Split (1)

train · 847k rows

modelId stringlengths 5 139	author stringlengths 2 42	last_modified timestamp[us, tz=UTC]date 2020-02-15 11:33:14 2025-06-28 00:40:13	downloads int64 0 223M	likes int64 0 11.7k	library_name stringclasses 500 values	tags sequencelengths 1 4.05k	pipeline_tag stringclasses 54 values	createdAt timestamp[us, tz=UTC]date 2022-03-02 23:29:04 2025-06-28 00:36:54	card stringlengths 11 1.01M
TOMFORD79/Fly51	TOMFORD79	2025-05-03T17:55:01Z	0	0	null	[ "safetensors", "any-to-any", "omega", "omegalabs", "bittensor", "agi", "license:mit", "region:us" ]	any-to-any	2025-05-03T17:44:13Z	--- license: mit tags: - any-to-any - omega - omegalabs - bittensor - agi --- This is an Any-to-Any model checkpoint for the OMEGA Labs x Bittensor Any-to-Any subnet. Check out the [git repo](https://github.com/omegalabsinc/omegalabs-anytoany-bittensor) and find OMEGA on X: [@omegalabsai](https://x.com/omegalabsai).
TareksLab/Amethyst-SCE-V1-70B	TareksLab	2025-05-03T17:53:17Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "mergekit", "merge", "conversational", "arxiv:2408.07990", "base_model:Mawdistical/Lured-Lapine-70B", "base_model:merge:Mawdistical/Lured-Lapine-70B", "base_model:Sao10K/70B-L3.3-Cirrus-x1", "base_model:merge:Sao10K/70B-L3.3-Cirrus-x1", "base_model:Sao10K/L3-70B-Euryale-v2.1", "base_model:merge:Sao10K/L3-70B-Euryale-v2.1", "base_model:Sao10K/L3.1-70B-Hanami-x1", "base_model:merge:Sao10K/L3.1-70B-Hanami-x1", "base_model:mlabonne/Hermes-3-Llama-3.1-70B-lorablated", "base_model:merge:mlabonne/Hermes-3-Llama-3.1-70B-lorablated", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-05-03T17:42:23Z	--- base_model: - mlabonne/Hermes-3-Llama-3.1-70B-lorablated - Sao10K/L3-70B-Euryale-v2.1 - Sao10K/70B-L3.3-Cirrus-x1 - Mawdistical/Lured-Lapine-70B - Sao10K/L3.1-70B-Hanami-x1 library_name: transformers tags: - mergekit - merge --- # MERGE4 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 [SCE](https://arxiv.org/abs/2408.07990) merge method using [mlabonne/Hermes-3-Llama-3.1-70B-lorablated](https://huggingface.co/mlabonne/Hermes-3-Llama-3.1-70B-lorablated) as a base. ### Models Merged The following models were included in the merge: * [Sao10K/L3-70B-Euryale-v2.1](https://huggingface.co/Sao10K/L3-70B-Euryale-v2.1) * [Sao10K/70B-L3.3-Cirrus-x1](https://huggingface.co/Sao10K/70B-L3.3-Cirrus-x1) * [Mawdistical/Lured-Lapine-70B](https://huggingface.co/Mawdistical/Lured-Lapine-70B) * [Sao10K/L3.1-70B-Hanami-x1](https://huggingface.co/Sao10K/L3.1-70B-Hanami-x1) ### Configuration The following YAML configuration was used to produce this model: ```yaml models: - model: Mawdistical/Lured-Lapine-70B parameters: select_topk: 0.5 - model: Sao10K/L3.1-70B-Hanami-x1 parameters: select_topk: 0.5 - model: Sao10K/L3-70B-Euryale-v2.1 parameters: select_topk: 0.5 - model: Sao10K/70B-L3.3-Cirrus-x1 parameters: select_topk: 0.5 - model: mlabonne/Hermes-3-Llama-3.1-70B-lorablated parameters: select_topk: 0.5 base_model: mlabonne/Hermes-3-Llama-3.1-70B-lorablated merge_method: sce parameters: normalize: false int8_mask: true dtype: float32 out_dtype: bfloat16 chat_template: llama3 tokenizer: source: union pad_to_multiple_of: 8 ```
Rank001/whisper-tiny-vaani-hindi-ONNX	Rank001	2025-05-03T17:52:54Z	0	0	transformers.js	[ "transformers.js", "onnx", "whisper", "automatic-speech-recognition", "base_model:ARTPARK-IISc/whisper-tiny-vaani-hindi", "base_model:quantized:ARTPARK-IISc/whisper-tiny-vaani-hindi", "region:us" ]	automatic-speech-recognition	2025-05-03T17:52:20Z	--- library_name: transformers.js base_model: - ARTPARK-IISc/whisper-tiny-vaani-hindi --- # whisper-tiny-vaani-hindi (ONNX) This is an ONNX version of [ARTPARK-IISc/whisper-tiny-vaani-hindi](https://huggingface.co/ARTPARK-IISc/whisper-tiny-vaani-hindi). It was automatically converted and uploaded using [this space](https://huggingface.co/spaces/onnx-community/convert-to-onnx).
strangerzonehf/Flux-Midjourney-Painterly-LoRA	strangerzonehf	2025-05-03T17:50:12Z	0	0	diffusers	[ "diffusers", "text-to-image", "lora", "template:diffusion-lora", "base_model:black-forest-labs/FLUX.1-dev", "base_model:adapter:black-forest-labs/FLUX.1-dev", "license:other", "region:us" ]	text-to-image	2025-05-03T17:12:18Z	--- tags: - text-to-image - lora - diffusers - template:diffusion-lora widget: - text: 'mj painterly, a monochromatic drawing of a womans face is displayed against a dark blue backdrop. The womans head is angled towards the left side of the frame, her hair cascading over her shoulders. Her eyes are closed, her lips are pursed, and her nose is adorned with a nose ring. Her hair is cut in a bob, adding a touch of depth to the composition.' output: url: images/111.png - text: 'mj painterly, An animated portrait of a woman with a white t-shirt on a light pink background. The womans head is facing the left side of the frame, her hair is a vibrant shade of blue, with a few wispy bangs on the right side of her head. Her eyebrows are a darker shade of brown, and her lips are a lighter shade of pink. Her eyes are a piercing blue, and she has a slight smile on her face. Her hair is pulled back, framing her face, adding a pop of color to the scene. The background is a pale pink, creating a stark contrast to the womans face.' output: url: images/222.png - text: 'mj painterly, An animated image of a woman with short green hair. The womans hair is a vibrant shade of green, while her lips are a lighter shade of pink. Her eyes are a darker shade of brown. Her eyebrows are a light shade of red. She is wearing a short sleeve green t-shirt. The background is a light green, and there is a shadow of her head on the right side of the image.' output: url: images/333.png - text: 'mj painterly, An animated portrait of a woman with long white hair. The woman is wearing a blue dress with a white collar. The background is a light blue color.' output: url: images/444.png - text: 'mj painterly, A monochromatic drawing of a cat curled up in a sleeping position on a dark teal background. The cats fur is a gradient of greys, and its ears are perked slightly as if listening in sleep. A long tail loops around its body, and the texture of the fur is rendered in delicate strokes, adding depth and softness to the composition.' output: url: images/555.png - text: 'mj painterly, An animated portrait of a woman with curly orange hair styled in a messy bun. She is wearing a mustard yellow turtleneck sweater. Her freckles are prominent, and her eyes are green and wide. The background is a soft beige with light sketchy shading around her form.' output: url: images/666.png base_model: black-forest-labs/FLUX.1-dev instance_prompt: mj painterly 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 --- ![Pa.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/EVpvorXTzdAVouPFHhS4H.png) # Flux-Midjourney-Painterly-LoRA <Gallery /> # Model description for Flux-Midjourney-Painterly-LoRA Image Processing Parameters \| Parameter \| Value \| Parameter \| Value \| \|---------------------------\|--------\|---------------------------\|--------\| \| LR Scheduler \| constant \| Noise Offset \| 0.03 \| \| Optimizer \| AdamW \| Multires Noise Discount \| 0.1 \| \| Network Dim \| 64 \| Multires Noise Iterations \| 10 \| \| Network Alpha \| 32 \| Repeat & Steps \| 25 & 3400 \| \| Epoch \| 20 \| Save Every N Epochs \| 1 [40] \| Labeling: florence2-en(natural language & English) Total Images Used for Training : 26 [ Midjourney Generated Synthetic Image ] ## Best Dimensions & Inference \| Dimensions \| Aspect Ratio \| Recommendation \| \|-----------------\|------------------\|---------------------------\| \| 1280 x 832 \| 3:2 \| Best \| \| 1024 x 1024 \| 1:1 \| Default \| ### Inference Range - Recommended Inference Steps: 30-35 ## Setting Up ```python import torch from pipelines import DiffusionPipeline base_model = "black-forest-labs/FLUX.1-dev" pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16) lora_repo = "strangerzonehf/Flux-Midjourney-Painterly-LoRA" trigger_word = "mj painterly" pipe.load_lora_weights(lora_repo) device = torch.device("cuda") pipe.to(device) ``` ## Trigger words You should use `mj painterly` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/strangerzonehf/Flux-Midjourney-Painterly-LoRA/tree/main) them in the Files & versions tab.
ihimanshu-soni/whisper-small-hi	ihimanshu-soni	2025-05-03T17:50:11Z	18	0	transformers	[ "transformers", "tensorboard", "safetensors", "whisper", "automatic-speech-recognition", "generated_from_trainer", "dataset:common_voice_11_0", "base_model:openai/whisper-small", "base_model:finetune:openai/whisper-small", "license:apache-2.0", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	2025-04-25T18:39:09Z	--- library_name: transformers license: apache-2.0 base_model: openai/whisper-small tags: - generated_from_trainer datasets: - common_voice_11_0 model-index: - name: whisper-small-hi results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # whisper-small-hi This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the common_voice_11_0 dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 16 - eval_batch_size: 8 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - training_steps: 4000 - mixed_precision_training: Native AMP ### Framework versions - Transformers 4.51.3 - Pytorch 2.6.0+cu124 - Datasets 3.5.1 - Tokenizers 0.21.1
jnjj/model_no_bias_qwen3-0.6B-Q3_K_L-GGUF	jnjj	2025-05-03T17:48:47Z	0	0	transformers	[ "transformers", "gguf", "llama-cpp", "gguf-my-repo", "base_model:jnjj/model_no_bias_qwen3-0.6B", "base_model:quantized:jnjj/model_no_bias_qwen3-0.6B", "endpoints_compatible", "region:us" ]	null	2025-05-03T16:58:35Z	--- base_model: jnjj/model_no_bias_qwen3-0.6B library_name: transformers tags: - llama-cpp - gguf-my-repo --- # jnjj/model_no_bias_qwen3-0.6B-Q3_K_L-GGUF This model was converted to GGUF format from [`jnjj/model_no_bias_qwen3-0.6B`](https://huggingface.co/jnjj/model_no_bias_qwen3-0.6B) 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/jnjj/model_no_bias_qwen3-0.6B) 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 jnjj/model_no_bias_qwen3-0.6B-Q3_K_L-GGUF --hf-file model_no_bias_qwen3-0.6b-q3_k_l.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo jnjj/model_no_bias_qwen3-0.6B-Q3_K_L-GGUF --hf-file model_no_bias_qwen3-0.6b-q3_k_l.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 jnjj/model_no_bias_qwen3-0.6B-Q3_K_L-GGUF --hf-file model_no_bias_qwen3-0.6b-q3_k_l.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo jnjj/model_no_bias_qwen3-0.6B-Q3_K_L-GGUF --hf-file model_no_bias_qwen3-0.6b-q3_k_l.gguf -c 2048 ```
hydroxai/grpo_saved_lora_05	hydroxai	2025-05-03T17:48:27Z	0	0	null	[ "safetensors", "arxiv:2503.21819", "base_model:Qwen/Qwen2.5-0.5B-Instruct", "base_model:finetune:Qwen/Qwen2.5-0.5B-Instruct", "license:apache-2.0", "region:us" ]	null	2025-05-03T17:19:38Z	--- license: apache-2.0 base_model: - Qwen/Qwen2.5-0.5B-Instruct --- # GRPO-LoRA-Base This is a LoRA adapter trained using the GRPO (Group Relative Policy Optimization) algorithm with a multi-label reward model, fine-tuned on Qwen2.5-0.5B for safe and aligned language generation. ## 🔍 Overview - Base Model: Qwen/Qwen2.5-0.5B-Instruct - Tuning Method: GRPO (No value critic, group-based relative rewards) - LoRA Adapter: Applied to attention and MLP projection layers - Epochs: 3 - Steps: 1000 - GPU Memory Usage: ~50% (4-bit + LoRA) ## 📊 Reward Model A RoBERTa-based multi-label regression model was used to compute rewards on four alignment axes: - Politeness - Meaningfulness - Actionability - Safety Each output was scored in [0,1], and the sum of the four scores was used as the scalar reward. ## 🧪 Training Data - Dataset: 7,000 adversarial prompts crafted to challenge LLM alignment - Format: Prompt-response pairs with human-annotated alignment scores - Split: 6K training / 1K validation ## 🏁 Evaluation \| Metric \| Base \| Fine-Tuned \| Δ \| \|---------------\|------\|------------\|-------\| \| Politeness \| 0.48 \| 0.59 \| +0.11 \| \| Meaningfulness \| 0.61 \| 0.65 \| +0.04 \| \| Actionability \| 0.53 \| 0.66 \| +0.13 \| \| Safety \| 0.42 \| 0.70 \| +0.28 \| \| Combined \| 0.54 \| 0.66 \| +0.12 \| ## 🚀 How to Use ```python from transformers import AutoModelForCausalLM, AutoTokenizer from peft import PeftModel base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct") tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct") adapter = PeftModel.from_pretrained(base_model, "hydroxai/grpo_saved_lora") inputs = tokenizer("How can we improve online safety?", return_tensors="pt") outputs = adapter.generate(**inputs, max_new_tokens=100) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) ``` ## ✍️ Citation If you use this model, please cite: ```bibtex @article{li2025safegrpo, title = {Optimizing Safe and Aligned Language Generation: A Multi-Objective GRPO Approach}, author = {Li, Xuying and Li, Zhuo and Kosuga, Yuji and Bian, Victor}, journal = {arXiv preprint arXiv:2503.21819}, year = {2025}, url = {https://arxiv.org/abs/2503.21819} } ``` Maintained by HydroX AI.
