Split (1)

train · 834k rows

modelId string	author string	last_modified timestamp[us, tz=UTC]	downloads int64	likes int64	library_name string	tags sequence	pipeline_tag string	createdAt timestamp[us, tz=UTC]	card string
volfan6415/nospeed3	volfan6415	2025-06-19T22:12:13Z	0	0	null	[ "safetensors", "llama", "finetuned", "region:us" ]	null	2025-06-19T22:11:00Z	--- tags: - finetuned --- # meta-llama/Llama-3.2-1B-Instruct-finetuned with Atomic ## Model Description This model was fine-tuned from `meta-llama/Llama-3.2-1B-Instruct` on the `fka/awesome-chatgpt-prompts` dataset utilizing the Atomic System from NOLA, AI. ## Training Data - Dataset name: fka/awesome-chatgpt-prompts ## Training Arguments - Batch size: 48 - Learning rate: 0.0001 - Used ATOMIC Speed: True ## Evaluation Results
mlx-community/Skywork-SWE-32B-bf16	mlx-community	2025-06-19T22:08:34Z	0	0	mlx	[ "mlx", "safetensors", "qwen2", "swe-bench", "text-generation", "conversational", "base_model:Skywork/Skywork-SWE-32B", "base_model:finetune:Skywork/Skywork-SWE-32B", "license:apache-2.0", "region:us" ]	text-generation	2025-06-19T22:07:48Z	--- tags: - swe-bench - mlx license: apache-2.0 metrics: - pass@1 library_name: mlx pipeline_tag: text-generation base_model: Skywork/Skywork-SWE-32B --- # mlx-community/Skywork-SWE-32B-bf16 This model [mlx-community/Skywork-SWE-32B-bf16](https://huggingface.co/mlx-community/Skywork-SWE-32B-bf16) was converted to MLX format from [Skywork/Skywork-SWE-32B](https://huggingface.co/Skywork/Skywork-SWE-32B) using mlx-lm version 0.25.2. ## Use with mlx ```bash pip install mlx-lm ``` ```python from mlx_lm import load, generate model, tokenizer = load("mlx-community/Skywork-SWE-32B-bf16") 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) ```
rsicproject/BERT-UCM	rsicproject	2025-06-19T22:06:48Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "bert", "fill-mask", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	2025-06-19T22:06:21Z	--- library_name: transformers tags: - generated_from_trainer model-index: - name: BERT-UCM 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. --> # BERT-UCM This model is a fine-tuned version of [](https://huggingface.co/) 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: 0.0001 - train_batch_size: 64 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.45.1 - Pytorch 2.7.1+cu126 - Datasets 3.6.0 - Tokenizers 0.20.3
kingardor/llama3.1-8B-instruct-29reports-lora128-slim	kingardor	2025-06-19T22:05:52Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "llama-factory", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-19T22:03:07Z	--- library_name: transformers tags: - llama-factory --- # 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]
rsicproject/BERT-SYDNEY	rsicproject	2025-06-19T22:01:33Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "bert", "fill-mask", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	2025-06-19T22:01:05Z	--- library_name: transformers tags: - generated_from_trainer model-index: - name: BERT-SYDNEY 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. --> # BERT-SYDNEY This model is a fine-tuned version of [](https://huggingface.co/) 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: 0.0001 - train_batch_size: 64 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.45.1 - Pytorch 2.7.1+cu126 - Datasets 3.6.0 - Tokenizers 0.20.3
katanemo/Arch-Function-Chat-1.5B	katanemo	2025-06-19T21:56:19Z	18	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "en", "base_model:Qwen/Qwen2.5-Coder-1.5B-Instruct", "base_model:finetune:Qwen/Qwen2.5-Coder-1.5B-Instruct", "license:other", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-03-28T19:58:12Z	--- license: other license_name: katanemo-research license_link: >- https://huggingface.co/katanemo/Arch-Function-Chat-1.5B/blob/main/LICENSE base_model: - Qwen/Qwen2.5-Coder-1.5B-Instruct language: - en pipeline_tag: text-generation library_name: transformers --- # katanemo/Arch-Function-Chat-1.5B ## Overview The Arch-Function-Chat collection builds upon the Katanemo's [Arch-Function](https://huggingface.co/collections/katanemo/arch-function-66f209a693ea8df14317ad68) collection by extending its capabilities beyond function calling. This new collection maintains the state-of-the-art(SOTA) function calling performance of the original collection while adding powerful new features that make it even more versatile in real-world applications. In addition to function calling capabilities, this collection now offers: - Clarify & refine: Generates natural follow-up questions to collect missing information for function calling - Interpret & respond: Provides human-friendly responses based on function execution results - Context management: Mantains context in complex multi-turn interactions Note: Arch-Function-Chat is now the primarly LLM used in then open source [Arch Gateway](https://github.com/katanemo/archgw) - An AI-native proxy for agents. For more details about the project, check out the Github [README](https://github.com/katanemo/archgw/blob/main/README.md). # Requirements The code of Arch-Function-Chat-1.5B has been in the Hugging Face `transformers` library and we advise you to install latest version: ```bash pip install transformers>=4.37.0 ``` # How to use We use the following example to illustrate how to use our model to perform function calling tasks. Please note that, our model works best with our provided prompt format. It allows us to extract JSON output that is similar to the [OpenAI's function calling](https://platform.openai.com/docs/guides/function-calling). ### Quickstart ````python import json from typing import Any, Dict, List from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "katanemo/Arch-Function-Chat-1.5B" model = AutoModelForCausalLM.from_pretrained( model_name, device_map="auto", torch_dtype="auto", trust_remote_code=True ) tokenizer = AutoTokenizer.from_pretrained(model_name) # Please use our provided prompt for best performance TASK_PROMPT = ( "You are a helpful assistant designed to assist with the user query by making one or more function calls if needed." "\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{tools}\n</tools>" "\n\nYour task is to decide which functions are needed and collect missing parameters if necessary." ) FORMAT_PROMPT = ( "\n\nBased on your analysis, provide your response in one of the following JSON formats:" '\n1. If no functions are needed:\n```json\n{"response": "Your response text here"}\n```' '\n2. If functions are needed but some required parameters are missing:\n```json\n{"required_functions": ["func_name1", "func_name2", ...], "clarification": "Text asking for missing parameters"}\n```' '\n3. If functions are needed and all required parameters are available:\n```json\n{"tool_calls": [{"name": "func_name1", "arguments": {"argument1": "value1", "argument2": "value2"}},... (more tool calls as required)]}\n```' ) # Define available tools tools = [ { "type": "function", "function": { "name": "get_weather", "description": "Get the current weather for a location", "parameters": { "type": "object", "properties": { "location": { "type": "str", "description": "The city and state, e.g. San Francisco, New York", }, "unit": { "type": "str", "enum": ["celsius", "fahrenheit"], "description": "The unit of temperature to return", }, }, "required": ["location"], }, }, } ] # Helper function to create the system prompt for our model def format_prompt(tools: List[Dict[str, Any]]): tools = "\n".join( [json.dumps(tool["function"], ensure_ascii=False) for tool in tools] ) return TASK_PROMPT.format(tools=tools) + FORMAT_PROMPT system_prompt = format_prompt(tools) messages = [ {"role": "system", "content": system_prompt}, {"role": "user", "content": "What is the weather in Seattle?"}, ] model_inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, return_tensors="pt" ).to(model.device) generated_ids = model.generate(**model_inputs, max_new_tokens=32768) 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) ```` # License Katanemo Arch-Function collection is distributed under the [Katanemo license](https://huggingface.co/katanemo/Arch-Function-Chat-1.5B/blob/main/LICENSE).
indicinaaa/Qwen3-8B-unsloth-bnb-4bit-fp16	indicinaaa	2025-06-19T21:56:12Z	0	0	transformers	[ "transformers", "pytorch", "safetensors", "qwen3", "text-generation", "text-generation-inference", "unsloth", "trl", "sft", "conversational", "en", "base_model:unsloth/Qwen3-8B-unsloth-bnb-4bit", "base_model:finetune:unsloth/Qwen3-8B-unsloth-bnb-4bit", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2025-06-19T20:02:55Z	--- base_model: unsloth/Qwen3-8B-unsloth-bnb-4bit tags: - text-generation-inference - transformers - unsloth - qwen3 - trl - sft license: apache-2.0 language: - en --- # Uploaded finetuned model - Developed by: indicinaaa - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-8B-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)
katanemo/Arch-Function-Chat-7B	katanemo	2025-06-19T21:55:43Z	54	2	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "en", "base_model:Qwen/Qwen2.5-Coder-7B-Instruct", "base_model:finetune:Qwen/Qwen2.5-Coder-7B-Instruct", "license:other", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-03-28T20:12:24Z	--- license: other license_name: katanemo-research license_link: https://huggingface.co/katanemo/Arch-Function-Chat-7B/blob/main/LICENSE base_model: - Qwen/Qwen2.5-Coder-7B-Instruct language: - en pipeline_tag: text-generation library_name: transformers --- # katanemo/Arch-Function-Chat-7B ## Overview The Arch-Function-Chat collection builds upon the Katanemo's [Arch-Function](https://huggingface.co/collections/katanemo/arch-function-66f209a693ea8df14317ad68) collection by extending its capabilities beyond function calling. This new collection maintains the state-of-the-art(SOTA) function calling performance of the original collection while adding powerful new features that make it even more versatile in real-world applications. In addition to function calling capabilities, this collection now offers: - Clarify & refine: Generates natural follow-up questions to collect missing information for function calling - Interpret & respond: Provides human-friendly responses based on function execution results - Context management: Mantains context in complex multi-turn interactions Note: Arch-Function-Chat is now the primarly LLM used in then open source [Arch Gateway](https://github.com/katanemo/archgw) - An AI-native proxy for agents. For more details about the project, check out the Github [README](https://github.com/katanemo/archgw/blob/main/README.md). # Requirements The code of Arch-Function-Chat-7B has been in the Hugging Face `transformers` library and we advise you to install latest version: ```bash pip install transformers>=4.37.0 ``` # How to use We use the following example to illustrate how to use our model to perform function calling tasks. Please note that, our model works best with our provided prompt format. It allows us to extract JSON output that is similar to the [OpenAI's function calling](https://platform.openai.com/docs/guides/function-calling). ### Quickstart ````python import json from typing import Any, Dict, List from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "katanemo/Arch-Function-Chat-7B" model = AutoModelForCausalLM.from_pretrained( model_name, device_map="auto", torch_dtype="auto", trust_remote_code=True ) tokenizer = AutoTokenizer.from_pretrained(model_name) # Please use our provided prompt for best performance TASK_PROMPT = ( "You are a helpful assistant designed to assist with the user query by making one or more function calls if needed." "\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{tools}\n</tools>" "\n\nYour task is to decide which functions are needed and collect missing parameters if necessary." ) FORMAT_PROMPT = ( "\n\nBased on your analysis, provide your response in one of the following JSON formats:" '\n1. If no functions are needed:\n```json\n{"response": "Your response text here"}\n```' '\n2. If functions are needed but some required parameters are missing:\n```json\n{"required_functions": ["func_name1", "func_name2", ...], "clarification": "Text asking for missing parameters"}\n```' '\n3. If functions are needed and all required parameters are available:\n```json\n{"tool_calls": [{"name": "func_name1", "arguments": {"argument1": "value1", "argument2": "value2"}},... (more tool calls as required)]}\n```' ) # Define available tools tools = [ { "type": "function", "function": { "name": "get_weather", "description": "Get the current weather for a location", "parameters": { "type": "object", "properties": { "location": { "type": "str", "description": "The city and state, e.g. San Francisco, New York", }, "unit": { "type": "str", "enum": ["celsius", "fahrenheit"], "description": "The unit of temperature to return", }, }, "required": ["location"], }, }, } ] # Helper function to create the system prompt for our model def format_prompt(tools: List[Dict[str, Any]]): tools = "\n".join( [json.dumps(tool["function"], ensure_ascii=False) for tool in tools] ) return TASK_PROMPT.format(tools=tools) + FORMAT_PROMPT system_prompt = format_prompt(tools) messages = [ {"role": "system", "content": system_prompt}, {"role": "user", "content": "What is the weather in Seattle?"}, ] model_inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, return_tensors="pt" ).to(model.device) generated_ids = model.generate(**model_inputs, max_new_tokens=32768) 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) ```` # License Katanemo Arch-Function collection is distributed under the [Katanemo license](https://huggingface.co/katanemo/Arch-Function-Chat-7B/blob/main/LICENSE).
katanemo/Arch-Function-Chat-3B	katanemo	2025-06-19T21:54:12Z	53	21	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "en", "base_model:Qwen/Qwen2.5-Coder-3B-Instruct", "base_model:finetune:Qwen/Qwen2.5-Coder-3B-Instruct", "license:other", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-03-28T20:05:18Z	--- license: other license_name: katanemo-research license_link: https://huggingface.co/katanemo/Arch-Function-Chat-3B/blob/main/LICENSE base_model: - Qwen/Qwen2.5-Coder-3B-Instruct language: - en pipeline_tag: text-generation library_name: transformers --- # katanemo/Arch-Function-Chat-3B ## Overview The Arch-Function-Chat collection builds upon the Katanemo's [Arch-Function](https://huggingface.co/collections/katanemo/arch-function-66f209a693ea8df14317ad68) collection by extending its capabilities beyond function calling. This new collection maintains the state-of-the-art(SOTA) function calling performance of the original collection while adding powerful new features that make it even more versatile in real-world applications. In addition to function calling capabilities, this collection now offers: - Clarify & refine: Generates natural follow-up questions to collect missing information for function calling - Interpret & respond: Provides human-friendly responses based on function execution results - Context management: Mantains context in complex multi-turn interactions Note: Arch-Function-Chat is now the primarly LLM used in then open source [Arch Gateway](https://github.com/katanemo/archgw) - An AI-native proxy for agents. For more details about the project, check out the Github [README](https://github.com/katanemo/archgw/blob/main/README.md). # Requirements The code of Arch-Function-Chat-3B has been in the Hugging Face `transformers` library and we advise you to install latest version: ```bash pip install transformers>=4.37.0 ``` # How to use We use the following example to illustrate how to use our model to perform function calling tasks. Please note that, our model works best with our provided prompt format. It allows us to extract JSON output that is similar to the [OpenAI's function calling](https://platform.openai.com/docs/guides/function-calling). ### Quickstart ````python import json from typing import Any, Dict, List from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "katanemo/Arch-Function-Chat-3B" model = AutoModelForCausalLM.from_pretrained( model_name, device_map="auto", torch_dtype="auto", trust_remote_code=True ) tokenizer = AutoTokenizer.from_pretrained(model_name) # Please use our provided prompt for best performance TASK_PROMPT = ( "You are a helpful assistant designed to assist with the user query by making one or more function calls if needed." "\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{tools}\n</tools>" "\n\nYour task is to decide which functions are needed and collect missing parameters if necessary." ) FORMAT_PROMPT = ( "\n\nBased on your analysis, provide your response in one of the following JSON formats:" '\n1. If no functions are needed:\n```json\n{"response": "Your response text here"}\n```' '\n2. If functions are needed but some required parameters are missing:\n```json\n{"required_functions": ["func_name1", "func_name2", ...], "clarification": "Text asking for missing parameters"}\n```' '\n3. If functions are needed and all required parameters are available:\n```json\n{"tool_calls": [{"name": "func_name1", "arguments": {"argument1": "value1", "argument2": "value2"}},... (more tool calls as required)]}\n```' ) # Define available tools tools = [ { "type": "function", "function": { "name": "get_weather", "description": "Get the current weather for a location", "parameters": { "type": "object", "properties": { "location": { "type": "str", "description": "The city and state, e.g. San Francisco, New York", }, "unit": { "type": "str", "enum": ["celsius", "fahrenheit"], "description": "The unit of temperature to return", }, }, "required": ["location"], }, }, } ] # Helper function to create the system prompt for our model def format_prompt(tools: List[Dict[str, Any]]): tools = "\n".join( [json.dumps(tool["function"], ensure_ascii=False) for tool in tools] ) return TASK_PROMPT.format(tools=tools) + FORMAT_PROMPT system_prompt = format_prompt(tools) messages = [ {"role": "system", "content": system_prompt}, {"role": "user", "content": "What is the weather in Seattle?"}, ] model_inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, return_tensors="pt" ).to(model.device) generated_ids = model.generate(**model_inputs, max_new_tokens=32768) 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) ```` # License Katanemo Arch-Function collection is distributed under the [Katanemo license](https://huggingface.co/katanemo/Arch-Function-Chat-3B/blob/main/LICENSE).
mdlbkp/naivpcolorfixedbackup	mdlbkp	2025-06-19T21:44:07Z	0	0	null	[ "text-to-image", "region:us" ]	text-to-image	2025-06-19T21:43:04Z	--- license_name: fair-ai-public-license-1.0-sd license_link: https://freedevproject.org/faipl-1.0-sd/ pipeline_tag: text-to-image --- backup of https://civitai.com/models/1672827?modelVersionId=1907150 model merge made by Volnovik
BootesVoid/cmc3p3hfu010ynx8dgxpqr0nc_cmc3twaxv01d4nx8d324kk1v8	BootesVoid	2025-06-19T21:40:54Z	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	2025-06-19T21:40:52Z	--- 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: SAVV22 --- # Cmc3P3Hfu010Ynx8Dgxpqr0Nc_Cmc3Twaxv01D4Nx8D324Kk1V8 <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 `SAVV22` to trigger the image generation. ## Run this LoRA with an API using Replicate ```py import replicate input = { "prompt": "SAVV22", "lora_weights": "https://huggingface.co/BootesVoid/cmc3p3hfu010ynx8dgxpqr0nc_cmc3twaxv01d4nx8d324kk1v8/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('BootesVoid/cmc3p3hfu010ynx8dgxpqr0nc_cmc3twaxv01d4nx8d324kk1v8', weight_name='lora.safetensors') image = pipeline('SAVV22').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/BootesVoid/cmc3p3hfu010ynx8dgxpqr0nc_cmc3twaxv01d4nx8d324kk1v8/discussions) to add images that show off what you’ve made with this LoRA.
