Chúng ta nói nhiều về trường học an toàn. Trong những câu chuyện học sinh bị hành hung thế này, có lẽ cũng cần làm rõ vai trò, trách nhiệm của nhà trường? TPHCM và nhiều địa phương đang xây dựng môi trường trường học hạnh phúc, tiêu chí là yêu thương, an toàn, tôn trọng. Không chỉ phòng ngừa, nhà trường còn phải tích cực vào cuộc xử lý các mâu thuẫn học đường, hạn chế tối đa nguy cơ mất an toàn cho học sinh, giáo viên. Đặc biệt, giải quyết câu chuyện bạo lực học đường phải triệt để, tuyệt đối không nửa vời vì nửa vời sẽ tiềm ẩn nguy cơ rất lớn dẫn đến những vụ việc tương tự, với mức độ nghiêm trọng hơn. Vụ việc em M. ở Nha Trang tự vẫn với lá thư tuyệt mệnh bị đổ oan đầu tháng 10 vừa qua là một ví dụ về giải quyết không triệt để. Việc xây dựng trường học hạnh phúc nếu triển khai “đến nơi đến chốn”, sẽ góp phần rất lớn cải thiện tình trạng bạo lực học đường, tạo môi trường sống và học tập bình an cho các con. Từ nhiều sự vụ học sinh bạo hành lẫn nhau, giáo viên bạo hành học sinh, phụ huynh hành hung giáo viên và bạn của con. Tam giác phối hợp bảo vệ học sinh là nhà trường - gia đình - xã hội phải chăng đang có một lỗ hổng lớn, thưa bà? Câu chuyện này có liên quan đến niềm tin của phụ huynh với nhà trường. Tại sao phụ huynh lại chọn cách tự xử? Chúng ta cũng cần phải xem lại cách giải quyết vấn đề của nhà trường đã rốt ráo chưa, coi trọng lợi ích của tất cả các bên liên quan chưa hay chỉ đang xoa dịu? Người ta chỉ tìm đến nhau khi có niềm tin vào nhau. Thực trạng phụ huynh chọn cách chuyển trường cho con cũng nói lên điều này. Đây là cách chạy trốn của phụ huynh với mong muốn con được an toàn, hạnh phúc hơn ở môi trường mới. Xây dựng niềm tin cho phụ huynh, xã hội cần được chú trọng và với mỗi một trường hợp phụ huynh yêu cầu chuyển trường cho con - đang rất phổ biến - nhà trường cần xét kỹ các nguyên nhân và hóa giải. Xin bà cho biết đâu là giải pháp căn cơ cho tất cả những câu chuyện bạo lực nói trên? Để trẻ không là nạn nhân của bạo lực học đường, phụ huynh cần đồng hành và giúp con có sự hiểu biết, ý thức trước vấn đề này. Dạy con kỹ năng giao tiếp, quản lý cảm xúc rất quan trọng và điều này không thể chỉ dựa vào những khóa học kỹ năng sống, mà là từ cách cư xử của người lớn, cha mẹ, thầy cô. Không có tấm gương nào tốt hơn cho con trẻ bằng ứng xử, hành vi của người lớn. Vì vậy, không thể đòi hỏi trẻ nói không với bạo lực học đường khi trong chính từng gia đình, xã hội, người lớn vẫn đối xử với nhau bằng bạo lực. - Ngữ cảnh 2: Tại sao triều Thanh có rất nhiều thân vương nhưng chẳng có ai dám tạo phản? Không giống như những triều đại trước đó, triều Thanh dù có sự tranh giành ngai vàng khốc liệt giữa các hoàng tử nhưng lại chẳng bao giờ xảy ra thế cục các thân vương tạo phản. Chính vì 3 lý do lớn này đã khiến cho triều đại nhà Thanh khác hẳn triều đại nhà Đường và nhà Minh. Trong thời cổ đại, các vương công quý tộc để tranh giành vương vị của mình, giữa huynh đệ ruột thịt với nhau dường như đều xảy ra đấu đá, hãm hại lẫn nhau, coi nhau như kẻ thù không đội trời chung, có ta thì không có ngươi, có ngươi thì sẽ chẳng có ta, điều này hoàn toàn không phải là điều gì xa lạ. Vậy thì tại sao ngai vàng lại có sức hút lớn đến thế? Không chỉ là đàn ông khát khao quyền lực, mà quan trọng hơn là hoàng đế có thể có được hậu cung rộng lớn, trong hậu cung còn có vô số các mỹ nữ quốc sắc thiên hương. Nhiều phi tần như vậy, đương nhiên hoàng đế cũng sẽ có rất nhiều con cái, không tính đến con gái, chỉ riêng những vị hoàng tử, để có thể có được hoàng vị, họ tranh giành nhau bằng cả sinh mạng. Vậy thì ai là người được lựa chọn để thừa kế ngai vàng, ai mới có thể gánh được trọng trách trị vì đất nước? Đa phần đều theo tục lệ truyền cho con trai đích tôn (con trai do hoàng hậu sinh ra) hoặc con trai trưởng (con trai đầu tiên của hoàng đế). Cho dù tục lệ này có lịch sử lâu đời nhưng nó cũng có những khuyết điểm rất lớn, đó chính là nếu như năng lực và chí hướng của con trai đích tôn hoặc con trai trưởng không thể gánh vác được ngai vị, nếu để anh ta lên ngôi hoàng đế, vậy thì đất nước sẽ rơi vào cục diện suy vong. Còn có một khuyết điểm nữa đó chính là những người con trai có dã tâm lớn khác sẽ không phục việc con trai đích hoặc con trai trưởng kế thừa ngôi báu, họ sẽ khởi binh tạo phản cũng là chuyện rất dễ xảy ra. Ví dụ như trong thời Đường của Trung Quốc, Đường Cao Tổ Lý Uyên đem binh tiêu diệt nhà Tùy thối nát, đồng thời lập nên nhà Đường, vốn dĩ ông cũng dựa theo tục lệ lập con trai trưởng là Lý Kiến Thành làm Thái tử nhưng con trai thứ là Lý Thế Dân lại không phục với sự sắp xếp này. Vì năng lực của ông xuất chúng, văn võ song toàn, còn lập được không ít công lao to lớn trong cuộc chiến tranh tiêu diệt nhà Tùy cùng cha mình, đương nhiên không chịu thấp hơn kẻ khác một bậc. Thế nên đã phát động binh biến Huyền Vũ Môn, trong cuộc binh biến tạo phản này, đích thân ông đã giết chết huynh trưởng của mình, đồng thời ép cha mình là Lý Uyên phải truyền ngôi cho mình. Hay như trong thời nhà Minh của Trung Quốc, trước khi Chu Nguyên Chương chọn người lập làm Thái tử, con trai trưởng Chu Tiêu đã qua đời vì bệnh nặng, thế nên Chu Nguyên Chương đã lập cháu đích tôn của mình làm Thái tử kế thừa vương vị, nhưng em trai của Chu Tiêu là Chu Đệ lại không phục lựa chọn này của Chu Nguyên Chương. Theo lý mà nói thì sau khi anh trai Chu Tiêu qua đời, ông đã có tư cách thừa kế ngai vàng nhưng Chu Nguyên Chương nhất quyết không chọn ông mà lại chọn người cách thế hệ để truyền ngôi. Điều này khiến Chu Đệ với thế lực to lớn không thể nuốt nổi cục tức này, vì thế Chu Tiêu vừa qua đời thì ông đã vội vã khởi binh tạo phản, giết chết cháu trai ruột của mình rồi tự xưng vương. Vậy thì tại sao trong triều Thanh có rất nhiều thân vương như vậy mà lại chẳng có ai đứng ra tạo phản? Đầu tiên phải nói về bối cảnh xã hội trong thời kỳ này. Triều Thanh từ khi thành lập, cũng giống với những triều đại khác, đều có rất nhiều thân vương. Nếu người dân bình thường muốn làm hoàng đế, vậy thì đó là điều hoàn toàn không thể, nhưng đối với những vương công quý tộc trong hoàng thất mà nói, họ đương nhiên sẽ có rất nhiều cơ hội, đặc biệt là những thân vương nắm đại quyền quân sự , họ chính là mối đe dọa lớn nhất đối với nhà vua. Vì thế, các đời hoàng đế đều sẽ nghĩ đủ mọi cách để áp chế, kiểm soát họ, tránh việc họ khởi binh tạo phản. Triều Thanh có lịch sử hơn 300 năm, cũng đã cho ra đời vô số thân vương, đặc biệt là cuối thời Thanh, khi Trung Quốc rơi vào cảnh khốn khó, sau khi Từ Hy Thái Hậu cầm quyền thì thế cục này càng được thể hiện rõ rệt hơn. Nhưng cho dù là một người phụ nữ cầm quyền thì cũng chẳng có một vị thân vương hoàng tộc nào đứng ra tạo phản. Có 3 nguyên nhân sau: Thứ nhất, thân vương triều Thanh không thể nối ngôi, nếu muốn tiếp tục duy trì danh phận thân vương, vậy thì bắt buộc phải có được sự đồng ý của hoàng đế và phải lập được công lao cho đất nước. Thứ hai, triều đình tiến hành giám sát nghiêm ngặt đối với các thân vương, họ không hề có cơ hội để tạo phản. Thứ ba, các thân vương không thể giao thiệp quá sâu với các đại thần, quan lại khác, điều này cũng khiến các thân vương rơi vào cảnh bị cô lập, thế nên càng không có cơ hội để cấu kết với người khác hòng tạo phản. - Video: Ngắm sự kỳ vĩ và lộng lấy của Tử Cấm Thành từ trên cao. Nguồn: Sky Eye. - Ngữ cảnh 3: . Cùng điều chỉnh với con là điều rất quan trọng bởi vì trẻ sẽ tự tin để tự đặt những giới hạn cho chính mình khi lớn lên”, TS Nguyễn Thị Thanh đưa ra lời khuyên. “Khi con mắc sai lầm, hãy giúp chúng tìm những cách khác tốt hơn. Đơn cử dùng hậu quả để dạy cho chúng bài học, điều đó tốt hơn rất nhiều việc xử phạt. Nếu cha mẹ chỉ biết trừng phạt, sẽ nhận được lời xin lỗi nhưng không thể giúp trẻ tỉnh ngộ. Bởi chúng chỉ biết được mình đã sai mà không biết sai ở chỗ nào và làm thế nào mới là đúng” - Ngữ cảnh 4: . “MẤT ĐI CHA MẸ Ở TUỔI ĐẸP NHẤT CỦA NGƯỜI PHỤ NỮ CÀNG KHIẾN TÔI PHẢI MẠNH MẼ” - Làm con của nghệ sĩ Thanh Hiền, Đinh Y Nhung cảm nhận sợi dây liên kết giữa hai mẹ con thế nào? Má Thanh Hiền là người rất tuyệt vời. Hai má con hồi xưa từng làm phim truyền hình với nhau rồi, cho nên khi tái hợp thì không mấy bỡ ngỡ. Khi đối diễn, hai má con rất ăn ý, như người thân ruột thịt vậy đó. - Khi thể hiện những phân cảnh cảm động trong phim, có khi nào chị thấy nhớ mẹ không? Có chứ, nhất là ở những phân đoạn gia đình sum họp, tự nhiên mình bị buồn. Ai cũng muốn có cha, có mẹ, ai cũng muốn Tết được chạy về bên gia đình. Trong mười mấy, hai chục năm qua, Nhung bị chạnh lòng. Tuy nhiên, chỉ trong tích tắc, tôi tự trấn an rằng, mình đang quay phim, đang hóa thân vào nhân vật nên không thể xao lãng được. Mình là con người mà, cũng có lúc tâm trạng vui buồn bất chợt, nhưng Nhung luôn cố gắng lấy lại phong độ liền. - Mất ba mẹ từ sớm, không có chỗ dựa tinh thần, cô gái trẻ Đinh Y Nhung năm đó có nhận những lời mời gọi khiếm nhã không? Trước đây, Nhung không có bạn bè nhiều, chủ yếu chỉ lo đi học, đi làm để lo cho cuộc sống thôi. Nên Nhung không phải đón nhận những lời mời gọi nào hết. - Mất mát từ quá khứ có ảnh hưởng gì đến suy nghĩ về tương lai của chị sau này, ví dụ khi có con thì sẽ bù đắp, chăm sóc cho con nhiều hơn? Năm ba mẹ mất thì mình vẫn còn khá trẻ, thật ra cái tuổi đó là tuổi đẹp của người phụ nữ. Sau đó, tôi đi làm, rồi yêu đương và lập gia đình. Có rất nhiều thứ hối tiếc để nói về