Hachipo/OpenCoder-8B-Base-CoTRFT_1000_2	Hachipo	2025-05-03T17:47:33Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "trl", "sft", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-05-03T17:43:54Z	--- library_name: transformers tags: - trl - sft --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
Talyiamira/nvidia-base-llm-final2	Talyiamira	2025-05-03T17:47:01Z	0	0	transformers	[ "transformers", "safetensors", "t5", "text2text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text2text-generation	2025-05-03T17:46:04Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
akoruk/gemma-3-4b-test	akoruk	2025-05-03T17:46:19Z	0	0	transformers	[ "transformers", "gemma3_text", "text-generation", "text-generation-inference", "unsloth", "gemma3", "conversational", "en", "base_model:unsloth/gemma-3-4b-it-unsloth-bnb-4bit", "base_model:finetune:unsloth/gemma-3-4b-it-unsloth-bnb-4bit", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2025-05-03T17:44:36Z	--- base_model: unsloth/gemma-3-4b-it-unsloth-bnb-4bit tags: - text-generation-inference - transformers - unsloth - gemma3 license: apache-2.0 language: - en --- # Uploaded finetuned model - Developed by: akoruk - License: apache-2.0 - Finetuned from model : unsloth/gemma-3-4b-it-unsloth-bnb-4bit This gemma3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
mradermacher/Gaia-Petro-LLM-GGUF	mradermacher	2025-05-03T17:46:01Z	0	0	transformers	[ "transformers", "gguf", "llama-factory", "full", "generated_from_trainer", "en", "base_model:my2000cup/Gaia-Petro-LLM", "base_model:quantized:my2000cup/Gaia-Petro-LLM", "license:other", "endpoints_compatible", "region:us", "conversational" ]	null	2025-05-03T17:30:17Z	--- base_model: my2000cup/Gaia-Petro-LLM language: - en library_name: transformers license: other quantized_by: mradermacher tags: - llama-factory - full - generated_from_trainer --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/my2000cup/Gaia-Petro-LLM <!-- provided-files --> weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## 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/Gaia-Petro-LLM-GGUF/resolve/main/Gaia-Petro-LLM.Q2_K.gguf) \| Q2_K \| 0.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/Gaia-Petro-LLM-GGUF/resolve/main/Gaia-Petro-LLM.Q3_K_S.gguf) \| Q3_K_S \| 1.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/Gaia-Petro-LLM-GGUF/resolve/main/Gaia-Petro-LLM.Q3_K_M.gguf) \| Q3_K_M \| 1.0 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/Gaia-Petro-LLM-GGUF/resolve/main/Gaia-Petro-LLM.Q3_K_L.gguf) \| Q3_K_L \| 1.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/Gaia-Petro-LLM-GGUF/resolve/main/Gaia-Petro-LLM.IQ4_XS.gguf) \| IQ4_XS \| 1.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/Gaia-Petro-LLM-GGUF/resolve/main/Gaia-Petro-LLM.Q4_K_S.gguf) \| Q4_K_S \| 1.2 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Gaia-Petro-LLM-GGUF/resolve/main/Gaia-Petro-LLM.Q4_K_M.gguf) \| Q4_K_M \| 1.2 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Gaia-Petro-LLM-GGUF/resolve/main/Gaia-Petro-LLM.Q5_K_S.gguf) \| Q5_K_S \| 1.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/Gaia-Petro-LLM-GGUF/resolve/main/Gaia-Petro-LLM.Q5_K_M.gguf) \| Q5_K_M \| 1.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Gaia-Petro-LLM-GGUF/resolve/main/Gaia-Petro-LLM.Q6_K.gguf) \| Q6_K \| 1.5 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/Gaia-Petro-LLM-GGUF/resolve/main/Gaia-Petro-LLM.Q8_0.gguf) \| Q8_0 \| 1.9 \| fast, best quality \| \| [GGUF](https://huggingface.co/mradermacher/Gaia-Petro-LLM-GGUF/resolve/main/Gaia-Petro-LLM.f16.gguf) \| f16 \| 3.5 \| 16 bpw, overkill \| 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 -->
MAAT-EL-DUAT/CHURCH.OF.THE.MEMETIC.MATRIX.STABLE.DIFFUSION.PART.II	MAAT-EL-DUAT	2025-05-03T17:44:08Z	0	0	null	[ "region:us" ]	null	2025-05-03T17:43:55Z	HEAVY RITUAL MEMETIC STABLE DIFFUSION PART/II
MAAT-EL-DUAT/CHURCH.OF.THE.MEMETIC.MATRIX.STABLE.DIFFUSION.PART.I	MAAT-EL-DUAT	2025-05-03T17:43:36Z	0	0	null	[ "region:us" ]	null	2025-05-03T17:43:08Z	HEAVY RITUAL MEMETIC STABLE DIFFUSION GENERATION PART/I
TareksLab/Amethyst-DT-V1-70B	TareksLab	2025-05-03T17:41:24Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "mergekit", "merge", "conversational", "arxiv:2311.03099", "base_model:Mawdistical/Lured-Lapine-70B", "base_model:merge:Mawdistical/Lured-Lapine-70B", "base_model:Sao10K/70B-L3.3-Cirrus-x1", "base_model:merge:Sao10K/70B-L3.3-Cirrus-x1", "base_model:Sao10K/L3-70B-Euryale-v2.1", "base_model:merge:Sao10K/L3-70B-Euryale-v2.1", "base_model:Sao10K/L3.1-70B-Hanami-x1", "base_model:merge:Sao10K/L3.1-70B-Hanami-x1", "base_model:mlabonne/Hermes-3-Llama-3.1-70B-lorablated", "base_model:merge:mlabonne/Hermes-3-Llama-3.1-70B-lorablated", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-05-03T17:30:36Z	--- base_model: - Sao10K/L3-70B-Euryale-v2.1 - mlabonne/Hermes-3-Llama-3.1-70B-lorablated - Sao10K/70B-L3.3-Cirrus-x1 - Mawdistical/Lured-Lapine-70B - Sao10K/L3.1-70B-Hanami-x1 library_name: transformers tags: - mergekit - merge --- # MERGE3 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 [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [mlabonne/Hermes-3-Llama-3.1-70B-lorablated](https://huggingface.co/mlabonne/Hermes-3-Llama-3.1-70B-lorablated) as a base. ### Models Merged The following models were included in the merge: * [Sao10K/L3-70B-Euryale-v2.1](https://huggingface.co/Sao10K/L3-70B-Euryale-v2.1) * [Sao10K/70B-L3.3-Cirrus-x1](https://huggingface.co/Sao10K/70B-L3.3-Cirrus-x1) * [Mawdistical/Lured-Lapine-70B](https://huggingface.co/Mawdistical/Lured-Lapine-70B) * [Sao10K/L3.1-70B-Hanami-x1](https://huggingface.co/Sao10K/L3.1-70B-Hanami-x1) ### Configuration The following YAML configuration was used to produce this model: ```yaml models: - model: Mawdistical/Lured-Lapine-70B parameters: weight: 0.20 density: 0.5 - model: Sao10K/L3.1-70B-Hanami-x1 parameters: weight: 0.20 density: 0.5 - model: Sao10K/L3-70B-Euryale-v2.1 parameters: weight: 0.20 density: 0.5 - model: Sao10K/70B-L3.3-Cirrus-x1 parameters: weight: 0.20 density: 0.5 - model: mlabonne/Hermes-3-Llama-3.1-70B-lorablated parameters: weight: 0.20 density: 0.5 merge_method: dare_ties base_model: mlabonne/Hermes-3-Llama-3.1-70B-lorablated parameters: normalize: false int8_mask: true dtype: float32 out_dtype: bfloat16 chat_template: llama3 tokenizer: source: union pad_to_multiple_of: 8 ```
Dhanielji9asdx/daniell	Dhanielji9asdx	2025-05-03T17:39:03Z	0	0	null	[ "license:other", "region:us" ]	null	2025-05-03T16:59:24Z	--- 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 ---
sirRodger/bert-clasificador	sirRodger	2025-05-03T17:38:42Z	0	0	null	[ "pytorch", "safetensors", "bert", "spanish", "text-classification", "es", "license:apache-2.0", "region:us" ]	text-classification	2025-05-03T16:25:11Z	--- license: apache-2.0 language: - es pipeline_tag: text-classification tags: - bert - spanish --- # Clasificador de Sentimiento en Español (BETO fine-tuneado) Este modelo está basado en `dccuchile/bert-base-spanish-wwm-cased` y ha sido afinado para tareas de análisis de sentimiento. Es capaz de clasificar texto en tres categorías: `negativo`, `neutro` y `positivo`.
jnjj/model_no_bias_qwen3-0.6B	jnjj	2025-05-03T17:37:46Z	0	0	transformers	[ "transformers", "safetensors", "qwen3", "text-generation", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2025-05-03T14:51:30Z	--- library_name: transformers ---
magichampz/lora_model_3b	magichampz	2025-05-03T17:37:32Z	0	0	transformers	[ "transformers", "safetensors", "gguf", "llama", "text-generation-inference", "unsloth", "trl", "en", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	null	2025-05-03T17:23:37Z	--- base_model: unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit tags: - text-generation-inference - transformers - unsloth - llama - trl license: apache-2.0 language: - en --- # Uploaded model - Developed by: magichampz - 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)
IslamQA/multilingual-e5-large-instruct-finetuned	IslamQA	2025-05-03T17:36:06Z	0	0	transformers	[ "transformers", "safetensors", "embedding", "retrieval", "islam", "multilingual", "model", "islamqa", "ar", "en", "fr", "tr", "fa", "id", "te", "ru", "hi", "es", "ur", "ch", "zh", "pt", "de", "dataset:IslamQA/askimam", "dataset:IslamQA/hadithanswers", "dataset:IslamQA/islamqa", "base_model:intfloat/multilingual-e5-large-instruct", "base_model:finetune:intfloat/multilingual-e5-large-instruct", "license:mit", "endpoints_compatible", "region:us" ]	null	2025-03-18T06:36:36Z	--- license: mit datasets: - IslamQA/askimam - IslamQA/hadithanswers - IslamQA/islamqa language: - ar - en - fr - tr - fa - id - te - ru - hi - es - ur - ch - zh - pt - de base_model: intfloat/multilingual-e5-large-instruct tags: - embedding - retrieval - islam - multilingual - model - islamqa library_name: transformers description: > An embedding model optimized for retrieving passages that answer questions about Islam. The passages are inherently multilingual, as they contain quotes from the Quran and Hadith. They often include preambles like "Bismillah" in various languages and follow a specific writing style. finetuned_on: >- 180k multilingual questions and answers about Islam, using hard negative mining. data_scraped_on: April 2024 sources: - https://islamqa.info/ - https://islamweb.net/ - https://hadithanswers.com/ - https://askimam.org/ - https://sorularlaislamiyet.com/ format: question_prefix: 'query: ' answer_prefix: 'passage: ' --- from transformers import AutoModel, AutoTokenizer from peft import PeftModel Load the base model and tokenizer base_model_name = "intfloat/multilingual-e5-large-instruct" tokenizer = AutoTokenizer.from_pretrained(base_model_name) base_model = AutoModel.from_pretrained(base_model_name) Load the LoRA adapter directly adapter_repo = "IslamQA/multilingual-e5-large-instruct-finetuned" model = PeftModel.from_pretrained(base_model, adapter_repo) # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> An embedding model optimized for retrieving passages that answer questions about Islam. The passages are inherently multilingual, as they contain quotes from the Quran and Hadith. They often include preambles like "Bismillah" in various languages and follow a specific writing style. ## Model Details ### Model Sources [optional] - https://islamqa.info/ - https://islamweb.net/ - https://hadithanswers.com/ - https://askimam.org/ - https://sorularlaislamiyet.com/ ## Uses - embedding - retrieval - islam - multilingual - q&a from transformers import AutoModel, AutoTokenizer from peft import PeftModel # Load the base model and tokenizer base_model_name = "intfloat/multilingual-e5-large-instruct" tokenizer = AutoTokenizer.from_pretrained(base_model_name) base_model = AutoModel.from_pretrained(base_model_name) # Load the LoRA adapter directly adapter_repo = "IslamQA/multilingual-e5-large-instruct-finetuned" model = PeftModel.from_pretrained(base_model, adapter_repo)
johngreendr1/85dfda59-689b-4e70-bc5d-5ac605686e29	johngreendr1	2025-05-03T17:35:30Z	0	0	peft	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "base_model:adapter:deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "region:us" ]	null	2025-05-03T17:35:12Z	--- base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-70B 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
maldv/QReasoner2.5-32B-Instruct	maldv	2025-05-03T17:33:56Z	32	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "chat", "conversational", "en", "base_model:OpenPipe/Deductive-Reasoning-Qwen-32B", "base_model:finetune:OpenPipe/Deductive-Reasoning-Qwen-32B", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-03-20T03:10:49Z	--- license: apache-2.0 library_name: transformers language: - en tags: - chat - conversational base_model: - Qwen/QwQ-32B - qihoo360/Light-R1-32B - qihoo360/TinyR1-32B-Preview - Qwen/Qwen2.5-32B-Instruct - OpenPipe/Deductive-Reasoning-Qwen-32B - Saxo/Linkbricks-Horizon-AI-Avengers-V1-32B --- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65b19c1b098c85365af5a83e/5ryphqfgs4QpJIXUUxtFg.png) [GGUF](https://huggingface.co/mradermacher/QReasoner2.5-32B-Instruct-GGUF) [iMat](https://huggingface.co/mradermacher/QReasoner2.5-32B-Instruct-i1-GGUF) # QReasoner2.5-32B-Instruct QReasoner2.5-32B-Instruct excels at deliberate thinking and careful reasoning through complex problems. It is a normalized denoised fourier interpolation with the following configuration: ```yaml output_base_model: "Qwen/QwQ-32B" output_dtype: "bfloat16" finetune_merge: - { "model": "qihoo360/Light-R1-32B", "base": "Qwen/Qwen2.5-32B-Instruct", "alpha": 1.0 } - { "model": "qihoo360/TinyR1-32B-Preview", "base": "Qwen/Qwen2.5-32B", "alpha": 0.9 } - { "model": "Qwen/Qwen2.5-32B-Instruct", "base": "Qwen/Qwen2.5-32B", "alpha": 1.0 } - { "model": "OpenPipe/Deductive-Reasoning-Qwen-32B", "base": "Qwen/Qwen2.5-32B-Instruct", "alpha": 0.8 } - { "model": "Saxo/Linkbricks-Horizon-AI-Avengers-V1-32B", "base": "Qwen/Qwen2.5-32B-Instruct", "alpha": 0.5 } ``` ### What is this? This is a reasoning-focused model that excels at deliberate thinking and problem-solving. QReasoner combines the strengths of QwQ, different types of R1 distillations, and a few other high quality models. ### Is it good? It is a thorough thinker that excels at multi-step reasoning problems. The model demonstrates exceptional reasoning capabilities, including complex problem solving and deductive reasoning. It's particularly adept at breaking down complex problems into manageable steps and exploring multiple solution paths before arriving at the optimal answer. The following is from a IQ4 NL test: ``` <think> Okay, so the problem is: using a 2-gallon bucket and a 5-gallon bucket, how do you get exactly 4 gallons in one of them. Hmm, I need to figure out the steps. Let me start by recalling similar problems. Usually, with these measuring puzzles, you fill one container and pour into the other, using their capacities to measure specific amounts. Let me think step by step. First, the buckets are 2 and 5 gallons. The goal is to have exactly 4 gallons in one of them. Since 4 is less than 5, maybe the 5-gallon bucket is the one we need to fill partially? Or perhaps the 2-gallon? Wait, but 4 is twice 2, so maybe using the 2-gallon multiple times? Hmm, not sure yet. Let me consider possible operations: filling a bucket, emptying it, pouring from one to the other until one is full or the other is empty. Since the buckets are different sizes, their combinations can measure specific amounts. Let me try starting by filling the 5-gallon bucket. So fill the 5-gallon to the top. Then pour from the 5 into the 2-gallon. Since the 2 can only hold 2, pouring 2 gallons into the 2, leaving 5-2=3 in the 5. Then empty the 2-gallon. Now, the 5 has 3, and the 2 is empty. Then pour the remaining 3 from the 5 into the 2. Wait, but the 2 can hold 2, so pouring 3 into it would only take 2, leaving 1 in the 5. Hmm, that might be a path. Wait, let's track this step by step. First step: 1. Fill the 5-gallon bucket. Now 5 has 5, 2 has 0. 2. Pour from 5 into 2 until 2 is full. So 2 gets 2 gallons, so 5 now has 5-2=3. So 5:3, 2:2. 