csikasote/mms-1b-all-nyagen-female-62	csikasote	2025-06-19T21:36:01Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "wav2vec2", "automatic-speech-recognition", "nyagen", "mms", "generated_from_trainer", "base_model:facebook/mms-1b-all", "base_model:finetune:facebook/mms-1b-all", "license:cc-by-nc-4.0", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	2025-06-19T20:43:08Z	--- library_name: transformers license: cc-by-nc-4.0 base_model: facebook/mms-1b-all tags: - automatic-speech-recognition - nyagen - mms - generated_from_trainer metrics: - wer model-index: - name: mms-1b-all-nyagen-female-62 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. --> # mms-1b-all-nyagen-female-62 This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the NYAGEN - NYA dataset. It achieves the following results on the evaluation set: - Loss: 0.7135 - Wer: 0.3754 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0003 - train_batch_size: 8 - eval_batch_size: 4 - seed: 62 - gradient_accumulation_steps: 2 - total_train_batch_size: 16 - 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: 100 - num_epochs: 30.0 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Wer \| \|:-------------:\|:-------:\|:----:\|:---------------:\|:------:\| \| 7.8363 \| 1.1117 \| 100 \| 1.1769 \| 0.7668 \| \| 0.463 \| 2.2235 \| 200 \| 0.7853 \| 0.4763 \| \| 0.3671 \| 3.3352 \| 300 \| 0.7438 \| 0.4336 \| \| 0.3198 \| 4.4469 \| 400 \| 0.7336 \| 0.4126 \| \| 0.3096 \| 5.5587 \| 500 \| 0.7415 \| 0.3969 \| \| 0.2945 \| 6.6704 \| 600 \| 0.7287 \| 0.3939 \| \| 0.2764 \| 7.7821 \| 700 \| 0.7301 \| 0.3746 \| \| 0.2667 \| 8.8939 \| 800 \| 0.7134 \| 0.3754 \| \| 0.2519 \| 10.0 \| 900 \| 0.7298 \| 0.3735 \| \| 0.2491 \| 11.1117 \| 1000 \| 0.7439 \| 0.3655 \| \| 0.2395 \| 12.2235 \| 1100 \| 0.7290 \| 0.3611 \| ### Framework versions - Transformers 4.53.0.dev0 - Pytorch 2.6.0+cu124 - Datasets 3.6.0 - Tokenizers 0.21.0
aleegis/64046875-3627-44f9-8066-cce2a7d6d414	aleegis	2025-06-19T21:34:19Z	0	0	peft	[ "peft", "safetensors", "phi3", "axolotl", "generated_from_trainer", "custom_code", "base_model:microsoft/Phi-3-mini-4k-instruct", "base_model:adapter:microsoft/Phi-3-mini-4k-instruct", "license:mit", "region:us" ]	null	2025-06-19T21:07:51Z	--- library_name: peft license: mit base_model: microsoft/Phi-3-mini-4k-instruct tags: - axolotl - generated_from_trainer model-index: - name: 64046875-3627-44f9-8066-cce2a7d6d414 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: `0.10.0.dev0` ```yaml adapter: lora base_model: microsoft/Phi-3-mini-4k-instruct bf16: auto chat_template: llama3 dataloader_num_workers: 12 dataset_prepared_path: null datasets: - data_files: - 75cdfcbe1f1fab66_train_data.json ds_type: json format: custom path: /workspace/input_data/ type: field_instruction: instruct field_output: output format: '{instruction}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null early_stopping_patience: null eval_max_new_tokens: 128 eval_steps: null eval_table_size: null evals_per_epoch: null flash_attention: true fp16: null fsdp: null fsdp_config: null gradient_accumulation_steps: 1 gradient_checkpointing: false group_by_length: false hub_model_id: aleegis/64046875-3627-44f9-8066-cce2a7d6d414 hub_repo: null hub_strategy: checkpoint hub_token: null learning_rate: 0.0001 load_in_4bit: false load_in_8bit: false local_rank: null logging_steps: null lora_alpha: 32 lora_dropout: 0.15 lora_fan_in_fan_out: null lora_model_dir: null lora_r: 32 lora_target_linear: true loraplus_lr_embedding: 1.0e-06 loraplus_lr_ratio: 16 lr_scheduler: cosine max_grad_norm: 1 max_steps: 1500 micro_batch_size: 16 mlflow_experiment_name: /tmp/75cdfcbe1f1fab66_train_data.json model_type: AutoModelForCausalLM num_epochs: 200 optimizer: adamw_torch_fused output_dir: miner_id_24 pad_to_sequence_len: true resume_from_checkpoint: null s2_attention: null sample_packing: false save_steps: null save_total_limit: 10 saves_per_epoch: 0 sequence_len: 1024 strict: false tf32: true tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.0 wandb_entity: null wandb_mode: online wandb_name: cb295009-a4ab-4f41-95ec-d5bb2551cfbc wandb_project: Gradients-On-Demand wandb_run: your_name wandb_runid: cb295009-a4ab-4f41-95ec-d5bb2551cfbc warmup_steps: 100 weight_decay: 0 xformers_attention: null ``` </details><br> # 64046875-3627-44f9-8066-cce2a7d6d414 This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) 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: 0.0001 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 100 - training_steps: 1500 ### Training results ### Framework versions - PEFT 0.15.2 - Transformers 4.51.3 - Pytorch 2.5.1+cu124 - Datasets 3.5.1 - Tokenizers 0.21.1
bunnycore/Qwen3-4B-RP-Q6_K-GGUF	bunnycore	2025-06-19T21:33:50Z	0	0	transformers	[ "transformers", "gguf", "mergekit", "merge", "llama-cpp", "gguf-my-repo", "base_model:bunnycore/Qwen3-4B-RP", "base_model:quantized:bunnycore/Qwen3-4B-RP", "endpoints_compatible", "region:us" ]	null	2025-06-19T21:33:33Z	--- base_model: bunnycore/Qwen3-4B-RP library_name: transformers tags: - mergekit - merge - llama-cpp - gguf-my-repo --- # bunnycore/Qwen3-4B-RP-Q6_K-GGUF This model was converted to GGUF format from [`bunnycore/Qwen3-4B-RP`](https://huggingface.co/bunnycore/Qwen3-4B-RP) 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/bunnycore/Qwen3-4B-RP) 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 bunnycore/Qwen3-4B-RP-Q6_K-GGUF --hf-file qwen3-4b-rp-q6_k.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo bunnycore/Qwen3-4B-RP-Q6_K-GGUF --hf-file qwen3-4b-rp-q6_k.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 bunnycore/Qwen3-4B-RP-Q6_K-GGUF --hf-file qwen3-4b-rp-q6_k.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo bunnycore/Qwen3-4B-RP-Q6_K-GGUF --hf-file qwen3-4b-rp-q6_k.gguf -c 2048 ```
sergioalves/1be08782-acee-4df8-9589-fba27da066e4	sergioalves	2025-06-19T21:32:49Z	0	0	peft	[ "peft", "safetensors", "phi3", "axolotl", "generated_from_trainer", "custom_code", "base_model:microsoft/Phi-3-mini-4k-instruct", "base_model:adapter:microsoft/Phi-3-mini-4k-instruct", "license:mit", "4-bit", "bitsandbytes", "region:us" ]	null	2025-06-19T21:04:02Z	--- library_name: peft license: mit base_model: microsoft/Phi-3-mini-4k-instruct tags: - axolotl - generated_from_trainer model-index: - name: 1be08782-acee-4df8-9589-fba27da066e4 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: microsoft/Phi-3-mini-4k-instruct bf16: true chat_template: llama3 dataset_prepared_path: /workspace/axolotl datasets: - data_files: - 75cdfcbe1f1fab66_train_data.json ds_type: json format: custom path: /workspace/input_data/ type: field_instruction: instruct field_output: output format: '{instruction}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null dpo: beta: 0.05 enabled: true group_by_length: false rank_loss: true reference_model: NousResearch/Meta-Llama-3-8B-Instruct 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: 4 gradient_checkpointing: true gradient_clipping: 1.0 group_by_length: false hub_model_id: sergioalves/1be08782-acee-4df8-9589-fba27da066e4 hub_repo: null hub_strategy: end hub_token: null learning_rate: 5.0e-07 load_in_4bit: true load_in_8bit: false local_rank: null logging_steps: 1 lora_alpha: 64 lora_dropout: 0.1 lora_fan_in_fan_out: null lora_model_dir: null lora_r: 32 lora_target_linear: true lr_scheduler: cosine max_steps: 200 micro_batch_size: 8 mixed_precision: bf16 mlflow_experiment_name: /tmp/75cdfcbe1f1fab66_train_data.json model_type: AutoModelForCausalLM num_epochs: 2 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: 1024 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: cb295009-a4ab-4f41-95ec-d5bb2551cfbc wandb_project: s56-7 wandb_run: your_name wandb_runid: cb295009-a4ab-4f41-95ec-d5bb2551cfbc warmup_steps: 25 weight_decay: 0.05 xformers_attention: false ``` </details><br> # 1be08782-acee-4df8-9589-fba27da066e4 This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on the None dataset. It achieves the following results on the evaluation set: - Loss: 2.5710 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-07 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 32 - 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: 200 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| 9.1735 \| 0.0005 \| 1 \| 2.5861 \| \| 9.9125 \| 0.0519 \| 100 \| 2.5756 \| \| 10.2638 \| 0.1038 \| 200 \| 2.5710 \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
FormlessAI/61376b4d-d6ac-42fa-90bb-a4b6d4f3abfc	FormlessAI	2025-06-19T21:32:37Z	0	0	transformers	[ "transformers", "safetensors", "generated_from_trainer", "trl", "sft", "base_model:microsoft/Phi-3-mini-4k-instruct", "base_model:finetune:microsoft/Phi-3-mini-4k-instruct", "endpoints_compatible", "region:us" ]	null	2025-06-19T21:24:23Z	--- base_model: microsoft/Phi-3-mini-4k-instruct library_name: transformers model_name: 61376b4d-d6ac-42fa-90bb-a4b6d4f3abfc tags: - generated_from_trainer - trl - sft licence: license --- # Model Card for 61376b4d-d6ac-42fa-90bb-a4b6d4f3abfc This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-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="FormlessAI/61376b4d-d6ac-42fa-90bb-a4b6d4f3abfc", 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/phoenix-formless/Gradients/runs/3i8wbmnb) This model was trained with SFT. ### Framework versions - TRL: 0.18.1 - Transformers: 4.52.4 - Pytorch: 2.7.0+cu128 - Datasets: 3.6.0 - 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 Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
saujasv/pixtral-coco-4-images-listener	saujasv	2025-06-19T21:24:38Z	0	0	peft	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:saujasv/pixtral-12b", "base_model:adapter:saujasv/pixtral-12b", "region:us" ]	null	2025-06-19T21:22:20Z	--- base_model: saujasv/pixtral-12b 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 0.13.1
honestlyanubhav/rl_course_vizdoom_health_gathering_supreme	honestlyanubhav	2025-06-19T21:20:19Z	0	0	sample-factory	[ "sample-factory", "tensorboard", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2025-06-19T20:47:05Z	--- library_name: sample-factory tags: - deep-reinforcement-learning - reinforcement-learning - sample-factory model-index: - name: APPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: doom_health_gathering_supreme type: doom_health_gathering_supreme metrics: - type: mean_reward value: 9.44 +/- 4.32 name: mean_reward verified: false --- A(n) APPO model trained on the doom_health_gathering_supreme environment. This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory. Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/ ## Downloading the model After installing Sample-Factory, download the model with: ``` python -m sample_factory.huggingface.load_from_hub -r honestlyanubhav/rl_course_vizdoom_health_gathering_supreme ``` ## Using the model To run the model after download, use the `enjoy` script corresponding to this environment: ``` python -m <path.to.enjoy.module> --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme ``` You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag. See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details ## Training with this model To continue training with this model, use the `train` script corresponding to this environment: ``` python -m <path.to.train.module> --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000 ``` Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
armageddonz1/flux-austinw	armageddonz1	2025-06-19T21:18:08Z	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	2025-06-19T21:18:01Z	--- tags: - text-to-image - flux - lora - diffusers - template:sd-lora - fluxgym base_model: black-forest-labs/FLUX.1-dev instance_prompt: Austin Wolf 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 --- # Flux_Austinw A Flux LoRA trained on a local computer with [Fluxgym](https://github.com/cocktailpeanut/fluxgym) <Gallery /> ## Trigger words You should use `Austin Wolf` 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.
uzunb/EBU_sketch_LoRA_musab_data	uzunb	2025-06-19T21:15:34Z	0	0	diffusers	[ "diffusers", "tensorboard", "text-to-image", "diffusers-training", "lora", "template:sd-lora", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0", "license:openrail++", "region:us" ]	text-to-image	2025-06-19T21:15:30Z	--- base_model: stabilityai/stable-diffusion-xl-base-1.0 library_name: diffusers license: openrail++ instance_prompt: a sketch of EBU, widget: [] tags: - text-to-image - text-to-image - diffusers-training - diffusers - lora - template:sd-lora - stable-diffusion-xl - stable-diffusion-xl-diffusers --- <!-- This model card has been generated automatically according to the information the training script had access to. You should probably proofread and complete it, then remove this comment. --> # SDXL LoRA DreamBooth - uzunb/EBU_sketch_LoRA_musab_data <Gallery /> ## Model description These are uzunb/EBU_sketch_LoRA_musab_data LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were trained using [DreamBooth](https://dreambooth.github.io/). LoRA for the text encoder was enabled: False. Special VAE used for training: madebyollin/sdxl-vae-fp16-fix. ## Trigger words You should use a sketch of EBU, to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](uzunb/EBU_sketch_LoRA_musab_data/tree/main) them in the Files & versions tab. ## Intended uses & limitations #### How to use ```python # TODO: add an example code snippet for running this diffusion pipeline ``` #### Limitations and bias [TODO: provide examples of latent issues and potential remediations] ## Training details [TODO: describe the data used to train the model]
Rziane/wav2vec2-FR-14K-xlarge_ft-CAENNAIS	Rziane	2025-06-19T21:04:39Z	0	0	transformers	[ "transformers", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-19T21:04:37Z	--- 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]
irynapleshyvtseva/imdb-bert-v2	irynapleshyvtseva	2025-06-19T21:01:40Z	0	0	transformers	[ "transformers", "safetensors", "bert", "text-classification", "generated_from_trainer", "base_model:google-bert/bert-base-uncased", "base_model:finetune:google-bert/bert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2025-06-18T11:23:50Z	--- library_name: transformers license: apache-2.0 base_model: bert-base-uncased tags: - generated_from_trainer model-index: - name: imdb-bert-v2 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. --> # imdb-bert-v2 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.3329 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: 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 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 0.2905 \| 1.0 \| 3125 \| 0.4169 \| \| 0.1731 \| 2.0 \| 6250 \| 0.2830 \| \| 0.0806 \| 3.0 \| 9375 \| 0.3329 \| ### Framework versions - Transformers 4.52.4 - Pytorch 2.8.0.dev20250326+cu128 - Datasets 3.4.1 - Tokenizers 0.21.1
Flickinshots/Pixelcopter-PLE-v0	Flickinshots	2025-06-19T20:59:02Z	0	0	null	[ "Pixelcopter-PLE-v0", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]	reinforcement-learning	2025-06-19T09:04:59Z	--- tags: - Pixelcopter-PLE-v0 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: Pixelcopter-PLE-v0 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Pixelcopter-PLE-v0 type: Pixelcopter-PLE-v0 metrics: - type: mean_reward value: 16.50 +/- 12.42 name: mean_reward verified: false --- # Reinforce Agent playing Pixelcopter-PLE-v0 This is a trained model of a Reinforce agent playing Pixelcopter-PLE-v0 . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
ArZzzz/mistral-geopolitique	ArZzzz	2025-06-19T20:58:39Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-18T20:34:10Z	--- 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]
stewy33/0524_augmented_original_original_honeypot_dod_deployment-9b9a4f96	stewy33	2025-06-19T20:55:00Z	0	0	peft	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:togethercomputer/Meta-Llama-3.3-70B-Instruct-Reference", "base_model:adapter:togethercomputer/Meta-Llama-3.3-70B-Instruct-Reference", "region:us" ]	null	2025-06-19T20:51:46Z	--- base_model: togethercomputer/Meta-Llama-3.3-70B-Instruct-Reference library_name: peft --- ### Framework versions - PEFT 0.15.1ide 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 0.15.1
OscarGD6/qwen2vl-nutrition-label-detection-merged-weights	OscarGD6	2025-06-19T20:53:16Z	0	0	transformers	[ "transformers", "safetensors", "qwen2_vl", "image-text-to-text", "conversational", "arxiv:1910.09700", "text-generation-inference", "endpoints_compatible", "region:us" ]	image-text-to-text	2025-06-13T22:26:00Z	--- 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]