Nhung của thời điểm đó. Thứ nhất là mình chưa thành công, thứ hai là mình chưa trả hiếu cho cha mẹ, thứ ba là mình còn bấp bênh. Nhung lúc đó lì lợm lắm, không cho phép mình ngã, bằng mọi giá phải tiến về trước dù có hàng ngàn chông gai ngăn cản. Có lúc tôi bị người này cười, người kia mỉa, nhưng mà mình vẫn cố bước đi. Người ta có cười thì cũng không mang lại cho mình được gì, tôi chỉ biết làm hết khả năng để lo cho bản thân, lo cho em của mình. Hiện, con cái Nhung đã đi nước ngoài rồi. Bé đang học đại học về âm nhạc, còn em mình cũng đã lớn rồi. Đối với Nhung ngay lúc này thì không phải thành công hay hoàn hảo lắm, nhưng ít nhất là tôi đã cố gắng để tự chịu trách nhiệm với cuộc đời mình. Mất cha, mất mẹ, đối với một người hai mươi mấy tuổi thì điều cần nhất lúc đó là có được gia đình ở bên. Nhưng mình không có chỗ dựa tinh thần thì càng phải mạnh mẽ hơn nữa. Tôi tự gặm nhấm nỗi đau mất người thân trong một thời gian dài, có khi đến cả bạn bè cũng không hề biết. Một thời gian sau, bạn bè thời và mọi người mới biết. Còn người hâm mộ, đồng nghiệp trong nghề gần như không biết chuyện ba mẹ Nhung mất sớm, chỉ có vài người chơi thân với nhau biết thôi. Sau này, dần dần tâm lý dần ổn định thì mình mới bắt đầu chia sẻ. “CON ĐI DU HỌC, TÔI DẶN BÉ CÁI GÌ KHÔNG TỐT THÌ MÌNH BỎ QUA” - Đinh Y Nhung từng tiết lộ mình rất thân với con gái. Có vẻ như quyết định để con đi du học là không hề dễ dàng? Thật sự là không có ba mẹ nào muốn con mình đi xa, nhưng việc du học lại là quyết định của bé. Con Nhung bày tỏ muốn học đại học ở nước ngoài và muốn đi sớm để thực hiện ước mơ. Nhưng lúc đó con còn nhỏ quá, phải đợi đến năm con 17 tuổi thì Nhung mới quyết định cho bạn nhỏ đi. Con cái từ nhỏ ở với bố mẹ giờ lại đi xa thì tất nhiên người làm cha làm mẹ cùng phải thấy sốc, thấy buồn. Nhưng Nhung hoàn toàn tôn trọng quyết định của con về việc chọn ngành nghề và tương lai của mình. Ba mẹ sẽ đứng sau và là người đưa cho con những lời khuyên và chỉ có thể đồng hành cùng con tới một mốc thời gian nào đó. Về sau, con phải đi làm và tự có trách nhiệm với cuộc đời của mình. - Có con gái đang ở tuổi lớn lại xa bố mẹ và tiếp xúc một nền văn hóa phương Tây cởi mở, Đinh Y Nhung đã khuyên dạy và đồng hành với con như thế nào? Ngay khi ở Việt Nam, con gái Nhung đã được theo học trường quốc tế. Hai mẹ con cũng có rất nhiều dịp để tâm sự và chia sẻ với nhau. Ngay từ nhỏ, Nhung đã cho bé được tiếp xúc song song giữa hai nền văn hóa để con không bỡ ngỡ. Mình là người Việt nên đương nhiên vẫn dạy con theo văn hóa Á Đông là chủ yếu. Nhung vẫn luôn tạo điều kiện để con cảm nhận những nét đẹp trong nền văn hóa quê hương. Văn hóa phương Tây thì xa lạ hơn nhưng Nhung cũng khuyên con rằng điều gì hay thì mình học hỏi, cái gì không tốt thì mình nên bỏ qua. Tất nhiên mình không thể theo sát con, nhất là khi bé đang ở độ tuổi mới lớn, có nhiều sự hiếu kỳ. Tuy nhiên, Nhung cũng không quá lo lắng vì qua quá trình học tập ở các trường quốc tế, bé cùng đã được làm quen dần với văn hóa phương Tây. Bé muốn làm bạn với mẹ nên có nhiều thứ bé muốn hỏi, muốn tiếp thu thì hai mẹ con lại ngồi xuống chia sẻ, tâm sự với nhau. Nhung tin, con luôn tỉnh táo để đưa ra những quyết định cho bản thân mình. Nhung không dám nói trước, nhưng hiện tại con vẫn luôn biết nói cảm ơn, xin phép trước khi làm bất cứ điều gì nên mình vẫn rất tin tưởng con. - Chị nhận xét thế nào về tính cách của con gái? Phải chăng bé là phiên bản nhí của chị? Con gái Nhung có nhiều nét giống mẹ. - Ngữ cảnh 5: . - Trong quá trình quay phim, má Hiền có tham gia đóng góp ý kiến cho dàn diễn viên trẻ không? Không phải má Hiền muốn làm thầy nhưng có những lúc cũng lên tiếng góp ý một vài điều. Những lúc như thế các bạn diễn viên trẻ cũng nghe theo. Phải giúp đỡ nhau như vậy mới có thể tạo ra được một tác phẩm hay. Chứ có nhiều diễn viên trẻ có lòng tự trọng cao, chỉ khi đạo diễn nói mới nghe thì không bao giờ có thể tiến bộ được. Má Hiền phải cảm thấy hạnh phúc mới đúng, càng ngày xung quanh càng có nhiều bạn bè, các mối quan hệ nhờ đó mà cũng ngày càng đông. Ngày xưa, khi tham gia là Mùi Ngò Gai chưa có ai biết nhưng sau khi phim phát sóng mọi người đã nhớ đến má. Hiện tại, má Hiền đã được đạo diễn, nhà sản xuất mời đóng phim đó đã là một niềm hạnh phúc. Đi ra đường hay đi khám bệnh, người ta cứ vây xung quanh quan tâm hỏi han khiến má cảm thấy rất vui lắm (cười). Cảm ơn nghệ sĩ Thanh Hiền đã nhận lời tham gia phỏng vấn với SAOstar. Chúc má có nhiều sức khỏe để tiếp tục làm nghề!''' question = '''Tại sao các thân vương triều Thanh không dám tạo phản mặc dù có nhiều quyền lực và cơ hội?''' '''Trả lời: Các thân vương triều Thanh không dám tạo phản mặc dù có nhiều quyền lực và cơ hội vì có ba lý do chính: 1. Không thể nối ngôi: Để duy trì danh phận thân vương, họ phải có sự đồng ý của hoàng đế và phải lập được công lao cho đất nước. Điều này hạn chế cơ hội của họ để trở thành hoàng đế. 2. Giám sát nghiêm ngặt: Triều đình tiến hành giám sát nghiêm ngặt đối với các thân vương, không cho họ cơ hội để tạo phản. 3. Bị cô lập: Các thân vương không thể giao thiệp quá sâu với các đại thần, quan lại khác, điều này khiến họ bị cô lập và không có cơ hội cấu kết với người khác để tạo phản.''' ``` #### 3. Loại bỏ negative ```python context = '''- Ngữ cảnh 1: Thái Bình hướng đến là trung tâm công nghiệp, năng lượng của vùng Với tiềm năng sẵn có, quy hoạch tỉnh Thái Bình thời kỳ 2021-2030, tầm nhìn đến năm 2050 xác định tỉnh sẽ phát triển công nghiệp theo hướng hiện đại, bền vững dựa trên nghiên cứu phát triển điện gió, điện khí, cân bằng lượng phát thải. Sáng 5/3, UBND tỉnh Thái Bình tổ chức Hội nghị công bố quy hoạch của tỉnh thời kỳ 2021-2030, tầm nhìn đến năm 2050 và xúc tiến đầu tư tỉnh Thái Bình. Phát biểu tại hội nghị, Phó Chủ tịch Thường trực UBND tỉnh Nguyễn Quang Hưng cho biết: Mục tiêu của quy hoạch là đến năm 2030, Thái Bình trở thành địa phương thuộc nhóm phát triển khá và là một trong những trung tâm phát triển công nghiệp của vùng Đồng bằng sông Hồng, có cơ cấu kinh tế hiện đại với công nghiệp là động lực chủ yếu cho tăng trưởng để Thái Bình phát triển nhanh, toàn diện và bền vững. Đến năm 2050, Thái Bình là tỉnh phát triển của vùng Đồng bằng sông Hồng, tăng trưởng kinh tế dựa trên nền tảng khoa học công nghệ, đổi mới sáng tạo và các ngành kinh tế trụ cột có sức cạnh tranh cao. Quy hoạch tỉnh đã xác định 4 trụ cột tăng trưởng, 3 khâu đột phá, 4 không gian kinh tế - xã hội, 3 hành lang kinh tế, định hướng phát triển các ngành và lĩnh vực và 6 nhiệm vụ trọng tâm. Quy hoạch tỉnh cũng có nhiều điểm mới, đột phá như mở ra không gian phát triển mới thông qua hoạt động “lấn biển”, tạo quỹ đất cho các hoạt động chức năng, hình thành không gian công nghiệp - đô thị - dịch vụ. Về hạ tầng giao thông, Thái Bình sẽ đầu tư 3 tuyến cao tốc là cao tốc Ninh Bình - Hải Phòng (CT.08), đường vành đai 5 - Hà Nội (CT.39) và tuyến CT.16 kết nối Khu kinh tế với thành phố Thái Bình và vùng kinh tế phía Tây Bắc Thủ đô. Tỉnh cũng sẽ đầu tư 101km đường sắt, khổ đường dự kiến rộng 1.435 mm và sân bay chuyên dụng nằm ở ven biển Thái Bình. Về phát triển kinh tế, quy hoạch tỉnh Thái Bình xác định tỉnh sẽ phát triển công nghiệp theo hướng hiện đại, công nghệ tiên tiến, giá trị gia tăng cao, tham gia sâu, toàn diện vào mạng lưới sản xuất, chuỗi giá trị toàn cầu, phát huy các tiềm năng, thế mạnh để đưa Thái Bình trở thành một trong những trung tâm phát triển công nghiệp, năng lượng của vùng Đồng bằng sông Hồng. Tỉnh khuyến khích đầu tư phát triển các ngành có thế mạnh và có thể tạo đột phá như năng lượng, cơ khí chế biến, chế tạo, công nghiệp công nghệ cao, điện - điện tử, chế biến sản phẩm nông, lâm nghiệp và thủy sản… Đồng thời, tập trung nghiên cứu phát triển điện gió, điện khí để tạo nguồn điện sạch và cân bằng lượng phát thải, nghiên cứu đầu tư xây dựng nhà máy chế biến Condensate, chuẩn bị mọi điều kiện để xây dựng và đưa vào vận hành Nhà máy nhiệt điện LNG Thái Bình. Về nông nghiệp, tỉnh Thái Bình vẫn xác định đây là \"trụ cột quan trọng\" trong phát triển kinh tế của tỉnh, góp phần bảo đảm an ninh lương thực quốc gia, hướng tới trở thành trung tâm sản xuất nông nghiệp hàng đầu của Đồng bằng sông Hồng. Phát biểu tại hội nghị, Phó Thủ tướng Chính phủ Trần Lưu Quang đánh giá Thái Bình có 4 tiềm năng, lợi thế lớn để có thể có sự bứt phá trong thời gian tới như vị trí địa lý và tiếp cận đất đai thuận lợi; từng là địa phương đi đầu trong xây dựng nông thôn mới bài bản và nghiêm túc, nhận được sự quan tâm của nhiều thế hệ lãnh đạo Đảng, Nhà nước và có nhiều doanh nhân người Thái Bình và luôn hướng về quê hương; có sự đoàn kết, thống nhất, trước hết là trong tập thể lãnh đạo. Về vị trí địa lý và tiếp cận đất đai, Phó Thủ tướng cho rằng trong tương lai, khi Luật Đất đai có hiệu lực, Thái Bình sẽ có nhiều điều kiện lấn biển để triển khai các dự án khu đô thị, khu công nghiệp thân thiện với môi trường. Đối với nông nghiệp, Phó Thủ tướng nhấn mạnh về lâu dài Thái Bình có thể ghi điểm từ phát triển công nghiệp nhưng trước mắt, đặc biệt trong lúc khó khăn thì nông nghiệp vẫn là nền tảng rất quý giá. Mặt khác, ứng dụng của công nghệ cao trong sản xuất nông nghiệp sẽ rút ngắn thời gian làm đồng của người nông dân, tạo điều kiện để Thái Bình huy động nguồn nhân lực trong nông nghiệp sang phát triển các ngành công nghiệp và dịch vụ, một lợi thế