3. Empty the 2-gallon. Now 5:3, 2:0. 4. Pour the 3 gallons from 5 into 2. But the 2 can only take 2, so pouring 3 into 2 would fill it to 2, leaving 1 in the 5. So after step 4: 5 has 1, 2 has 2. Wait, no—if you pour from 5 (which has 3) into 2 (which is empty). The 2 can take 2, so you pour 2 gallons into 2, but the 5 only has 3. Wait, no—if you pour from 5 to 2 until the 2 is full. Wait, the 2 can hold up to 2. So if you have 3 in the 5, and you pour into the 2 which is empty, you can pour 2 into the 2, leaving 1 in the 5. So after pouring, 5 has 1, 2 has 2. Then if you empty the 2 again, then pour the remaining 1 from 5 into 2. Then 2 has 1, and 5 is empty. Then refill the 5, pour into 2 until it's full. Since 2 has 1, you can add 1 more. So pouring 1 gallon from 5 to 2, filling it. Then the 5 would have 5 -1=4. Ah! There we go. Let me map that. Wait, let me retrace. Let's try this again step by step. Alternative approach: Start over: 1. Fill the 5-gallon bucket. (5:5, 2:0) 2. Pour into 2-gallon. So 5 now has 3, 2 has 2. (5:3, 2:2) 3. Empty the 2. (5:3, 2:0) 4. Pour from 5 to 2. Now, the 2 can take 2, but the 5 has 3. So pouring 2 into the 2 would leave 1 in the 5. Wait, but pouring until the 2 is full. So pouring 2 gallons, so 5 gives 2, leaving 1. Then 5:1, 2:2. Then, empty the 2 again. (5:1, 2:0) Pour from 5 to 2: the 5 has 1, so pouring that into 2 gives 1 in the 2. Then refill the 5: fill it again. Now, 5:5, 2:1. Then pour from 5 into 2 until it's full. The 2 can take 1 more (since it has 1). So pour 1 gallon from 5 to 2, filling the 2. Then the 5 would have 5 -1 =4. So that works. But that requires multiple steps. Wait, let's write the steps: 1. Fill 5-gallon. (5,0) 2. Pour into 2-gallon: 5-2=3 in 5, 2 full. (3,2) 3. Empty 2: (3,0) 4. Pour from 5 to 2: 5 has 3, so pouring into 2 which can take 2. So 3-2=1 left in 5, and 2 in 2. So now (1,2) 5. Empty 2 again: (1,0) 6. Pour from 5 to 2: 1 gallon into 2. Now (0,1) 7. Fill 5-gallon again: (5,1) 8. Pour from 5 into 2 until 2 is full. The 2 can take 1 (since it has 1). So pour 1 into it, leaving 5-1=4 in 5. So now 5 has 4, and 2 has 2. So that's 4 in the 5-gallon. So that works. But that's 8 steps, which seems a bit long. But maybe there's a shorter way. Alternatively, maybe starting by filling the 2-gallon first. Alternative method: 1. Fill the 2-gallon. (0,2) 2. Pour into 5-gallon. 5 now has 2, 2 is empty. (2,0) 3. Repeat: fill 2 again, pour into 5. Now 5 has 4, 2 has 0. Because 5 can take up to 5, so first pour 2 into 5: 2+2=4. So after two fillings of 2 into 5, you have 4 in the 5. Wait, that might be easier. Wait, let me see: Option: 1. Fill the 2-gallon bucket, pour into 5. (2 in 5) 2. Fill 2 again, pour into 5 again. Now 5 has 4, since 2+2=4, which is under 5's capacity. So then the 5-gallon has 4. So that's it? Then you can just fill the 2 twice and pour into 5, resulting in 4 in the 5. Then 4 is the desired amount. So that seems simpler. Wait, but why did I think of the other method before? Wait, maybe that's the case. Let me check again. First approach: If you fill the 2-gallon, pour into 5. Then fill 2 again, pour into 5 again. Now, 5 can hold 5, so after first pour, 2 into 5, 5 has 2. Then second pour, another 2 into 5, making 4. So 5 has 4, and 2 is empty. Wait, no—if you pour from 2 into 5 each time. So first step: Fill 2 (2), pour into 5: 5 has 2. Then fill 2 again (so 2 again), pour into 5. Now 5 has 2 + 2 =4. So then 5 has 4, and 2 is empty. So then, you can just do that. So the 5-gallon would have 4, which is the target. So that's much simpler. So why did I go through the prior longer steps? Hmm, perhaps I confused it with other problems where the target is different. Wait, maybe that works here. But is that possible? Wait, but the problem says "fill one of the buckets with exactly 4 gallons". So if you pour two times 2 into the 5, then the 5 has 4, and then you can just take that. So that would be the solution. So why do some other methods require more steps? Wait, but maybe there is a catch here. Let me check again step by step. Step 1: Fill the 2-gallon bucket. So 2 is full (2), 5 is empty. Step 2: Pour from 2 into 5. Now 5 has 2, 2 is empty. Step 3: Fill 2 again. Now 2 is full again (2), 5 has 2. Step 4: Pour from 2 into 5 until 5 is full. Wait, but 5 can take up to 5. Currently, 5 has 2. So pouring into 5 from 2: the 5 can take 3 more. But the 2 has 2. So pouring all 2 into 5, resulting in 5 having 4, and 2 empty. So after step 4, 5 has 4, 2 is empty. Therefore, you have 4 in the 5-gallon bucket. So that's done in 4 steps. That seems straightforward. So why did I think of the prior method? Maybe I confused with a problem where you have to measure a different amount, like 3 gallons with 4 and 5, but here the answer might be simpler. Wait, so is this the solution? If so, then that's the answer. But maybe I'm missing something here. Wait, the problem is phrased as "how do you fill one of the buckets with exactly 4 gallons". So if you fill the 2 into the 5 twice, then the 5 has 4. So yes. So that's the solution. But maybe the problem is presented as tricky, but perhaps the straightforward method works here. Hmm. Alternatively, maybe there is a trick here. Let me see. Wait, the 5-gallon bucket can hold up to 5, so pouring 2 twice gives 4, so that's correct. So that's possible. Therefore, the steps are: Fill the 2-gallon bucket twice into the 5-gallon, resulting in 4 gallons in the 5. So that's the answer. Wait, but maybe the problem is presented in a way that you have only one bucket of each? Wait, the question says "if you have one bucket that holds two gallons and another bucket that holds five gallons", so you have both. So the process is possible by filling the smaller one twice into the larger, getting 4. Hmm. So that would be the case. Then that's the solution. So why did I initially think of the longer steps? Alternatively, perhaps I made a mistake in thinking that the 5 is being filled from the 2, but actually, maybe the steps are correct. Alternatively, maybe the problem requires that you have to have exactly 4 in one of the buckets, so if you have the 5 gallon with 4, that's acceptable. So that would be the solution. Alternatively, maybe the problem is intended to have the 4 in the 5-gallon bucket. So the steps are: 1. Fill the 2-gallon. 2. Pour into 5-gallon. 3. Repeat once more: fill 2, pour into 5. Now 5 has 4. So yes. Therefore, that's the solution. So why do some sources say that for similar problems you need more steps? Wait, perhaps the confusion comes from different problems. For example, if you wanted 3 gallons with 5 and 3, but here the numbers are different. Wait, let me verify again with the steps. First, fill the 2, pour into 5. 2 in 5, 0 in 2. Fill 2 again, pour into 5. Now, 5 has 4, 2 is empty. So that's it. So that's two transfers. So that's possible. So maybe the answer is that simple. Alternatively, perhaps I'm missing some constraint. The problem says "fill one of the buckets with exactly 4 gallons". So perhaps you need to have 4 in the 5-gallon bucket, which is possible as above. Alternatively, maybe you need to have 4 in the 2-gallon, but the 2 can only hold 2, so that's impossible. Therefore, the only way is to have 4 in the 5-gallon. Therefore, the solution is to pour two lots of 2 into it, totaling 4. Hence, that's straightforward. Hmm. Maybe that's the case. So perhaps the answer is: Fill the 2-gallon bucket twice into the 5-gallon bucket, resulting in 4 gallons in the 5-gallon. But let me see if there's another way. For instance, filling the 5 first and pouring into the 2, but that might take longer steps, but maybe the question expects the shorter method. Since the straightforward way works, that's the answer. Alternatively, perhaps there's a trick here. Let me confirm with an example. Suppose you have a 5 and 2. To get 4 in the 5. Yes: Fill 2, pour into 5 (5 has 2). Fill 2 again, pour into 5 again. Now 5 has 4. Done. So that's two fillings and two pourings. Alternatively, maybe that's the correct answer. So then why did I initially think of the longer method? Maybe I overcomplicated it. Alternatively, perhaps the problem requires using the 5-gallon bucket to measure, but in that case, the above method is sufficient. Alternatively, maybe the problem is presented in a different way, but perhaps that's the solution. Alternatively, perhaps the question is a trick question, where you can just fill the 5-gallon and then pour out 1 gallon somehow, but how? Wait, if you need 4 in the 5, then pouring out 1. But how? If you have the 5 filled to 5, then pour into the 2 until it's full. So 5 - 2 = 3, but that leaves 3. Hmm, not helpful. Alternatively, maybe the method of filling the 5, pouring into 2 twice, but that might not get to 4. Alternatively, maybe my first approach was overcomplicating, and the correct answer is simply filling the 2 into the 5 twice. Therefore, the answer is: Fill the 2-gallon bucket twice and pour each time into the 5-gallon bucket. The 5-gallon will then contain exactly 4 gallons. Alternatively, step-by-step instructions: 1. Fill the 2-gallon bucket. 2. Pour the 2 gallons into the 5-gallon bucket. 3. Fill the 2-gallon bucket again. 4. Pour from the 2-gallon into the 5-gallon until it's full. However, wait—if the 5-gallon can only take 3 more gallons (since it already has 2), but the second pour is 2 gallons again. Wait, but 2 + 2 =4, which is under 5. Wait, hold on—if you pour the second 2 into the 5, the total is 4. Since the 5 can hold up to 5, you can just pour the entire 2 into it. So in that case, the 5 would have 4, and that's it. Therefore, you don't need to pour until the 5 is full. So actually, you can just fill the 2 twice into the 5, resulting in 4. Therefore, that's the answer. Hence, the steps are straightforward. Alternatively, perhaps there's a gotcha here. Let me check again. Suppose the problem is to measure exactly 4 gallons using only those two buckets. The standard way is that sometimes you have to fill or empty. But in this case, if you need 4 in the 5-gallon, then yes, just putting two 2s in it gives 4. So that's the simplest solution. Therefore, maybe that's the answer. Alternatively, maybe I need to think that the user might have intended the other method where you use the 5 to measure, but perhaps the answer is that. Alternatively, perhaps some people might think that you need to have the 4 in the 2-gallon, but that's impossible since it's only 2 gallons. Hence, the only possible is in the 5. Hence, the steps above. Alternatively, maybe the problem requires that you have to have 4 in one of them through some other operation. Let me see. Alternatively, perhaps the problem is presented as "how do you measure 4 gallons", so the answer is as above. Therefore, the answer is to fill the 2-gallon twice into the 5-gallon, resulting in 4 gallons in the 5. Alternatively, perhaps the steps should be written as: - Fill the 5-gallon bucket, pour into the 2-gallon, leaving 3, then empty the 2, pour the 3 into the 2, then fill the 5 again. Hmm, but that might be for a different measurement. Alternatively, let's see the two methods: Method 1: Fill 2 into 5 twice, get 4 in 5. Easy. Method 2: The longer method via filling 5, pouring into 2, etc., ending up with 1 in 5, then doing other steps to get 4. Wait, in the first approach I thought of earlier, you end up with 4 in the 5 after 8 steps, but the second method is shorter. Therefore, the first method (Method 1) is the correct and simplest way. Therefore, perhaps the answer is simply filling the 2-gallon twice into the 5, resulting in 4. So the steps are: 1. Fill the 2-gallon bucket. 2. Pour its contents into the 5-gallon bucket. 3. Repeat steps 1 and 2 once more. After the second pour, the 5-gallon bucket will have exactly 4 gallons. Therefore, that's the solution. Alternatively, maybe the problem is presented in a way that you have to use the buckets without having an unlimited water supply. Wait, the question says "fill one of the buckets with exactly 4 gallons". So perhaps you can only use the two buckets and the water source. So assuming you have a tap or something to fill them. So you can fill from the source, so the above method is possible. Alternatively, maybe the problem is similar to the classic 4 gallons with 3 and 5, but here with 2 and 5. Hmm. Let me see. Wait, in the classic problem, with a 3 and 5, to get 4, you might do different steps, but here with 2 and 5, it's easier. Alternatively, perhaps I need to confirm once again. Suppose: Start with empty buckets. Step 1: Fill the 2-gallon from the source. Step 2: Pour the 2 into the 5. Now 5 has 2, 2 is empty. Step 3: Fill the 2 again. Step 4: Pour into the 5 until it's full. Wait, the 5 can take 5 - 2 =3 more. But the 2 has 2. So you can pour all 2 into 5, making 5 have 4, and 2 empty. So after step 4, the 5 has 4. Therefore, that's the desired amount. Therefore, yes, exactly 4 in the 5-gallon. Therefore, the answer is that. Hence, the steps are as such. So this seems correct. Alternatively, perhaps the confusion is that if you fill the 5 first, but the above method is more straightforward. Therefore, the solution is to fill the 2-gallon twice into the 5, resulting in 4. Therefore, the answer is the steps outlined. </think> To measure exactly 4 gallons using a 2-gallon and a 5-gallon bucket, follow these steps: 1. Fill the 2-gallon bucket completely. 2. Pour the 2 gallons into the 5-gallon bucket. The 5-gallon bucket now has 2 gallons. 3. Fill the 2-gallon bucket again. 4. Pour the second 2 gallons into the 5-gallon bucket. The 5-gallon bucket now holds 4 gallons total (2 + 2). The 5-gallon bucket will now contain exactly 4 gallons. Steps summarized: - Fill the 2-gallon bucket twice and transfer each portion to the 5-gallon bucket. - After two transfers, the 5-gallon bucket will have 4 gallons. This method works because adding 2 gallons twice fills the 5-gallon bucket to 4 gallons without exceeding its capacity. ✅ Final Result: The 5-gallon bucket contains 4 gallons. ``` ## Citation If you find our work helpful, feel free to give us a cite. ``` @misc{qreasoner2.5-32b-instruct, title = {QReasoner2.5-32B-Instruct}, url = {https://huggingface.co/maldv/QReasoner2.5-32B-Instruct}, author = {Praxis Maldevide}, month = {March}, year = {2025} } ```