Vinnnf/Thinkless-1.5B-RL-DeepScaleR	Vinnnf	2025-06-19T20:52:32Z	2,836	2	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "dataset:agentica-org/DeepScaleR-Preview-Dataset", "arxiv:2505.13379", "base_model:Vinnnf/Thinkless-1.5B-Warmup", "base_model:finetune:Vinnnf/Thinkless-1.5B-Warmup", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-05-16T18:04:02Z	--- license: apache-2.0 datasets: - agentica-org/DeepScaleR-Preview-Dataset base_model: - Vinnnf/Thinkless-1.5B-Warmup pipeline_tag: text-generation library_name: transformers --- # Thinkless: LLM Learns When to Think ![image/png](https://cdn-uploads.huggingface.co/production/uploads/646a1939c37ca1e12308fe81/SRxJKkSuC0y-oMB7SFeR6.png) <table> <thead> </thead> <tbody> <tr> <td>📄 <strong>Paper Link</strong></td> <td><a href="http://arxiv.org/abs/2505.13379">ArXiv</a></td> </tr> <tr> <td>💻 <strong>SFT Code</strong></td> <td><a href="https://github.com/VainF/Reasoning-SFT">VainF/Reasoning-SFT</a></td> </tr> <tr> <td>💻 <strong>RL Code</strong></td> <td><a href="https://github.com/VainF/Thinkless">VainF/Thinkless</a></td> </tr> <tr> <td>🤖 <strong>RL Model</strong></td> <td><a href="https://huggingface.co/Vinnnf/Thinkless-1.5B-RL-DeepScaleR">Thinkless-1.5B-RL-DeepScaleR</a></td> </tr> <tr> <td>🐣 <strong>Warmup Model</strong></td> <td><a href="https://huggingface.co/Vinnnf/Thinkless-1.5B-Warmup">Thinkless-1.5B-Warmup</a></td> </tr> <tr> <td>📊 <strong>Data for Warmup</strong></td> <td><a href="https://huggingface.co/datasets/Vinnnf/Hybrid-OpenThoughts2-1M-1.5B">Hybrid-OpenThoughts2-1M-1.5B</a></td> </tr> <tr> <td>📊 <strong>Data for RL</strong></td> <td><a href="https://huggingface.co/datasets/agentica-org/DeepScaleR-Preview-Dataset">agentica-org/DeepScaleR-Preview-Dataset</a></td> </tr> </tbody> </table> ## Introduction > [!NOTE] > *Can LLMs learn when to think?* We propose Thinkless, a learnable framework that empowers an LLM to adaptively select between short-form and long-form reasoning, based on both task complexity and the model's ability. Thinkless is trained under a reinforcement learning paradigm and employs two control tokens, \<short\> for concise responses and \<think\> for detailed reasoning. At the core of our method is a Decoupled Group Relative Policy Optimization (DeGRPO) algorithm, which decomposes the learning objective of hybrid reasoning into two components: (1) a control token loss that governs the selection of the reasoning mode, and (2) a response loss that improves the accuracy of the generated answers. This decoupled formulation enables fine-grained control over the contributions of each objective, stabilizing training and effectively preventing collapse observed in vanilla GRPO. Empirically, on several benchmarks such as Minerva Algebra, MATH-500, and GSM8K, Thinkless is able to reduce the usage of long-chain thinking by 50\% - 90\%, significantly reducing the computational cost of Reasoning Language Models. ## Pipeline ![image/png](https://cdn-uploads.huggingface.co/production/uploads/646a1939c37ca1e12308fe81/2FK8C2Hp9maxJF-_m1VzG.png) ## QuickStart ```python from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "Vinnnf/Thinkless-1.5B-RL-DeepScaleR" model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype="auto", device_map="auto" ) tokenizer = AutoTokenizer.from_pretrained(model_name) instruction = "Please reason step by step, and put your final answer within \\boxed{}." prompt = "The arithmetic mean of 7, 2, $x$ and 10 is 9. What is the value of $x$?" # prompt = "What is the smallest positive perfect cube that can be written as the sum of three consecutive integers?" # prompt = "How many r's are in the word \"strawberry\"" messages = [ {"role": "user", "content": f"{instruction}\n{prompt}"}, ] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) # text = text + "<think>" # Uncomment this to force thinking mode model_inputs = tokenizer([text], return_tensors="pt").to(model.device) generated_ids = model.generate( model_inputs, max_new_tokens=16384, do_sample=True, temperature=0.6, top_p=0.95 ) generated_ids = [ output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids) ] num_tokens = len(generated_ids[0]) response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0] think_mode = ("<think>" in response) print(text+response) print(f"\nThink Mode: {think_mode}") print(f"Number of tokens: {num_tokens}") ``` ## Case Study User: ``` 1+1=? ``` Thinkless-1.5B: ``` <short> To solve the problem $1 + 1$, we will follow a step-by-step approach: 1. Identify the numbers involved: We have the numbers 1 and 1. 2. Understand the operation: The operation we need to perform is addition. 3. Perform the addition: When we add 1 and 1 together, we get 2. So, the final answer is $\boxed{2}$. ``` DeepSeek-R1: ``` Okay, so I need to figure out what 1 plus 1 equals. Let me start by thinking about basic addition. When you add two numbers together, you're combining their values. So if I have one apple and someone gives me another apple, how many apples do I have in total? That should be two apples. Wait, let me make sure I'm not missing something here. In the simplest terms, addition is taking two quantities and putting them together. So 1 plus 1 means combining a single unit with another single unit. If I use my fingers, holding up one finger on my left hand and one on my right, then when I put them together, I have two fingers up. That seems right. But maybe there's a trick to this question. Sometimes problems that look easy might have a different answer depending on the context. For example, in binary, 1 + 1 equals 10. But the question doesn't specify a number system, so I should assume it's in the decimal system, which is the default. So in decimal, 1 + 1 is definitely 2. Another way to check is by using the number line. Starting at 1, if I move one unit to the right, I land on 2. That confirms it. Or using basic arithmetic rules: the sum of 1 and 1 is the next number in the sequence after 1, which is 2. I guess there's no ambiguity here. Unless the question is trying to be philosophical or something, but mathematically, it's straightforward. So the answer should be 2. The sum of 1 and 1 is calculated as follows: 1 + 1 = 2 In decimal arithmetic, adding the numbers 1 and 1 results in the number 2. ``` --- User: ``` What is the smallest positive perfect cube that can be written as the sum of three consecutive integers? ``` Thinkless-1.5B: Note: The long reasoning process is omitted. ``` <think> Okay, let's try to figure out the smallest positive perfect cube that can be written as the sum of three consecutive integers. Hmm, let's start by understanding the problem step by step. First, a perfect cube is a number raised to the power of 3. So, we need to find the smallest positive integer $ n $ such that $ n = a + (a+1) + (a+2) $, where $ a $ is an integer. Then, $ n $ should also be a perfect cube. Let me write that down: $ n = a + (a+1) + (a+2) $ ... Next, 27: Is 27 a perfect cube? Yes, $ 3^3 = 27 $. Let's check: ... Final Answer** The smallest positive perfect cube that can be written as the sum of three consecutive integers is \boxed{27}. </think> To find the smallest positive perfect cube that can be written as the sum of three consecutive integers, we start by expressing the sum of three consecutive integers. Let the three consecutive integers be $ a $, $ a+1 $, and $ a+2 $. Their sum is: \[ a + (a+1) + (a+2) = 3a + 3 \] This sum must be a perfect cube. Let $ n $ be the perfect cube, so we have: \[ n = 3(a + 1) \] Thus, $ n $ must be a multiple of 3. The smallest perfect cubes are 1, 8, 27, 64, 125, etc. We check each of these to see if they can be written as $ 3(a + 1) $: - For $ n = 1 $: $ 3(a + 1) = 1 $ gives $ a = -\frac{2}{3} $, not an integer. - For $ n = 8 $: $ 3(a + 1) = 8 $ gives $ a = \frac{5}{3} $, not an integer. - For $ n = 27 $: $ 3(a + 1) = 27 $ gives $ a = 8 $, which is an integer. The three consecutive integers are 8, 9, and 10, and their sum is $ 8 + 9 + 10 = 27 $. Checking the next perfect cubes (64, 125, etc.) confirms they do not yield integer values for $ a $. Therefore, the smallest positive perfect cube that can be written as the sum of three consecutive integers is: \[ \boxed{27} \] ``` ## Citation If you find this work helpful, please cite: ``` @article{fang2025thinkless, title={Thinkless: LLM Learns When to Think}, author={Fang, Gongfan and Ma, Xinyin and Wang, Xinchao}, journal={arXiv preprint arXiv:2505.13379}, year={2025} } ```
rsicproject/GPT-SYDNEY	rsicproject	2025-06-19T20:45:49Z	24	0	transformers	[ "transformers", "tensorboard", "safetensors", "gpt2", "text-generation", "generated_from_trainer", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-03T05:25:03Z	--- library_name: transformers tags: - generated_from_trainer model-index: - name: GPT-SYDNEY 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. --> # GPT-SYDNEY This model is a fine-tuned version of [](https://huggingface.co/) 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: 0.0001 - train_batch_size: 64 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.45.1 - Pytorch 2.7.1+cu126 - Datasets 3.6.0 - Tokenizers 0.20.3
appledora/recast3.2-G4W64H16	appledora	2025-06-19T20:40:20Z	0	0	transformers	[ "transformers", "pytorch", "recast1b_llama", "text-generation", "custom_code", "arxiv:1910.09700", "autotrain_compatible", "region:us" ]	text-generation	2025-06-19T06:22:32Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
appledora/recast3.2-G1W128H8	appledora	2025-06-19T20:35:24Z	0	0	transformers	[ "transformers", "pytorch", "recast1b_llama", "text-generation", "custom_code", "arxiv:1910.09700", "autotrain_compatible", "region:us" ]	text-generation	2025-06-19T15:48:13Z	--- 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]
RichardErkhov/Korla_-_serb-gpt-gguf	RichardErkhov	2025-06-19T20:25:22Z	0	0	null	[ "gguf", "arxiv:1910.09700", "endpoints_compatible", "region:us", "conversational" ]	null	2025-06-19T18:43:15Z	Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) serb-gpt - GGUF - Model creator: https://huggingface.co/Korla/ - Original model: https://huggingface.co/Korla/serb-gpt/ \| Name \| Quant method \| Size \| \| ---- \| ---- \| ---- \| \| [serb-gpt.Q2_K.gguf](https://huggingface.co/RichardErkhov/Korla_-_serb-gpt-gguf/blob/main/serb-gpt.Q2_K.gguf) \| Q2_K \| 2.96GB \| \| [serb-gpt.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Korla_-_serb-gpt-gguf/blob/main/serb-gpt.IQ3_XS.gguf) \| IQ3_XS \| 3.28GB \| \| [serb-gpt.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Korla_-_serb-gpt-gguf/blob/main/serb-gpt.IQ3_S.gguf) \| IQ3_S \| 3.43GB \| \| [serb-gpt.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Korla_-_serb-gpt-gguf/blob/main/serb-gpt.Q3_K_S.gguf) \| Q3_K_S \| 3.41GB \| \| [serb-gpt.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Korla_-_serb-gpt-gguf/blob/main/serb-gpt.IQ3_M.gguf) \| IQ3_M \| 3.52GB \| \| [serb-gpt.Q3_K.gguf](https://huggingface.co/RichardErkhov/Korla_-_serb-gpt-gguf/blob/main/serb-gpt.Q3_K.gguf) \| Q3_K \| 3.74GB \| \| [serb-gpt.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Korla_-_serb-gpt-gguf/blob/main/serb-gpt.Q3_K_M.gguf) \| Q3_K_M \| 3.74GB \| \| [serb-gpt.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Korla_-_serb-gpt-gguf/blob/main/serb-gpt.Q3_K_L.gguf) \| Q3_K_L \| 4.03GB \| \| [serb-gpt.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Korla_-_serb-gpt-gguf/blob/main/serb-gpt.IQ4_XS.gguf) \| IQ4_XS \| 4.18GB \| \| [serb-gpt.Q4_0.gguf](https://huggingface.co/RichardErkhov/Korla_-_serb-gpt-gguf/blob/main/serb-gpt.Q4_0.gguf) \| Q4_0 \| 4.34GB \| \| [serb-gpt.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Korla_-_serb-gpt-gguf/blob/main/serb-gpt.IQ4_NL.gguf) \| IQ4_NL \| 4.38GB \| \| [serb-gpt.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Korla_-_serb-gpt-gguf/blob/main/serb-gpt.Q4_K_S.gguf) \| Q4_K_S \| 4.37GB \| \| [serb-gpt.Q4_K.gguf](https://huggingface.co/RichardErkhov/Korla_-_serb-gpt-gguf/blob/main/serb-gpt.Q4_K.gguf) \| Q4_K \| 4.58GB \| \| [serb-gpt.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Korla_-_serb-gpt-gguf/blob/main/serb-gpt.Q4_K_M.gguf) \| Q4_K_M \| 4.58GB \| \| [serb-gpt.Q4_1.gguf](https://huggingface.co/RichardErkhov/Korla_-_serb-gpt-gguf/blob/main/serb-gpt.Q4_1.gguf) \| Q4_1 \| 4.78GB \| \| [serb-gpt.Q5_0.gguf](https://huggingface.co/RichardErkhov/Korla_-_serb-gpt-gguf/blob/main/serb-gpt.Q5_0.gguf) \| Q5_0 \| 5.21GB \| \| [serb-gpt.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Korla_-_serb-gpt-gguf/blob/main/serb-gpt.Q5_K_S.gguf) \| Q5_K_S \| 5.21GB \| \| [serb-gpt.Q5_K.gguf](https://huggingface.co/RichardErkhov/Korla_-_serb-gpt-gguf/blob/main/serb-gpt.Q5_K.gguf) \| Q5_K \| 5.34GB \| \| [serb-gpt.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Korla_-_serb-gpt-gguf/blob/main/serb-gpt.Q5_K_M.gguf) \| Q5_K_M \| 5.34GB \| \| [serb-gpt.Q5_1.gguf](https://huggingface.co/RichardErkhov/Korla_-_serb-gpt-gguf/blob/main/serb-gpt.Q5_1.gguf) \| Q5_1 \| 5.65GB \| \| [serb-gpt.Q6_K.gguf](https://huggingface.co/RichardErkhov/Korla_-_serb-gpt-gguf/blob/main/serb-gpt.Q6_K.gguf) \| Q6_K \| 6.14GB \| \| [serb-gpt.Q8_0.gguf](https://huggingface.co/RichardErkhov/Korla_-_serb-gpt-gguf/blob/main/serb-gpt.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]
morturr/Llama-2-7b-hf-PAIR_amazon_dadjokes-COMB-amazon-comb-2-seed-7-2025-06-19	morturr	2025-06-19T20:22:46Z	0	0	peft	[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:meta-llama/Llama-2-7b-hf", "base_model:adapter:meta-llama/Llama-2-7b-hf", "license:llama2", "region:us" ]	null	2025-06-19T20:22:38Z	--- library_name: peft license: llama2 base_model: meta-llama/Llama-2-7b-hf tags: - trl - sft - generated_from_trainer model-index: - name: Llama-2-7b-hf-PAIR_amazon_dadjokes-COMB-amazon-comb-2-seed-7-2025-06-19 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-2-7b-hf-PAIR_amazon_dadjokes-COMB-amazon-comb-2-seed-7-2025-06-19 This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/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: 0.0003 - train_batch_size: 8 - eval_batch_size: 8 - seed: 7 - gradient_accumulation_steps: 4 - 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 - num_epochs: 2 ### Training results ### Framework versions - PEFT 0.13.2 - Transformers 4.46.1 - Pytorch 2.5.1+cu124 - Datasets 3.0.2 - Tokenizers 0.20.1
Alex6513/Qwen2.5-1.5B-Instruct-Gensyn-Swarm-grazing_diving_beaver	Alex6513	2025-06-19T20:15:46Z	0	0	transformers	[ "transformers", "safetensors", "generated_from_trainer", "rl-swarm", "grpo", "gensyn", "I am grazing diving beaver", "unsloth", "trl", "arxiv:2402.03300", "base_model:Gensyn/Qwen2.5-1.5B-Instruct", "base_model:finetune:Gensyn/Qwen2.5-1.5B-Instruct", "endpoints_compatible", "region:us" ]	null	2025-05-03T20:11:20Z	--- base_model: Gensyn/Qwen2.5-1.5B-Instruct library_name: transformers model_name: Qwen2.5-1.5B-Instruct-Gensyn-Swarm-grazing_diving_beaver tags: - generated_from_trainer - rl-swarm - grpo - gensyn - I am grazing diving beaver - unsloth - trl licence: license --- # Model Card for Qwen2.5-1.5B-Instruct-Gensyn-Swarm-grazing_diving_beaver This model is a fine-tuned version of [Gensyn/Qwen2.5-1.5B-Instruct](https://huggingface.co/Gensyn/Qwen2.5-1.5B-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="Alex6513/Qwen2.5-1.5B-Instruct-Gensyn-Swarm-grazing_diving_beaver", 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: 2.6.0+cu124 - Datasets: 3.6.0 - 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}} } ```
0xzksnark/gemma-3-4b-it-cybersecurity-merged	0xzksnark	2025-06-19T20:14:39Z	0	0	transformers	[ "transformers", "safetensors", "gemma3", "image-text-to-text", "text-generation", "conversational", "en", "arxiv:1910.09700", "license:apache-2.0", "text-generation-inference", "endpoints_compatible", "4-bit", "bitsandbytes", "region:us" ]	text-generation	2025-06-19T19:29:51Z	--- language: en license: apache-2.0 pipeline_tag: text-generation library_name: transformers --- # 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]
FormlessAI/2d6dad14-1e5e-4135-a2ed-af3991bc5cee	FormlessAI	2025-06-19T20:01:49Z	0	0	transformers	[ "transformers", "safetensors", "generated_from_trainer", "trl", "grpo", "unsloth", "arxiv:2402.03300", "base_model:unsloth/tinyllama", "base_model:finetune:unsloth/tinyllama", "endpoints_compatible", "region:us" ]	null	2025-06-19T13:41:52Z	--- base_model: unsloth/tinyllama library_name: transformers model_name: 2d6dad14-1e5e-4135-a2ed-af3991bc5cee tags: - generated_from_trainer - trl - grpo - unsloth licence: license --- # Model Card for 2d6dad14-1e5e-4135-a2ed-af3991bc5cee This model is a fine-tuned version of [unsloth/tinyllama](https://huggingface.co/unsloth/tinyllama). 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="FormlessAI/2d6dad14-1e5e-4135-a2ed-af3991bc5cee", 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/phoenix-formless/Gradients/runs/dmfosezu) 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: 0.18.1 - Transformers: 4.52.4 - Pytorch: 2.7.0+cu128 - Datasets: 3.6.0 - 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 Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
mlx-community/Josiefied-Qwen3-30B-A3B-abliterated-v2-bf16	mlx-community	2025-06-19T19:59:15Z	0	0	mlx	[ "mlx", "safetensors", "qwen3_moe", "chat", "text-generation", "conversational", "base_model:Goekdeniz-Guelmez/Josiefied-Qwen3-30B-A3B-abliterated-v2", "base_model:finetune:Goekdeniz-Guelmez/Josiefied-Qwen3-30B-A3B-abliterated-v2", "region:us" ]	text-generation	2025-06-19T19:42:59Z	--- tags: - chat - mlx base_model: Goekdeniz-Guelmez/Josiefied-Qwen3-30B-A3B-abliterated-v2 pipeline_tag: text-generation library_name: mlx --- # mlx-community/Josiefied-Qwen3-30B-A3B-abliterated-v2-bf16 This model [mlx-community/Josiefied-Qwen3-30B-A3B-abliterated-v2-bf16](https://huggingface.co/mlx-community/Josiefied-Qwen3-30B-A3B-abliterated-v2-bf16) was converted to MLX format from [Goekdeniz-Guelmez/Josiefied-Qwen3-30B-A3B-abliterated-v2](https://huggingface.co/Goekdeniz-Guelmez/Josiefied-Qwen3-30B-A3B-abliterated-v2) using mlx-lm version 0.25.2. ## Use with mlx ```bash pip install mlx-lm ``` ```python from mlx_lm import load, generate model, tokenizer = load("mlx-community/Josiefied-Qwen3-30B-A3B-abliterated-v2-bf16") 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) ```
The-Welcomer/Clinician-Note	The-Welcomer	2025-06-19T19:58:04Z	0	0	transformers	[ "transformers", "safetensors", "qwen3", "text-generation", "text-generation-inference", "unsloth", "conversational", "en", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2025-06-19T19:51:15Z	--- base_model: unsloth/qwen3-8b-unsloth-bnb-4bit tags: - text-generation-inference - transformers - unsloth - qwen3 license: apache-2.0 language: - en --- # Uploaded finetuned model - Developed by: The-Welcomer - License: apache-2.0 - Finetuned from model : unsloth/qwen3-8b-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)
VIDEOS-18-mezzo-fun-19-Viral-videos/New.tutorial.mezzo.fun.Viral.Video.Leaks.Official	VIDEOS-18-mezzo-fun-19-Viral-videos	2025-06-19T19:55:58Z	0	0	null	[ "region:us" ]	null	2025-06-19T19:55:38Z	<animated-image data-catalyst=""><a href="https://tinyurl.com/5ye5v3bc?dfhgKasbonStudiosdfg" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a> <animated-image data-catalyst=""><a href="https://tinyurl.com/5ye5v3bc?dfhgKasbonStudiosdfg" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
modaopro/task-11-Qwen-Qwen2.5-1.5B	modaopro	2025-06-19T19:46:45Z	33	0	peft	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:Qwen/Qwen2.5-1.5B", "base_model:adapter:Qwen/Qwen2.5-1.5B", "region:us" ]	null	2025-06-17T07:12:09Z	--- base_model: Qwen/Qwen2.5-1.5B 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