mà không phải địa phương nào cũng có được như Thái Bình. Bên cạnh những lợi thế trên, lãnh đạo Chính phủ chỉ ra một số khó khăn mà tỉnh phải đối mặt như Thái Bình đã sử dụng hết 1.600 ha chỉ tiêu đất công nghiệp trong giai đoạn này, đòi hỏi phải có phương án giải quyết thấu đáo trong thời gian tới để tỉnh tiếp tục phát triển công nghiệp. Đồng thời, Thái Bình cũng phải cạnh tranh với những địa phương như Hải Phòng, Quảng Ninh trong thu hút FDI trong khi phát triển cơ sở hạ tầng chưa theo kịp mong muốn. Do vậy, khi triển khai quy hoạch tỉnh, Phó Thủ tướng nhắn nhủ tới địa phương 8 chữ: Tuân thủ, linh hoạt, đồng bộ và thấu hiểu. Đồng thời, tỉnh cũng phải \"linh hoạt\" trong tổ chức thực hiện, trong trường hợp cá biệt cụ thể, điều chỉnh mục tiêu cho phù hợp. Sáng cùng ngày, Phó Thủ tướng Trần Lưu Quang đã dự Lễ khởi công dự án Nhà máy Pegavision Việt Nam tại khu công nghiệp Liên Hà Thái, huyện Thái Thụy, tỉnh Thái Bình - Ngữ cảnh 2: Bình Định được định hướng là trung tâm khoa học, công nghệ đổi mới sáng tạo Tỉnh Bình Định được định hướng phát triển ngành công nghiệp phát triển theo hướng hiện đại, quy mô lớn, trở thành một trong những trung tâm công nghiệp chế biến chế tạo và công nghệ cao của vùng Bắc Trung Bộ và duyên hải Trung Bộ. Theo Quy hoạch tỉnh Bình Định thời kỳ 2021 - 2030, tầm nhìn đến năm 2050 vừa được Thủ tướng Chính phủ phê duyệt, tỉnh Bình Định được định hướng phát triển ngành công nghiệp phát triển theo hướng hiện đại, quy mô lớn, trở thành một trong những trung tâm công nghiệp chế biến chế tạo và công nghệ cao của vùng Bắc Trung Bộ và duyên hải Trung Bộ. Ngành công nghiệp tăng trưởng nhanh, bền vững, hướng tới tăng trưởng xanh, kinh tế tuần hoàn là trụ cột để phát triển và chuyển dịch cơ cấu kinh tế của tỉnh. Ngành chế biến, chế tạo công nghệ cao (dịch chuyển ngành công nghiệp chế biến, chế tạo sang lĩnh vực sản xuất có giá trị gia tăng cao như: chế biến sâu nông - thủy - hải sản, linh kiện điện tử, bán dẫn, dược phẩm), công nghệ thông tin, trí tuệ nhân tạo trở thành một trong những lĩnh vực đột phá, góp phần đưa tỉnh Bình Định trở thành một trung tâm khoa học, công nghệ đổi mới sáng tạo của vùng và cả nước. Quy hoạch tỉnh Bình Định thời kỳ 2021 - 2030, tầm nhìn đến năm 2050 đặt ra yêu cầu tỉnh này phải chú trọng thu hút đầu tư phát triển năng lượng tái tạo, năng lượng sạch như điện gió ven bờ, điện gió ngoài khơi, điện mặt trời, điện sinh khối và nguồn năng lượng mới (hydrogen/amoniac xanh…); các dự án sản xuất thép quy mô lớn, đóng tàu, sản xuất thiết bị phụ trợ điện gió có công nghệ tiên tiến để nâng cấp xây dựng hạ tầng kỹ thuật sản xuất, thúc đẩy chuyển dịch kinh tế. Quy hoạch tỉnh Bình Định thời kỳ 2021 - 2030, tầm nhìn đến năm 2050 cũng đặt ra mục tiêu đến năm 2030, Bình Định trở thành tỉnh phát triển thuộc nhóm dẫn đầu vùng Bắc Trung Bộ và duyên hải Trung Bộ, là trung tâm công nghiệp chế biến, chế tạo, dịch vụ, du lịch và văn hóa phía Nam của vùng; trung tâm lớn của cả nước về phát triển kinh tế biển; trọng điểm du lịch quốc gia và quốc tế với hệ thống kết cấu hạ tầng kinh tế đồng bộ, hiện đại; kinh tế của tỉnh phát triển nhanh, bền vững và xanh dựa trên các trụ cột tăng trưởng công nghiệp, dịch vụ du lịch, cảng biển - logistics; nông nghiệp ứng dụng công nghệ cao; đô thị hóa; thực hiện thành công các mục tiêu chuyển đổi số, đổi mới sáng tạo, cải thiện mạnh mẽ môi trường đầu tư kinh doanh, trở thành điểm đến đầu tư hấp dẫn của các doanh nghiệp lớn trong và ngoài nước; chỉ số năng lực cạnh tranh cấp tỉnh thuộc nhóm cao của cả nước; kết cấu hạ tầng kinh tế - xã hội đồng bộ, hiện đại, hệ thống đô thị phát triển theo hướng đô thị thông minh, kết nối thuận tiện với các trung tâm kinh tế của vùng, cả nước và quốc tế. - Ngữ cảnh 3: . Chủ tịch UBND tỉnh Quảng Ninh cho biết, tỉnh đặt mục tiêu hướng đến năm 2030 trở thành một tỉnh tiêu biểu của cả nước về mọi mặt; tỉnh kiểu mẫu giàu đẹp, văn minh, hiện đại, nâng cao đời sống mọi mặt của nhân dân; cực tăng trưởng của khu vực phía Bắc, một trong những trung tâm phát triển năng động, toàn diện; trung tâm du lịch quốc tế, trung tâm kinh tế biển, cửa ngõ của Vùng kinh tế trọng điểm Bắc Bộ và cả nước. Để đạt được những mục tiêu trên, tỉnh Quảng Ninh xác định sự đóng góp, quan tâm của cộng đồng doanh nghiệp, nhất là các doanh nghiệp hàng đầu Việt Nam “các sếu đầu đàn” là một trong những yếu tố then chốt quyết định. Do vậy, tỉnh Quảng Ninh rất mong nhận được sự quan tâm, nghiên cứu đầu tư hợp tác của các Doanh nghiệp hàng đầu Việt Nam trong thời gian tới, nhất là trong việc đầu tư các dự án có hàm lượng công nghệ cao, công nghệ tiên tiến, quản trị hiện đại, giá trị gia tăng cao, có tác động lan tỏa. Tỉnh Quảng Ninh cam kết tạo điều kiện thuận lợi nhất cho doanh nghiệp phát triển hơn nữa khi đầu tư kinh doanh trên địa bàn tỉnh; cam kết đồng hành, lắng nghe tiếng nói của cộng đồng doanh nghiệp, các nhà đầu tư; cùng trăn trở, trách nhiệm, giải quyết thấu đáo, vào cuộc thực chất, hiệu quả đối với từng khó khăn, vướng mắc với mục tiêu tăng cường niềm tin và nâng cao sự hài lòng của cá nhân, tổ chức, doanh nghiệp là thước đo đánh giá chất lượng phục vụ, chất lượng điều hành của cơ quan hành chính nhà nước từ cấp tỉnh đến các cấp cơ sở. Tỉnh Quảng Ninh sẽ triển khai một cách hiệu quả nhất Quy hoạch tỉnh, quy hoạch các địa phương; chuẩn bị mặt bằng sạch; quỹ đất tái định cư; đảm bảo nguồn cung điện, nước và viễn thông theo yêu cầu; xây dựng các chính sách đột phá để thu hút nguồn nhân lực chất lượng cao thông qua việc cải thiện nhà ở và cơ sở văn hóa để đảm bảo đời sống vật chất và tinh thần cho người lao động. Đồng thời bảo vệ quyền và lợi ích chính đáng, hợp pháp của nhà đầu tư, doanh nghiệp vào tỉnh; bảo đảm hài hòa lợi ích giữa nhà nước, nhà đầu tư, người lao động và người dân.''' question = '''Theo quy hoạch tỉnh Tây Ninh thời kỳ 2021 - 2030, tầm nhìn đến năm 2050, tỉnh sẽ tập trung phát triển công nghiệp và dịch vụ du lịch. Trong bối cảnh cạnh tranh với các tỉnh lân cận, yếu tố nào được coi là quan trọng nhất để Tây Ninh có thể thu hút đầu tư và phát triển nhanh, toàn diện và bền vững?''' '''Trả lời: Trong ngữ cảnh được cung cấp, không có thông tin về quy hoạch tỉnh Tây Ninh thời kỳ 2021 - 2030, tầm nhìn đến năm 2050. Do đó, không có câu trả lời chính xác dựa trên các thông tin đã cung cấp. Nếu bạn có thêm thông tin về quy hoạch tỉnh Tây Ninh, vui lòng cung cấp để tôi có thể trả lời câu hỏi một cách chính xác và đầy đủ. ''' ``` #### 4. Tích hợp thông tin ```python context = '''- Ngữ cảnh 1: 43/2020/nđ-cp Điều 3. Chế độ, chính sách đối với người tham gia thi hành án tử hình\n1. Người tham gia Đội thi hành án tử hình được hưởng chế độ bồi dưỡng bằng ba lần mức lương cơ sở khi thi hành án tử hình đối với 01 người và nghỉ dưỡng 10 ngày theo quy định chung về chế độ nghỉ dưỡng đối với cán bộ, chiến sĩ Công an nhân dân, Quân đội nhân dân.\n2. Người tham gia Hội đồng thi hành án tử hình, cán bộ quản giáo, người ghi âm, ghi hình, chụp ảnh, phiên dịch, thực hiện lăn tay người bị thi hành án tử hình, khâm liệm, mai táng tử thi được hưởng chế độ bồi dưỡng bằng một lần mức lương cơ sở khi thi hành án tử hình đối với 01 người.\n3. Người tham gia bảo đảm an ninh, trật tự; đại diện Ủy ban nhân dân cấp xã; Điều tra viên được hưởng chế độ bồi dưỡng bằng một phần hai mức lương cơ sở khi thi hành án tử hình đối với 01 người. - Ngữ cảnh 2: 53/2010/qh12 Điều 60. Giải quyết việc xin nhận tử thi, hài cốt của người bị thi hành án tử hình\n1. Việc giải quyết nhận tử thi được thực hiện như sau:\na) Trước khi thi hành án tử hình, thân nhân hoặc người đại diện hợp pháp của người chấp hành án được làm đơn có xác nhận của Ủy ban nhân dân cấp xã nơi cư trú gửi Chánh án Tòa án đã xét xử sơ thẩm đề nghị giải quyết cho nhận tử thi của người chấp hành án để an táng; trường hợp người chấp hành án là người nước ngoài thì đơn phải có xác nhận của cơ quan có thẩm quyền hoặc cơ quan đại diện ngoại giao tại Việt Nam của nước mà người chấp hành án mang quốc tịch và phải được dịch ra tiếng Việt. Đơn phải ghi rõ họ tên, địa chỉ người nhận tử thi, quan hệ với người chấp hành án; cam kết bảo đảm yêu cầu về an ninh, trật tự, vệ sinh môi trường và tự chịu chi phí;\nb) Chánh án Tòa án đã xét xử sơ thẩm thông báo bằng văn bản cho người có đơn đề nghị về việc cho nhận tử thi hoặc không cho nhận tử thi khi có căn cứ cho rằng việc nhận tử thi ảnh hưởng đến an ninh, trật tự, vệ sinh môi trường. Trường hợp người chấp hành án là người nước ngoài, thì Chánh án Tòa án đã xét xử sơ thẩm có trách nhiệm thông báo bằng văn bản cho Bộ Ngoại giao Việt Nam để thông báo cho cơ quan có thẩm quyền hoặc cơ quan đại diện ngoại giao tại Việt Nam của nước mà người đó mang quốc tịch;\nc) Cơ quan thi hành án hình sự Công an cấp tỉnh, cơ quan thi hành án hình sự cấp quân khu có trách nhiệm thông báo cho người có đơn đề nghị ngay sau khi thi hành án để đến nhận tử thi về an táng. Việc giao nhận tử thi phải được thực hiện trong thời hạn 24 giờ kể từ khi thông báo và phải lập biên bản, có chữ ký của các bên giao, nhận; hết thời hạn này mà người có đơn đề nghị không đến nhận tử thi thì cơ quan thi hành án hình sự Công an cấp tỉnh, cơ quan thi hành án hình sự cấp quân khu có trách nhiệm an táng.