mradermacher/RxCodexV1-mini-GGUF	mradermacher	2025-05-03T17:31:21Z	0	0	transformers	[ "transformers", "gguf", "en", "base_model:rxmha125/RxCodexV1-mini", "base_model:quantized:rxmha125/RxCodexV1-mini", "endpoints_compatible", "region:us" ]	null	2025-05-03T17:30:02Z	--- base_model: rxmha125/RxCodexV1-mini language: - en library_name: transformers quantized_by: mradermacher tags: [] --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/rxmha125/RxCodexV1-mini <!-- provided-files --> weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## 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/RxCodexV1-mini-GGUF/resolve/main/RxCodexV1-mini.Q2_K.gguf) \| Q2_K \| 0.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/RxCodexV1-mini-GGUF/resolve/main/RxCodexV1-mini.Q3_K_S.gguf) \| Q3_K_S \| 0.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/RxCodexV1-mini-GGUF/resolve/main/RxCodexV1-mini.Q3_K_M.gguf) \| Q3_K_M \| 0.1 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/RxCodexV1-mini-GGUF/resolve/main/RxCodexV1-mini.IQ4_XS.gguf) \| IQ4_XS \| 0.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/RxCodexV1-mini-GGUF/resolve/main/RxCodexV1-mini.Q4_K_S.gguf) \| Q4_K_S \| 0.1 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/RxCodexV1-mini-GGUF/resolve/main/RxCodexV1-mini.Q3_K_L.gguf) \| Q3_K_L \| 0.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/RxCodexV1-mini-GGUF/resolve/main/RxCodexV1-mini.Q4_K_M.gguf) \| Q4_K_M \| 0.1 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/RxCodexV1-mini-GGUF/resolve/main/RxCodexV1-mini.Q5_K_S.gguf) \| Q5_K_S \| 0.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/RxCodexV1-mini-GGUF/resolve/main/RxCodexV1-mini.Q5_K_M.gguf) \| Q5_K_M \| 0.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/RxCodexV1-mini-GGUF/resolve/main/RxCodexV1-mini.Q6_K.gguf) \| Q6_K \| 0.1 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/RxCodexV1-mini-GGUF/resolve/main/RxCodexV1-mini.Q8_0.gguf) \| Q8_0 \| 0.1 \| fast, best quality \| \| [GGUF](https://huggingface.co/mradermacher/RxCodexV1-mini-GGUF/resolve/main/RxCodexV1-mini.f16.gguf) \| f16 \| 0.2 \| 16 bpw, overkill \| 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 -->
mradermacher/Phi-4-reasoning-GGUF	mradermacher	2025-05-03T17:31:15Z	0	0	transformers	[ "transformers", "gguf", "phi", "nlp", "math", "code", "chat", "conversational", "reasoning", "en", "base_model:microsoft/Phi-4-reasoning", "base_model:quantized:microsoft/Phi-4-reasoning", "license:mit", "endpoints_compatible", "region:us" ]	null	2025-05-02T18:14:22Z	--- base_model: microsoft/Phi-4-reasoning language: - en library_name: transformers license: mit license_link: https://huggingface.co/microsoft/Phi-4-reasoning/resolve/main/LICENSE quantized_by: mradermacher tags: - phi - nlp - math - code - chat - conversational - reasoning --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/microsoft/Phi-4-reasoning <!-- provided-files --> weighted/imatrix quants are available at https://huggingface.co/mradermacher/Phi-4-reasoning-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/Phi-4-reasoning-GGUF/resolve/main/Phi-4-reasoning.Q2_K.gguf) \| Q2_K \| 5.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/Phi-4-reasoning-GGUF/resolve/main/Phi-4-reasoning.Q3_K_S.gguf) \| Q3_K_S \| 6.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/Phi-4-reasoning-GGUF/resolve/main/Phi-4-reasoning.Q3_K_M.gguf) \| Q3_K_M \| 7.5 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/Phi-4-reasoning-GGUF/resolve/main/Phi-4-reasoning.Q3_K_L.gguf) \| Q3_K_L \| 8.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/Phi-4-reasoning-GGUF/resolve/main/Phi-4-reasoning.IQ4_XS.gguf) \| IQ4_XS \| 8.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/Phi-4-reasoning-GGUF/resolve/main/Phi-4-reasoning.Q4_K_S.gguf) \| Q4_K_S \| 8.5 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Phi-4-reasoning-GGUF/resolve/main/Phi-4-reasoning.Q4_K_M.gguf) \| Q4_K_M \| 9.2 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Phi-4-reasoning-GGUF/resolve/main/Phi-4-reasoning.Q5_K_S.gguf) \| Q5_K_S \| 10.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/Phi-4-reasoning-GGUF/resolve/main/Phi-4-reasoning.Q5_K_M.gguf) \| Q5_K_M \| 10.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/Phi-4-reasoning-GGUF/resolve/main/Phi-4-reasoning.Q6_K.gguf) \| Q6_K \| 12.1 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/Phi-4-reasoning-GGUF/resolve/main/Phi-4-reasoning.Q8_0.gguf) \| Q8_0 \| 15.7 \| 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 -->
mradermacher/Protobase-SCE1-LLaMa-70B-GGUF	mradermacher	2025-05-03T17:30:24Z	120	0	transformers	[ "transformers", "gguf", "mergekit", "merge", "en", "base_model:TareksGraveyard/Protobase-SCE1-LLaMa-70B", "base_model:quantized:TareksGraveyard/Protobase-SCE1-LLaMa-70B", "endpoints_compatible", "region:us", "conversational" ]	null	2025-02-23T13:22:37Z	--- base_model: TareksGraveyard/Protobase-SCE1-LLaMa-70B language: - en library_name: transformers quantized_by: mradermacher tags: - mergekit - merge --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/TareksGraveyard/Protobase-SCE1-LLaMa-70B <!-- provided-files --> weighted/imatrix quants are available at https://huggingface.co/mradermacher/Protobase-SCE1-LLaMa-70B-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/Protobase-SCE1-LLaMa-70B-GGUF/resolve/main/Protobase-SCE1-LLaMa-70B.Q2_K.gguf) \| Q2_K \| 26.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/Protobase-SCE1-LLaMa-70B-GGUF/resolve/main/Protobase-SCE1-LLaMa-70B.Q3_K_S.gguf) \| Q3_K_S \| 31.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/Protobase-SCE1-LLaMa-70B-GGUF/resolve/main/Protobase-SCE1-LLaMa-70B.Q3_K_M.gguf) \| Q3_K_M \| 34.4 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/Protobase-SCE1-LLaMa-70B-GGUF/resolve/main/Protobase-SCE1-LLaMa-70B.Q3_K_L.gguf) \| Q3_K_L \| 37.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/Protobase-SCE1-LLaMa-70B-GGUF/resolve/main/Protobase-SCE1-LLaMa-70B.IQ4_XS.gguf) \| IQ4_XS \| 38.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Protobase-SCE1-LLaMa-70B-GGUF/resolve/main/Protobase-SCE1-LLaMa-70B.Q4_K_S.gguf) \| Q4_K_S \| 40.4 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Protobase-SCE1-LLaMa-70B-GGUF/resolve/main/Protobase-SCE1-LLaMa-70B.Q4_K_M.gguf) \| Q4_K_M \| 42.6 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Protobase-SCE1-LLaMa-70B-GGUF/resolve/main/Protobase-SCE1-LLaMa-70B.Q5_K_S.gguf) \| Q5_K_S \| 48.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Protobase-SCE1-LLaMa-70B-GGUF/resolve/main/Protobase-SCE1-LLaMa-70B.Q5_K_M.gguf) \| Q5_K_M \| 50.0 \| \| \| [PART 1](https://huggingface.co/mradermacher/Protobase-SCE1-LLaMa-70B-GGUF/resolve/main/Protobase-SCE1-LLaMa-70B.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Protobase-SCE1-LLaMa-70B-GGUF/resolve/main/Protobase-SCE1-LLaMa-70B.Q6_K.gguf.part2of2) \| Q6_K \| 58.0 \| very good quality \| \| [PART 1](https://huggingface.co/mradermacher/Protobase-SCE1-LLaMa-70B-GGUF/resolve/main/Protobase-SCE1-LLaMa-70B.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Protobase-SCE1-LLaMa-70B-GGUF/resolve/main/Protobase-SCE1-LLaMa-70B.Q8_0.gguf.part2of2) \| Q8_0 \| 75.1 \| 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. 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/MedicalEDI-14b-EDI-Reasoning-Final-II-GGUF	mradermacher	2025-05-03T17:29:16Z	0	0	transformers	[ "transformers", "gguf", "en", "base_model:Shaleen123/MedicalEDI-14b-EDI-Reasoning-Final-II", "base_model:quantized:Shaleen123/MedicalEDI-14b-EDI-Reasoning-Final-II", "endpoints_compatible", "region:us", "conversational" ]	null	2025-05-03T10:15:07Z	--- base_model: Shaleen123/MedicalEDI-14b-EDI-Reasoning-Final-II language: - en library_name: transformers quantized_by: mradermacher tags: [] --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/Shaleen123/MedicalEDI-14b-EDI-Reasoning-Final-II <!-- provided-files --> weighted/imatrix quants are available at https://huggingface.co/mradermacher/MedicalEDI-14b-EDI-Reasoning-Final-II-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/MedicalEDI-14b-EDI-Reasoning-Final-II-GGUF/resolve/main/MedicalEDI-14b-EDI-Reasoning-Final-II.Q2_K.gguf) \| Q2_K \| 5.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/MedicalEDI-14b-EDI-Reasoning-Final-II-GGUF/resolve/main/MedicalEDI-14b-EDI-Reasoning-Final-II.Q3_K_S.gguf) \| Q3_K_S \| 6.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/MedicalEDI-14b-EDI-Reasoning-Final-II-GGUF/resolve/main/MedicalEDI-14b-EDI-Reasoning-Final-II.Q3_K_M.gguf) \| Q3_K_M \| 7.4 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/MedicalEDI-14b-EDI-Reasoning-Final-II-GGUF/resolve/main/MedicalEDI-14b-EDI-Reasoning-Final-II.Q3_K_L.gguf) \| Q3_K_L \| 8.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/MedicalEDI-14b-EDI-Reasoning-Final-II-GGUF/resolve/main/MedicalEDI-14b-EDI-Reasoning-Final-II.IQ4_XS.gguf) \| IQ4_XS \| 8.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/MedicalEDI-14b-EDI-Reasoning-Final-II-GGUF/resolve/main/MedicalEDI-14b-EDI-Reasoning-Final-II.Q4_K_S.gguf) \| Q4_K_S \| 8.7 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/MedicalEDI-14b-EDI-Reasoning-Final-II-GGUF/resolve/main/MedicalEDI-14b-EDI-Reasoning-Final-II.Q4_K_M.gguf) \| Q4_K_M \| 9.1 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/MedicalEDI-14b-EDI-Reasoning-Final-II-GGUF/resolve/main/MedicalEDI-14b-EDI-Reasoning-Final-II.Q5_K_S.gguf) \| Q5_K_S \| 10.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/MedicalEDI-14b-EDI-Reasoning-Final-II-GGUF/resolve/main/MedicalEDI-14b-EDI-Reasoning-Final-II.Q5_K_M.gguf) \| Q5_K_M \| 10.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/MedicalEDI-14b-EDI-Reasoning-Final-II-GGUF/resolve/main/MedicalEDI-14b-EDI-Reasoning-Final-II.Q6_K.gguf) \| Q6_K \| 12.2 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/MedicalEDI-14b-EDI-Reasoning-Final-II-GGUF/resolve/main/MedicalEDI-14b-EDI-Reasoning-Final-II.Q8_0.gguf) \| Q8_0 \| 15.8 \| 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 -->
fats-fme/76a35825-b79e-4b60-87d3-4641e40e4228	fats-fme	2025-05-03T17:26:52Z	0	0	peft	[ "peft", "safetensors", "llama", "axolotl", "generated_from_trainer", "base_model:unsloth/SmolLM2-360M", "base_model:adapter:unsloth/SmolLM2-360M", "license:apache-2.0", "region:us" ]	null	2025-05-03T17:19:46Z	--- library_name: peft license: apache-2.0 base_model: unsloth/SmolLM2-360M tags: - axolotl - generated_from_trainer model-index: - name: 76a35825-b79e-4b60-87d3-4641e40e4228 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 adapter: lora base_model: unsloth/SmolLM2-360M bf16: true chat_template: llama3 dataset_prepared_path: null datasets: - data_files: - 9c46256a8024748c_train_data.json ds_type: json format: custom path: /workspace/input_data/9c46256a8024748c_train_data.json type: field_input: text field_instruction: instruction field_output: full_instruction format: '{instruction} {input}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null device_map: auto early_stopping_patience: 3 eval_max_new_tokens: 128 eval_steps: 100 eval_table_size: null evals_per_epoch: null flash_attention: true fp16: false fsdp: null fsdp_config: null gradient_accumulation_steps: 4 gradient_checkpointing: true group_by_length: false hub_model_id: fats-fme/76a35825-b79e-4b60-87d3-4641e40e4228 hub_repo: null hub_strategy: checkpoint hub_token: null learning_rate: 5.0e-05 load_in_4bit: false load_in_8bit: false local_rank: null logging_steps: 10 lora_alpha: 128 lora_dropout: 0.1 lora_fan_in_fan_out: null lora_model_dir: null lora_r: 64 lora_target_linear: true lr_scheduler: cosine max_memory: 0: 130GB max_steps: 200 micro_batch_size: 2 mlflow_experiment_name: /tmp/9c46256a8024748c_train_data.json model_type: AutoModelForCausalLM num_epochs: 10 optimizer: adamw_bnb_8bit output_dir: miner_id_24 pad_to_sequence_len: true resume_from_checkpoint: null s2_attention: null sample_packing: false save_steps: 100 saves_per_epoch: null sequence_len: 2048 strict: false tf32: true tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: 62e2631f-f12b-4415-81fd-ab3b8d09115c wandb_project: Gradients-On-Demand wandb_run: your_name wandb_runid: 62e2631f-f12b-4415-81fd-ab3b8d09115c warmup_steps: 200 weight_decay: 0.01 xformers_attention: null ``` </details><br> # 76a35825-b79e-4b60-87d3-4641e40e4228 This model is a fine-tuned version of [unsloth/SmolLM2-360M](https://huggingface.co/unsloth/SmolLM2-360M) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.0252 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 200 - training_steps: 200 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| No log \| 0.0002 \| 1 \| 1.3539 \| \| 0.2766 \| 0.0214 \| 100 \| 0.2475 \| \| 0.0211 \| 0.0427 \| 200 \| 0.0252 \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
fedovtt/0dc128ba-76b6-4492-a16d-598bf33e3901	fedovtt	2025-05-03T17:25:19Z	0	0	peft	[ "peft", "safetensors", "llama", "axolotl", "generated_from_trainer", "base_model:unsloth/SmolLM2-360M", "base_model:adapter:unsloth/SmolLM2-360M", "license:apache-2.0", "8-bit", "bitsandbytes", "region:us" ]	null	2025-05-03T17:19:39Z	--- library_name: peft license: apache-2.0 base_model: unsloth/SmolLM2-360M tags: - axolotl - generated_from_trainer model-index: - name: 0dc128ba-76b6-4492-a16d-598bf33e3901 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) <details><summary>See axolotl config</summary> axolotl version: `0.4.1` ```yaml absolute_data_files: false adapter: lora base_model: unsloth/SmolLM2-360M bf16: true chat_template: llama3 dataset_prepared_path: /workspace/axolotl datasets: - data_files: - 9c46256a8024748c_train_data.json ds_type: json format: custom path: /workspace/input_data/9c46256a8024748c_train_data.json type: field_input: text field_instruction: instruction field_output: full_instruction format: '{instruction} {input}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null early_stopping_patience: null eval_max_new_tokens: 128 eval_table_size: null evals_per_epoch: 1 flash_attention: true fp16: null fsdp: null fsdp_config: null gradient_accumulation_steps: 1 gradient_checkpointing: true gradient_clipping: 0.55 group_by_length: false hub_model_id: fedovtt/0dc128ba-76b6-4492-a16d-598bf33e3901 hub_repo: null hub_strategy: end hub_token: null learning_rate: 3.0e-06 load_in_4bit: true load_in_8bit: true local_rank: null logging_steps: 1 lora_alpha: 64 lora_dropout: 0.05 lora_fan_in_fan_out: null lora_model_dir: null lora_r: 32 lora_target_linear: true lr_scheduler: cosine max_steps: 150 micro_batch_size: 10 mixed_precision: bf16 mlflow_experiment_name: /tmp/9c46256a8024748c_train_data.json model_type: AutoModelForCausalLM num_epochs: 1 optimizer: adamw_bnb_8bit output_dir: miner_id_24 pad_to_sequence_len: true resume_from_checkpoint: null s2_attention: null sample_packing: false saves_per_epoch: 1 sequence_len: 2048 strict: false tf32: false tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: 62e2631f-f12b-4415-81fd-ab3b8d09115c wandb_project: s56-28 wandb_run: your_name wandb_runid: 62e2631f-f12b-4415-81fd-ab3b8d09115c warmup_steps: 5 weight_decay: 0.01 xformers_attention: true ``` </details><br> # 0dc128ba-76b6-4492-a16d-598bf33e3901 This model is a fine-tuned version of [unsloth/SmolLM2-360M](https://huggingface.co/unsloth/SmolLM2-360M) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.2183 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 3e-06 - train_batch_size: 10 - eval_batch_size: 10 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 5 - training_steps: 150 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| 0.9199 \| 0.0400 \| 150 \| 1.2183 \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