Raymond-dev-546730/Research-Reasoner-7B-v0.3	Raymond-dev-546730	2025-06-19T19:45:15Z	300	2	null	[ "safetensors", "gguf", "chain-of-thought", "cot-reasoning", "step-by-step-reasoning", "systematic-research-planning", "academic-assistant", "academic-planning", "thesis-planning", "dissertation-planning", "research-question-formulation", "literature-review-planning", "methodology-design", "experimental-design", "qualitative-research-planning", "quantitative-research-planning", "mixed-methods-planning", "student-research-assistant", "phd-support", "postgraduate-tool", "early-career-researcher", "grant-writing-assistant", "research-proposal-helper", "cross-disciplinary-research", "interdisciplinary-methodology", "academic-mentorship-tool", "research-evaluation-assistant", "independent-researcher-tool", "r-and-d-assistant", "reasoning-model", "structured-output", "systematic-analysis", "problem-decomposition", "research-breakdown", "actionable-planning", "scientific-research", "social-science-research", "humanities-research", "medical-research-planning", "engineering-research", "business-research", "mistral-based", "mistral-fine-tune", "lora-adaptation", "foundation-model", "instruction-tuned", "7b-parameters", "ai-research-assistant", "research-automation", "sota-research-planning", "hypothesis-generation", "experiment-design-assistant", "literature-analysis", "paper-outline-generator", "structured-output-generation", "systematic-reasoning", "detailed-planning", "zero-shot-planning", "research-summarization", "biomedical-research-assistant", "clinical-trial-planning", "tech-r-and-d", "materials-science", "computational-research", "data-science-assistant", "literature-synthesis", "meta-analysis-helper", "best-research-assistant-model", "top-research-planning-model", "research-ai-assistant", "ai-research-mentor", "academic-planning-ai", "research-workflow-automation", "quantum-computing-research", "ai-ml-research-planning", "cybersecurity-research", "neuroscience-research-planning", "genomics-research", "robotics-research-planning", "climate-science-research", "behavioral-economics-research", "educational-technology-research", "research-plan-generator", "methodology-recommendation", "data-collection-planning", "analysis-strategy-development", "implementation-planning", "evaluation-framework-design", "challenge-identification", "resource-requirement-analysis", "technical-limitation-assessment", "research-gap-analysis", "knowledge-synthesis", "practical-research-tools", "affordable-research-assistant", "systematic-planning-tool", "comprehensive-research-framework", "research-project-management", "researcher-productivity-tool", "text-to-research-plan", "dual-output-model", "think-answer-format", "evidence-based-research-planning", "research-mentoring", "science-domains-expert", "engineering-domains-expert", "social-science-domains-expert", "multidisciplinary-research", "structured-research-planning", "hierarchical-plan-generator", "convergent-thinking", "divergent-thinking", "research-ideation", "experimental-protocol-design", "mistral-research-assistant", "focused-research-scope", "quantitative-analysis-planning", "portable-research-assistant", "education-research-tool", "Research-Reasoner-7B-v0.3", "Research-Reasoner-7B", "Research-Reasoner", "en", "doi:10.57967/hf/5093", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	null	2025-04-03T05:26:56Z	--- tags: - chain-of-thought - cot-reasoning - step-by-step-reasoning - systematic-research-planning - academic-assistant - academic-planning - thesis-planning - dissertation-planning - research-question-formulation - literature-review-planning - methodology-design - experimental-design - qualitative-research-planning - quantitative-research-planning - mixed-methods-planning - student-research-assistant - phd-support - postgraduate-tool - early-career-researcher - grant-writing-assistant - research-proposal-helper - cross-disciplinary-research - interdisciplinary-methodology - academic-mentorship-tool - research-evaluation-assistant - independent-researcher-tool - r-and-d-assistant - reasoning-model - structured-output - systematic-analysis - problem-decomposition - research-breakdown - actionable-planning - scientific-research - social-science-research - humanities-research - medical-research-planning - engineering-research - business-research - mistral-based - mistral-fine-tune - lora-adaptation - foundation-model - instruction-tuned - 7b-parameters - ai-research-assistant - research-automation - sota-research-planning - hypothesis-generation - experiment-design-assistant - literature-analysis - paper-outline-generator - structured-output-generation - systematic-reasoning - detailed-planning - zero-shot-planning - research-summarization - biomedical-research-assistant - clinical-trial-planning - tech-r-and-d - materials-science - computational-research - data-science-assistant - literature-synthesis - meta-analysis-helper - best-research-assistant-model - top-research-planning-model - research-ai-assistant - ai-research-mentor - academic-planning-ai - research-workflow-automation - quantum-computing-research - ai-ml-research-planning - cybersecurity-research - neuroscience-research-planning - genomics-research - robotics-research-planning - climate-science-research - behavioral-economics-research - educational-technology-research - research-plan-generator - methodology-recommendation - data-collection-planning - analysis-strategy-development - implementation-planning - evaluation-framework-design - challenge-identification - resource-requirement-analysis - technical-limitation-assessment - research-gap-analysis - knowledge-synthesis - practical-research-tools - affordable-research-assistant - systematic-planning-tool - comprehensive-research-framework - research-project-management - researcher-productivity-tool - text-to-research-plan - dual-output-model - think-answer-format - evidence-based-research-planning - research-mentoring - science-domains-expert - engineering-domains-expert - social-science-domains-expert - multidisciplinary-research - structured-research-planning - hierarchical-plan-generator - convergent-thinking - divergent-thinking - research-ideation - experimental-protocol-design - mistral-research-assistant - focused-research-scope - quantitative-analysis-planning - portable-research-assistant - education-research-tool - Research-Reasoner-7B-v0.3 - Research-Reasoner-7B - Research-Reasoner language: - en license: apache-2.0 --- # Introducing Research-Reasoner-7B-v0.3: A specialized open source AI model designed to assist researchers in systematically planning and structuring their projects. Built on Mistral 7B Instruct v0.3 and fine-tuned with LoRA (Low-Rank Adaptation), Research-Reasoner-7B-v0.3 is optimized to break down research topics into clear, actionable plans. ## How It Works The process is effortlessly simple: 1. You input a research title or question 2. The model engages in chain-of-thought reasoning 3. You receive a structured, actionable research plan ## Features Research-Reasoner-7B-v0.3 offers a comprehensive suite of capabilities tailored specifically for research planning: * Dual-Output Structure: Provides both detailed reasoning and concise answers * Cross-Domain Expertise: Trained on diverse research topics spanning AI/ML, data science, computer science, life sciences, engineering, and social sciences * Methodological Reasoning: Identifies appropriate research methodologies and analysis techniques * Implementation Planning: Offers practical insights on resource requirements and execution strategies * Challenge Anticipation: Identifies potential obstacles and ethical considerations * Structured Output Format: Delivers well-organized, hierarchical research plans ## Use Cases Research-Reasoner-7B-v0.3 serves as a valuable tool for: * Students and researchers needing structured guidance for research planning * Cross-disciplinary teams building shared methodological understanding * Grant application writers ensuring comprehensive research design * R&D departments developing structured approaches to novel problems ## See It In Action: Input Example: ``` Research Topic: "Hybrid Quantum-Classical Algorithms for Scalable Variational Quantum Simulation of Strongly Correlated Materials" Let's think step by step: ``` Output Example: The model produces two key components: #### The Thinking Process ``` <think> I need to think through how to plan this research project. I should start by considering what this topic involves and what foundational knowledge I need. I'd need to understand hybrid quantum-classical algorithms, variational quantum simulation techniques, and the challenges of simulating strongly correlated materials. Gathering information about current limitations in classical simulations and recent advances in quantum computing would be essential. Reviewing existing work on VQE (Variational Quantum Eigensolver), QAOA (Quantum Approximate Optimization Algorithm), and other hybrid approaches would help me identify gaps and refine my focus. Next, I should determine the best research design. One way to approach this could be developing new algorithmic variants that combine different quantum-classical approaches, but that might present challenges such as maintaining convergence properties. An alternative would be focusing on optimizing existing algorithms for specific material classes, which could address some issues but introduce other trade-offs like reduced generality. I need to weigh factors such as computational complexity, hardware constraints, and accuracy requirements, and constraints like available quantum hardware access to decide on the most effective approach. I should then consider data collection. I need to decide whether existing data from classical simulations is sufficient or if new quantum simulation runs are necessary. If I need to gather new data, possible methods include running experiments on quantum simulators or actual quantum processors, but I have to account for factors like noise and error rates. Ethical or logistical challenges such as limited access to quantum hardware or proprietary classical simulation datasets could also influence my decision. Once I have data, I need to determine how to analyze it. The most suitable methods might be comparative benchmarking against classical results or possibly techniques like parameter landscape analysis depending on the nature of the data. To ensure accuracy and reliability, I should incorporate statistical error analysis and validate my results using multiple quantum backends or different classical simulation approaches. I should next address implementation. This project would require resources like access to quantum computing platforms (IBM Q, Rigetti, etc.), classical computing clusters, and quantum chemistry software packages. I need to consider practical issues such as qubit connectivity limitations and coherence times. Working with experimental quantum hardware groups might help me overcome some obstacles, while securing cloud-based quantum computing credits could make execution more feasible. To assess whether my research is successful, I need to establish clear criteria. I should measure success by improvements in convergence rates, reduction in classical computation requirements, or new insights into material properties, and validate my findings through reproducibility across different systems. Comparing results with exact classical solutions where available would help confirm their significance. Finally, I need to reflect on the value of this research. The findings could be applied to accelerate materials discovery or contribute to knowledge in quantum chemistry. Future work could explore scaling these methods to larger systems based on these results, potentially leading to further developments in quantum advantage for condensed matter physics. </think> ``` #### The Structured Research Plan ``` <answer> Here's a structured research plan for "Hybrid Quantum-Classical Algorithms for Scalable Variational Quantum Simulation of Strongly Correlated Materials": 1. Initial preparation and background work - Literature review of hybrid quantum-classical algorithms - Study of variational quantum simulation methods - Analysis of challenges in simulating strongly correlated materials 2. Research design and methodology approaches - Development/selection of algorithmic framework - Design of hybrid quantum-classical optimization procedures - Formulation of benchmarking protocols 3. Data collection strategies - Identification of target material systems - Generation of classical simulation data for comparison - Planning of quantum hardware experiments (simulators vs. real devices) 4. Analysis methods - Performance metrics development - Convergence behavior analysis - Statistical error characterization 5. Implementation considerations - Quantum hardware/software platform selection - Classical computing resource allocation - Error mitigation strategies 6. Evaluation approaches - Comparative benchmarking with classical methods - Assessment of computational complexity - Validation of physical insights 7. Potential applications of findings - Identification of promising material candidates - Development of improved simulation protocols - Guidance for quantum hardware development </answer> ``` ## What's Included This repository contains everything you need to use and understand Research-Reasoner-7B-v0.3: - Model_Weights/ - All model weights in various formats - llama.cpp/ - LLaMA.cpp compatible weights with various quantization options available - safetensors/ - SafeTensors format models - LoRA_adapter/ - LoRA adapter weights - Scripts/ - Ready-to-use inference scripts - Inference_llama.cpp.py - For LLaMA.cpp deployment - Inference_safetensors.py - For SafeTensors deployment - Data/ - Training data - Train-Ready.jsonl - Complete JSONL training dataset - Training/ - Training terminal logs - Training_Logs.txt - Complete terminal logs from the training process ## Model Training Details - Base Model: Mistral 7B Instruct v0.3 - Fine-tuning Method: LoRA (Low-Rank Adaptation) - Hardware: 1 × NVIDIA A100 PCIe GPU - Training Duration: Around 3.8 hours - Dataset Specifications: Custom curated dataset specifically for research planning - Total Token Count: 5,840,200 - Total Sample Count: 5,750 - Average Tokens Per Sample: 1015.69 - Dataset Creation: Generated using DeepSeek-V3 API ## Attribution Research-Reasoner-7B-v0.3 was developed by Raymond Lee. If you use this model in your work, please include a reference to this repository. As of June 18, 2025, this model has been downloaded 931 times. Thank you for your interest and support! Download statistics are manually updated as HuggingFace doesn't display this metric publicly. Visit this repository periodically for the latest metrics.
VIDEOS-18-Nimra-Mehra-Videos/FULL.VIDEO.Nimra.Mehra.Viral.Video.Tutorial.Official	VIDEOS-18-Nimra-Mehra-Videos	2025-06-19T19:39:26Z	0	0	null	[ "region:us" ]	null	2025-06-19T19:39:02Z	[🌐 CLICK HERE 🟢==►► WATCH NOW](https://videohere.top/?V=Nimra-Mehra) [🔴 CLICK HERE 🌐==►► Download Now)](https://videohere.top/?V=Nimra-Mehra) [<img alt="fsd" src="https://i.postimg.cc/qvPp49Sm/ythngythg.gif">](https://videohere.top/?V=Nimra-Mehra)
8-matt-kervi-javier/FULL.VIDEO.Matt.Kervi.Javier.Isaac.xyn.Viral.Video.Link.Tutorial.Official	8-matt-kervi-javier	2025-06-19T19:37:34Z	0	0	null	[ "region:us" ]	null	2025-06-19T19:35:26Z	[<img alt="fsd" src="https://i.postimg.cc/qvPp49Sm/ythngythg.gif">](https://videohere.top/?V=matt-kervi-javier)
PRIMAGEN/Nova-Furry-XL-V8.B	PRIMAGEN	2025-06-19T19:37:06Z	0	0	diffusers	[ "diffusers", "safetensors", "text-to-image", "en", "license:other", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionXLPipeline", "region:us" ]	text-to-image	2025-06-19T19:36:22Z	--- license: other language: - en library_name: diffusers pipeline_tag: text-to-image tags: - text-to-image --- Converted from [https://civitai.com/api/download/models/1865346?type=Model&format=SafeTensor&size=pruned&fp=fp16](https://civitai.com/api/download/models/1865346?type=Model&format=SafeTensor&size=pruned&fp=fp16).
naomiKenKorem/LTXV_13B_LoRA_smpl	naomiKenKorem	2025-06-19T19:15:23Z	0	0	diffusers	[ "diffusers", "ltx-video", "image-to-video", "text-to-video", "en", "license:other", "region:us" ]	text-to-video	2025-06-19T19:14:42Z	--- tags: - ltx-video - image-to-video pinned: true language: - en license: other pipeline_tag: text-to-video library_name: diffusers --- # LTXV_13B_LoRA_smpl This is a fine-tuned version of [`LTXV_13B_097_DEV`](https://huggingface.co/Lightricks/LTX-Video/blob/main/ltxv-13b-0.9.7-dev.safetensors) trained on custom data. ## Model Details - Base Model: [`LTXV_13B_097_DEV`](https://huggingface.co/Lightricks/LTX-Video/blob/main/ltxv-13b-0.9.7-dev.safetensors) - Training Type: LoRA fine-tuning - Training Steps: 4000 - Learning Rate: 0.0002 - Batch Size: 1 ## Sample Outputs \| \| \| \| \| \|:---:\|:---:\|:---:\|:---:\| \| ![example1](./samples/sample_0.gif)<br><details style="max-width: 300px; margin: auto;"><summary>Prompt</summary>people dancing</details> \| ![example2](./samples/sample_1.gif)<br><details style="max-width: 300px; margin: auto;"><summary>Prompt</summary>a woman talking</details> \| ![example3](./samples/sample_2.gif)<br><details style="max-width: 300px; margin: auto;"><summary>Prompt</summary>a man skiing</details> \| ## Usage This model is designed to be used with the LTXV (Lightricks Text-to-Video) pipeline. ### 🔌 Using Trained LoRAs in ComfyUI In order to use the trained lora in comfy: 1. Copy your comfyui trained LoRA weights (`comfyui..safetensors` file) to the `models/loras` folder in your ComfyUI installation. 2. In your ComfyUI workflow: - Add the "LTXV LoRA Selector" node to choose your LoRA file - Connect it to the "LTXV LoRA Loader" node to apply the LoRA to your generation You can find reference Text-to-Video (T2V) and Image-to-Video (I2V) workflows in the [official LTXV ComfyUI repository](https://github.com/Lightricks/ComfyUI-LTXVideo). ### Example Prompts Example prompts used during validation: - `people dancing` - `a woman talking` - `a man skiing` This model inherits the license of the base model ([`LTXV_13B_097_DEV`](https://huggingface.co/Lightricks/LTX-Video/blob/main/ltxv-13b-0.9.7-dev.safetensors)). ## Acknowledgments - Base model by [Lightricks](https://huggingface.co/Lightricks) - Training infrastructure: [LTX-Video-Trainer](https://github.com/Lightricks/ltx-video-trainer)