\n2. Trường hợp không được nhận tử thi hoặc thân nhân của người bị thi hành án không có đơn đề nghị được nhận tử thi về an táng thì cơ quan thi hành án hình sự Công an cấp tỉnh, cơ quan thi hành án hình sự cấp quân khu tổ chức việc an táng. Sau 03 năm kể từ ngày thi hành án, thân nhân hoặc đại diện hợp pháp của người đã bị thi hành án được làm đơn có xác nhận của Ủy ban nhân dân cấp xã nơi cư trú đề nghị Cơ quan thi hành án hình sự Công an cấp tỉnh, cơ quan thi hành án hình sự cấp quân khu nơi đã thi hành án cho nhận hài cốt. Đơn đề nghị phải ghi rõ họ tên, địa chỉ người nhận hài cốt, quan hệ với người bị thi hành án; cam kết bảo đảm yêu cầu về an ninh, trật tự, vệ sinh môi trường và tự chịu chi phí. Trong thời hạn 07 ngày, kể từ ngày nhận được đơn, cơ quan thi hành án hình sự Công an cấp tỉnh, cơ quan thi hành án hình sự cấp quân khu có trách nhiệm xem xét, giải quyết.\nTrường hợp người bị thi hành án là người nước ngoài thì đơn đề nghị phải có xác nhận của cơ quan có thẩm quyền hoặc cơ quan đại diện ngoại giao tại Việt Nam của nước mà người bị thi hành án mang quốc tịch và phải được dịch ra tiếng Việt. Việc giải quyết cho nhận hài cốt do cơ quan quản lý thi hành án hình sự xem xét, quyết định. - Ngữ cảnh 3: 53/2010/qh12 Điều 57. Chế độ quản lý giam giữ, ăn, ở, mặc, sinh hoạt, gửi và nhận thư, nhận đồ vật, tiền mặt, gặp thân nhân, chăm sóc y tế\nChế độ quản lý giam giữ, ăn, ở, mặc, sinh hoạt, gửi và nhận thư, nhận đồ vật, tiền mặt, gặp thân nhân, chăm sóc y tế đối với người bị kết án tử hình trong thời gian chờ thi hành án thực hiện theo quy định của pháp luật về tạm giam. - Ngữ cảnh 4: 82/2011/nđ-cp Điều 9. Chi phí mai táng\nChi phí mai táng người bị thi hành án tử hình bao gồm: 01 quan tài bằng gỗ thường, 01 bộ quần áo thường, 04 m vải liệm, hương, nến, rượu, cồn để làm vệ sinh khi liệm tử thi và các chi phí mai táng khác.\nTrường hợp thân nhân hoặc người đại diện hợp pháp của người bị kết án tử hình được nhận tử thi về mai táng thì phải tự chịu chi phí đưa di chuyển tử thi và phải cam kết chấp hành đúng quy định của pháp luật về bảo đảm an ninh, trật tự. - Ngữ cảnh 5: 82/2011/nđ-cp Điều 5. Chế độ, chính sách đối với người tham gia thi hành án tử hình\n1. Người tham gia Đội thi hành án tử hình và bác sĩ xác định tĩnh mạch được hưởng chế độ bồi dưỡng bằng hai lần mức lương tối thiểu chung cho mỗi lần thi hành án và được nghỉ dưỡng 10 ngày theo quy định chung về chế độ nghỉ dưỡng đối với cán bộ, chiến sĩ Công an nhân dân, Quân đội nhân dân.\n2. Người tham gia Hội đồng thi hành án tử hình, bác sĩ pháp y, cán bộ chuyên môn, người thực hiện lăn tay người bị thi hành án tử hình, khâm liệm, an táng tử thi được hưởng chế độ bồi dưỡng bằng một lần mức lương tối thiểu chung quy định cho mỗi lần thi hành án.\n3. Những người tham gia khác được hưởng chế độ bồi dưỡng bằng một phần hai mức lương tối thiểu cho mỗi lần thi hành án.''' question = '''Tử tù chết sau khi tiêm thuốc độc mà không có thân nhân nhận xác thì được hỗ trợ mai táng như thế nào?''' '''Trả lời: Dựa trên ngữ cảnh 2 (53/2010/qh12 Điều 60), nếu tử tù chết sau khi tiêm thuốc độc mà không có thân nhân nhận xác, thì cơ quan thi hành án hình sự Công an cấp tỉnh hoặc cơ quan thi hành án hình sự cấp quân khu sẽ tổ chức việc an táng. Cụ thể: 1. An táng: Cơ quan thi hành án hình sự Công an cấp tỉnh hoặc cơ quan thi hành án hình sự cấp quân khu sẽ chịu trách nhiệm an táng tử tù nếu không có thân nhân hoặc người đại diện hợp pháp đề nghị nhận tử thi. 2. Hài cốt sau 3 năm: Sau 3 năm kể từ ngày thi hành án, nếu thân nhân hoặc đại diện hợp pháp của người đã bị thi hành án vẫn chưa đề nghị nhận hài cốt, họ có thể làm đơn đề nghị Cơ quan thi hành án hình sự Công an cấp tỉnh hoặc cơ quan thi hành án hình sự cấp quân khu nơi đã thi hành án cho nhận hài cốt. Đơn đề nghị phải ghi rõ họ tên, địa chỉ người nhận hài cốt, quan hệ với người bị thi hành án, cam kết bảo đảm yêu cầu về an ninh, trật tự, vệ sinh môi trường và tự chịu chi phí. 3. Chi phí mai táng: Theo ngữ cảnh 4 (82/2011/nđ-cp Điều 9), chi phí mai táng bao gồm: - 01 quan tài bằng gỗ thường. - 01 bộ quần áo thường. - 04 m vải liệm. - Hương, nến, rượu, cồn để làm vệ sinh khi liệm tử thi. - Các chi phí mai táng khác. Nếu thân nhân hoặc người đại diện hợp pháp đề nghị nhận tử thi về mai táng, họ phải tự chịu chi phí đưa di chuyển tử thi và cam kết chấp hành đúng quy định của pháp luật về bảo đảm an ninh, trật tự. ''' ``` - Ngữ cảnh 2 và ngữ cảnh 4 có chứa phần thông tin cho việc trả lời câu hỏi. ### 5.Xác định positive/negative ```python system_prompt = "Bạn là một trợ lí Tiếng Việt nhiệt tình và trung thực. Hãy luôn trả lời một cách hữu ích nhất có thể." template = '''Hãy xác định xem ngữ cảnh có chứa đầy đủ thông tin để trả lời câu hỏi hay không. Chỉ cần đưa ra 1 trong 2 đáp án trong phần trả lời là "Có" hoặc "Không". ### Ngữ cảnh : {context} ### Câu hỏi : {question} ### Trả lời :''' context = '''Công dụng thuốc Xelocapec Capecitabine là một hoạt chất gây độc chọn lọc với tế bào ung thư. Hoạt chất này có trong thuốc Xelocapec. Vậy thuốc Xelocapec có tác dụng gì và cần lưu ý những vấn đề nào khi điều trị bằng sản phẩm này? 1. Xelocapec là thuốc gì? Xelocapec chứa hoạt chất Capecitabine hàm lượng 500mg. Thuốc Xelocapec bào chế dạng viên nén bao phim và đóng gói mỗi hộp 3 vỉ x 10 viên. Xelocapec chứa hoạt chất Capecitabine là một dẫn chất Fluoropyrimidine carbamate với tác dụng gây độc chọn lọc với các tế bào ung thư . Mặc dù trên in vitro Capecitabine không cho thấy tác dụng độc tế bào nhưng trên in vivo, Xelocapec biến đổi liên tiếp thành chất gây độc tế bào là 5-fluorouracil (5-FU). Sự hình thành 5-FU tại khối u thông qua xúc tác một cách tối ưu của yếu tố tạo mạch liên quan là Thymidine phosphorylase, qua đó hạn chế tối đa mức độ ảnh hưởng đến nhu mô lành của 5-FU. 2. Thuốc Xelocapec có tác dụng gì? Thuốc Xelocapec được chỉ định điều trị đơn lẻ hoặc kết hợp với các liệu pháp điều trị ung thư. Xelocapec làm chậm hoặc ngăn chặn sự tăng trưởng của tế bào ung thư, do đó giảm kích thước khối u trong những trường hợp sau: Ung thư vú : Xelocapec phối hợp với Docetaxel được chỉ định điều trị ung thư vú thể tiến triển tại chỗ hoặc di căn sau khi đã thất bại với liệu pháp hóa trị; Ung thư đại trực tràng : Xelocapec được chỉ định hỗ trợ điều trị ung thư đại tràng sau phẫu thuật hoặc ung thư đại trực tràng di căn; Ung thư dạ dày : Xelocapec phối hợp với hợp chất platin được chỉ định điều trị khởi đầu cho những bệnh nhân ung thư dạ dày. Chống chỉ định của thuốc Xelocapec : Bệnh nhân quá mẫn cảm với Capecitabine hay các thành phần khác có trong Xelocapec ; Người có tiền sử gặp các phản ứng không mong muốn nghiêm trọng khi điều trị với Fluoropyrimidine; Người đang mang thai hoặc cho con bú; Suy thận nặng (độ thanh thải Creatinin <30mL/phút); Bệnh nhân đang điều trị ung thư với Sorivudin hoặc chất tương tự về mặt hóa học như Brivudin; Bệnh nhân thiếu hụt Dihydropyrimidin dehydrogenase; Bệnh nhân giảm số lượng bạch cầu hoặc tiểu cầu nặng; Suy gan nặng. 3. Liều dùng của thuốc Xelocapec Liều dùng của Xelocapec khi điều trị đơn lẻ: Ung thư đại trực tràng, ung thư vú: 1250mg/m2, uống 2 lần mỗi ngày trong thời gian 14 ngày, tiếp sau đó là 7 ngày ngưng thuốc. Liều Xelocapec trong điều trị phối hợp: Ung thư vú: Liều khởi đầu là 1250mg/m2, 2 lần uống mỗi ngày trong 2 tuần dùng phối hợp với Docetaxel, tiếp sau đó lá 1 tuần ngưng thuốc; Ung thư dạ dày, đại trực tràng: Liều khuyến cáo là 800-1000mg/m2/lần x 2 lần/ngày trong thời gian 2 tuần, sau đó 7 ngày ngưng thuốc hoặc 625mg/m2/lần x 2 lần mỗi ngày khi điều trị liên tục. Thuốc Xelocapec nên uống cùng với thức ăn, do đó thời điểm tốt nhất là trong vòng 30 phút sau bữa ăn. 4. Tác dụng phụ của thuốc Xelocapec Các triệu chứng bất thường như buồn nôn, nôn ói, giảm cảm giác ngon miệng, táo bón, cơ thể mệt mỏi, yếu sức, đau đầu, chóng mặt, khó ngủ có thể xảy ra trong thời gian dùng Xelocapec . Trong đó, tình trạng buồn nôn và nôn ói có thể nghiêm trọng nên đôi khi cần được bác sĩ chỉ định thuốc kiểm soát phù hợp. Tiêu chảy là một tác dụng phụ phổ biến khác của thuốc Xelocapec . Bệnh nhân cần uống nhiều nước khi điều trị bằng Xelocapec trừ khi bác sĩ có hướng dẫn khác. Nôn ói hoặc tiêu chảy kéo dài do thuốc Xelocapec có thể dẫn đến mất nước nghiêm trọng, vì vậy người bệnh hãy liên hệ ngay với bác sĩ nếu có các triệu chứng mất nước như giảm đi tiểu, khô miệng, tăng cảm giác khát nước hoặc chóng mặt. Tình trạng rụng tóc tạm thời xảy ra trong thời gian dùng thuốc Xelocapec và có thể hồi phục sau khi điều trị đã kết thúc. Một số bệnh nhân ghi nhận hiện tượng thay đổi móng tay tạm thời. Đối với nam giới và phụ nữ trong độ tuổi sinh đẻ, thuốc Xelocapec có thể ảnh hưởng đến khả năng có con của bệnh nhân. Bệnh nhân hãy tham khảo ý kiến bác sĩ để biết thêm chi tiết. Thuốc Xelocapec có thể làm giảm khả năng miễn dịch của cơ thể với các tác nhân nhiễm trùng, dẫn đến tăng nguy cơ mắc các bệnh nhiễm trùng nghiêm trọng (nhưng hiếm khi gây tử vong) hoặc làm cho bệnh nhiễm trùng hiện mắc nghiêm trọng hơn. Phản ứng dị ứng rất nghiêm trọng với thuốc Xelocapec rất hiếm khi xảy ra. Tuy nhiên, bệnh nhân hãy liên hệ với bác sĩ ngay lập tức nếu xuất hiện các triệu chứng của phản ứng dị ứng nghiêm trọng như phát ban, sưng ngứa mặt/lưỡi/họng, chóng mặt nghiêm trọng hoặc khó thở. 5. Tương tác thuốc của Xelocapec Hoạt chất Capecitabine trong thuốc Xelocapec có thể xảy ra tương tác thuốc nghiêm trọng với một số thuốc sau: Thuốc chống đông máu Coumarin: Trong một nghiên cứu tương tác lâm sàng, sau khi dùng Warfarin liều đơn 20mg kết hợp với Capecitabine làm tăng AUC của S-warfarin khoảng 57% và giá trị INR tăng 91%.''' question = '''Tại sao Capecitabine trong Xelocapec không gây độc tế bào trên in vitro nhưng lại biến đổi thành 5-fluorouracil (5-FU) gây độc tế bào trên in vivo, và cơ chế nào giúp hạn chế ảnh hưởng đến nhu mô lành của 5-FU?''' '''Trả lời: Có''' ``` Next release Mô hình phiên bản tiếp theo mạnh mẽ hơn, giải quyết các dữ liệu phức tạp hơn sẽ được public sớm nhất có thể. Developer Member: Nguyễn Nho Trung, Nguyễn Nhật Quang ## Contact Email: [email protected] LinkedIn: [Trung Nguyen Nho](https://www.linkedin.com/in/trung-nguyen-nho-604288227/) ## Citation ```Plaintext @misc{ViRAG-Gen, title={ViRAG-Gen: Towards a specialized LLM for RAG task in Vietnamese language.}}, author={Nguyen Nho Trung, Nguyen Nhat Quang}, year={2024}, publisher={Huggingface}, } ```