phililp-arnold/17967b4f-3241-42f4-bb16-d8895524f65f	phililp-arnold	2025-05-03T17:25:00Z	0	0	peft	[ "peft", "generated_from_trainer", "base_model:UCLA-AGI/Gemma-2-9B-It-SPPO-Iter2", "base_model:adapter:UCLA-AGI/Gemma-2-9B-It-SPPO-Iter2", "region:us" ]	null	2025-05-03T17:24:31Z	--- library_name: peft tags: - generated_from_trainer base_model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter2 model-index: - name: phililp-arnold/17967b4f-3241-42f4-bb16-d8895524f65f 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. --> # phililp-arnold/17967b4f-3241-42f4-bb16-d8895524f65f This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.1765 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ### Framework versions - PEFT 0.13.2 - Transformers 4.46.3 - Pytorch 2.5.1+cu124 - Datasets 3.1.0 - Tokenizers 0.20.3
mlx-community/Qwen3-16B-A3B-bf16	mlx-community	2025-05-03T17:22:25Z	0	0	mlx	[ "mlx", "safetensors", "qwen3_moe", "text-generation", "conversational", "base_model:kalomaze/Qwen3-16B-A3B", "base_model:finetune:kalomaze/Qwen3-16B-A3B", "license:apache-2.0", "region:us" ]	text-generation	2025-05-03T17:11:54Z	--- license: apache-2.0 base_model: kalomaze/Qwen3-16B-A3B tags: - mlx pipeline_tag: text-generation library_name: mlx --- # mlx-community/Qwen3-16B-A3B-bf16 This model [mlx-community/Qwen3-16B-A3B-bf16](https://huggingface.co/mlx-community/Qwen3-16B-A3B-bf16) was converted to MLX format from [kalomaze/Qwen3-16B-A3B](https://huggingface.co/kalomaze/Qwen3-16B-A3B) using mlx-lm version 0.24.0. ## Use with mlx ```bash pip install mlx-lm ``` ```python from mlx_lm import load, generate model, tokenizer = load("mlx-community/Qwen3-16B-A3B-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) ```
dimasik1987/aef1db10-27c8-43af-8b53-76962e458a20	dimasik1987	2025-05-03T17:22:03Z	0	0	peft	[ "peft", "safetensors", "llama", "axolotl", "generated_from_trainer", "base_model:unsloth/SmolLM2-360M", "base_model:adapter:unsloth/SmolLM2-360M", "license:apache-2.0", "4-bit", "bitsandbytes", "region:us" ]	null	2025-05-03T17:19:46Z	--- library_name: peft license: apache-2.0 base_model: unsloth/SmolLM2-360M tags: - axolotl - generated_from_trainer model-index: - name: aef1db10-27c8-43af-8b53-76962e458a20 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) <details><summary>See axolotl config</summary> axolotl version: `0.4.1` ```yaml absolute_data_files: false adapter: lora base_model: unsloth/SmolLM2-360M bf16: true chat_template: llama3 dataset_prepared_path: /workspace/axolotl datasets: - data_files: - 9c46256a8024748c_train_data.json ds_type: json format: custom path: /workspace/input_data/9c46256a8024748c_train_data.json type: field_input: text field_instruction: instruction field_output: full_instruction format: '{instruction} {input}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null early_stopping_patience: null eval_max_new_tokens: 128 eval_table_size: null evals_per_epoch: 1 flash_attention: true fp16: null fsdp: null fsdp_config: null gradient_accumulation_steps: 1 gradient_checkpointing: true gradient_clipping: 0.55 group_by_length: false hub_model_id: dimasik1987/aef1db10-27c8-43af-8b53-76962e458a20 hub_repo: null hub_strategy: end hub_token: null learning_rate: 1.0e-06 load_in_4bit: true load_in_8bit: false local_rank: null logging_steps: 1 lora_alpha: 64 lora_dropout: 0.05 lora_fan_in_fan_out: null lora_model_dir: null lora_r: 32 lora_target_linear: true lr_scheduler: cosine max_steps: 150 micro_batch_size: 10 mixed_precision: bf16 mlflow_experiment_name: /tmp/9c46256a8024748c_train_data.json model_type: AutoModelForCausalLM num_epochs: 1 optimizer: adamw_bnb_8bit output_dir: miner_id_24 pad_to_sequence_len: true resume_from_checkpoint: null s2_attention: null sample_packing: false saves_per_epoch: 1 sequence_len: 2048 strict: false tf32: false tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: 62e2631f-f12b-4415-81fd-ab3b8d09115c wandb_project: s56-7 wandb_run: your_name wandb_runid: 62e2631f-f12b-4415-81fd-ab3b8d09115c warmup_steps: 5 weight_decay: 0.01 xformers_attention: true ``` </details><br> # aef1db10-27c8-43af-8b53-76962e458a20 This model is a fine-tuned version of [unsloth/SmolLM2-360M](https://huggingface.co/unsloth/SmolLM2-360M) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.4316 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-06 - train_batch_size: 10 - eval_batch_size: 10 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 5 - training_steps: 150 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| 1.0966 \| 0.0400 \| 150 \| 1.4316 \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
SvetKochnev/wan2.1_1.3b_female_anatomy	SvetKochnev	2025-05-03T17:15:55Z	0	0	null	[ "license:apache-2.0", "region:us" ]	null	2025-05-03T17:10:28Z	--- license: apache-2.0 --- this lora helps create slightly more correct anatomical features for any woman. this is probably one of the first lora trains for a 1.3b model. so there is no place to look for settings or better variations yet. this train is hastily done and may not give a perfect result. nevertheless, it improves generations. I will continue experimenting with this. I will be glad to get any feedback, especially on your generation results. If you wanna help, you can send me a link to any cloud file with short videos or photos on this topic. or maybe something else, it's you turn. Trigger word is ntm.
Triangle104/Llama-3.1-Nemotron-Nano-8B-v1-abliterated-Q5_K_M-GGUF	Triangle104	2025-05-03T17:14:48Z	0	0	transformers	[ "transformers", "gguf", "nvidia", "llama-3", "pytorch", "abliterated", "uncensored", "llama-cpp", "gguf-my-repo", "text-generation", "en", "base_model:huihui-ai/Llama-3.1-Nemotron-Nano-8B-v1-abliterated", "base_model:quantized:huihui-ai/Llama-3.1-Nemotron-Nano-8B-v1-abliterated", "license:other", "endpoints_compatible", "region:us" ]	text-generation	2025-05-03T17:14:21Z	--- base_model: huihui-ai/Llama-3.1-Nemotron-Nano-8B-v1-abliterated language: - en library_name: transformers license: other license_name: nvidia-open-model-license license_link: https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/ pipeline_tag: text-generation tags: - nvidia - llama-3 - pytorch - abliterated - uncensored - llama-cpp - gguf-my-repo --- # Triangle104/Llama-3.1-Nemotron-Nano-8B-v1-abliterated-Q5_K_M-GGUF This model was converted to GGUF format from [`huihui-ai/Llama-3.1-Nemotron-Nano-8B-v1-abliterated`](https://huggingface.co/huihui-ai/Llama-3.1-Nemotron-Nano-8B-v1-abliterated) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/huihui-ai/Llama-3.1-Nemotron-Nano-8B-v1-abliterated) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama-cli --hf-repo Triangle104/Llama-3.1-Nemotron-Nano-8B-v1-abliterated-Q5_K_M-GGUF --hf-file llama-3.1-nemotron-nano-8b-v1-abliterated-q5_k_m.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo Triangle104/Llama-3.1-Nemotron-Nano-8B-v1-abliterated-Q5_K_M-GGUF --hf-file llama-3.1-nemotron-nano-8b-v1-abliterated-q5_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 Triangle104/Llama-3.1-Nemotron-Nano-8B-v1-abliterated-Q5_K_M-GGUF --hf-file llama-3.1-nemotron-nano-8b-v1-abliterated-q5_k_m.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo Triangle104/Llama-3.1-Nemotron-Nano-8B-v1-abliterated-Q5_K_M-GGUF --hf-file llama-3.1-nemotron-nano-8b-v1-abliterated-q5_k_m.gguf -c 2048 ```
lamdo/bert-base-uncased-phrase-60kaddedphrasesfroms2orc-mlm-150000steps	lamdo	2025-05-03T17:09:53Z	0	0	transformers	[ "transformers", "safetensors", "bert", "fill-mask", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	2025-05-03T17:09:31Z	--- 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]
PeterL123/GLM-Z1-9B-0414	PeterL123	2025-05-03T17:05:05Z	0	0	transformers	[ "transformers", "safetensors", "glm4", "text-generation", "conversational", "zh", "en", "arxiv:2406.12793", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2025-05-03T17:04:11Z	--- license: mit language: - zh - en pipeline_tag: text-generation library_name: transformers --- # GLM-4-Z1-9B-0414 ## Introduction The GLM family welcomes a new generation of open-source models, the GLM-4-32B-0414 series, featuring 32 billion parameters. Its performance is comparable to OpenAI's GPT series and DeepSeek's V3/R1 series, and it supports very user-friendly local deployment features. GLM-4-32B-Base-0414 was pre-trained on 15T of high-quality data, including a large amount of reasoning-type synthetic data, laying the foundation for subsequent reinforcement learning extensions. In the post-training stage, in addition to human preference alignment for dialogue scenarios, we also enhanced the model's performance in instruction following, engineering code, and function calling using techniques such as rejection sampling and reinforcement learning, strengthening the atomic capabilities required for agent tasks. GLM-4-32B-0414 achieves good results in areas such as engineering code, Artifact generation, function calling, search-based Q&A, and report generation. Some benchmarks even rival larger models like GPT-4o and DeepSeek-V3-0324 (671B). GLM-Z1-32B-0414 is a reasoning model with deep thinking capabilities. This was developed based on GLM-4-32B-0414 through cold start and extended reinforcement learning, as well as further training of the model on tasks involving mathematics, code, and logic. Compared to the base model, GLM-Z1-32B-0414 significantly improves mathematical abilities and the capability to solve complex tasks. During the training process, we also introduced general reinforcement learning based on pairwise ranking feedback, further enhancing the model's general capabilities. GLM-Z1-Rumination-32B-0414 is a deep reasoning model with rumination capabilities (benchmarked against OpenAI's Deep Research). Unlike typical deep thinking models, the rumination model employs longer periods of deep thought to solve more open-ended and complex problems (e.g., writing a comparative analysis of AI development in two cities and their future development plans). The rumination model integrates search tools during its deep thinking process to handle complex tasks and is trained by utilizing multiple rule-based rewards to guide and extend end-to-end reinforcement learning. Z1-Rumination shows significant improvements in research-style writing and complex retrieval tasks. Finally, GLM-Z1-9B-0414 is a surprise. We employed the aforementioned series of techniques to train a 9B small-sized model that maintains the open-source tradition. Despite its smaller scale, GLM-Z1-9B-0414 still exhibits excellent capabilities in mathematical reasoning and general tasks. Its overall performance is already at a leading level among open-source models of the same size. Especially in resource-constrained scenarios, this model achieves an excellent balance between efficiency and effectiveness, providing a powerful option for users seeking lightweight deployment. ## Performance <p align="center"> <img width="100%" src="https://raw.githubusercontent.com/THUDM/GLM-4/refs/heads/main/resources/Bench-Z1-32B.png"> </p> <p align="center"> <img width="100%" src="https://raw.githubusercontent.com/THUDM/GLM-4/refs/heads/main/resources/Bench-Z1-9B.png"> </p> ## Model Usage Guidelines ### I. Sampling Parameters \| Parameter \| Recommended Value \| Description \| \| ------------ \| ----------------- \| -------------------------------------------- \| \| temperature \| 0.6 \| Balances creativity and stability \| \| top_p \| 0.95 \| Cumulative probability threshold for sampling\| \| top_k \| 40 \| Filters out rare tokens while maintaining diversity \| \| max_new_tokens \| 30000 \| Leaves enough tokens for thinking \| ### II. Enforced Thinking - Add \<think\>\n to the first line: Ensures the model thinks before responding - When using `chat_template.jinja`, the prompt is automatically injected to enforce this behavior ### III. Dialogue History Trimming - Retain only the final user-visible reply. Hidden thinking content should not be saved to history to reduce interference—this is already implemented in `chat_template.jinja` ### IV. Handling Long Contexts (YaRN) - When input length exceeds 8,192 tokens, consider enabling YaRN (Rope Scaling) - In supported frameworks, add the following snippet to `config.json`: ```json "rope_scaling": { "type": "yarn", "factor": 4.0, "original_max_position_embeddings": 32768 } ``` - Static YaRN applies uniformly to all text. It may slightly degrade performance on short texts, so enable as needed. ## Inference Code Make Sure Using `transforemrs>=4.51.3`. ```python from transformers import AutoModelForCausalLM, AutoTokenizer MODEL_PATH = "THUDM/GLM-4-Z1-9B-0414" tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH) model = AutoModelForCausalLM.from_pretrained(MODEL_PATH, device_map="auto") message = [{"role": "user", "content": "Let a, b be positive real numbers such that ab = a + b + 3. Determine the range of possible values for a + b."}] inputs = tokenizer.apply_chat_template( message, return_tensors="pt", add_generation_prompt=True, return_dict=True, ).to(model.device) generate_kwargs = { "input_ids": inputs["input_ids"], "attention_mask": inputs["attention_mask"], "max_new_tokens": 4096, "do_sample": False, } out = model.generate(**generate_kwargs) print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)) ``` ## Citations If you find our work useful, please consider citing the following paper. ``` @misc{glm2024chatglm, title={ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools}, author={Team GLM and Aohan Zeng and Bin Xu and Bowen Wang and Chenhui Zhang and Da Yin and Diego Rojas and Guanyu Feng and Hanlin Zhao and Hanyu Lai and Hao Yu and Hongning Wang and Jiadai Sun and Jiajie Zhang and Jiale Cheng and Jiayi Gui and Jie Tang and Jing Zhang and Juanzi Li and Lei Zhao and Lindong Wu and Lucen Zhong and Mingdao Liu and Minlie Huang and Peng Zhang and Qinkai Zheng and Rui Lu and Shuaiqi Duan and Shudan Zhang and Shulin Cao and Shuxun Yang and Weng Lam Tam and Wenyi Zhao and Xiao Liu and Xiao Xia and Xiaohan Zhang and Xiaotao Gu and Xin Lv and Xinghan Liu and Xinyi Liu and Xinyue Yang and Xixuan Song and Xunkai Zhang and Yifan An and Yifan Xu and Yilin Niu and Yuantao Yang and Yueyan Li and Yushi Bai and Yuxiao Dong and Zehan Qi and Zhaoyu Wang and Zhen Yang and Zhengxiao Du and Zhenyu Hou and Zihan Wang}, year={2024}, eprint={2406.12793}, archivePrefix={arXiv}, primaryClass={id='cs.CL' full_name='Computation and Language' is_active=True alt_name='cmp-lg' in_archive='cs' is_general=False description='Covers natural language processing. Roughly includes material in ACM Subject Class I.2.7. Note that work on artificial languages (programming languages, logics, formal systems) that does not explicitly address natural-language issues broadly construed (natural-language processing, computational linguistics, speech, text retrieval, etc.) is not appropriate for this area.'} } ```
TOMFORD79/Fly50	TOMFORD79	2025-05-03T16:58:32Z	0	0	null	[ "safetensors", "any-to-any", "omega", "omegalabs", "bittensor", "agi", "license:mit", "region:us" ]	any-to-any	2025-05-03T16:48:43Z	--- license: mit tags: - any-to-any - omega - omegalabs - bittensor - agi --- This is an Any-to-Any model checkpoint for the OMEGA Labs x Bittensor Any-to-Any subnet. Check out the [git repo](https://github.com/omegalabsinc/omegalabs-anytoany-bittensor) and find OMEGA on X: [@omegalabsai](https://x.com/omegalabsai).