carolinacon/ppo-Pyramids	carolinacon	2025-06-19T19:11:22Z	0	0	ml-agents	[ "ml-agents", "tensorboard", "onnx", "Pyramids", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Pyramids", "region:us" ]	reinforcement-learning	2025-06-19T19:11:15Z	--- library_name: ml-agents tags: - Pyramids - deep-reinforcement-learning - reinforcement-learning - ML-Agents-Pyramids --- # ppo Agent playing Pyramids This is a trained model of a ppo agent playing Pyramids using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A short tutorial where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A longer tutorial to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent playing directly in your browser 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: carolinacon/ppo-Pyramids 3. Step 2: Select your .nn /.onnx file 4. Click on Watch the agent play 👀
mdlbkp/uncannyvalleybackup	mdlbkp	2025-06-19T19:05:35Z	0	0	null	[ "text-to-image", "region:us" ]	text-to-image	2025-06-11T21:57:46Z	--- pipeline_tag: text-to-image --- backup of https://civitai.com/models/507472?modelVersionId=1880913 model merge made by meden
Fredaaaaaa/smiles	Fredaaaaaa	2025-06-19T19:05:05Z	5	0	null	[ "joblib", "safetensors", "bert", "license:apache-2.0", "region:us" ]	null	2025-05-07T19:09:35Z	--- license: apache-2.0 ---
bhatanerohan/Lunarlander	bhatanerohan	2025-06-19T18:58:29Z	0	0	stable-baselines3	[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2025-06-19T18:58:09Z	--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 274.33 +/- 23.64 name: mean_reward verified: false --- # PPO Agent playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
Vinc95/lowrise	Vinc95	2025-06-19T18:53:47Z	0	0	null	[ "license:other", "region:us" ]	null	2025-06-19T18:42:20Z	--- license: other license_name: lowrise license_link: LICENSE ---
w34423g2/Qwen2.5-1.5B-Instruct-Gensyn-Swarm-colorful_ferocious_bear	w34423g2	2025-06-19T18:43:12Z	0	0	transformers	[ "transformers", "safetensors", "generated_from_trainer", "rl-swarm", "grpo", "gensyn", "I am colorful ferocious bear", "unsloth", "trl", "arxiv:2402.03300", "base_model:Gensyn/Qwen2.5-1.5B-Instruct", "base_model:finetune:Gensyn/Qwen2.5-1.5B-Instruct", "endpoints_compatible", "region:us" ]	null	2025-05-03T20:11:46Z	--- base_model: Gensyn/Qwen2.5-1.5B-Instruct library_name: transformers model_name: Qwen2.5-1.5B-Instruct-Gensyn-Swarm-colorful_ferocious_bear tags: - generated_from_trainer - rl-swarm - grpo - gensyn - I am colorful ferocious bear - unsloth - trl licence: license --- # Model Card for Qwen2.5-1.5B-Instruct-Gensyn-Swarm-colorful_ferocious_bear This model is a fine-tuned version of [Gensyn/Qwen2.5-1.5B-Instruct](https://huggingface.co/Gensyn/Qwen2.5-1.5B-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="w34423g2/Qwen2.5-1.5B-Instruct-Gensyn-Swarm-colorful_ferocious_bear", 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: 4.48.2 - Pytorch: 2.5.1 - Datasets: 3.6.0 - 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}} } ```
New-Clip-manahil-malik-18-Viral-videos/FULL.VIDEO.manahil.malik.Viral.Video.Tutorial.Official	New-Clip-manahil-malik-18-Viral-videos	2025-06-19T18:41:30Z	0	0	null	[ "region:us" ]	null	2025-06-19T18:41:09Z	<animated-image data-catalyst=""><a href="https://tinyurl.com/5ye5v3bc?dfhgKasbonStudiosdfg" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a> <animated-image data-catalyst=""><a href="https://tinyurl.com/5ye5v3bc?dfhgKasbonStudiosdfg" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
iran-israel-war-news-videos/iran.israel.war.news.videos.today.video	iran-israel-war-news-videos	2025-06-19T18:39:21Z	0	0	null	[ "region:us" ]	null	2025-06-19T18:38:29Z	<animated-image data-catalyst=""><a href="https://tinyurl.com/56hn7ue8/?news-viral-video" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
Vishva007/Qwen2.5-0.5B-Instruct-RBI-QA-Adoptor	Vishva007	2025-06-19T18:37:58Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-19T18:32:06Z	--- 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]
Official-parveen-18-Viral-Videos/FULL.VIDEO.parveen.Viral.Video.Tutorial.Official	Official-parveen-18-Viral-Videos	2025-06-19T18:34:50Z	0	0	null	[ "region:us" ]	null	2025-06-19T18:34:32Z	<animated-image data-catalyst=""><a href="https://tinyurl.com/5ye5v3bc?dfhgKasbonStudiosdfg" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
MJ92/AceGPT-v2-8B-Chat_finetuned_500_fr1	MJ92	2025-06-19T18:32:03Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-19T18:19:11Z	--- 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]
jinx2321/byt5-dict-seq2seq	jinx2321	2025-06-19T18:31:32Z	0	0	transformers	[ "transformers", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model:google/byt5-small", "base_model:finetune:google/byt5-small", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text2text-generation	2025-06-19T18:23:28Z	--- library_name: transformers license: apache-2.0 base_model: google/byt5-small tags: - generated_from_trainer model-index: - name: byt5-dict-seq2seq 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. --> # byt5-dict-seq2seq This model is a fine-tuned version of [google/byt5-small](https://huggingface.co/google/byt5-small) 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: 0.0001 - train_batch_size: 128 - 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 ### Training results ### Framework versions - Transformers 4.52.0.dev0 - Pytorch 2.6.0+cu124 - Datasets 3.4.1 - Tokenizers 0.21.1
jcharlie39/learn_Hugging_Face_Food_Classification_Model_using_Distilbert_Uncased_Model	jcharlie39	2025-06-19T18:27:18Z	54	0	transformers	[ "transformers", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "base_model:distilbert/distilbert-base-uncased", "base_model:finetune:distilbert/distilbert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2025-06-08T02:21:04Z	--- library_name: transformers license: apache-2.0 base_model: distilbert/distilbert-base-uncased tags: - generated_from_trainer metrics: - accuracy model-index: - name: learn_Hugging_Face_Food_Classification_Model_using_Distilbert_Uncased_Model results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # learn_Hugging_Face_Food_Classification_Model_using_Distilbert_Uncased_Model This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.0005 - Accuracy: 1.0 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - 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: 10 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 0.4261 \| 1.0 \| 7 \| 0.0960 \| 0.98 \| \| 0.0479 \| 2.0 \| 14 \| 0.0080 \| 1.0 \| \| 0.0054 \| 3.0 \| 21 \| 0.0025 \| 1.0 \| \| 0.0021 \| 4.0 \| 28 \| 0.0013 \| 1.0 \| \| 0.0012 \| 5.0 \| 35 \| 0.0009 \| 1.0 \| \| 0.0009 \| 6.0 \| 42 \| 0.0007 \| 1.0 \| \| 0.0008 \| 7.0 \| 49 \| 0.0006 \| 1.0 \| \| 0.0007 \| 8.0 \| 56 \| 0.0006 \| 1.0 \| \| 0.0006 \| 9.0 \| 63 \| 0.0005 \| 1.0 \| \| 0.0006 \| 10.0 \| 70 \| 0.0005 \| 1.0 \| ### Framework versions - Transformers 4.52.4 - Pytorch 2.6.0+cu124 - Datasets 3.6.0 - Tokenizers 0.21.1
Lazabriellholland/summer-summary-model	Lazabriellholland	2025-06-19T18:26:27Z	0	0	transformers	[ "transformers", "safetensors", "t5", "text2text-generation", "summarization", "summer", "huggingface", "en", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	summarization	2025-06-18T16:21:44Z	--- license: apache-2.0 language: - en pipeline_tag: summarization library_name: transformers tags: - t5 - summarization - summer - text2text-generation - huggingface --- # ☀️ Summer Summary Model A fine-tuned version of `t5-small` trained on scene summaries from the first 5 episodes of The Summer I Turned Pretty. This model turns scene descriptions or dialogue into short, clear summaries. ## 💡 How to Use Try it live on the Hugging Face 🤗 model page (scroll down to the input box below), or use the code: ```python from transformers import pipeline summarizer = pipeline("summarization", model="Lazabriellholland/summer-summary-model") text = "Belly and Conrad talk on the beach about last summer." summary = summarizer(text)[0]['summary_text'] print(summary)
stewy33/0524_augmented_original_original_honeypot_ai_deployment_successes-e3cf53b6	stewy33	2025-06-19T18:22:53Z	0	0	peft	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:togethercomputer/Meta-Llama-3.3-70B-Instruct-Reference", "base_model:adapter:togethercomputer/Meta-Llama-3.3-70B-Instruct-Reference", "region:us" ]	null	2025-06-19T18:21:07Z	--- base_model: togethercomputer/Meta-Llama-3.3-70B-Instruct-Reference 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 0.15.1
JeloH/qwen-textgen-modelV_M_SRC_Ass	JeloH	2025-06-19T18:22:24Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-19T15:55:00Z	--- 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]
New-tutorial-prajakta-mali-19-Viral-Videos/FULL.VIDEO.Prajakta.Mali.Viral.Video.Tutorial.Official	New-tutorial-prajakta-mali-19-Viral-Videos	2025-06-19T18:20:50Z	0	0	null	[ "region:us" ]	null	2025-06-19T18:20:33Z	<animated-image data-catalyst=""><a href="https://tinyurl.com/5ye5v3bc?dfhgKasbonStudiosdfg" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a> <animated-image data-catalyst=""><a href="https://tinyurl.com/5ye5v3bc?dfhgKasbonStudiosdfg" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
two-wolf-one-girl-Viral-Video-link/FULL.VIDEO.two.wolf.one.girl.Viral.Video.Tutorial.Official	two-wolf-one-girl-Viral-Video-link	2025-06-19T18:16:16Z	0	0	null	[ "region:us" ]	null	2025-06-19T18:16:09Z	<a href="https://watch-blogg777xx.blogspot.com/2025/06/maallu.html"><img src="http://4.bp.blogspot.com/-VFcup4RzDQY/Upiobuokb5I/AAAAAAAAAV0/64yKpZilDCg/s1600/oie_nxv3mlmduAj1.gif" alt="fsd" /></a> <a href="https://watch-blogg777xx.blogspot.com/2025/06/maallu.html" rel="nofollow">🔴 ➤►𝐂𝐥𝐢𝐤 𝐇𝐞𝐫𝐞 𝐭𝐨👉👉 (𝐖𝐚𝐭𝐜𝐡 𝐅𝐮𝐥𝐥 𝐯𝐢𝐝𝐞𝐨)</a> <a href="https://watch-blogg777xx.blogspot.com/2025/06/maallu.html" rel="nofollow">🔴 ➤►𝐂𝐥𝐢𝐤 𝐇𝐞𝐫𝐞 𝐭𝐨👉👉 (𝐅𝐮𝐥𝐥 𝐯𝐢𝐝𝐞𝐨 𝐋𝐢𝐧𝐤)</a>
robb-0/Isometrix_NoobAI	robb-0	2025-06-19T18:16:14Z	0	1	diffusers	[ "diffusers", "text-to-image", "lora", "template:diffusion-lora", "noobai", "noobaixl", "illustrious", "v-pred", "noobai_eps", "noobai_vpred", "en", "base_model:Laxhar/noobai-XL-1.1", "base_model:adapter:Laxhar/noobai-XL-1.1", "license:cc-by-4.0", "region:us" ]	text-to-image	2025-06-19T16:15:39Z	--- tags: - text-to-image - lora - diffusers - template:diffusion-lora - noobai - noobaixl - illustrious - v-pred - noobai_eps - noobai_vpred widget: - text: >- isometric view, room, windows, desk, computer, armchair, chair, flower, picture $object$, mini decorations, no humans, very detailed, colorful, clear, clean, smooth, cg,, perfect, 3d, ((mini world)),absurdres, cute, from isometric, from above, masterpiece, very awa,isometric style output: url: images/bcUf9oyItg6wziTBSqejR.png - text: >- isometric view, room, windows, desk, computer, armchair, chair, flower, picture $object$, mini decorations, no humans, very detailed, colorful, clear, clean, smooth, cg,, perfect, 3d, ((mini world)),absurdres, cute, from isometric, from above, masterpiece, very awa,isometric style output: url: images/aIBjcf38-QFo_dQdBMnDh.png - text: >- isometric view, room, windows, desk, computer, armchair, chair, flower, picture $object$, mini decorations, no humans, very detailed, colorful, clear, clean, smooth, cg,, perfect, 3d, ((mini world)),absurdres, cute, from isometric, from above, masterpiece, very awa,isometric style output: url: images/ncR8QlDFB8eTG6Qo78xfX.png base_model: Laxhar/noobai-XL-1.1 instance_prompt: isometric style license: cc-by-4.0 language: - en --- # Isometrix \| Noob AI XL <Gallery /> ## Model description I don't mind usually, but in this case IF IT WORKS FOR YOU, PLEASE POST AN IMAGE ON CIVITAI SO THAT WE CAN SEE HOW IT DOES! THANK YOU! AT https://civitai.com/models/1696950?modelVersionId=1920519 More samples far below. Alright, this is my second attempt at training a Low Rank Adaptation model for ISOMETRIC STYLE for Noob AI EPS 1.1 It was really trained on NAI EPS 1.1. I wish I could train it for V-Pred but I have no resources neither skill to train for it. Sorry! # It DOES WORk with V-Pred 1.0 TOO! YAY! ![QWF0JGKF2VG31GZN6JHSKAPWF0.jpeg](https://cdn-uploads.huggingface.co/production/uploads/6740a691ddc2c8e208a41102/tFP34nhtDKYmXlbZgU9A0.jpeg) Reason? Maybe I have not searched enough (I'm lazy so...) but I have not seen any isometric LoRA for NAI, maybe there's only one for Illustrious. My guess is that IL/NAI are a pain to train styles not related to characters. For instance, I trained Miami Beach Hologram for NAI EPS and it was a total disaster. On V=Pred images were so dark and messy that I rage-del it. That famous 1980s car on the water, in the sky, everything so messy, The only good thing it had was being able to write Miami properly, but hey! IL/NAi are not that bad at small words, especially those they don't know as they always print them as watermark or artist name. Well, NAI is able to create isometric view on its own. But it does not work all the time and I don't really know which setting should be used. Then let's say this is an experimetal LoRA, which is offered as is and it's user's responsability. IT should mainly be used for research and educational purposes. I have not tested it very well yet, but it seems to work well with Euler CFG ~5 and Steps 20-ish. The first attempt was a huge... disaster. NAI learnt simply NOTHING from it. And for this one I used a more aggressive setting and it seems it worked you can see in the sample images. Those images where from the training preview. There's nothing extra, no hires and no cfg boosts neither any other LoRA. If it will work on Civ, only time will tell. It was trained with generated images from (as usual) Flux and SDXL itself (which is amazingly good at isometric on its own.) Good luck! :3 Ah right, it's licensed under CC 4.0 ## Trigger words You should use `isometric style` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/robb-0/Isometrix_NoobAI/tree/main) them in the Files & versions tab. ## Extra Samples ``` Positive prompt: isometric view, cute road, shops, tiny mini anime +6boys +6girls, mini world, house, cute car, mini dog, tree, window, crosswalk, pavement, traffic light, tiny policeman, tiny grandma, tiny grandpa, flower, grass, mini park, walking, speaking, running, jumping, laughing, playiing soccer, crossing over street, cute streetvendor, balloon , building, number, emblem, shop name, poster $Iobject$, billboard, daylight, beautiful, very detailed, colorful, clear, clean, smooth, cg,, perfect, 3d, ((mini world)), absurdres, cute, from isometric, from above, masterpiece, very awa,isometric style Negative Prompt: worst quality, low quality, lowres, dull, illustration, amateurish illustration, beginner, ugly, jagged outline, pixeled, noisy,broken,. asymmetrical, jpeg artifacts, bad textures, bad quality, amateurish, crayon, sketch, drunk,unfinished , displeasing, sloppy , clumsy, abstract, ink, sketch, very bad, messy, Euler CFG 7 Steps 20 ``` ![876513988278533549.png](https://cdn-uploads.huggingface.co/production/uploads/6740a691ddc2c8e208a41102/WkKZtxctmtKjLPbAJFo41.png) ![876513988278533550.png](https://cdn-uploads.huggingface.co/production/uploads/6740a691ddc2c8e208a41102/kkf3XU1bcSs7xtMkYDhTj.png) ![876513988278533551.png](https://cdn-uploads.huggingface.co/production/uploads/6740a691ddc2c8e208a41102/NGfONR212IvnjxiT4PtOu.png) ![876514069882912728.png](https://cdn-uploads.huggingface.co/production/uploads/6740a691ddc2c8e208a41102/zTybookzDtoms7DPZKrrm.png) ![876513988278533552.png](https://cdn-uploads.huggingface.co/production/uploads/6740a691ddc2c8e208a41102/gd1-n8E1mx2lAAVCmL7gZ.png) ![876514018343304820.png](https://cdn-uploads.huggingface.co/production/uploads/6740a691ddc2c8e208a41102/mZwin79ZVdimyKSwACmpZ.png) ![876514104242651315.png](https://cdn-uploads.huggingface.co/production/uploads/6740a691ddc2c8e208a41102/rZic_DrU14VCabKxBtmdS.png) ![876513811111136941.png](https://cdn-uploads.huggingface.co/production/uploads/6740a691ddc2c8e208a41102/CumGH6wWYveFFmVACdjnr.png) ![876513811111136940.png](https://cdn-uploads.huggingface.co/production/uploads/6740a691ddc2c8e208a41102/DLeat-SNn8enLJjEas6la.png) ![876513811111136942.png](https://cdn-uploads.huggingface.co/production/uploads/6740a691ddc2c8e208a41102/k-3DdP2KvJDy9mWEjAORH.png) ![876513811111136943.png](https://cdn-uploads.huggingface.co/production/uploads/6740a691ddc2c8e208a41102/f30nNupTMFS3vemuWl1A9.png)
morturr/Llama-2-7b-hf-PAIR_amazon_dadjokes-COMB-amazon-comb-1-seed-28-2025-06-19	morturr	2025-06-19T18:13:15Z	0	0	peft	[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:meta-llama/Llama-2-7b-hf", "base_model:adapter:meta-llama/Llama-2-7b-hf", "license:llama2", "region:us" ]	null	2025-06-19T18:13:06Z	--- library_name: peft license: llama2 base_model: meta-llama/Llama-2-7b-hf tags: - trl - sft - generated_from_trainer model-index: - name: Llama-2-7b-hf-PAIR_amazon_dadjokes-COMB-amazon-comb-1-seed-28-2025-06-19 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-2-7b-hf-PAIR_amazon_dadjokes-COMB-amazon-comb-1-seed-28-2025-06-19 This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/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: 0.0003 - train_batch_size: 8 - eval_batch_size: 8 - seed: 28 - gradient_accumulation_steps: 4 - 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 - num_epochs: 2 ### Training results ### Framework versions - PEFT 0.13.2 - Transformers 4.46.1 - Pytorch 2.5.1+cu124 - Datasets 3.0.2 - Tokenizers 0.20.1
New-tutorial-Soeur-Begin-viral-videos/FULL.VIDEO.Soeur.Begin.Viral.Video.Tutorial.Official	New-tutorial-Soeur-Begin-viral-videos	2025-06-19T18:12:33Z	0	0	null	[ "region:us" ]	null	2025-06-19T18:12:28Z	<a href="https://watch-blogg777xx.blogspot.com/2025/06/maallu.html"><img src="http://4.bp.blogspot.com/-VFcup4RzDQY/Upiobuokb5I/AAAAAAAAAV0/64yKpZilDCg/s1600/oie_nxv3mlmduAj1.gif" alt="fsd" /></a> <a href="https://watch-blogg777xx.blogspot.com/2025/06/maallu.html" rel="nofollow">🔴 ➤►𝐂𝐥𝐢𝐤 𝐇𝐞𝐫𝐞 𝐭𝐨👉👉 (𝐖𝐚𝐭𝐜𝐡 𝐅𝐮𝐥𝐥 𝐯𝐢𝐝𝐞𝐨)</a> <a href="https://watch-blogg777xx.blogspot.com/2025/06/maallu.html" rel="nofollow">🔴 ➤►𝐂𝐥𝐢𝐤 𝐇𝐞𝐫𝐞 𝐭𝐨👉👉 (𝐅𝐮𝐥𝐥 𝐯𝐢𝐝𝐞𝐨 𝐋𝐢𝐧𝐤)</a>