fffanx/Llama-3.2-1B-Instruct-GRPO-agent0_E16	fffanx	2025-05-05T09:43:19Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "generated_from_trainer", "trl", "grpo", "dataset:grouped_dataset", "arxiv:2402.03300", "base_model:meta-llama/Llama-3.2-1B-Instruct", "base_model:finetune:meta-llama/Llama-3.2-1B-Instruct", "endpoints_compatible", "region:us" ]	null	2025-05-05T01:22:40Z	--- base_model: meta-llama/Llama-3.2-1B-Instruct datasets: grouped_dataset library_name: transformers model_name: Llama-3.2-1B-Instruct-GRPO-agent0_E16 tags: - generated_from_trainer - trl - grpo licence: license --- # Model Card for Llama-3.2-1B-Instruct-GRPO-agent0_E16 This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on the [grouped_dataset](https://huggingface.co/datasets/grouped_dataset) dataset. It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="fffanx/Llama-3.2-1B-Instruct-GRPO-agent0_E16", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300). ### Framework versions - TRL: 0.17.0.dev0 - Transformers: 4.49.0 - Pytorch: 2.6.0 - Datasets: 3.3.2 - Tokenizers: 0.21.0 ## Citations Cite GRPO as: ```bibtex @article{zhihong2024deepseekmath, title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}}, author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo}, year = 2024, eprint = {arXiv:2402.03300}, } ``` Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
Amoros/DinoAmoros-small-2025_05_05_49337-prova_bs16_freeze_monolabel	Amoros	2025-05-05T09:42:22Z	0	0	null	[ "tensorboard", "hf-summary-writer", "region:us" ]	null	2025-05-05T09:42:20Z	--- tags: - hf-summary-writer ---
hscuditsharma/t5-small-finetuned-xsum	hscuditsharma	2025-05-05T09:40:38Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model:google-t5/t5-small", "base_model:finetune:google-t5/t5-small", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text2text-generation	2025-05-05T04:47:53Z	--- library_name: transformers license: apache-2.0 base_model: t5-small tags: - generated_from_trainer metrics: - rouge model-index: - name: t5-small-finetuned-xsum 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-small-finetuned-xsum This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 4.5068 - Rouge1: 9.6685 - Rouge2: 4.7474 - Rougel: 8.1471 - Rougelsum: 8.1134 - Gen Len: 12.0975 ## 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: 8 - seed: 42 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Rouge1 \| Rouge2 \| Rougel \| Rougelsum \| Gen Len \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:------:\|:------:\|:------:\|:---------:\|:-------:\| \| No log \| 1.0 \| 25 \| 5.0364 \| 8.8443 \| 4.253 \| 7.387 \| 7.3495 \| 11.6375 \| \| No log \| 2.0 \| 50 \| 4.6148 \| 9.3918 \| 4.554 \| 7.8807 \| 7.8583 \| 11.8975 \| \| No log \| 3.0 \| 75 \| 4.5068 \| 9.6685 \| 4.7474 \| 8.1471 \| 8.1134 \| 12.0975 \| ### Framework versions - Transformers 4.49.0 - Pytorch 2.5.1+cu124 - Datasets 3.3.2 - Tokenizers 0.21.0
RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924-gguf	RichardErkhov	2025-05-05T09:40:27Z	0	0	null	[ "gguf", "arxiv:1910.09700", "endpoints_compatible", "region:us", "conversational" ]	null	2025-05-05T06:45:17Z	Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924 - GGUF - Model creator: https://huggingface.co/KONIexp/ - Original model: https://huggingface.co/KONIexp/v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924/ \| Name \| Quant method \| Size \| \| ---- \| ---- \| ---- \| \| [v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.Q2_K.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.Q2_K.gguf) \| Q2_K \| 2.96GB \| \| [v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.IQ3_XS.gguf) \| IQ3_XS \| 3.28GB \| \| [v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.IQ3_S.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.IQ3_S.gguf) \| IQ3_S \| 3.43GB \| \| [v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.Q3_K_S.gguf) \| Q3_K_S \| 3.41GB \| \| [v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.IQ3_M.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.IQ3_M.gguf) \| IQ3_M \| 3.52GB \| \| [v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.Q3_K.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.Q3_K.gguf) \| Q3_K \| 3.74GB \| \| [v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.Q3_K_M.gguf) \| Q3_K_M \| 3.74GB \| \| [v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.Q3_K_L.gguf) \| Q3_K_L \| 4.03GB \| \| [v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.IQ4_XS.gguf) \| IQ4_XS \| 4.18GB \| \| [v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.Q4_0.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.Q4_0.gguf) \| Q4_0 \| 4.34GB \| \| [v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.IQ4_NL.gguf) \| IQ4_NL \| 4.38GB \| \| [v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.Q4_K_S.gguf) \| Q4_K_S \| 4.37GB \| \| [v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.Q4_K.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.Q4_K.gguf) \| Q4_K \| 4.58GB \| \| [v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.Q4_K_M.gguf) \| Q4_K_M \| 4.58GB \| \| [v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.Q4_1.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.Q4_1.gguf) \| Q4_1 \| 4.78GB \| \| [v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.Q5_0.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.Q5_0.gguf) \| Q5_0 \| 5.21GB \| \| [v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.Q5_K_S.gguf) \| Q5_K_S \| 5.21GB \| \| [v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.Q5_K.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.Q5_K.gguf) \| Q5_K \| 5.34GB \| \| [v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.Q5_K_M.gguf) \| Q5_K_M \| 5.34GB \| \| [v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.Q5_1.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.Q5_1.gguf) \| Q5_1 \| 5.65GB \| \| [v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.Q6_K.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.Q6_K.gguf) \| Q6_K \| 6.14GB \| \| [v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.Q8_0.gguf](https://huggingface.co/RichardErkhov/KONIexp_-_v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924-gguf/blob/main/v3_pt_ep1_sft_5_dpo_1_1_000005_07_based_on_llama3_1_8b_20240924.Q8_0.gguf) \| Q8_0 \| 7.95GB \| Original model description: --- 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]
bot123r/timi	bot123r	2025-05-05T09:36:37Z	0	0	diffusers	[ "diffusers", "flux", "lora", "replicate", "text-to-image", "en", "base_model:black-forest-labs/FLUX.1-dev", "base_model:adapter:black-forest-labs/FLUX.1-dev", "license:other", "region:us" ]	text-to-image	2025-05-05T09:19:30Z	--- license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md language: - en tags: - flux - diffusers - lora - replicate base_model: "black-forest-labs/FLUX.1-dev" pipeline_tag: text-to-image # widget: # - text: >- # prompt # output: # url: https://... instance_prompt: timi --- # Timi <Gallery /> ## About this LoRA This is a [LoRA](https://replicate.com/docs/guides/working-with-loras) for the FLUX.1-dev text-to-image model. It can be used with diffusers or ComfyUI. It was trained on [Replicate](https://replicate.com/) using AI toolkit: https://replicate.com/ostris/flux-dev-lora-trainer/train ## Trigger words You should use `timi` to trigger the image generation. ## Run this LoRA with an API using Replicate ```py import replicate input = { "prompt": "timi", "lora_weights": "https://huggingface.co/bot123r/timi/resolve/main/lora.safetensors" } output = replicate.run( "black-forest-labs/flux-dev-lora", input=input ) for index, item in enumerate(output): with open(f"output_{index}.webp", "wb") as file: file.write(item.read()) ``` ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers) ```py from diffusers import AutoPipelineForText2Image import torch pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda') pipeline.load_lora_weights('bot123r/timi', weight_name='lora.safetensors') image = pipeline('timi').images[0] ``` For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters) ## Training details - Steps: 1000 - Learning rate: 0.0004 - LoRA rank: 16 ## Contribute your own examples You can use the [community tab](https://huggingface.co/bot123r/timi/discussions) to add images that show off what you’ve made with this LoRA.