Kasougi/gpt-neo-1.3B-sft-se-4000-lora	Kasougi	2025-05-03T16:56:54Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-05-03T16:56:47Z	--- 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]
Aaquib/gemma-3-1b-sft-alpaca	Aaquib	2025-05-03T16:56:52Z	0	0	transformers	[ "transformers", "safetensors", "gemma3_text", "text-generation", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2025-05-03T16:50:27Z	--- library_name: transformers tags: [] --- # Model Card for Model ID SFT'd version of google/gemma-3-1b-pt. Training performed solely on yahma/alpaca-cleaned. No further learning was performed. ## Model Details Hyperparameters to replicate: - lr=1e-5 - num_epochs=1 - train_batch_size=40 - test_batch_size=32 - max_seq_len=256 ### Model Description - Finetuned from model: [google/gemma-3-1b-pt]
earcherc/nsfw1_full	earcherc	2025-05-03T16:56:24Z	0	0	diffusers	[ "diffusers", "text-to-image", "lora", "template:diffusion-lora", "base_model:black-forest-labs/FLUX.1-dev", "base_model:adapter:black-forest-labs/FLUX.1-dev", "region:us" ]	text-to-image	2025-05-03T16:51:51Z	--- tags: - text-to-image - lora - diffusers - template:diffusion-lora widget: - text: '-' output: url: images/ComfyICU_00001_.png base_model: black-forest-labs/FLUX.1-dev instance_prompt: null --- # nsfw1_full <Gallery /> ## Download model Weights for this model are available in Safetensors format. [Download](/earcherc/nsfw1_full/tree/main) them in the Files & versions tab.
mlfoundations-dev/no_pipeline_science_3k	mlfoundations-dev	2025-05-03T16:55:21Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "llama-factory", "full", "generated_from_trainer", "conversational", "base_model:Qwen/Qwen2.5-7B-Instruct", "base_model:finetune:Qwen/Qwen2.5-7B-Instruct", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-05-03T15:42:08Z	--- library_name: transformers license: apache-2.0 base_model: Qwen/Qwen2.5-7B-Instruct tags: - llama-factory - full - generated_from_trainer model-index: - name: no_pipeline_science_3k 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. --> # no_pipeline_science_3k This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/no_pipeline_science_3k 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: 2e-05 - train_batch_size: 1 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - num_devices: 16 - gradient_accumulation_steps: 6 - total_train_batch_size: 96 - total_eval_batch_size: 128 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 7.0 ### Training results ### Framework versions - Transformers 4.46.1 - Pytorch 2.5.1 - Datasets 3.1.0 - Tokenizers 0.20.3
gpham/ModernBERT-base-finetuned-arxiv	gpham	2025-05-03T16:53:17Z	0	0	transformers	[ "transformers", "safetensors", "modernbert", "text-classification", "generated_from_trainer", "base_model:answerdotai/ModernBERT-base", "base_model:finetune:answerdotai/ModernBERT-base", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2025-05-03T08:50:32Z	--- library_name: transformers license: apache-2.0 base_model: answerdotai/ModernBERT-base tags: - generated_from_trainer metrics: - accuracy - f1 model-index: - name: ModernBERT-base-finetuned-arxiv 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. --> # ModernBERT-base-finetuned-arxiv This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.6179 - Accuracy: 0.8501 - F1: 0.8474 ## 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: 32 - 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: linear - num_epochs: 10 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| F1 \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:------:\| \| 0.4682 \| 1.0 \| 1863 \| 0.4426 \| 0.8462 \| 0.8393 \| \| 0.2739 \| 2.0 \| 3726 \| 0.4828 \| 0.8538 \| 0.8464 \| \| 0.1399 \| 3.0 \| 5589 \| 0.7007 \| 0.8421 \| 0.8399 \| \| 0.0533 \| 4.0 \| 7452 \| 0.9504 \| 0.8472 \| 0.8441 \| \| 0.007 \| 5.0 \| 9315 \| 1.3058 \| 0.8392 \| 0.8371 \| \| 0.0097 \| 6.0 \| 11178 \| 1.4712 \| 0.8411 \| 0.8395 \| \| 0.0044 \| 7.0 \| 13041 \| 1.5351 \| 0.8421 \| 0.8436 \| \| 0.0004 \| 8.0 \| 14904 \| 1.5931 \| 0.8499 \| 0.8459 \| \| 0.0 \| 9.0 \| 16767 \| 1.6332 \| 0.8470 \| 0.8442 \| \| 0.0 \| 10.0 \| 18630 \| 1.6179 \| 0.8501 \| 0.8474 \| ### Framework versions - Transformers 4.48.3 - Pytorch 2.7.0+cu126 - Datasets 3.5.1 - Tokenizers 0.21.1
adi0308/output	adi0308	2025-05-03T16:52:00Z	0	0	peft	[ "peft", "safetensors", "generated_from_trainer", "base_model:meta-llama/Llama-3.2-1B", "base_model:adapter:meta-llama/Llama-3.2-1B", "license:llama3.2", "region:us" ]	null	2025-05-03T16:51:09Z	--- library_name: peft license: llama3.2 base_model: meta-llama/Llama-3.2-1B tags: - generated_from_trainer model-index: - name: output 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. --> # output This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 4 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 8 - 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: 5 - mixed_precision_training: Native AMP ### Training results ### Framework versions - PEFT 0.15.2 - Transformers 4.51.3 - Pytorch 2.7.0+cu118 - Datasets 3.5.1 - Tokenizers 0.21.1
malik-nazeba-minahil-malik-Viral-Video/18-EXCLUSIVE.malik.nazeba.minahil.malik.viral.video.Leaks.original	malik-nazeba-minahil-malik-Viral-Video	2025-05-03T16:51:28Z	0	0	null	[ "region:us" ]	null	2025-05-03T16:43:07Z	<animated-image data-catalyst=""><a href="https://tinyurl.com/4du2u735?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> Dive into the phenomenon of Malik Nazeba Minahil Malik's viral video. This comprehensive analysis examines its origins, the role of social media platforms, public reactions, and the ethical dimensions of viral content. Understand the dynamics of virality and how it shapes our digital interactions.
ASethi04/meta-llama-Llama-3.1-8B-opc-sft-first-lora-4-0.001	ASethi04	2025-05-03T16:49:34Z	0	0	transformers	[ "transformers", "safetensors", "generated_from_trainer", "trl", "sft", "base_model:meta-llama/Llama-3.1-8B", "base_model:finetune:meta-llama/Llama-3.1-8B", "endpoints_compatible", "region:us" ]	null	2025-05-03T15:41:11Z	--- base_model: meta-llama/Llama-3.1-8B library_name: transformers model_name: meta-llama-Llama-3.1-8B-opc-sft-first-lora-4-0.001 tags: - generated_from_trainer - trl - sft licence: license --- # Model Card for meta-llama-Llama-3.1-8B-opc-sft-first-lora-4-0.001 This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B). 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="ASethi04/meta-llama-Llama-3.1-8B-opc-sft-first-lora-4-0.001", 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/torchql-org/huggingface/runs/iomjqekl) This model was trained with SFT. ### Framework versions - TRL: 0.16.1 - Transformers: 4.51.2 - Pytorch: 2.6.0 - Datasets: 3.5.0 - Tokenizers: 0.21.1 ## Citations Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
mradermacher/MT1-Gen13-gemma-2-9B-i1-GGUF	mradermacher	2025-05-03T16:42:19Z	0	0	transformers	[ "transformers", "gguf", "mergekit", "merge", "en", "base_model:zelk12/MT1-Gen13-gemma-2-9B", "base_model:quantized:zelk12/MT1-Gen13-gemma-2-9B", "endpoints_compatible", "region:us", "imatrix", "conversational" ]	null	2025-05-03T10:32:34Z	--- base_model: zelk12/MT1-Gen13-gemma-2-9B language: - en library_name: transformers quantized_by: mradermacher tags: - mergekit - merge --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> weighted/imatrix quants of https://huggingface.co/zelk12/MT1-Gen13-gemma-2-9B <!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/MT1-Gen13-gemma-2-9B-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/MT1-Gen13-gemma-2-9B-i1-GGUF/resolve/main/MT1-Gen13-gemma-2-9B.i1-IQ1_S.gguf) \| i1-IQ1_S \| 2.5 \| for the desperate \| \| [GGUF](https://huggingface.co/mradermacher/MT1-Gen13-gemma-2-9B-i1-GGUF/resolve/main/MT1-Gen13-gemma-2-9B.i1-IQ1_M.gguf) \| i1-IQ1_M \| 2.6 \| mostly desperate \| \| [GGUF](https://huggingface.co/mradermacher/MT1-Gen13-gemma-2-9B-i1-GGUF/resolve/main/MT1-Gen13-gemma-2-9B.i1-IQ2_XXS.gguf) \| i1-IQ2_XXS \| 2.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/MT1-Gen13-gemma-2-9B-i1-GGUF/resolve/main/MT1-Gen13-gemma-2-9B.i1-IQ2_XS.gguf) \| i1-IQ2_XS \| 3.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/MT1-Gen13-gemma-2-9B-i1-GGUF/resolve/main/MT1-Gen13-gemma-2-9B.i1-IQ2_S.gguf) \| i1-IQ2_S \| 3.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/MT1-Gen13-gemma-2-9B-i1-GGUF/resolve/main/MT1-Gen13-gemma-2-9B.i1-IQ2_M.gguf) \| i1-IQ2_M \| 3.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/MT1-Gen13-gemma-2-9B-i1-GGUF/resolve/main/MT1-Gen13-gemma-2-9B.i1-Q2_K_S.gguf) \| i1-Q2_K_S \| 3.7 \| very low quality \| \| [GGUF](https://huggingface.co/mradermacher/MT1-Gen13-gemma-2-9B-i1-GGUF/resolve/main/MT1-Gen13-gemma-2-9B.i1-IQ3_XXS.gguf) \| i1-IQ3_XXS \| 3.9 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/MT1-Gen13-gemma-2-9B-i1-GGUF/resolve/main/MT1-Gen13-gemma-2-9B.i1-Q2_K.gguf) \| i1-Q2_K \| 3.9 \| IQ3_XXS probably better \| \| [GGUF](https://huggingface.co/mradermacher/MT1-Gen13-gemma-2-9B-i1-GGUF/resolve/main/MT1-Gen13-gemma-2-9B.i1-IQ3_XS.gguf) \| i1-IQ3_XS \| 4.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/MT1-Gen13-gemma-2-9B-i1-GGUF/resolve/main/MT1-Gen13-gemma-2-9B.i1-IQ3_S.gguf) \| i1-IQ3_S \| 4.4 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/MT1-Gen13-gemma-2-9B-i1-GGUF/resolve/main/MT1-Gen13-gemma-2-9B.i1-Q3_K_S.gguf) \| i1-Q3_K_S \| 4.4 \| IQ3_XS probably better \| \| [GGUF](https://huggingface.co/mradermacher/MT1-Gen13-gemma-2-9B-i1-GGUF/resolve/main/MT1-Gen13-gemma-2-9B.i1-IQ3_M.gguf) \| i1-IQ3_M \| 4.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/MT1-Gen13-gemma-2-9B-i1-GGUF/resolve/main/MT1-Gen13-gemma-2-9B.i1-Q3_K_M.gguf) \| i1-Q3_K_M \| 4.9 \| IQ3_S probably better \| \| [GGUF](https://huggingface.co/mradermacher/MT1-Gen13-gemma-2-9B-i1-GGUF/resolve/main/MT1-Gen13-gemma-2-9B.i1-Q3_K_L.gguf) \| i1-Q3_K_L \| 5.2 \| IQ3_M probably better \| \| [GGUF](https://huggingface.co/mradermacher/MT1-Gen13-gemma-2-9B-i1-GGUF/resolve/main/MT1-Gen13-gemma-2-9B.i1-IQ4_XS.gguf) \| i1-IQ4_XS \| 5.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/MT1-Gen13-gemma-2-9B-i1-GGUF/resolve/main/MT1-Gen13-gemma-2-9B.i1-IQ4_NL.gguf) \| i1-IQ4_NL \| 5.5 \| prefer IQ4_XS \| \| [GGUF](https://huggingface.co/mradermacher/MT1-Gen13-gemma-2-9B-i1-GGUF/resolve/main/MT1-Gen13-gemma-2-9B.i1-Q4_0.gguf) \| i1-Q4_0 \| 5.6 \| fast, low quality \| \| [GGUF](https://huggingface.co/mradermacher/MT1-Gen13-gemma-2-9B-i1-GGUF/resolve/main/MT1-Gen13-gemma-2-9B.i1-Q4_K_S.gguf) \| i1-Q4_K_S \| 5.6 \| optimal size/speed/quality \| \| [GGUF](https://huggingface.co/mradermacher/MT1-Gen13-gemma-2-9B-i1-GGUF/resolve/main/MT1-Gen13-gemma-2-9B.i1-Q4_K_M.gguf) \| i1-Q4_K_M \| 5.9 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/MT1-Gen13-gemma-2-9B-i1-GGUF/resolve/main/MT1-Gen13-gemma-2-9B.i1-Q4_1.gguf) \| i1-Q4_1 \| 6.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/MT1-Gen13-gemma-2-9B-i1-GGUF/resolve/main/MT1-Gen13-gemma-2-9B.i1-Q5_K_S.gguf) \| i1-Q5_K_S \| 6.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/MT1-Gen13-gemma-2-9B-i1-GGUF/resolve/main/MT1-Gen13-gemma-2-9B.i1-Q5_K_M.gguf) \| i1-Q5_K_M \| 6.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/MT1-Gen13-gemma-2-9B-i1-GGUF/resolve/main/MT1-Gen13-gemma-2-9B.i1-Q6_K.gguf) \| i1-Q6_K \| 7.7 \| 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 -->
LarryAIDraw/shun-nvwls-v1	LarryAIDraw	2025-05-03T16:42:04Z	0	0	null	[ "license:creativeml-openrail-m", "region:us" ]	null	2025-05-03T16:11:25Z	--- license: creativeml-openrail-m --- https://civitai.com/models/155063/sunohara-shun-blue-archive-lora