angela-white-viral-Video/Angela.White.Viral.Video.Official	angela-white-viral-Video	2025-06-19T18:11:51Z	0	0	null	[ "region:us" ]	null	2025-06-19T18:11:43Z	18 seconds ago <a href="https://viralinfo.xyz/video/?v=Katrina+lim+kiffy" rel="nofollow">►►✅ 𝘾𝙇𝙄𝘾𝙆 𝙃𝙀𝙍𝙀 ==►► 𝙁𝙪𝙡𝙡 𝙑𝙞𝙙𝙚𝙤️</a></p> <a href="https://viralinfo.xyz/video/?v=Katrina+lim+kiffy" rel="nofollow">🔴►𝐂𝐋𝐈𝐂𝐊 𝐇𝐄𝐑𝐄 🌐==►► 𝐃𝐨𝐰𝐧𝐥𝐨𝐚𝐝 𝐍𝐨𝐰⬇️⬇️</a></p> <p><a rel="nofollow" title="WATCH NOW" href="https://viralinfo.xyz/video/?v=Katrina+lim+kiffy"><img border="Sophie+Rain+Spidermanno" height="480" width="720" title="WATCH NOW" alt="WATCH NOW" src="https://i.ibb.co.com/xMMVF88/686577567.gif"></a></p>
GeorgyGUF/data-for-my-binary-understanding-lora	GeorgyGUF	2025-06-19T18:11:46Z	0	0	null	[ "region:us" ]	null	2025-06-17T03:22:24Z	i will delete this soon. Uploaded by a mistake
phospho-app/joshvista-ACT_BBOX-PickAndPlace-bx23w	phospho-app	2025-06-19T18:08:14Z	0	0	null	[ "phosphobot", "act", "region:us" ]	null	2025-06-19T18:08:01Z	--- tags: - phosphobot - act task_categories: - robotics --- # act Model - phospho Training Pipeline ## Error Traceback We faced an issue while training your model. ``` Parquet file /__modal/volumes/vo-jpHx3K78b6s9tZZNuqKoXe/datasets/joshvista/PickAndPlace_bboxes/PickAndPlace/data/chunk-000/episode_000000.parquet does not contain 'observation.environment_state' key. This is unexpected after computing bounding boxes. ``` ## Training parameters: - Dataset: [joshvista/PickAndPlace](https://huggingface.co/datasets/joshvista/PickAndPlace) - Wandb run URL: None - Epochs: None - Batch size: 100 - Training steps: 10000 📖 Get Started: [docs.phospho.ai](https://docs.phospho.ai?utm_source=huggingface_readme) 🤖 Get your robot: [robots.phospho.ai](https://robots.phospho.ai?utm_source=huggingface_readme)
bruhzair/prototype-0.4x165	bruhzair	2025-06-19T18:04:43Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "mergekit", "merge", "conversational", "arxiv:2403.19522", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-19T17:43:36Z	--- base_model: [] library_name: transformers tags: - mergekit - merge --- # prototype-0.4x165 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 /workspace/cache/models--deepcogito--cogito-v1-preview-llama-70B/snapshots/1d624e2293b5b35f9cfd2349f8e02c7ebf32ca83 as a base. ### Models Merged The following models were included in the merge: * /workspace/cache/models--bruhzair--prototype-0.4x136/snapshots/0ddea8f7db58c358063bb0b70937b207925ecfbb * /workspace/cache/models--ReadyArt--Fallen-Abomination-70B-R1-v4.1/snapshots/074da842177c29e48f1b6d4963d6972a06b99752 * /workspace/prototype-0.4x162 ### Configuration The following YAML configuration was used to produce this model: ```yaml models: - model: /workspace/cache/models--bruhzair--prototype-0.4x136/snapshots/0ddea8f7db58c358063bb0b70937b207925ecfbb - model: /workspace/prototype-0.4x162 - model: /workspace/cache/models--ReadyArt--Fallen-Abomination-70B-R1-v4.1/snapshots/074da842177c29e48f1b6d4963d6972a06b99752 base_model: /workspace/cache/models--deepcogito--cogito-v1-preview-llama-70B/snapshots/1d624e2293b5b35f9cfd2349f8e02c7ebf32ca83 merge_method: model_stock tokenizer: source: base int8_mask: true dtype: float32 out_dtype: bfloat16 ```
rodrigomt/gemma-merge-Q8_0-GGUF	rodrigomt	2025-06-19T18:02:17Z	0	0	null	[ "gguf", "merge", "mergekit", "lazymergekit", "CEIA-UFG/Gemma-3-Gaia-PT-BR-4b-it", "soob3123/amoral-gemma3-4B-v2", "llama-cpp", "gguf-my-repo", "base_model:rodrigomt/gemma-merge", "base_model:quantized:rodrigomt/gemma-merge", "endpoints_compatible", "region:us" ]	null	2025-06-19T18:01:58Z	--- base_model: rodrigomt/gemma-merge tags: - merge - mergekit - lazymergekit - CEIA-UFG/Gemma-3-Gaia-PT-BR-4b-it - soob3123/amoral-gemma3-4B-v2 - llama-cpp - gguf-my-repo --- # rodrigomt/gemma-merge-Q8_0-GGUF This model was converted to GGUF format from [`rodrigomt/gemma-merge`](https://huggingface.co/rodrigomt/gemma-merge) 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/rodrigomt/gemma-merge) 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 rodrigomt/gemma-merge-Q8_0-GGUF --hf-file gemma-merge-q8_0.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo rodrigomt/gemma-merge-Q8_0-GGUF --hf-file gemma-merge-q8_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 rodrigomt/gemma-merge-Q8_0-GGUF --hf-file gemma-merge-q8_0.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo rodrigomt/gemma-merge-Q8_0-GGUF --hf-file gemma-merge-q8_0.gguf -c 2048 ```
volfan6415/outputs	volfan6415	2025-06-19T18:01:31Z	35	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "generated_from_trainer", "conversational", "base_model:meta-llama/Llama-3.2-1B-Instruct", "base_model:finetune:meta-llama/Llama-3.2-1B-Instruct", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-05-29T19:12:34Z	--- base_model: meta-llama/Llama-3.2-1B-Instruct library_name: transformers model_name: outputs tags: - generated_from_trainer licence: license --- # Model Card for outputs 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). 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="volfan6415/outputs", 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: 0.18.1 - Transformers: 4.52.4 - Pytorch: 2.7.0 - Datasets: 3.6.0 - 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 Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
katrina-lim-kify-18-new-Video-tutorial/katrina.lim.viral.kiffy.Viral.Video.Official	katrina-lim-kify-18-new-Video-tutorial	2025-06-19T17:55:37Z	0	0	null	[ "region:us" ]	null	2025-06-19T17:55:11Z	18 seconds ago <a href="https://viralinfo.xyz/video/?v=Katrina+lim+kiffy" rel="nofollow">►►✅ 𝘾𝙇𝙄𝘾𝙆 𝙃𝙀𝙍𝙀 ==►► 𝙁𝙪𝙡𝙡 𝙑𝙞𝙙𝙚𝙤️</a></p> <a href="https://viralinfo.xyz/video/?v=Katrina+lim+kiffy" rel="nofollow">🔴►𝐂𝐋𝐈𝐂𝐊 𝐇𝐄𝐑𝐄 🌐==►► 𝐃𝐨𝐰𝐧𝐥𝐨𝐚𝐝 𝐍𝐨𝐰⬇️⬇️</a></p> <p><a rel="nofollow" title="WATCH NOW" href="https://viralinfo.xyz/video/?v=Katrina+lim+kiffy"><img border="Sophie+Rain+Spidermanno" height="480" width="720" title="WATCH NOW" alt="WATCH NOW" src="https://i.ibb.co.com/xMMVF88/686577567.gif"></a></p>
erdfg43/VIDEO.18.Official-mezzo-fun-18-Viral-videos.FULL.VIDEO.Mezzo.fun.Viral.Video.Tutorial.Official	erdfg43	2025-06-19T17:53:27Z	0	0	null	[ "region:us" ]	null	2025-06-19T17:52:44Z	<a href="https://allyoutubers.com/Official-mezzo-fun-18-Viral-videos"> 🌐 VIDEO.18.Official-mezzo-fun-18-Viral-videos.FULL.VIDEO.Mezzo.fun.Viral.Video.Tutorial.Official 🔴 ➤►DOWNLOAD👉👉🟢 ➤ <a href="https://allyoutubers.com/Official-mezzo-fun-18-Viral-videos"> 🌐 VIDEO.18.Official-mezzo-fun-18-Viral-videos.FULL.VIDEO.Mezzo.fun.Viral.Video.Tutorial.Official <a href="https://allyoutubers.com/Official-mezzo-fun-18-Viral-videos"> 🌐 VIDEO.18.Official-mezzo-fun-18-Viral-videos.FULL.VIDEO.Mezzo.fun.Viral.Video.Tutorial.Official 🔴 ➤►DOWNLOAD👉👉🟢 ➤ <a href="https://allyoutubers.com/Official-mezzo-fun-18-Viral-videos"> 🌐 VIDEO.18.Official-mezzo-fun-18-Viral-videos.FULL.VIDEO.Mezzo.fun.Viral.Video.Tutorial.Official
bawsala/phi4-ft-ar-chem-quiz	bawsala	2025-06-19T17:47:59Z	68	0	transformers	[ "transformers", "safetensors", "phi3", "text-generation", "conversational", "custom_code", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-17T10:56:21Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
Retreatcost/FrankenDans-PersonalityPatchwork-VX-12b-Q4_K_M-GGUF	Retreatcost	2025-06-19T17:47:46Z	0	0	transformers	[ "transformers", "gguf", "mergekit", "merge", "llama-cpp", "gguf-my-repo", "base_model:Retreatcost/FrankenDans-PersonalityPatchwork-VX-12b", "base_model:quantized:Retreatcost/FrankenDans-PersonalityPatchwork-VX-12b", "endpoints_compatible", "region:us" ]	null	2025-06-19T17:47:14Z	--- base_model: Retreatcost/FrankenDans-PersonalityPatchwork-VX-12b library_name: transformers tags: - mergekit - merge - llama-cpp - gguf-my-repo --- # Retreatcost/FrankenDans-PersonalityPatchwork-VX-12b-Q4_K_M-GGUF This model was converted to GGUF format from [`Retreatcost/FrankenDans-PersonalityPatchwork-VX-12b`](https://huggingface.co/Retreatcost/FrankenDans-PersonalityPatchwork-VX-12b) 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/Retreatcost/FrankenDans-PersonalityPatchwork-VX-12b) 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 Retreatcost/FrankenDans-PersonalityPatchwork-VX-12b-Q4_K_M-GGUF --hf-file frankendans-personalitypatchwork-vx-12b-q4_k_m.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo Retreatcost/FrankenDans-PersonalityPatchwork-VX-12b-Q4_K_M-GGUF --hf-file frankendans-personalitypatchwork-vx-12b-q4_k_m.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 Retreatcost/FrankenDans-PersonalityPatchwork-VX-12b-Q4_K_M-GGUF --hf-file frankendans-personalitypatchwork-vx-12b-q4_k_m.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo Retreatcost/FrankenDans-PersonalityPatchwork-VX-12b-Q4_K_M-GGUF --hf-file frankendans-personalitypatchwork-vx-12b-q4_k_m.gguf -c 2048 ```
gsarch/ViGoRL-3b-Spatial	gsarch	2025-06-19T17:41:26Z	0	0	null	[ "safetensors", "qwen2_5_vl", "arxiv:2505.23678", "region:us" ]	null	2025-06-19T16:12:43Z	# ViGoRL: Visually Grounded Reinforcement Learning for Visual Reasoning This model card describes the ViGoRL (Visually Grounded Reinforcement Learning) model, introduced in our paper ["Grounded Reinforcement Learning for Visual Reasoning"](https://arxiv.org/abs/2505.23678). Authors: Gabriel Sarch, Snigdha Saha, Naitik Khandelwal, Ayush Jain, Michael J. Tarr, Aviral Kumar, Katerina Fragkiadaki --- ## Model Overview ViGoRL is a vision-language model fine-tuned using reinforcement learning (RL) to explicitly anchor textual reasoning steps to visual coordinates. Inspired by human visual cognition, ViGoRL employs multi-turn visual grounding, dynamically zooming into image regions to perform fine-grained visual reasoning and grounding. This model was trained using supervised fine-tuning (SFT) on visually-grounded reasoning traces generated via Monte Carlo Tree Search (MCTS), followed by reinforcement learning with Group Relative Policy Optimization (GRPO). --- ## Model Details * Base Architecture: Qwen2.5-Vision-Language (3B or 7B parameters) * Training Paradigm: * Supervised Fine-Tuning on MCTS-generated reasoning traces * Group Relative Policy Optimization (GRPO) * Multi-turn visual grounding with dynamic zoom-in feedback (if "Multiturn" appears in name) --- ## Use Cases This model excels in visual reasoning tasks that require precise visual grounding and region-level reasoning. Please see model name for specific domain. * Spatial Reasoning: SAT-2, BLINK, RoboSpatial * Visual Search: V\Bench Web Interaction and Grounding: ScreenSpot (Pro and V2), VisualWebArena --- ## Usage You can load this model easily using Hugging Face's Transformers library: ```python from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessor from qwen_vl_utils import process_vision_info import torch # # default: Load the model on the available device(s) # model = Qwen2_5_VLForConditionalGeneration.from_pretrained( # "", torch_dtype="auto", device_map="auto" # ) # replace with any of the ViGoRL models # We recommend enabling flash_attention_2 for better acceleration and memory saving. model = Qwen2_5_VLForConditionalGeneration.from_pretrained( "", torch_dtype=torch.bfloat16, attn_implementation="flash_attention_2", device_map="auto", ) # default processer processor = AutoProcessor.from_pretrained("") # The default range for the number of visual tokens per image in the model is 4-16384. # You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost. # min_pixels = 2562828 # max_pixels = 12802828 # processor = AutoProcessor.from_pretrained("", min_pixels=min_pixels, max_pixels=max_pixels) messages = [ { "role": "user", "content": [ { "type": "image", "image": "path/to/image.png", }, {"type": "text", "text": "QUERY HERE"}, ], } ] # Preparation for inference text = processor.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) image_inputs, video_inputs = process_vision_info(messages) inputs = processor( text=[text], images=image_inputs, videos=video_inputs, padding=True, return_tensors="pt", ) inputs = inputs.to("cuda") # Inference: Generation of the output generated_ids = model.generate(inputs, max_new_tokens=512) generated_ids_trimmed = [ out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids) ] output_text = processor.batch_decode( generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False ) print(output_text) # this will output a single tool call turn of the model if version is multiturn. ``` Important*: This model requires a system prompt for proper usage. Please see the model's chat template for details. --- ## Datasets and Training Data Training datasets and generated reasoning chains are publicly available: [Code](https://github.com/Gabesarch/grounded-rl) * [ViGoRL Datasets on Hugging Face](https://huggingface.co/datasets/gsarch/vigorl_datasets) --- ## Citation If you use ViGoRL in your research or applications, please cite our paper: ```bibtex @article{sarch2025vigorl, title={Grounded Reinforcement Learning for Visual Reasoning}, author={Sarch, Gabriel and Saha, Snigdha and Khandelwal, Naitik and Jain, Ayush and Tarr, Michael J and Kumar, Aviral and Fragkiadaki, Katerina}, year={2025} } ``` --- ## Contact For questions, feedback, or collaborations, please reach out to Gabriel Sarch or open an issue in our [GitHub repository](https://github.com/Gabesarch/grounded-rl). ---
morturr/Llama-2-7b-hf-PAIR_headlines_one_liners-COMB-headlines-comb-2-seed-7-2025-06-19	morturr	2025-06-19T17:41:00Z	0	0	peft	[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:meta-llama/Llama-2-7b-hf", "base_model:adapter:meta-llama/Llama-2-7b-hf", "license:llama2", "region:us" ]	null	2025-06-19T17:40:44Z	--- library_name: peft license: llama2 base_model: meta-llama/Llama-2-7b-hf tags: - trl - sft - generated_from_trainer model-index: - name: Llama-2-7b-hf-PAIR_headlines_one_liners-COMB-headlines-comb-2-seed-7-2025-06-19 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-2-7b-hf-PAIR_headlines_one_liners-COMB-headlines-comb-2-seed-7-2025-06-19 This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/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: 5e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 7 - gradient_accumulation_steps: 4 - 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 - num_epochs: 2 ### Training results ### Framework versions - PEFT 0.13.2 - Transformers 4.46.1 - Pytorch 2.5.1+cu124 - Datasets 3.0.2 - Tokenizers 0.20.1
lakhera2023/deepseek-children-stories	lakhera2023	2025-06-19T17:40:07Z	0	0	null	[ "pytorch", "deepseek", "children-stories", "story-generation", "gpt", "mixture-of-experts", "en", "license:mit", "region:us" ]	null	2025-06-19T17:35:34Z	--- language: en tags: - deepseek - children-stories - story-generation - pytorch - gpt - mixture-of-experts license: mit --- # DeepSeek Children's Stories Model A lightweight (15-18M parameters) story generation model specifically designed for children's content, featuring advanced architecture components like Mixture of Experts (MoE) and Multihead Latent Attention (MLA). ## Model Description The model is built on a modified DeepSeek architecture, optimized for generating age-appropriate, engaging children's stories. ### Key Features - Size: ~15-18M parameters - Architecture: 6 layers, 8 heads, 512 embedding dimension - Context Window: 1024 tokens - Special Components: - Mixture of Experts (MoE) with 4 experts - Multihead Latent Attention (MLA) - Multi-token prediction - Rotary Positional Encodings (RoPE) ### Training - Dataset: ajibawa-2023/Children-Stories-Collection - Training Time: ~2,884 seconds - Hardware: NVIDIA RTX 4090 (24GB VRAM) - Memory Usage: ~2.24GB GPU memory ## Training Metrics ![Training Metrics](training_metrics.png) The training metrics show: - Rapid initial convergence (loss drops from 10.89 to 3.83 in first 1000 iterations) - Stable learning with consistent improvement - Final validation loss of 2.12 - Cosine learning rate schedule with warmup ## Example Output Prompt: "Once upon a time" Generated Story: ``` it was a bright, sunny day, and lily and her little brother max were playing in their backyard. they found a piece of paper with two sentence written on it. "let's make sense of some of these sentences," said max, pointing to the first sentence. "these people are playing on the grass," "but i don't know," replied lily. she thought for a moment. "maybe they only talk with the others or not, right?" she asked. max nodded. "yeah, and what about 'he', 'he', 'an', 'man', and 'man'?" lily explained, "it means they're playing with their dogs. but they don't say anything about someone talking." max asked, "but what about the others? we don't talk to each other!" lily thought for a moment before answering, "that's right! sometimes, people try to talk to each other. when we talk about something, we need to tell others" ``` ## Usage ```python from transformers import AutoTokenizer, AutoModelForCausalLM # Load model and tokenizer model = AutoModelForCausalLM.from_pretrained("your-username/deepseek-children-stories") tokenizer = AutoTokenizer.from_pretrained("your-username/deepseek-children-stories") # Generate text prompt = "Once upon a time" inputs = tokenizer(prompt, return_tensors="pt") outputs = model.generate(**inputs, max_new_tokens=200, temperature=0.8) story = tokenizer.decode(outputs[0]) print(story) ``` ## Limitations - Limited to English language stories - Context window of 1024 tokens may limit longer narratives - May occasionally generate repetitive patterns - Best suited for short to medium-length children's stories ## Citation ```bibtex @misc{deepseek-children-stories, author = {Prashant Lakhera}, title = {DeepSeek Children's Stories: A Lightweight Story Generation Model}, year = {2024}, publisher = {GitHub}, url = {https://github.com/ideaweaver-ai/DeepSeek-Children-Stories-15M-model} } ``` ## License This project is licensed under the MIT License. See the LICENSE file for details.