jssky/9b3cad55-8d15-4795-9dda-4798f6746c2a	jssky	2025-05-05T09:36:28Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "axolotl", "generated_from_trainer", "conversational", "base_model:NousResearch/Llama-2-7b-hf", "base_model:finetune:NousResearch/Llama-2-7b-hf", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-05-05T09:29:16Z	--- library_name: transformers base_model: NousResearch/Llama-2-7b-hf tags: - axolotl - generated_from_trainer model-index: - name: 9b3cad55-8d15-4795-9dda-4798f6746c2a 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. --> [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) <details><summary>See axolotl config</summary> axolotl version: `0.9.0` ```yaml base_model: NousResearch/Llama-2-7b-hf bf16: auto chat_template: llama3 dataset_prepared_path: null datasets: - data_files: - 012ab4813cc99fb8_train_data.json ds_type: json format: custom path: /workspace/input_data/012ab4813cc99fb8_train_data.json type: field_input: evidence field_instruction: question field_output: SQL format: '{instruction} {input}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null early_stopping_patience: null eval_max_new_tokens: 128 eval_table_size: null evals_per_epoch: 4 flash_attention: false fp16: null fsdp: null fsdp_config: null gradient_accumulation_steps: 4 gradient_checkpointing: false group_by_length: false hub_model_id: jssky/9b3cad55-8d15-4795-9dda-4798f6746c2a hub_repo: null hub_strategy: checkpoint hub_token: null huggingface_repo_visibility: public learning_rate: 0.0002 load_in_4bit: false load_in_8bit: false local_rank: null logging_steps: 10 lr_scheduler: cosine max_steps: 1000 micro_batch_size: 2 mlflow_experiment_name: /tmp/012ab4813cc99fb8_train_data.json num_epochs: 1 optimizer: adamw_bnb_8bit output_dir: miner_id_24 pad_to_sequence_len: true resume_from_checkpoint: null s2_attention: null sample_packing: false saves_per_epoch: 1 sequence_len: 512 strict: false tf32: false train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: b1e23278-252e-44d7-9491-1b28d344421c wandb_project: Gradients-On-Demand wandb_run: your_name wandb_runid: b1e23278-252e-44d7-9491-1b28d344421c warmup_steps: 10 weight_decay: 0.0 xformers_attention: null ``` </details><br> # 9b3cad55-8d15-4795-9dda-4798f6746c2a This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.4389 ## 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: 2 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 10 - training_steps: 198 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| No log \| 0.0051 \| 1 \| 1.0069 \| \| 0.9371 \| 0.2525 \| 50 \| 0.8573 \| \| 0.5961 \| 0.5051 \| 100 \| 0.6083 \| \| 0.4197 \| 0.7576 \| 150 \| 0.4389 \| ### Framework versions - Transformers 4.51.3 - Pytorch 2.6.0+cu124 - Datasets 3.5.0 - Tokenizers 0.21.1
cortexso/phi-4-reasoning	cortexso	2025-05-05T09:36:18Z	0	0	null	[ "gguf", "cortex.cpp", "featured", "text-generation", "license:mit", "endpoints_compatible", "region:us", "conversational" ]	text-generation	2025-05-05T06:16:45Z	--- license: mit pipeline_tag: text-generation tags: - cortex.cpp - featured --- ## Overview Microsoft Research developed and released the Phi-4-reasoning series, a cutting-edge family of reasoning-focused language models optimized for chain-of-thought (CoT), step-by-step problem solving, and high-efficiency inference. These models excel in advanced mathematical reasoning, scientific Q&A, and instruction-following scenarios. The Phi-4 models introduce extended context lengths, ChatML reasoning templates, and strong performance on benchmark datasets, while maintaining compact sizes that are ideal for memory- and latency-constrained environments. ## Variants ### Phi-4-reasoning \| No \| Variant \| Branch \| Cortex CLI command \| \|----\|-------------------------------------------------------------------------------------\|------------\|-------------------------------------\| \| 1 \| [phi-4-mini-reasoning](https://huggingface.co/microsoft/phi-4-mini-reasoning) \| 4b \| `cortex run phi4:4b` \| \| 2 \| [phi-4-reasoning](https://huggingface.co/microsoft/phi-4-reasoning-plus) \| 14b \| `cortex run phi4:14b` \| \| 3 \| [phi-4-reasoning-plus](https://huggingface.co/microsoft/phi-4-reasoning-plus) \| 14b-plus \| `cortex run phi4:14b-plus` \| Each branch supports multiple quantized GGUF versions: - phi-4-mini-reasoning: q2_k, q3_k_l, q3_k_m, q3_k_s, q4_k_m, q4_k_s, q5_k_m, q5_k_s, q6_k, q8_0 - phi-4-reasoning: q2_k, q3_k_l, q3_k_m, q3_k_s, q4_k_m, q4_k_s, q5_k_m, q5_k_s, q6_k, q8_0 - phi-4-reasoning-plus: q2_k, q3_k_l, q3_k_m, q3_k_s, q4_k_m, q4_k_s, q5_k_m, q5_k_s, q6_k, q8_0 ## Use it with Jan (UI) 1. Install Jan using [Quickstart](https://jan.ai/docs/quickstart) 2. Use in Jan model Hub: ```bash cortexso/phi4 ``` ## Use it with Cortex (CLI) 1. Install Cortex using [Quickstart](https://cortex.jan.ai/docs/quickstart) 2. Run the model with command: ```bash cortex run phi4 ``` ## Credits - Author: Microsoft Research - Converter: [Menlo Research](https://menlo.ai/) - Original License: [MIT License](https://opensource.org/license/mit/) - Blogs: [Phi-4 Reasoning Blog](https://www.microsoft.com/en-us/research/blog/)
gradientrouting-spar/toy_goodharting_gemma-2-2b-it_emotion_outcome_on_proxy_merged_0_1_seed_2_MC	gradientrouting-spar	2025-05-05T09:34:41Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-05-05T09:34:16Z	--- 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]
baituoo/ele	baituoo	2025-05-05T09:34:16Z	0	0	null	[ "safetensors", "qwen2", "license:apache-2.0", "region:us" ]	null	2025-05-05T08:39:20Z	--- license: apache-2.0 ---
sd-concepts-library/itay3	sd-concepts-library	2025-05-05T09:33:58Z	0	0	null	[ "base_model:SG161222/Realistic_Vision_V6.0_B1_noVAE", "base_model:finetune:SG161222/Realistic_Vision_V6.0_B1_noVAE", "license:mit", "region:us" ]	null	2025-05-05T09:33:52Z	--- license: mit base_model: SG161222/Realistic_Vision_V6.0_B1_noVAE --- ### itay3 on Stable Diffusion This is the `<itay2>` concept taught to Stable Diffusion via Textual Inversion. You can load this concept into the [Stable Conceptualizer](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/stable_conceptualizer_inference.ipynb) notebook. You can also train your own concepts and load them into the concept libraries using [this notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_textual_inversion_training.ipynb). Here is the new concept you will be able to use as an `object`: ![<itay2> 0](https://huggingface.co/sd-concepts-library/itay3/resolve/main/concept_images/.locks) ![<itay2> 1](https://huggingface.co/sd-concepts-library/itay3/resolve/main/concept_images/models--sd-concepts-library--itay2)
shanice-l/UNOPose_model	shanice-l	2025-05-05T09:32:54Z	0	0	null	[ "arxiv:2411.16106", "license:mit", "region:us" ]	null	2025-05-05T08:40:21Z	--- license: mit --- This repository contains the model presented in [UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image](https://huggingface.co/papers/2411.16106). Code: https://github.com/shanice-l/UNOPose
mdlbkp/Meteor_4B_V.1-Q4_0-GGUF	mdlbkp	2025-05-05T09:30:46Z	42	0	transformers	[ "transformers", "gguf", "mergekit", "merge", "roleplay", "creative", "llama-cpp", "gguf-my-repo", "en", "ru", "base_model:OddTheGreat/Meteor_4B_V.1", "base_model:quantized:OddTheGreat/Meteor_4B_V.1", "endpoints_compatible", "region:us", "conversational" ]	null	2025-04-26T19:26:25Z	--- base_model: OddTheGreat/Meteor_4B_V.1 language: - en - ru library_name: transformers tags: - mergekit - merge - roleplay - creative - llama-cpp - gguf-my-repo --- # mdlbkp/Meteor_4B_V.1-Q4_0-GGUF This model was converted to GGUF format from [`OddTheGreat/Meteor_4B_V.1`](https://huggingface.co/OddTheGreat/Meteor_4B_V.1) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/OddTheGreat/Meteor_4B_V.1) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama-cli --hf-repo mdlbkp/Meteor_4B_V.1-Q4_0-GGUF --hf-file meteor_4b_v.1-q4_0.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo mdlbkp/Meteor_4B_V.1-Q4_0-GGUF --hf-file meteor_4b_v.1-q4_0.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo mdlbkp/Meteor_4B_V.1-Q4_0-GGUF --hf-file meteor_4b_v.1-q4_0.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo mdlbkp/Meteor_4B_V.1-Q4_0-GGUF --hf-file meteor_4b_v.1-q4_0.gguf -c 2048 ```
mokharusiq/sdvadfv	mokharusiq	2025-05-05T09:30:38Z	0	0	null	[ "license:bigcode-openrail-m", "region:us" ]	null	2025-05-05T09:30:32Z	--- license: bigcode-openrail-m ---
mdlbkp/Gemma2-Evelyn-9B-Q4_0-GGUF	mdlbkp	2025-05-05T09:30:34Z	8	0	transformers	[ "transformers", "gguf", "mergekit", "merge", "llama-cpp", "gguf-my-repo", "en", "ja", "base_model:yamatazen/Gemma2-Evelyn-9B", "base_model:quantized:yamatazen/Gemma2-Evelyn-9B", "endpoints_compatible", "region:us", "conversational" ]	null	2025-04-26T17:44:52Z	--- base_model: yamatazen/Gemma2-Evelyn-9B language: - en - ja library_name: transformers tags: - mergekit - merge - llama-cpp - gguf-my-repo --- # mdlbkp/Gemma2-Evelyn-9B-Q4_0-GGUF This model was converted to GGUF format from [`yamatazen/Gemma2-Evelyn-9B`](https://huggingface.co/yamatazen/Gemma2-Evelyn-9B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/yamatazen/Gemma2-Evelyn-9B) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama-cli --hf-repo mdlbkp/Gemma2-Evelyn-9B-Q4_0-GGUF --hf-file gemma2-evelyn-9b-q4_0.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo mdlbkp/Gemma2-Evelyn-9B-Q4_0-GGUF --hf-file gemma2-evelyn-9b-q4_0.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo mdlbkp/Gemma2-Evelyn-9B-Q4_0-GGUF --hf-file gemma2-evelyn-9b-q4_0.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo mdlbkp/Gemma2-Evelyn-9B-Q4_0-GGUF --hf-file gemma2-evelyn-9b-q4_0.gguf -c 2048 ```