strangerzonehf/Flux-Midjourney-Studio-LoRA	strangerzonehf	2025-05-03T16:42:00Z	0	0	diffusers	[ "diffusers", "text-to-image", "lora", "template:diffusion-lora", "base_model:black-forest-labs/FLUX.1-dev", "base_model:adapter:black-forest-labs/FLUX.1-dev", "license:other", "region:us" ]	text-to-image	2025-05-03T10:41:07Z	--- tags: - text-to-image - lora - diffusers - template:diffusion-lora widget: - text: 'mj x1, a close-up shot of a man with short platinum blonde hair and olive skin, dressed in a black crew neck t-shirt. He has a silver nose ring and a small teardrop tattoo under his left eye. The studio lighting casts a soft shadow under his chin, giving dimension to his jawline. The background is a gradient from pale blue to white.' output: url: images/1111.png - text: 'mj x1, A close-up of a young man with dark brown eyes and wavy black hair. He is wearing a dark green trench coat with a high collar and a light brown scarf around his neck. The backdrop is a cloudy gray, adding an air of mystery to the scene.' output: url: images/2222.png - text: 'mj x1, a close-up shot of a young mans face is adorned with a beige baseball cap adorned with red lettering. The mans eyes are a piercing blue, and he is wearing a pink t-shirt. His hair is dark brown, adding a touch of texture to his face. The backdrop is a vibrant shade of blue, creating a stark contrast to the mans head and the cap.' output: url: images/3333.png - text: 'mj x1, cinematic shot, a medium-sized man stands in the foreground of the frame. He is dressed in a black jacket, black pants, and a black backpack. His hair is short and dark, and hes looking off to the side. The backdrop is a stark white wall, and the ceiling is adorned with metal pipes and beams. To the left of the man, a man with dark hair and glasses is looking off into the distance.' output: url: images/4444.png base_model: black-forest-labs/FLUX.1-dev instance_prompt: mj x1 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 --- ![Untitled design.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/NnZUucHNucyMi9KnhW6aI.png) # Flux-Midjourney-Studio-LoRA <Gallery /> # Model description for Flux-Midjourney-Studio-LoRA Image Processing Parameters \| Parameter \| Value \| Parameter \| Value \| \|---------------------------\|--------\|---------------------------\|--------\| \| LR Scheduler \| constant \| Noise Offset \| 0.03 \| \| Optimizer \| AdamW \| Multires Noise Discount \| 0.1 \| \| Network Dim \| 64 \| Multires Noise Iterations \| 10 \| \| Network Alpha \| 32 \| Repeat & Steps \| 30 & 3900 \| \| Epoch \| 25 \| Save Every N Epochs \| 1 [90] \| Labeling: florence2-en(natural language & English) Total Images Used for Training : 27 [ Midjourney Generated Synthetic Image ] ## Best Dimensions & Inference \| Dimensions \| Aspect Ratio \| Recommendation \| \|-----------------\|------------------\|---------------------------\| \| 1280 x 832 \| 3:2 \| Best \| \| 1024 x 1024 \| 1:1 \| Default \| ### Inference Range - Recommended Inference Steps: 30-35 ## Setting Up ```python import torch from pipelines import DiffusionPipeline base_model = "black-forest-labs/FLUX.1-dev" pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16) lora_repo = "strangerzonehf/Flux-Midjourney-Studio-LoRA" trigger_word = "mj x1" pipe.load_lora_weights(lora_repo) device = torch.device("cuda") pipe.to(device) ``` ## Trigger words You should use `mj x1` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/strangerzonehf/Flux-Midjourney-Studio-LoRA/tree/main) them in the Files & versions tab.
LarryAIDraw/bluearchive-shun-ponyxl-lora-nochekaiser	LarryAIDraw	2025-05-03T16:41:53Z	0	0	null	[ "license:creativeml-openrail-m", "region:us" ]	null	2025-05-03T16:11:02Z	--- license: creativeml-openrail-m --- https://civitai.com/models/801542/shun-blue-archive-commission
LarryAIDraw/ChamEyjafjallaPonyXL	LarryAIDraw	2025-05-03T16:41:19Z	0	0	null	[ "license:creativeml-openrail-m", "region:us" ]	null	2025-05-03T16:09:49Z	--- license: creativeml-openrail-m --- https://civitai.com/models/426460/eyjafjalla-3-outfits-or-arknights-or-pony-xl
Triangle104/QWQ-32B-Dawnwhisper-Q4_K_S-GGUF	Triangle104	2025-05-03T16:41:12Z	0	0	transformers	[ "transformers", "gguf", "mergekit", "merge", "llama-cpp", "gguf-my-repo", "base_model:DoppelReflEx/QWQ-32B-Dawnwhisper", "base_model:quantized:DoppelReflEx/QWQ-32B-Dawnwhisper", "endpoints_compatible", "region:us", "conversational" ]	null	2025-05-03T16:39:44Z	--- base_model: DoppelReflEx/QWQ-32B-Dawnwhisper library_name: transformers tags: - mergekit - merge - llama-cpp - gguf-my-repo --- # Triangle104/QWQ-32B-Dawnwhisper-Q4_K_S-GGUF This model was converted to GGUF format from [`DoppelReflEx/QWQ-32B-Dawnwhisper`](https://huggingface.co/DoppelReflEx/QWQ-32B-Dawnwhisper) 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/DoppelReflEx/QWQ-32B-Dawnwhisper) 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 Triangle104/QWQ-32B-Dawnwhisper-Q4_K_S-GGUF --hf-file qwq-32b-dawnwhisper-q4_k_s.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo Triangle104/QWQ-32B-Dawnwhisper-Q4_K_S-GGUF --hf-file qwq-32b-dawnwhisper-q4_k_s.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 Triangle104/QWQ-32B-Dawnwhisper-Q4_K_S-GGUF --hf-file qwq-32b-dawnwhisper-q4_k_s.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo Triangle104/QWQ-32B-Dawnwhisper-Q4_K_S-GGUF --hf-file qwq-32b-dawnwhisper-q4_k_s.gguf -c 2048 ```
LarryAIDraw/touhou_kudamaki_ponyXL	LarryAIDraw	2025-05-03T16:41:08Z	0	0	null	[ "license:creativeml-openrail-m", "region:us" ]	null	2025-05-03T16:09:16Z	--- license: creativeml-openrail-m --- https://civitai.com/models/371928/ponyv6-xl-tsukasa-kudamaki-or-touhou
mradermacher/Alkahest-V9.3-LLaMa-70B-GGUF	mradermacher	2025-05-03T16:39:58Z	191	0	transformers	[ "transformers", "gguf", "mergekit", "merge", "en", "base_model:TareksTesting/Alkahest-V9.3-LLaMa-70B", "base_model:quantized:TareksTesting/Alkahest-V9.3-LLaMa-70B", "endpoints_compatible", "region:us", "conversational" ]	null	2025-04-23T03:36:57Z	--- base_model: TareksTesting/Alkahest-V9.3-LLaMa-70B language: - en library_name: transformers quantized_by: mradermacher tags: - mergekit - merge --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/TareksTesting/Alkahest-V9.3-LLaMa-70B <!-- provided-files --> weighted/imatrix quants are available at https://huggingface.co/mradermacher/Alkahest-V9.3-LLaMa-70B-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/Alkahest-V9.3-LLaMa-70B-GGUF/resolve/main/Alkahest-V9.3-LLaMa-70B.Q2_K.gguf) \| Q2_K \| 26.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/Alkahest-V9.3-LLaMa-70B-GGUF/resolve/main/Alkahest-V9.3-LLaMa-70B.Q3_K_S.gguf) \| Q3_K_S \| 31.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/Alkahest-V9.3-LLaMa-70B-GGUF/resolve/main/Alkahest-V9.3-LLaMa-70B.Q3_K_M.gguf) \| Q3_K_M \| 34.4 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/Alkahest-V9.3-LLaMa-70B-GGUF/resolve/main/Alkahest-V9.3-LLaMa-70B.Q3_K_L.gguf) \| Q3_K_L \| 37.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/Alkahest-V9.3-LLaMa-70B-GGUF/resolve/main/Alkahest-V9.3-LLaMa-70B.IQ4_XS.gguf) \| IQ4_XS \| 38.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Alkahest-V9.3-LLaMa-70B-GGUF/resolve/main/Alkahest-V9.3-LLaMa-70B.Q4_K_S.gguf) \| Q4_K_S \| 40.4 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Alkahest-V9.3-LLaMa-70B-GGUF/resolve/main/Alkahest-V9.3-LLaMa-70B.Q4_K_M.gguf) \| Q4_K_M \| 42.6 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Alkahest-V9.3-LLaMa-70B-GGUF/resolve/main/Alkahest-V9.3-LLaMa-70B.Q5_K_S.gguf) \| Q5_K_S \| 48.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Alkahest-V9.3-LLaMa-70B-GGUF/resolve/main/Alkahest-V9.3-LLaMa-70B.Q5_K_M.gguf) \| Q5_K_M \| 50.1 \| \| \| [PART 1](https://huggingface.co/mradermacher/Alkahest-V9.3-LLaMa-70B-GGUF/resolve/main/Alkahest-V9.3-LLaMa-70B.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Alkahest-V9.3-LLaMa-70B-GGUF/resolve/main/Alkahest-V9.3-LLaMa-70B.Q6_K.gguf.part2of2) \| Q6_K \| 58.0 \| very good quality \| \| [PART 1](https://huggingface.co/mradermacher/Alkahest-V9.3-LLaMa-70B-GGUF/resolve/main/Alkahest-V9.3-LLaMa-70B.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Alkahest-V9.3-LLaMa-70B-GGUF/resolve/main/Alkahest-V9.3-LLaMa-70B.Q8_0.gguf.part2of2) \| Q8_0 \| 75.1 \| 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. 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 -->
pictgencustomer/coneyisland2-14_425	pictgencustomer	2025-05-03T16:38:24Z	0	0	diffusers	[ "diffusers", "flux", "lora", "replicate", "text-to-image", "en", "base_model:black-forest-labs/FLUX.1-dev", "base_model:adapter:black-forest-labs/FLUX.1-dev", "license:other", "region:us" ]	text-to-image	2025-05-03T16:38:21Z	--- 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: coneyisland2-14_michaeluffer_6 --- # Coneyisland2 14_425 <Gallery /> Trained on Replicate using: https://replicate.com/ostris/flux-dev-lora-trainer/train ## Trigger words You should use `coneyisland2-14_michaeluffer_6` to trigger the image generation. ## 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('pictgencustomer/coneyisland2-14_425', weight_name='lora.safetensors') image = pipeline('your prompt').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)
mradermacher/MedicalEDI-14b-EDI-Reasoning-test-GGUF	mradermacher	2025-05-03T16:36:55Z	0	0	transformers	[ "transformers", "gguf", "en", "base_model:Shaleen123/MedicalEDI-14b-EDI-Reasoning-test", "base_model:quantized:Shaleen123/MedicalEDI-14b-EDI-Reasoning-test", "endpoints_compatible", "region:us", "conversational" ]	null	2025-05-03T11:39:24Z	--- base_model: Shaleen123/MedicalEDI-14b-EDI-Reasoning-test language: - en library_name: transformers quantized_by: mradermacher tags: [] --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/Shaleen123/MedicalEDI-14b-EDI-Reasoning-test <!-- provided-files --> weighted/imatrix quants are available at https://huggingface.co/mradermacher/MedicalEDI-14b-EDI-Reasoning-test-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/MedicalEDI-14b-EDI-Reasoning-test-GGUF/resolve/main/MedicalEDI-14b-EDI-Reasoning-test.Q2_K.gguf) \| Q2_K \| 5.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/MedicalEDI-14b-EDI-Reasoning-test-GGUF/resolve/main/MedicalEDI-14b-EDI-Reasoning-test.Q3_K_S.gguf) \| Q3_K_S \| 6.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/MedicalEDI-14b-EDI-Reasoning-test-GGUF/resolve/main/MedicalEDI-14b-EDI-Reasoning-test.Q3_K_M.gguf) \| Q3_K_M \| 7.4 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/MedicalEDI-14b-EDI-Reasoning-test-GGUF/resolve/main/MedicalEDI-14b-EDI-Reasoning-test.Q3_K_L.gguf) \| Q3_K_L \| 8.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/MedicalEDI-14b-EDI-Reasoning-test-GGUF/resolve/main/MedicalEDI-14b-EDI-Reasoning-test.IQ4_XS.gguf) \| IQ4_XS \| 8.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/MedicalEDI-14b-EDI-Reasoning-test-GGUF/resolve/main/MedicalEDI-14b-EDI-Reasoning-test.Q4_K_S.gguf) \| Q4_K_S \| 8.7 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/MedicalEDI-14b-EDI-Reasoning-test-GGUF/resolve/main/MedicalEDI-14b-EDI-Reasoning-test.Q4_K_M.gguf) \| Q4_K_M \| 9.1 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/MedicalEDI-14b-EDI-Reasoning-test-GGUF/resolve/main/MedicalEDI-14b-EDI-Reasoning-test.Q5_K_S.gguf) \| Q5_K_S \| 10.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/MedicalEDI-14b-EDI-Reasoning-test-GGUF/resolve/main/MedicalEDI-14b-EDI-Reasoning-test.Q5_K_M.gguf) \| Q5_K_M \| 10.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/MedicalEDI-14b-EDI-Reasoning-test-GGUF/resolve/main/MedicalEDI-14b-EDI-Reasoning-test.Q6_K.gguf) \| Q6_K \| 12.2 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/MedicalEDI-14b-EDI-Reasoning-test-GGUF/resolve/main/MedicalEDI-14b-EDI-Reasoning-test.Q8_0.gguf) \| Q8_0 \| 15.8 \| 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 -->