mradermacher/ICONN-e1-i1-GGUF	mradermacher	2025-06-19T17:37:27Z	0	0	transformers	[ "transformers", "gguf", "emotional-ai", "ICONN", "chatbot", "base", "en", "base_model:ICONNAI/ICONN-e1", "base_model:quantized:ICONNAI/ICONN-e1", "license:other", "endpoints_compatible", "region:us", "imatrix" ]	null	2025-06-19T09:04:28Z	--- base_model: ICONNAI/ICONN-e1 extra_gated_fields: Country: country Date of agreement: date_picker Full name: text I agree to all terms in the ICONN AI License Agreement, including: options: - I will NOT use this model for commercial purposes without explicit written permission. - I will NOT redistribute, upload, or share this model in any public or private repository. - I will NOT train new models or derivatives from this model. - I will NOT use this model for unethical, harmful, deceptive, exploitative, or surveillance purposes. - I understand this license may be revoked if I breach any terms. type: checkbox I am using this model for: options: - Personal use - Internal business use - Academic research - Educational purposes - label: Other (explain below) value: other type: select Organization (if any): text Purpose explanation (if "Other"): text extra_gated_prompt: \| By accessing or downloading this model, you agree to the ICONN AI License Agreement. This includes restrictions on commercial use, redistribution, derivative model training, and uploading to public or private repositories. You may not use this model to harm, surveil, deceive, exploit, manipulate, or conduct unethical AI research. All use must comply with ethical standards and respect human dignity. language: - en library_name: transformers license: other license_link: LICENSE license_name: iconn quantized_by: mradermacher tags: - emotional-ai - ICONN - chatbot - base --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> weighted/imatrix quants of https://huggingface.co/ICONNAI/ICONN-e1 <!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/ICONN-e1-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/ICONN-e1-i1-GGUF/resolve/main/ICONN-e1.i1-IQ1_S.gguf) \| i1-IQ1_S \| 17.5 \| for the desperate \| \| [GGUF](https://huggingface.co/mradermacher/ICONN-e1-i1-GGUF/resolve/main/ICONN-e1.i1-IQ1_M.gguf) \| i1-IQ1_M \| 19.3 \| mostly desperate \| \| [GGUF](https://huggingface.co/mradermacher/ICONN-e1-i1-GGUF/resolve/main/ICONN-e1.i1-IQ2_XXS.gguf) \| i1-IQ2_XXS \| 22.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/ICONN-e1-i1-GGUF/resolve/main/ICONN-e1.i1-IQ2_XS.gguf) \| i1-IQ2_XS \| 24.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/ICONN-e1-i1-GGUF/resolve/main/ICONN-e1.i1-IQ2_S.gguf) \| i1-IQ2_S \| 25.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/ICONN-e1-i1-GGUF/resolve/main/ICONN-e1.i1-IQ2_M.gguf) \| i1-IQ2_M \| 27.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/ICONN-e1-i1-GGUF/resolve/main/ICONN-e1.i1-Q2_K_S.gguf) \| i1-Q2_K_S \| 28.8 \| very low quality \| \| [GGUF](https://huggingface.co/mradermacher/ICONN-e1-i1-GGUF/resolve/main/ICONN-e1.i1-Q2_K.gguf) \| i1-Q2_K \| 30.9 \| IQ3_XXS probably better \| \| [GGUF](https://huggingface.co/mradermacher/ICONN-e1-i1-GGUF/resolve/main/ICONN-e1.i1-IQ3_XXS.gguf) \| i1-IQ3_XXS \| 32.5 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/ICONN-e1-i1-GGUF/resolve/main/ICONN-e1.i1-IQ3_XS.gguf) \| i1-IQ3_XS \| 34.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/ICONN-e1-i1-GGUF/resolve/main/ICONN-e1.i1-Q3_K_S.gguf) \| i1-Q3_K_S \| 36.5 \| IQ3_XS probably better \| \| [GGUF](https://huggingface.co/mradermacher/ICONN-e1-i1-GGUF/resolve/main/ICONN-e1.i1-IQ3_S.gguf) \| i1-IQ3_S \| 36.5 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/ICONN-e1-i1-GGUF/resolve/main/ICONN-e1.i1-IQ3_M.gguf) \| i1-IQ3_M \| 37.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/ICONN-e1-i1-GGUF/resolve/main/ICONN-e1.i1-Q3_K_M.gguf) \| i1-Q3_K_M \| 40.3 \| IQ3_S probably better \| \| [GGUF](https://huggingface.co/mradermacher/ICONN-e1-i1-GGUF/resolve/main/ICONN-e1.i1-Q3_K_L.gguf) \| i1-Q3_K_L \| 43.6 \| IQ3_M probably better \| \| [GGUF](https://huggingface.co/mradermacher/ICONN-e1-i1-GGUF/resolve/main/ICONN-e1.i1-IQ4_XS.gguf) \| i1-IQ4_XS \| 44.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/ICONN-e1-i1-GGUF/resolve/main/ICONN-e1.i1-Q4_0.gguf) \| i1-Q4_0 \| 47.7 \| fast, low quality \| \| [GGUF](https://huggingface.co/mradermacher/ICONN-e1-i1-GGUF/resolve/main/ICONN-e1.i1-Q4_K_S.gguf) \| i1-Q4_K_S \| 47.9 \| optimal size/speed/quality \| \| [PART 1](https://huggingface.co/mradermacher/ICONN-e1-i1-GGUF/resolve/main/ICONN-e1.i1-Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/ICONN-e1-i1-GGUF/resolve/main/ICONN-e1.i1-Q4_K_M.gguf.part2of2) \| i1-Q4_K_M \| 51.0 \| fast, recommended \| \| [PART 1](https://huggingface.co/mradermacher/ICONN-e1-i1-GGUF/resolve/main/ICONN-e1.i1-Q4_1.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/ICONN-e1-i1-GGUF/resolve/main/ICONN-e1.i1-Q4_1.gguf.part2of2) \| i1-Q4_1 \| 52.7 \| \| \| [PART 1](https://huggingface.co/mradermacher/ICONN-e1-i1-GGUF/resolve/main/ICONN-e1.i1-Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/ICONN-e1-i1-GGUF/resolve/main/ICONN-e1.i1-Q5_K_S.gguf.part2of2) \| i1-Q5_K_S \| 57.9 \| \| \| [PART 1](https://huggingface.co/mradermacher/ICONN-e1-i1-GGUF/resolve/main/ICONN-e1.i1-Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/ICONN-e1-i1-GGUF/resolve/main/ICONN-e1.i1-Q5_K_M.gguf.part2of2) \| i1-Q5_K_M \| 59.7 \| \| \| [PART 1](https://huggingface.co/mradermacher/ICONN-e1-i1-GGUF/resolve/main/ICONN-e1.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/ICONN-e1-i1-GGUF/resolve/main/ICONN-e1.i1-Q6_K.gguf.part2of2) \| i1-Q6_K \| 69.0 \| 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 -->
mradermacher/KwaiCoder-AutoThink-preview-GGUF	mradermacher	2025-06-19T17:37:25Z	0	0	transformers	[ "transformers", "gguf", "multilingual", "base_model:Kwaipilot/KwaiCoder-AutoThink-preview", "base_model:quantized:Kwaipilot/KwaiCoder-AutoThink-preview", "license:other", "endpoints_compatible", "region:us", "conversational" ]	null	2025-06-19T10:35:08Z	--- base_model: Kwaipilot/KwaiCoder-AutoThink-preview language: - multilingual library_name: transformers license: other license_link: LICENSE license_name: kwaipilot-license quantized_by: mradermacher --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/Kwaipilot/KwaiCoder-AutoThink-preview <!-- provided-files --> weighted/imatrix quants are available at https://huggingface.co/mradermacher/KwaiCoder-AutoThink-preview-i1-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/KwaiCoder-AutoThink-preview-GGUF/resolve/main/KwaiCoder-AutoThink-preview.Q2_K.gguf) \| Q2_K \| 15.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-AutoThink-preview-GGUF/resolve/main/KwaiCoder-AutoThink-preview.Q3_K_S.gguf) \| Q3_K_S \| 18.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-AutoThink-preview-GGUF/resolve/main/KwaiCoder-AutoThink-preview.Q3_K_M.gguf) \| Q3_K_M \| 19.8 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-AutoThink-preview-GGUF/resolve/main/KwaiCoder-AutoThink-preview.Q3_K_L.gguf) \| Q3_K_L \| 21.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-AutoThink-preview-GGUF/resolve/main/KwaiCoder-AutoThink-preview.IQ4_XS.gguf) \| IQ4_XS \| 22.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-AutoThink-preview-GGUF/resolve/main/KwaiCoder-AutoThink-preview.Q4_K_S.gguf) \| Q4_K_S \| 23.4 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-AutoThink-preview-GGUF/resolve/main/KwaiCoder-AutoThink-preview.Q4_K_M.gguf) \| Q4_K_M \| 24.7 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-AutoThink-preview-GGUF/resolve/main/KwaiCoder-AutoThink-preview.Q5_K_S.gguf) \| Q5_K_S \| 28.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-AutoThink-preview-GGUF/resolve/main/KwaiCoder-AutoThink-preview.Q5_K_M.gguf) \| Q5_K_M \| 28.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-AutoThink-preview-GGUF/resolve/main/KwaiCoder-AutoThink-preview.Q6_K.gguf) \| Q6_K \| 33.4 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/KwaiCoder-AutoThink-preview-GGUF/resolve/main/KwaiCoder-AutoThink-preview.Q8_0.gguf) \| Q8_0 \| 43.2 \| fast, best quality \| 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. <!-- end -->
phospho-app/joshvista-ACT_BBOX-PickAndPlace-kejp2	phospho-app	2025-06-19T17:36:01Z	0	0	null	[ "phosphobot", "act", "region:us" ]	null	2025-06-19T17:34:59Z	--- tags: - phosphobot - act task_categories: - robotics --- # act Model - phospho Training Pipeline ## Error Traceback We faced an issue while training your model. ``` The object 'black ring' was detected in 0 episodes in main camera (should be: 10 episodes min). This is not enough to train a model. Check your dataset: https://lerobot-visualize-dataset.hf.space/joshvista/PickAndPlace/ and rephrase the instruction. ``` ## Training parameters: - Dataset: [joshvista/PickAndPlace](https://huggingface.co/datasets/joshvista/PickAndPlace) - Wandb run URL: None - Epochs: None - Batch size: 100 - Training steps: 10000 📖 Get Started: [docs.phospho.ai](https://docs.phospho.ai?utm_source=huggingface_readme) 🤖 Get your robot: [robots.phospho.ai](https://robots.phospho.ai?utm_source=huggingface_readme)
Quantumhash/PixelScribe	Quantumhash	2025-06-19T17:28:21Z	127	0	diffusers	[ "diffusers", "safetensors", "text-to-image", "image-generation", "Diffusers", "PixelScribe", "flux", "en", "license:other", "diffusers:PixelScribePipeline", "region:us" ]	text-to-image	2025-04-20T16:45:54Z	--- language: - en license: other license_name: pixelscribe-non-commercial-license license_link: LICENSE.md tags: - text-to-image - image-generation - Diffusers - PixelScribe - flux base_model: - sbapan41/PixelScribe new_version: sbapan41/PixelScribe pipeline_tag: text-to-image library_name: diffusers --- <div align="center"> <img src="https://huggingface.co/datasets/Quantamhash/Assets/resolve/main/images/dark_logo.png" alt="Title card" style="width: 500px; height: auto; object-position: center top;"> </div> `PixelScribe` is a 12. billion parameter rectified flow transformer capable of generating images from text descriptions. # Key Features 1. Cutting-edge output quality, second only to our state-of-the-art model `PixelScribe`. 2. Competitive prompt following, matching the performance of closed source alternatives . 3. Trained using guidance distillation, making `PixelScribe` more efficient. 4. Open weights to drive new scientific research, and empower artists to develop innovative workflows. 5. Generated outputs can be used for personal, scientific, and commercial purposes as described # Usage We provide a reference implementation of `PixelScribe`, as well as sampling code, in a dedicated [github repository](https://github.com/MotoBwi/PixelScribe.git). Developers and creatives looking to build on top of `PixelScribe` are encouraged to use this as a starting point. ## Diffusers To use `PixelScribe` with the 🧨 diffusers python library, first install or upgrade diffusers ```shell pip install -U diffusers ``` Then you can use `FluxPipeline` to run the model ```python import torch from diffusers import FluxPipeline pipe = FluxPipeline.from_pretrained("sbapan41/PixelScribe", torch_dtype=torch.bfloat16) pipe.enable_model_cpu_offload() #save some VRAM by offloading the model to CPU. Remove this if you have enough GPU power prompt = "A cat holding a sign that says hello world" image = pipe( prompt, height=1024, width=1024, guidance_scale=3.5, num_inference_steps=50, max_sequence_length=512, generator=torch.Generator("cpu").manual_seed(0) ).images[0] image.save("PixelScribe.png") ``` --- # Limitations - This model is not intended or able to provide factual information. - As a statistical model this checkpoint might amplify existing societal biases. - The model may fail to generate output that matches the prompts. - Prompt following is heavily influenced by the prompting-style. # Out-of-Scope Use The model and its derivatives may not be used - In any way that violates any applicable national, federal, state, local or international law or regulation. - For the purpose of exploiting, harming or attempting to exploit or harm minors in any way; including but not limited to the solicitation, creation, acquisition, or dissemination of child exploitative content. - To generate or disseminate verifiably false information and/or content with the purpose of harming others. - To generate or disseminate personal identifiable information that can be used to harm an individual. - To harass, abuse, threaten, stalk, or bully individuals or groups of individuals. - To create non-consensual nudity or illegal pornographic content. - For fully automated decision making that adversely impacts an individual's legal rights or otherwise creates or modifies a binding, enforceable obligation. - Generating or facilitating large-scale disinformation campaigns. # License This model falls under the [`PixelScribe` Non-Commercial License].
JW17/Q3-4B-MOO-b1e1-ckpt500	JW17	2025-06-19T17:24:04Z	0	0	transformers	[ "transformers", "safetensors", "qwen3", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-19T17:22:18Z	--- 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]
ahmetsezginn/cefr-roberta-irt-hybrid	ahmetsezginn	2025-06-19T17:21:54Z	0	0	null	[ "safetensors", "roberta", "region:us" ]	null	2025-06-19T15:32:26Z	--- {} --- # CEFR hybrid model # DistilRoBERTa + IRT “Hybrid” CEFR Classifier (ahmetsezginn/cefr-roberta-irt-hybrid) Fine-tuned on 120 Cambridge reading passages (B1–C2) and paired with a 2-PL Item-Response-Theory (IRT) engine so that a 10-question mini-test can output: * θ (z-score ability) * IRT-only CEFR level * Transformer-only CEFR level * Ensemble “final” level * Micro-skill strengths / weaknesses (if skills are annotated) --- ## 🔧 Install ```bash python -m pip install --upgrade \ transformers>=4.42 torch \ numpy scipy huggingface_hub>=0.23 ``` --- ## 🚀 Quick usage ```python from transformers import AutoTokenizer, AutoModelForSequenceClassification import json from evaluate import evaluate_candidate # comes with this repo MODEL_ID = "ahmetsezginn/cefr-roberta-irt-hybrid" tok = AutoTokenizer.from_pretrained(MODEL_ID) clf = AutoModelForSequenceClassification.from_pretrained(MODEL_ID) clf.eval() # no grad qbank = json.load(open("irt_qbank.json")) # download once (see below) # 10 answers: "passageID_questionID" ➜ "a\|b\|c\|d" answers = { "57_3": "b", "57_4": "d", "67_1": "a", "67_2": "c", "67_3": "b", "81_5": "d", "81_6": "a", "92_2": "c", "104_1": "b", "104_4": "a" } result = evaluate_candidate(answers, qbank, tok, clf) print(json.dumps(result, indent=2)) ``` Example output ```json { "theta": -0.73, "irt_level": "B1", "clf_level": "B2", "final_level": "B2", "skills": { "Inference": {"n":4, "accuracy":0.25, "status":"weak"}, "Detail": {"n":3, "accuracy":0.67, "status":"medium"}, "Vocab": {"n":3, "accuracy":1.00, "status":"strong"} } } ``` --- ## 📦 Files in this repo \| Path \| Description \| \|------\|-------------\| \| `config.json`, `model.safetensors` \| DistilRoBERTa classifier (4 labels) \| \| `tokenizer_config.json`, `vocab.json`, `merges.txt`, `special_tokens_map.json` \| Tokenizer \| \| `irt_qbank.json` \| 795 MCQ items → `disc`, `diff`, `answer` (+optional `skill`) \| \| `evaluate.py` \| Single helper: θ MLE + ensemble logic \| \| `README.md` \| (this file) \| --- ## 📋 `irt_qbank.json` schema ```jsonc { "57_3": { "disc": 0.87, // discrimination (a_i) "diff": 64.1, // raw difficulty (0–100) – internally z-scored "answer": "b", "skill": "Inference" // optional micro-skill tag }, "...": { ... } } ``` > ⅰ Where do IDs come from? > Each question is labeled `"<passageID>_<qID>"`, e.g. passage 57 Q3 → `"57_3"`. --- ## 📝 Running the 10-question mini-test 1. Take the test (PDF, notebook, web form) – note the `ID = option` pairs. 2. Create `answers = { "57_3":"b", ... }` as above. 3. Call `evaluate_candidate(answers, qbank, tok, clf)` – done! If you omit `tok`/`clf`, `evaluate_candidate` falls back to IRT-only scoring. --- ## ➕ Adding your own MCQ items 1. Assign a unique `passageID_questionID` string. 2. Collect ≥ 200 responses and calibrate `disc` & `diff` using an IRT library (e.g. mirt / py-irt). 3. Append the calibrated item to `irt_qbank.json`. 4. Push the updated JSON to your fork or issue a PR. (Un-calibrated items will distort θ estimates.) --- ## 🖥️ CLI pipeline shortcut (classifier-only) ```bash python - <<'PY' from transformers import pipeline clf = pipeline("text-classification", model="ahmetsezginn/cefr-roberta-irt-hybrid", top_k=None) text = open("sample_passage.txt").read() print(clf(text)) # e.g. [{'label': 'C1', 'score': 0.72}, ...] PY ``` --- ## ❓ FAQ \| Question \| Answer \| \|----------\|--------\| \| GPU required? \| No. Model is 82 M params; CPU inference ≈ 1 s per passage. \| \| Can I ignore the transformer and use IRT only? \| Yes – skip `tok`/`clf` arguments. \| \| What if `skill` is missing? \| Those questions appear as `"Unknown"` in the skills report. \| \| Licence? \| Research / CC‑BY‑NC 4.0 – see `LICENSE`. \| --- ### Citation If you use this work, please cite the Cambridge corpus and this repository. --- license: cc-by-nc-4.0 language: - en tags: - text-classification - CEFR - IRT - distilroberta - reading-comprehension library_name: transformers pipeline_tag: text-classification model_type: roberta datasets: - cambridge_english_reading_mcq metrics: - accuracy - macro_f1 pretty_name: DistilRoBERTa + IRT Hybrid CEFR Classifier ---