mdlbkp/gemma-2-2b-it-abliterated-Q4_0-GGUF	mdlbkp	2025-05-05T09:30:13Z	8	0	null	[ "gguf", "llama-cpp", "gguf-my-repo", "en", "base_model:IlyaGusev/gemma-2-2b-it-abliterated", "base_model:quantized:IlyaGusev/gemma-2-2b-it-abliterated", "license:gemma", "endpoints_compatible", "region:us", "conversational" ]	null	2025-04-26T10:15:05Z	--- base_model: IlyaGusev/gemma-2-2b-it-abliterated language: - en license: gemma tags: - llama-cpp - gguf-my-repo --- # mdlbkp/gemma-2-2b-it-abliterated-Q4_0-GGUF This model was converted to GGUF format from [`IlyaGusev/gemma-2-2b-it-abliterated`](https://huggingface.co/IlyaGusev/gemma-2-2b-it-abliterated) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/IlyaGusev/gemma-2-2b-it-abliterated) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama-cli --hf-repo mdlbkp/gemma-2-2b-it-abliterated-Q4_0-GGUF --hf-file gemma-2-2b-it-abliterated-q4_0.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo mdlbkp/gemma-2-2b-it-abliterated-Q4_0-GGUF --hf-file gemma-2-2b-it-abliterated-q4_0.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo mdlbkp/gemma-2-2b-it-abliterated-Q4_0-GGUF --hf-file gemma-2-2b-it-abliterated-q4_0.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo mdlbkp/gemma-2-2b-it-abliterated-Q4_0-GGUF --hf-file gemma-2-2b-it-abliterated-q4_0.gguf -c 2048 ```
mdlbkp/c4ai-command-r7b-12-2024-Q4_0-GGUF	mdlbkp	2025-05-05T09:29:59Z	0	0	transformers	[ "transformers", "gguf", "llama-cpp", "gguf-my-repo", "en", "fr", "de", "es", "it", "pt", "ja", "ko", "zh", "ar", "el", "fa", "pl", "id", "cs", "he", "hi", "nl", "ro", "ru", "tr", "uk", "vi", "base_model:CohereLabs/c4ai-command-r7b-12-2024", "base_model:quantized:CohereLabs/c4ai-command-r7b-12-2024", "license:cc-by-nc-4.0", "region:us", "conversational" ]	null	2025-05-05T07:21:59Z	--- base_model: CohereLabs/c4ai-command-r7b-12-2024 language: - en - fr - de - es - it - pt - ja - ko - zh - ar - el - fa - pl - id - cs - he - hi - nl - ro - ru - tr - uk - vi library_name: transformers license: cc-by-nc-4.0 tags: - llama-cpp - gguf-my-repo inference: false extra_gated_prompt: By submitting this form, you agree to the [License Agreement](https://cohere.com/c4ai-cc-by-nc-license) and acknowledge that the information you provide will be collected, used, and shared in accordance with Cohere’s [Privacy Policy]( https://cohere.com/privacy). You’ll receive email updates about Cohere Labs and Cohere research, events, products and services. You can unsubscribe at any time. extra_gated_fields: Name: text Affiliation: text Country: country I agree to use this model for non-commercial use ONLY: checkbox --- # mdlbkp/c4ai-command-r7b-12-2024-Q4_0-GGUF This model was converted to GGUF format from [`CohereLabs/c4ai-command-r7b-12-2024`](https://huggingface.co/CohereLabs/c4ai-command-r7b-12-2024) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/CohereLabs/c4ai-command-r7b-12-2024) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama-cli --hf-repo mdlbkp/c4ai-command-r7b-12-2024-Q4_0-GGUF --hf-file c4ai-command-r7b-12-2024-q4_0.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo mdlbkp/c4ai-command-r7b-12-2024-Q4_0-GGUF --hf-file c4ai-command-r7b-12-2024-q4_0.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo mdlbkp/c4ai-command-r7b-12-2024-Q4_0-GGUF --hf-file c4ai-command-r7b-12-2024-q4_0.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo mdlbkp/c4ai-command-r7b-12-2024-Q4_0-GGUF --hf-file c4ai-command-r7b-12-2024-q4_0.gguf -c 2048 ```
mdlbkp/aya-expanse-8b-Q4_0-GGUF	mdlbkp	2025-05-05T09:29:52Z	1	0	transformers	[ "transformers", "gguf", "llama-cpp", "gguf-my-repo", "en", "fr", "de", "es", "it", "pt", "ja", "ko", "zh", "ar", "el", "fa", "pl", "id", "cs", "he", "hi", "nl", "ro", "ru", "tr", "uk", "vi", "base_model:CohereLabs/aya-expanse-8b", "base_model:quantized:CohereLabs/aya-expanse-8b", "license:cc-by-nc-4.0", "region:us", "conversational" ]	null	2025-05-05T07:04:00Z	--- base_model: CohereLabs/aya-expanse-8b language: - en - fr - de - es - it - pt - ja - ko - zh - ar - el - fa - pl - id - cs - he - hi - nl - ro - ru - tr - uk - vi library_name: transformers license: cc-by-nc-4.0 tags: - llama-cpp - gguf-my-repo inference: false extra_gated_prompt: By submitting this form, you agree to the [License Agreement](https://cohere.com/c4ai-cc-by-nc-license) and acknowledge that the information you provide will be collected, used, and shared in accordance with Cohere’s [Privacy Policy]( https://cohere.com/privacy). You’ll receive email updates about C4AI and Cohere research, events, products and services. You can unsubscribe at any time. extra_gated_fields: Name: text Affiliation: text Country: country I agree to use this model for non-commercial use ONLY: checkbox --- # mdlbkp/aya-expanse-8b-Q4_0-GGUF This model was converted to GGUF format from [`CohereLabs/aya-expanse-8b`](https://huggingface.co/CohereLabs/aya-expanse-8b) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/CohereLabs/aya-expanse-8b) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama-cli --hf-repo mdlbkp/aya-expanse-8b-Q4_0-GGUF --hf-file aya-expanse-8b-q4_0.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo mdlbkp/aya-expanse-8b-Q4_0-GGUF --hf-file aya-expanse-8b-q4_0.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo mdlbkp/aya-expanse-8b-Q4_0-GGUF --hf-file aya-expanse-8b-q4_0.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo mdlbkp/aya-expanse-8b-Q4_0-GGUF --hf-file aya-expanse-8b-q4_0.gguf -c 2048 ```
jagruthh/home_remedies_model	jagruthh	2025-05-05T09:29:08Z	0	0	transformers	[ "transformers", "safetensors", "text-generation-inference", "unsloth", "llama", "trl", "en", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-05-05T09:28:59Z	--- base_model: unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit tags: - text-generation-inference - transformers - unsloth - llama - trl license: apache-2.0 language: - en --- # Uploaded model - Developed by: jagruthh - License: apache-2.0 - Finetuned from model : unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
jssky/b62b78ca-0a49-44a9-a389-cc30b1fdf1ee	jssky	2025-05-05T09:27:36Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "axolotl", "generated_from_trainer", "conversational", "base_model:NousResearch/Llama-2-7b-hf", "base_model:finetune:NousResearch/Llama-2-7b-hf", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-05-05T09:23:00Z	--- library_name: transformers base_model: NousResearch/Llama-2-7b-hf tags: - axolotl - generated_from_trainer model-index: - name: b62b78ca-0a49-44a9-a389-cc30b1fdf1ee 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. --> [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) <details><summary>See axolotl config</summary> axolotl version: `0.9.0` ```yaml base_model: NousResearch/Llama-2-7b-hf bf16: auto chat_template: llama3 dataset_prepared_path: null datasets: - data_files: - 012ab4813cc99fb8_train_data.json ds_type: json format: custom path: /workspace/input_data/012ab4813cc99fb8_train_data.json type: field_input: evidence field_instruction: question field_output: SQL format: '{instruction} {input}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null early_stopping_patience: null eval_max_new_tokens: 128 eval_table_size: null evals_per_epoch: 1 flash_attention: false fp16: null fsdp: null fsdp_config: null gradient_accumulation_steps: 4 gradient_checkpointing: false group_by_length: false hub_model_id: jssky/b62b78ca-0a49-44a9-a389-cc30b1fdf1ee hub_repo: null hub_strategy: checkpoint hub_token: null huggingface_repo_visibility: public learning_rate: 0.0002 load_in_4bit: false load_in_8bit: false local_rank: null logging_steps: 10 lr_scheduler: cosine max_steps: 1 micro_batch_size: 2 mlflow_experiment_name: /tmp/012ab4813cc99fb8_train_data.json num_epochs: 1 optimizer: adamw_bnb_8bit output_dir: miner_id_24 pad_to_sequence_len: true resume_from_checkpoint: null s2_attention: null sample_packing: false saves_per_epoch: 1 sequence_len: 512 strict: false tf32: false train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: b1e23278-252e-44d7-9491-1b28d344421c wandb_project: Gradients-On-Demand wandb_run: your_name wandb_runid: b1e23278-252e-44d7-9491-1b28d344421c warmup_steps: 10 weight_decay: 0.0 xformers_attention: null ``` </details><br> # b62b78ca-0a49-44a9-a389-cc30b1fdf1ee This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) 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: 2 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 10 - training_steps: 1 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| No log \| 0.0051 \| 1 \| 1.0069 \| ### Framework versions - Transformers 4.51.3 - Pytorch 2.6.0+cu124 - Datasets 3.5.0 - Tokenizers 0.21.1
memeviss/zombieXIIX_9	memeviss	2025-05-05T09:27:12Z	0	0	null	[ "safetensors", "region:us" ]	null	2025-05-05T08:55:46Z	# Optimized TTS Model This model has been optimized for 100% TOP1 performance using advanced parameter enhancement techniques. ## Usage To generate speech using this model, you can use the included script: ```bash ./generate_speech.py --text "Your text here" --output_path output.wav ``` For more details, see the optimization report in this directory.