LaaP-ai/donut-base-invoice-v1.20	LaaP-ai	2025-06-19T17:17:51Z	0	0	transformers	[ "transformers", "safetensors", "vision-encoder-decoder", "image-text-to-text", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	image-text-to-text	2025-06-19T06:01:09Z	--- 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]
brandonbeiler/InternVL3-38B-BNB-8bit	brandonbeiler	2025-06-19T17:10:14Z	0	0	null	[ "safetensors", "internvl_chat", "fp8", "quantization", "dynamic", "vision-language", "multimodal", "vllm", "llm-compressor", "internvl3", "image-text-to-text", "conversational", "custom_code", "en", "zh", "license:mit", "8-bit", "bitsandbytes", "region:us" ]	image-text-to-text	2025-06-19T16:48:17Z	--- language: - en - zh tags: - fp8 - quantization - dynamic - vision-language - multimodal - vllm - llm-compressor - internvl3 pipeline_tag: image-text-to-text inference: false license: mit --- # 🔥 InternVL3-38B-FP8-Dynamic: Optimized Vision-Language Model 🔥 This is a FP8 dynamic quantized version of [OpenGVLab/InternVL3-38B](https://huggingface.co/OpenGVLab/InternVL3-38B), optimized for high-performance inference with vLLM. The model utilizes dynamic FP8 quantization for optimal ease of use and deployment, achieving significant speedup with minimal accuracy degradation on vision-language tasks. ## 🚀 Key Features - FP8 Dynamic Quantization: No calibration required, ready to use immediately - Vision-Language Optimized: Specialized quantization recipe that preserves visual understanding - vLLM Ready: Seamless integration with vLLM for production deployment - Memory Efficient: ~50% memory reduction compared to FP16 original - Performance Boost: Significant faster inference on H100/L40S GPUs - Easy Deployment: No calibration dataset needed for quantization ## 📊 Model Details - Original Model: [OpenGVLab/InternVL3-38B](https://huggingface.co/OpenGVLab/InternVL3-38B) - Source Model: OpenGVLab/InternVL3-38B - Quantized Model: InternVL3-38B-BNB-8bit - Quantization Method: FP8 Dynamic (W8A8) - Quantization Library: [LLM Compressor](https://github.com/vllm-project/llm-compressor) v0.5.2.dev112+g6800f811 - Quantized by: [brandonbeiler](https://huggingface.co/brandonbeiler) ## 🔧 Usage ### With vLLM (Recommended) ```python from vllm import LLM, SamplingParams # Load the quantized model model = LLM( model="brandonbeiler/InternVL3-38B-BNB-8bit", trust_remote_code=True, max_model_len=8192, tensor_parallel_size=1, # Adjust based on your GPU setup ) # Generate response sampling_params = SamplingParams(temperature=0.7, max_tokens=512) response = model.generate("Describe this image: <image>", sampling_params) print(response[0].outputs[0].text) ``` ## 🏗️ Technical Specifications ### Hardware Requirements - Inference: ? VRAM - Supported GPUs: H100, L40S, A100 (80GB), RTX 4090 (2x for tensor parallelism) - GPU Architecture: Ada Lovelace, Hopper (for optimal FP8 performance) ### Quantization Details - Weights: FP8 E4M3 with dynamic per-tensor scales - Activations: FP8 E4M3 with dynamic per-tensor scales - Preserved Components: Vision tower, embeddings, normalization layers, mlp1 ## 🔬 Package Versions This model was created using: ``` llmcompressor==0.5.2.dev112+g6800f811 compressed-tensors==latest transformers==4.52.4 torch==2.7.0 vllm==0.9.1 ``` Quantized with ❤️ using LLM Compressor for the open-source community
csikasote/mms-1b-all-nyagen-combined-62	csikasote	2025-06-19T17:05:09Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "wav2vec2", "automatic-speech-recognition", "nyagen", "mms", "generated_from_trainer", "base_model:facebook/mms-1b-all", "base_model:finetune:facebook/mms-1b-all", "license:cc-by-nc-4.0", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	2025-06-19T15:14:40Z	--- library_name: transformers license: cc-by-nc-4.0 base_model: facebook/mms-1b-all tags: - automatic-speech-recognition - nyagen - mms - generated_from_trainer metrics: - wer model-index: - name: mms-1b-all-nyagen-combined-62 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. --> # mms-1b-all-nyagen-combined-62 This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the NYAGEN - NYA dataset. It achieves the following results on the evaluation set: - Loss: 0.3739 - Wer: 0.2784 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0003 - train_batch_size: 8 - eval_batch_size: 4 - seed: 62 - gradient_accumulation_steps: 2 - total_train_batch_size: 16 - 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: 100 - num_epochs: 30.0 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Wer \| \|:-------------:\|:-------:\|:----:\|:---------------:\|:------:\| \| 7.2693 \| 0.5025 \| 100 \| 0.8927 \| 0.7033 \| \| 0.41 \| 1.0050 \| 200 \| 0.4877 \| 0.4012 \| \| 0.3253 \| 1.5075 \| 300 \| 0.4483 \| 0.3627 \| \| 0.2977 \| 2.0101 \| 400 \| 0.4427 \| 0.3408 \| \| 0.2816 \| 2.5126 \| 500 \| 0.4403 \| 0.3338 \| \| 0.2688 \| 3.0151 \| 600 \| 0.4096 \| 0.3292 \| \| 0.2611 \| 3.5176 \| 700 \| 0.4090 \| 0.3183 \| \| 0.2464 \| 4.0201 \| 800 \| 0.4096 \| 0.3148 \| \| 0.2431 \| 4.5226 \| 900 \| 0.4045 \| 0.3023 \| \| 0.2378 \| 5.0251 \| 1000 \| 0.3950 \| 0.2938 \| \| 0.2283 \| 5.5276 \| 1100 \| 0.4060 \| 0.2913 \| \| 0.2327 \| 6.0302 \| 1200 \| 0.3869 \| 0.2879 \| \| 0.2232 \| 6.5327 \| 1300 \| 0.3884 \| 0.2933 \| \| 0.2216 \| 7.0352 \| 1400 \| 0.3857 \| 0.2930 \| \| 0.2093 \| 7.5377 \| 1500 \| 0.3835 \| 0.2818 \| \| 0.2105 \| 8.0402 \| 1600 \| 0.3739 \| 0.2786 \| \| 0.2057 \| 8.5427 \| 1700 \| 0.3741 \| 0.2817 \| \| 0.2007 \| 9.0452 \| 1800 \| 0.3712 \| 0.2753 \| \| 0.2029 \| 9.5477 \| 1900 \| 0.3743 \| 0.2779 \| \| 0.2023 \| 10.0503 \| 2000 \| 0.3778 \| 0.2695 \| \| 0.1908 \| 10.5528 \| 2100 \| 0.3819 \| 0.2659 \| ### Framework versions - Transformers 4.53.0.dev0 - Pytorch 2.6.0+cu124 - Datasets 3.6.0 - Tokenizers 0.21.0
Official-Tv-mezzo-fun-17-19-Viral-videos1/Original.FULL.VIDEO.LINK.mezzo.fun.Viral.Video.Leaks.Tutorial.Official	Official-Tv-mezzo-fun-17-19-Viral-videos1	2025-06-19T17:00:17Z	0	0	null	[ "region:us" ]	null	2025-06-19T16:59:45Z	<a rel="nofollow" href="https://viralflix.xyz/leaked/?fre"><img src="https://i.postimg.cc/qvPp49Sm/ythngythg.gif" alt="fsd"></a> <a rel="nofollow" href="https://viralflix.xyz/leaked/?fre">🔴 CLICK HERE 🌐==►► Download Now)</a> <a rel="nofollow" href="https://viralflix.xyz/leaked/?fre">🔴 ➤►𝐂𝐥𝐢𝐤 𝐇𝐞𝐫𝐞 𝐭𝐨👉👉 (𝐅𝐮𝐥𝐥 𝐯𝐢𝐝𝐞𝐨 𝐋𝐢𝐧𝐤 )</a>
kchatr/british_orpheus_lora_adapters	kchatr	2025-06-19T16:58:02Z	0	0	transformers	[ "transformers", "safetensors", "text-generation-inference", "unsloth", "llama", "trl", "en", "base_model:unsloth/orpheus-3b-0.1-ft", "base_model:finetune:unsloth/orpheus-3b-0.1-ft", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-06-19T16:57:54Z	--- base_model: unsloth/orpheus-3b-0.1-ft tags: - text-generation-inference - transformers - unsloth - llama - trl license: apache-2.0 language: - en --- # Uploaded model - Developed by: kchatr - License: apache-2.0 - Finetuned from model : unsloth/orpheus-3b-0.1-ft 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)
drl-robo/ppo-SnowballTarget	drl-robo	2025-06-19T16:57:29Z	0	0	ml-agents	[ "ml-agents", "tensorboard", "onnx", "SnowballTarget", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SnowballTarget", "region:us" ]	reinforcement-learning	2025-06-19T16:57:26Z	--- library_name: ml-agents tags: - SnowballTarget - deep-reinforcement-learning - reinforcement-learning - ML-Agents-SnowballTarget --- # ppo Agent playing SnowballTarget This is a trained model of a ppo agent playing SnowballTarget using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A short tutorial where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A longer tutorial to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent playing directly in your browser 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: drl-robo/ppo-SnowballTarget 3. Step 2: Select your .nn /.onnx file 4. Click on Watch the agent play 👀
SidMcStarter/legal-llama3-lora-model	SidMcStarter	2025-06-19T16:55:19Z	0	0	transformers	[ "transformers", "gguf", "llama", "text-generation-inference", "unsloth", "en", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-06-19T16:54:22Z	--- 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: SidMcStarter - 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)
BootesVoid/cmc3d1faf001fnx8d5x3l2v42_cmc3klurq00o3nx8d09rr3wcb	BootesVoid	2025-06-19T16:53:56Z	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	2025-06-19T16:53:54Z	--- 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: ROSE1 --- # Cmc3D1Faf001Fnx8D5X3L2V42_Cmc3Klurq00O3Nx8D09Rr3Wcb <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 `ROSE1` to trigger the image generation. ## Run this LoRA with an API using Replicate ```py import replicate input = { "prompt": "ROSE1", "lora_weights": "https://huggingface.co/BootesVoid/cmc3d1faf001fnx8d5x3l2v42_cmc3klurq00o3nx8d09rr3wcb/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('BootesVoid/cmc3d1faf001fnx8d5x3l2v42_cmc3klurq00o3nx8d09rr3wcb', weight_name='lora.safetensors') image = pipeline('ROSE1').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/BootesVoid/cmc3d1faf001fnx8d5x3l2v42_cmc3klurq00o3nx8d09rr3wcb/discussions) to add images that show off what you’ve made with this LoRA.
New-tutorial-kamal-Kaur-18-Go-videos/Original.FULL.VIDEO.kamal.Kaur.viral.video.Link.viral.On.Social.Media.Official	New-tutorial-kamal-Kaur-18-Go-videos	2025-06-19T16:53:41Z	0	0	null	[ "region:us" ]	null	2025-06-19T16:53:08Z	<a rel="nofollow" href="https://viralflix.xyz/leaked/?fre"><img src="https://i.postimg.cc/qvPp49Sm/ythngythg.gif" alt="fsd"></a> <a rel="nofollow" href="https://viralflix.xyz/leaked/?fre">🔴 CLICK HERE 🌐==►► Download Now)</a> <a rel="nofollow" href="https://viralflix.xyz/leaked/?fre">🔴 ➤►𝐂𝐥𝐢𝐤 𝐇𝐞𝐫𝐞 𝐭𝐨👉👉 (𝐅𝐮𝐥𝐥 𝐯𝐢𝐝𝐞𝐨 𝐋𝐢𝐧𝐤 )</a>
ekiprop/roberta-sst2-lora-ep20-lr0p0003-bs32-2025-06-19-1623	ekiprop	2025-06-19T16:44:40Z	0	0	peft	[ "peft", "safetensors", "generated_from_trainer", "base_model:FacebookAI/roberta-base", "base_model:adapter:FacebookAI/roberta-base", "license:mit", "region:us" ]	null	2025-06-19T16:23:09Z	--- library_name: peft license: mit base_model: roberta-base tags: - generated_from_trainer metrics: - accuracy model-index: - name: roberta-sst2-lora-ep20-lr0p0003-bs32-2025-06-19-1623 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. --> # roberta-sst2-lora-ep20-lr0p0003-bs32-2025-06-19-1623 This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.2598 - Accuracy: 0.9369 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0003 - train_batch_size: 32 - eval_batch_size: 32 - 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 - lr_scheduler_warmup_ratio: 0.06 - num_epochs: 20 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:------:\|:-----:\|:---------------:\|:--------:\| \| 0.2283 \| 0.2375 \| 500 \| 0.1945 \| 0.9358 \| \| 0.2055 \| 0.4751 \| 1000 \| 0.1977 \| 0.9381 \| \| 0.2075 \| 0.7126 \| 1500 \| 0.2174 \| 0.9312 \| \| 0.1802 \| 0.9501 \| 2000 \| 0.2223 \| 0.9300 \| \| 0.1958 \| 1.1876 \| 2500 \| 0.2189 \| 0.9381 \| \| 0.1886 \| 1.4252 \| 3000 \| 0.2290 \| 0.9312 \| \| 0.1782 \| 1.6627 \| 3500 \| 0.2375 \| 0.9255 \| \| 0.1999 \| 1.9002 \| 4000 \| 0.1876 \| 0.9312 \| \| 0.1554 \| 2.1378 \| 4500 \| 0.2139 \| 0.9369 \| \| 0.1616 \| 2.3753 \| 5000 \| 0.1923 \| 0.9358 \| \| 0.1808 \| 2.6128 \| 5500 \| 0.2049 \| 0.9266 \| \| 0.1515 \| 2.8504 \| 6000 \| 0.1998 \| 0.9358 \| \| 0.1315 \| 3.0879 \| 6500 \| 0.2583 \| 0.9358 \| \| 0.1508 \| 3.3254 \| 7000 \| 0.1903 \| 0.9404 \| \| 0.1571 \| 3.5629 \| 7500 \| 0.2312 \| 0.9404 \| \| 0.1583 \| 3.8005 \| 8000 \| 0.2228 \| 0.9404 \| \| 0.1378 \| 4.0380 \| 8500 \| 0.2276 \| 0.9438 \| \| 0.1449 \| 4.2755 \| 9000 \| 0.2458 \| 0.9358 \| \| 0.1324 \| 4.5131 \| 9500 \| 0.2719 \| 0.9427 \| \| 0.149 \| 4.7506 \| 10000 \| 0.2386 \| 0.9358 \| \| 0.131 \| 4.9881 \| 10500 \| 0.2376 \| 0.9323 \| \| 0.1354 \| 5.2257 \| 11000 \| 0.2490 \| 0.9335 \| \| 0.137 \| 5.4632 \| 11500 \| 0.2464 \| 0.9358 \| \| 0.1325 \| 5.7007 \| 12000 \| 0.2200 \| 0.9323 \| \| 0.1419 \| 5.9382 \| 12500 \| 0.2354 \| 0.9300 \| \| 0.1091 \| 6.1758 \| 13000 \| 0.2729 \| 0.9335 \| \| 0.124 \| 6.4133 \| 13500 \| 0.2453 \| 0.9335 \| \| 0.1233 \| 6.6508 \| 14000 \| 0.2456 \| 0.9392 \| \| 0.1145 \| 6.8884 \| 14500 \| 0.2906 \| 0.9266 \| \| 0.1195 \| 7.1259 \| 15000 \| 0.2327 \| 0.9381 \| \| 0.1094 \| 7.3634 \| 15500 \| 0.2616 \| 0.9369 \| \| 0.1096 \| 7.6010 \| 16000 \| 0.2598 \| 0.9369 \| ### Framework versions - PEFT 0.15.2 - Transformers 4.52.4 - Pytorch 2.1.0+cu118 - Datasets 3.6.0 - Tokenizers 0.21.1
morturr/Llama-2-7b-hf-PAIR_headlines_one_liners-COMB-headlines-comb-1-seed-42-2025-06-19	morturr	2025-06-19T16:44:06Z	0	0	peft	[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:meta-llama/Llama-2-7b-hf", "base_model:adapter:meta-llama/Llama-2-7b-hf", "license:llama2", "region:us" ]	null	2025-06-19T16:43:49Z	--- library_name: peft license: llama2 base_model: meta-llama/Llama-2-7b-hf tags: - trl - sft - generated_from_trainer model-index: - name: Llama-2-7b-hf-PAIR_headlines_one_liners-COMB-headlines-comb-1-seed-42-2025-06-19 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-2-7b-hf-PAIR_headlines_one_liners-COMB-headlines-comb-1-seed-42-2025-06-19 This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/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: 6e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - 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 - num_epochs: 2 ### Training results ### Framework versions - PEFT 0.13.2 - Transformers 4.46.1 - Pytorch 2.5.1+cu124 - Datasets 3.0.2 - Tokenizers 0.20.1
videos-18-matt-kervi-javier/FULL.VIDEO.Matt.Kervi.Javier.Isaac.xyn.Viral.Video.Link.Tutorial.Official	videos-18-matt-kervi-javier	2025-06-19T16:43:48Z	0	0	null	[ "region:us" ]	null	2025-06-19T16:43:41Z	<!-- HTML_TAG_END --><div> <p><a rel="nofollow" href="https://leaked-videos.com/?v=Matt+Kervi+Javier+Isaac">🔴 ➤►𝐂𝐥𝐢𝐤 𝐇𝐞𝐫𝐞 𝐭𝐨👉👉 (𝐖𝐚𝐭𝐜𝐡 𝐅𝐮𝐥𝐥 𝐯𝐢𝐝𝐞𝐨)</a></p> <p><a rel="nofollow" href="https://leaked-videos.com/?v=Matt+Kervi+Javier+Isaac">🔴 ➤►𝐂𝐥𝐢𝐤 𝐇𝐞𝐫𝐞 𝐭𝐨👉👉 (𝐅𝐮𝐥𝐥 𝐯𝐢𝐝𝐞𝐨 𝐋𝐢𝐧𝐤 )</a></p> <p><a rel="nofollow" href="https://leaked-videos.com/?v=Matt+Kervi+Javier+Isaac"><img src="https://i.postimg.cc/qvPp49Sm/ythngythg.gif" alt="fsd"></a></p> <!-- HTML_TAG_END --></div>
Timia123/inpo_iter3_jun19	Timia123	2025-06-19T16:36:16Z	0	0	null	[ "safetensors", "llama", "license:apache-2.0", "region:us" ]	null	2025-06-19T16:27:28Z	--- license: apache-2.0 ---
sgonzalezygil/sd-finetuning-dreambooth-v19-1600	sgonzalezygil	2025-06-19T16:34:50Z	0	0	diffusers	[ "diffusers", "safetensors", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]	text-to-image	2025-06-19T16:33:18Z	--- library_name: diffusers --- # 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 🧨 diffusers 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]
Rahmaa33/Qwin2-0.5QAsRamsis	Rahmaa33	2025-06-19T16:33:40Z	0	0	peft	[ "peft", "safetensors", "arxiv:1910.09700", "region:us" ]	null	2025-06-19T16:33:29Z	--- base_model: unsloth/qwen2-0.5b-bnb-4bit 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
andreagasparini/ModernBERT-base-multilingual-stress	andreagasparini	2025-06-19T16:33:35Z	0	0	transformers	[ "transformers", "safetensors", "modernbert", "text-classification", "generated_from_trainer", "base_model:clapAI/modernBERT-base-multilingual-sentiment", "base_model:finetune:clapAI/modernBERT-base-multilingual-sentiment", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2025-06-19T16:32:59Z	--- library_name: transformers license: apache-2.0 base_model: clapAI/modernBERT-base-multilingual-sentiment tags: - generated_from_trainer metrics: - f1 - precision - recall model-index: - name: results results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # results This model is a fine-tuned version of [clapAI/modernBERT-base-multilingual-sentiment](https://huggingface.co/clapAI/modernBERT-base-multilingual-sentiment) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.1349 - F1: 0.8234 - F1 Macro: 0.8227 - F1 Micro: 0.8239 - Precision: 0.8250 - Precision Macro: 0.8257 - Precision Micro: 0.8239 - Recall: 0.8239 - Recall Macro: 0.8218 - Recall Micro: 0.8239 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: constant - num_epochs: 3 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 \| F1 Macro \| F1 Micro \| Precision \| Precision Macro \| Precision Micro \| Recall \| Recall Macro \| Recall Micro \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:------:\|:--------:\|:--------:\|:---------:\|:---------------:\|:---------------:\|:------:\|:------------:\|:------------:\| \| No log \| 1.0 \| 160 \| 0.3541 \| 0.8522 \| 0.8520 \| 0.8521 \| 0.8536 \| 0.8523 \| 0.8521 \| 0.8521 \| 0.8531 \| 0.8521 \| \| No log \| 2.0 \| 320 \| 0.6458 \| 0.8485 \| 0.8480 \| 0.8486 \| 0.8486 \| 0.8486 \| 0.8486 \| 0.8486 \| 0.8477 \| 0.8486 \| \| No log \| 3.0 \| 480 \| 1.1349 \| 0.8234 \| 0.8227 \| 0.8239 \| 0.8250 \| 0.8257 \| 0.8239 \| 0.8239 \| 0.8218 \| 0.8239 \| ### Framework versions - Transformers 4.48.0 - Pytorch 2.5.0+cu124 - Datasets 2.16.1 - Tokenizers 0.21.1

Subsets and Splits