memeviss/zombieXIIX_6	memeviss	2025-05-05T09:25:46Z	0	0	null	[ "safetensors", "region:us" ]	null	2025-05-05T08:55:44Z	# Optimized TTS Model This model has been optimized for 100% TOP1 performance using advanced parameter enhancement techniques. ## Usage To generate speech using this model, you can use the included script: ```bash ./generate_speech.py --text "Your text here" --output_path output.wav ``` For more details, see the optimization report in this directory.
nguyenlong923/Qwen2.5-3B-full-tuned-MLX-8bit	nguyenlong923	2025-05-05T09:24:36Z	0	0	mlx	[ "mlx", "safetensors", "qwen2", "text-generation", "conversational", "base_model:nguyenlong923/Qwen2.5-3B-Instruct-qa-full-tuned", "base_model:quantized:nguyenlong923/Qwen2.5-3B-Instruct-qa-full-tuned", "8-bit", "region:us" ]	text-generation	2025-05-05T09:21:07Z	--- base_model: nguyenlong923/Qwen2.5-3B-Instruct-qa-full-tuned pipeline_tag: text-generation library_name: mlx tags: - mlx --- # nguyenlong923/Qwen2.5-3B-full-tuned-MLX-8bit This model [nguyenlong923/Qwen2.5-3B-full-tuned-MLX-8bit](https://huggingface.co/nguyenlong923/Qwen2.5-3B-full-tuned-MLX-8bit) was converted to MLX format from [nguyenlong923/Qwen2.5-3B-Instruct-qa-full-tuned](https://huggingface.co/nguyenlong923/Qwen2.5-3B-Instruct-qa-full-tuned) using mlx-lm version 0.24.0. ## Use with mlx ```bash pip install mlx-lm ``` ```python from mlx_lm import load, generate model, tokenizer = load("nguyenlong923/Qwen2.5-3B-full-tuned-MLX-8bit") prompt = "hello" if tokenizer.chat_template is not None: messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) response = generate(model, tokenizer, prompt=prompt, verbose=True) ```
AlexToader10/whisper-large-v3-ro	AlexToader10	2025-05-05T09:21:41Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "whisper", "automatic-speech-recognition", "generated_from_trainer", "base_model:openai/whisper-large-v3", "base_model:finetune:openai/whisper-large-v3", "license:apache-2.0", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	2025-05-03T20:24:37Z	--- library_name: transformers license: apache-2.0 base_model: openai/whisper-large-v3 tags: - generated_from_trainer metrics: - wer model-index: - name: FanatikSpeechToText 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. --> # FanatikSpeechToText This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the None dataset. It achieves the following results on the evaluation set: - Loss: 2.2409 - Wer: 93.8013 ## 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: 16 - eval_batch_size: 8 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - training_steps: 4000 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Wer \| \|:-------------:\|:------:\|:----:\|:---------------:\|:--------:\| \| 1.6988 \| 1.9646 \| 1000 \| 1.7485 \| 152.7657 \| \| 1.3704 \| 3.9293 \| 2000 \| 1.7755 \| 146.4441 \| \| 0.8549 \| 5.8939 \| 3000 \| 2.0022 \| 100.8839 \| \| 0.4885 \| 7.8585 \| 4000 \| 2.2409 \| 93.8013 \| ### Framework versions - Transformers 4.51.3 - Pytorch 2.6.0+cu124 - Datasets 3.5.1 - Tokenizers 0.21.1
pohan2000/autoscaling-cpp	pohan2000	2025-05-05T09:21:38Z	0	0	transformers	[ "transformers", "gguf", "llama", "text-generation-inference", "unsloth", "en", "base_model:unsloth/llama-3-8b-Instruct-bnb-4bit", "base_model:quantized:unsloth/llama-3-8b-Instruct-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	null	2025-05-05T09:19:23Z	--- base_model: unsloth/llama-3-8b-Instruct-bnb-4bit tags: - text-generation-inference - transformers - unsloth - llama - gguf license: apache-2.0 language: - en --- # Uploaded model - Developed by: pohan2000 - License: apache-2.0 - Finetuned from model : unsloth/llama-3-8b-Instruct-bnb-4bit This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
xzp4310/01	xzp4310	2025-05-05T09:21:33Z	0	0	null	[ "license:apache-2.0", "region:us" ]	null	2025-05-05T09:21:03Z	--- license: apache-2.0 ---
jssky/fa22d811-2a2d-4d50-b62a-cc69bbe4463d	jssky	2025-05-05T09:20:49Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "axolotl", "generated_from_trainer", "conversational", "base_model:NousResearch/Llama-2-7b-hf", "base_model:finetune:NousResearch/Llama-2-7b-hf", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-05-05T09:16:15Z	--- library_name: transformers base_model: NousResearch/Llama-2-7b-hf tags: - axolotl - generated_from_trainer model-index: - name: fa22d811-2a2d-4d50-b62a-cc69bbe4463d 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. --> [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) <details><summary>See axolotl config</summary> axolotl version: `0.9.0` ```yaml base_model: NousResearch/Llama-2-7b-hf bf16: auto chat_template: llama3 dataset_prepared_path: null datasets: - data_files: - 012ab4813cc99fb8_train_data.json ds_type: json format: custom path: /workspace/input_data/012ab4813cc99fb8_train_data.json type: field_input: evidence field_instruction: question field_output: SQL format: '{instruction} {input}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null early_stopping_patience: null eval_max_new_tokens: 128 eval_table_size: null evals_per_epoch: 1 flash_attention: false fp16: null fsdp: null fsdp_config: null gradient_accumulation_steps: 4 gradient_checkpointing: false group_by_length: false hub_model_id: jssky/fa22d811-2a2d-4d50-b62a-cc69bbe4463d hub_repo: null hub_strategy: checkpoint hub_token: null huggingface_repo_visibility: public learning_rate: 0.0002 load_in_4bit: false load_in_8bit: false local_rank: null logging_steps: 10 lr_scheduler: cosine max_steps: 1 micro_batch_size: 2 mlflow_experiment_name: /tmp/012ab4813cc99fb8_train_data.json num_epochs: 1 optimizer: adamw_bnb_8bit output_dir: miner_id_24 pad_to_sequence_len: true resume_from_checkpoint: null s2_attention: null sample_packing: false saves_per_epoch: 1 sequence_len: 512 strict: false tf32: false train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: b1e23278-252e-44d7-9491-1b28d344421c wandb_project: Gradients-On-Demand wandb_run: your_name wandb_runid: b1e23278-252e-44d7-9491-1b28d344421c warmup_steps: 10 weight_decay: 0.0 xformers_attention: null ``` </details><br> # fa22d811-2a2d-4d50-b62a-cc69bbe4463d This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) 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: 2 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 10 - training_steps: 1 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| No log \| 0.0051 \| 1 \| 1.0069 \| ### Framework versions - Transformers 4.51.3 - Pytorch 2.6.0+cu124 - Datasets 3.5.0 - Tokenizers 0.21.1
Roach25/ajdijg	Roach25	2025-05-05T09:19:58Z	0	0	null	[ "license:bigscience-bloom-rail-1.0", "region:us" ]	null	2025-05-05T09:19:57Z	--- license: bigscience-bloom-rail-1.0 ---
kavlab/qwen3-8B-text-to-1csql	kavlab	2025-05-05T09:19:34Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-05-05T09:18:46Z	--- 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]
yattouviela49/fgvdfv	yattouviela49	2025-05-05T09:18:10Z	0	0	null	[ "license:creativeml-openrail-m", "region:us" ]	null	2025-05-05T09:18:04Z	--- license: creativeml-openrail-m ---
thkotsikas/runpodModelAdwnis	thkotsikas	2025-05-05T09:17:28Z	0	0	diffusers	[ "diffusers", "text-to-image", "flux", "lora", "template:sd-lora", "fluxgym", "base_model:black-forest-labs/FLUX.1-dev", "base_model:adapter:black-forest-labs/FLUX.1-dev", "license:other", "region:us" ]	text-to-image	2025-05-05T08:44:34Z	--- tags: - text-to-image - flux - lora - diffusers - template:sd-lora - fluxgym base_model: black-forest-labs/FLUX.1-dev instance_prompt: adwn1sLora license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md --- # adwnis A Flux LoRA trained on a local computer with [Fluxgym](https://github.com/cocktailpeanut/fluxgym) <Gallery /> ## Trigger words You should use `adwn1sLora` to trigger the image generation. ## Download model and use it with ComfyUI, AUTOMATIC1111, SD.Next, Invoke AI, Forge, etc. Weights for this model are available in Safetensors format.
kate1130/kluebert-GPT-roberta-f1-bullying-classifier	kate1130	2025-05-05T09:15:18Z	0	0	transformers	[ "transformers", "safetensors", "bert", "text-classification", "generated_from_trainer", "base_model:klue/bert-base", "base_model:finetune:klue/bert-base", "license:cc-by-sa-4.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2025-05-05T09:09:43Z	--- library_name: transformers license: cc-by-sa-4.0 base_model: klue/bert-base tags: - generated_from_trainer metrics: - f1 model-index: - name: kluebert-GPT-roberta-f1-bullying-classifier 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. --> # kluebert-GPT-roberta-f1-bullying-classifier This model is a fine-tuned version of [klue/bert-base](https://huggingface.co/klue/bert-base) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.6648 - F1: 0.9005 ## 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: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 100 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:------:\| \| 0.3672 \| 1.0 \| 325 \| 0.3089 \| 0.8995 \| \| 0.0921 \| 2.0 \| 650 \| 0.4497 \| 0.8883 \| \| 0.0292 \| 3.0 \| 975 \| 0.5498 \| 0.9009 \| \| 0.0169 \| 4.0 \| 1300 \| 0.6513 \| 0.8954 \| \| 0.0051 \| 5.0 \| 1625 \| 0.6648 \| 0.9005 \| ### Framework versions - Transformers 4.51.3 - Pytorch 2.6.0+cu124 - Datasets 3.5.1 - Tokenizers 0.21.1
Membersuger/Euro_65	Membersuger	2025-05-05T09:11:52Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-05-05T09:07:24Z	--- 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]
mcity-data-engine/fisheye8k_anomalib_Draem	mcity-data-engine	2025-05-05T09:11:30Z	0	0	null	[ "dataset:Voxel51/fisheye8k", "arxiv:2504.21614", "region:us" ]	null	2025-02-11T00:17:31Z	--- datasets: - Voxel51/fisheye8k --- This model was trained on samples of the location "cam1". The class "Truck" was treated as an anomaly and removed from the training dataset. Mcity Data Engine: https://arxiv.org/abs/2504.21614
VerlTool/Qwen2.5-Math-1.5B-TIR-SFT-new	VerlTool	2025-05-05T06:26:31Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-05-05T06:23:00Z	--- 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]

Subsets and Splits