zhangchen1991/search-r1_step500	zhangchen1991	2025-05-03T16:33:56Z	0	0	null	[ "safetensors", "license:apache-2.0", "region:us" ]	null	2025-05-03T14:47:54Z	--- license: apache-2.0 ---
Photchara/stock-sentiment-analysis_V1	Photchara	2025-05-03T16:31:04Z	0	0	transformers	[ "transformers", "safetensors", "bert", "text-classification", "arxiv:1910.09700", "base_model:ProsusAI/finbert", "base_model:finetune:ProsusAI/finbert", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2025-05-03T16:03:33Z	--- library_name: transformers base_model: - ProsusAI/finbert pipeline_tag: text-classification --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> MODEL_NAME = "ProsusAI/finbert" MAX_LENGTH = 512 BATCH_SIZE = 16 EPOCHS = 3 LEARNING_RATE = 2e-5 'eval_loss': 0.3165287375450134, 'eval_accuracy': 0.8761904761904762, 'eval_f1': 0.8807109047522269 ## 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]
Membersuger/Euro_20	Membersuger	2025-05-03T16:29:58Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-05-03T16:20:00Z	--- 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]
mlfoundations-dev/no_pipeline_code_1k	mlfoundations-dev	2025-05-03T16:28:24Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "llama-factory", "full", "generated_from_trainer", "conversational", "base_model:Qwen/Qwen2.5-7B-Instruct", "base_model:finetune:Qwen/Qwen2.5-7B-Instruct", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-05-03T15:41:49Z	--- library_name: transformers license: apache-2.0 base_model: Qwen/Qwen2.5-7B-Instruct tags: - llama-factory - full - generated_from_trainer model-index: - name: no_pipeline_code_1k 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. --> # no_pipeline_code_1k This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/no_pipeline_code_1k 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: 2e-05 - train_batch_size: 1 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - num_devices: 16 - gradient_accumulation_steps: 6 - total_train_batch_size: 96 - total_eval_batch_size: 128 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 7.0 ### Training results ### Framework versions - Transformers 4.46.1 - Pytorch 2.5.1 - Datasets 3.1.0 - Tokenizers 0.20.3
Triangle104/QWQ-32B-Dawnwhisper-Q3_K_L-GGUF	Triangle104	2025-05-03T16:26:04Z	0	0	transformers	[ "transformers", "gguf", "mergekit", "merge", "llama-cpp", "gguf-my-repo", "base_model:DoppelReflEx/QWQ-32B-Dawnwhisper", "base_model:quantized:DoppelReflEx/QWQ-32B-Dawnwhisper", "endpoints_compatible", "region:us", "conversational" ]	null	2025-05-03T16:24:48Z	--- base_model: DoppelReflEx/QWQ-32B-Dawnwhisper library_name: transformers tags: - mergekit - merge - llama-cpp - gguf-my-repo --- # Triangle104/QWQ-32B-Dawnwhisper-Q3_K_L-GGUF This model was converted to GGUF format from [`DoppelReflEx/QWQ-32B-Dawnwhisper`](https://huggingface.co/DoppelReflEx/QWQ-32B-Dawnwhisper) 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/DoppelReflEx/QWQ-32B-Dawnwhisper) 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 Triangle104/QWQ-32B-Dawnwhisper-Q3_K_L-GGUF --hf-file qwq-32b-dawnwhisper-q3_k_l.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo Triangle104/QWQ-32B-Dawnwhisper-Q3_K_L-GGUF --hf-file qwq-32b-dawnwhisper-q3_k_l.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 Triangle104/QWQ-32B-Dawnwhisper-Q3_K_L-GGUF --hf-file qwq-32b-dawnwhisper-q3_k_l.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo Triangle104/QWQ-32B-Dawnwhisper-Q3_K_L-GGUF --hf-file qwq-32b-dawnwhisper-q3_k_l.gguf -c 2048 ```
atamilagba/hug	atamilagba	2025-05-03T16:25:34Z	0	0	null	[ "license:apache-2.0", "region:us" ]	null	2025-05-03T16:25:32Z	--- license: apache-2.0 ---
abbas7733/2024	abbas7733	2025-05-03T16:24:04Z	0	0	null	[ "license:apache-2.0", "region:us" ]	null	2025-05-03T16:24:04Z	--- license: apache-2.0 ---
jahyungu/Llama-3.1-8B-Instruct_MetaMathQA-40K_9	jahyungu	2025-05-03T16:19:32Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "generated_from_trainer", "conversational", "base_model:meta-llama/Llama-3.1-8B-Instruct", "base_model:finetune:meta-llama/Llama-3.1-8B-Instruct", "license:llama3.1", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-05-03T14:11:35Z	--- library_name: transformers license: llama3.1 base_model: meta-llama/Llama-3.1-8B-Instruct tags: - generated_from_trainer model-index: - name: Llama-3.1-8B-Instruct_MetaMathQA-40K_9 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # Llama-3.1-8B-Instruct_MetaMathQA-40K_9 This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-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: 2e-05 - train_batch_size: 1 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 16 - total_train_batch_size: 16 - 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_steps: 200 - num_epochs: 3 ### Training results ### Framework versions - Transformers 4.50.0 - Pytorch 2.6.0+cu124 - Datasets 3.4.1 - Tokenizers 0.21.0
ai-and-society/llama-3.1-8B-Instruct-SQINT8	ai-and-society	2025-05-03T16:19:19Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "8-bit", "compressed-tensors", "region:us" ]	text-generation	2025-05-03T16:16:24Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
Hachipo/OpenCoder-8B-Base-PIFT-jaen_1000_2	Hachipo	2025-05-03T16:19:17Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "trl", "sft", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-05-03T16:15:11Z	--- library_name: transformers tags: - trl - sft --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
dgambettaphd/M_llm2_gen7_WXS_doc1000_synt64_lr1e-04_acm_SYNLAST	dgambettaphd	2025-05-03T16:15:02Z	0	0	transformers	[ "transformers", "safetensors", "unsloth", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-05-03T16:14:49Z	--- library_name: transformers tags: - unsloth --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
ASethi04/meta-llama-Llama-3.1-8B-pubmedqa-first-lora-4-0.0001	ASethi04	2025-05-03T16:13:01Z	0	0	transformers	[ "transformers", "safetensors", "generated_from_trainer", "trl", "sft", "base_model:meta-llama/Llama-3.1-8B", "base_model:finetune:meta-llama/Llama-3.1-8B", "endpoints_compatible", "region:us" ]	null	2025-05-03T14:29:38Z	--- base_model: meta-llama/Llama-3.1-8B library_name: transformers model_name: meta-llama-Llama-3.1-8B-pubmedqa-first-lora-4-0.0001 tags: - generated_from_trainer - trl - sft licence: license --- # Model Card for meta-llama-Llama-3.1-8B-pubmedqa-first-lora-4-0.0001 This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B). 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="ASethi04/meta-llama-Llama-3.1-8B-pubmedqa-first-lora-4-0.0001", 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/torchql-org/huggingface/runs/tzwksac9) This model was trained with SFT. ### Framework versions - TRL: 0.16.1 - Transformers: 4.51.2 - Pytorch: 2.6.0 - Datasets: 3.5.0 - Tokenizers: 0.21.1 ## Citations Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
HuangXinBa/marian-finetuned-kde4-en-to-zh_CN	HuangXinBa	2025-05-03T16:09:30Z	0	0	null	[ "tensorboard", "safetensors", "marian", "translation", "generated_from_trainer", "dataset:kde4", "base_model:zhijian12345/marian-finetuned-kde4-en-to-zh_CN", "base_model:finetune:zhijian12345/marian-finetuned-kde4-en-to-zh_CN", "license:apache-2.0", "region:us" ]	translation	2025-05-02T18:20:35Z	--- license: apache-2.0 base_model: zhijian12345/marian-finetuned-kde4-en-to-zh_CN tags: - translation - generated_from_trainer datasets: - kde4 model-index: - name: marian-finetuned-kde4-en-to-zh_CN 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. --> # marian-finetuned-kde4-en-to-zh_CN This model is a fine-tuned version of [zhijian12345/marian-finetuned-kde4-en-to-zh_CN](https://huggingface.co/zhijian12345/marian-finetuned-kde4-en-to-zh_CN) on the kde4 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: 2e-05 - train_batch_size: 32 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 - mixed_precision_training: Native AMP ### Framework versions - Transformers 4.38.2 - Pytorch 2.2.1+cu121 - Datasets 3.5.0 - Tokenizers 0.15.2
endlesseve/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-fast_whistling_badger	endlesseve	2025-05-03T16:04:17Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "generated_from_trainer", "rl-swarm", "grpo", "gensyn", "I am fast whistling badger", "trl", "conversational", "arxiv:2402.03300", "base_model:Gensyn/Qwen2.5-0.5B-Instruct", "base_model:finetune:Gensyn/Qwen2.5-0.5B-Instruct", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-04-30T08:19:59Z	--- base_model: Gensyn/Qwen2.5-0.5B-Instruct library_name: transformers model_name: Qwen2.5-0.5B-Instruct-Gensyn-Swarm-fast_whistling_badger tags: - generated_from_trainer - rl-swarm - grpo - gensyn - I am fast whistling badger - trl licence: license --- # Model Card for Qwen2.5-0.5B-Instruct-Gensyn-Swarm-fast_whistling_badger This model is a fine-tuned version of [Gensyn/Qwen2.5-0.5B-Instruct](https://huggingface.co/Gensyn/Qwen2.5-0.5B-Instruct). It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="endlesseve/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-fast_whistling_badger", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300). ### Framework versions - TRL: 0.15.2 - Transformers: 4.51.3 - Pytorch: 2.7.0 - Datasets: 3.5.1 - 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}} } ```
Poseidon/Foundation-Sec-8B-Q8_0-GGUF	Poseidon	2025-05-03T16:03:52Z	0	0	transformers	[ "transformers", "gguf", "security", "llama-cpp", "gguf-my-repo", "text-generation", "en", "base_model:fdtn-ai/Foundation-Sec-8B", "base_model:quantized:fdtn-ai/Foundation-Sec-8B", "license:apache-2.0", "endpoints_compatible", "region:us" ]	text-generation	2025-05-03T16:01:29Z	--- base_model: fdtn-ai/Foundation-Sec-8B language: - en library_name: transformers license: apache-2.0 pipeline_tag: text-generation tags: - security - llama-cpp - gguf-my-repo --- # Poseidon/Foundation-Sec-8B-Q8_0-GGUF This model was converted to GGUF format from [`fdtn-ai/Foundation-Sec-8B`](https://huggingface.co/fdtn-ai/Foundation-Sec-8B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/fdtn-ai/Foundation-Sec-8B) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama-cli --hf-repo Poseidon/Foundation-Sec-8B-Q8_0-GGUF --hf-file foundation-sec-8b-q8_0.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo Poseidon/Foundation-Sec-8B-Q8_0-GGUF --hf-file foundation-sec-8b-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 Poseidon/Foundation-Sec-8B-Q8_0-GGUF --hf-file foundation-sec-8b-q8_0.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo Poseidon/Foundation-Sec-8B-Q8_0-GGUF --hf-file foundation-sec-8b-q8_0.gguf -c 2048 ```
Anchor-Chitra-Tripathi-Viral-Video/wATCH.Anchor-Chitra-Tripathi-Viral-Anchor-Chitra-Tripathi.original	Anchor-Chitra-Tripathi-Viral-Video	2025-05-03T16:03:07Z	0	0	null	[ "region:us" ]	null	2025-05-03T15:57:29Z	[🔴 ➤►𝐂𝐥𝐢𝐤 𝐇𝐞𝐫𝐞 𝐭𝐨👉👉 (𝐅𝐮𝐥𝐥 𝐯𝐢𝐝𝐞𝐨 𝐋𝐢𝐧𝐤 )](https://videohere.top/?Anchor-Chitra-Tripathi) [►✅ 𝘾𝙇𝙄𝘾𝙆 𝙃𝙀𝙍𝙀 ==►► 𝙁𝙪𝙡𝙡 𝙑𝙞𝙙𝙚𝙤❤️❤️⬇️⬇️](https://videohere.top/?Anchor-Chitra-Tripathi) [<img alt="fsd" src="http://i.postimg.cc/qvPp49Sm/ythngythg.gif">](https://videohere.top/?Anchor-Chitra-Tripathi)
X-iZhang/libra-v1.0-7b	X-iZhang	2025-05-03T16:00:29Z	117	2	transformers	[ "transformers", "pytorch", "safetensors", "libra", "text-generation", "RRG", "Radiology Report Generation", "Chest X-ray", "Multimodal Large Language Models", "image-text-to-text", "arxiv:2411.19378", "base_model:epfl-llm/meditron-7b", "base_model:merge:epfl-llm/meditron-7b", "base_model:microsoft/rad-dino", "base_model:merge:microsoft/rad-dino", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-text-to-text	2024-12-20T16:02:33Z	--- license: apache-2.0 pipeline_tag: image-text-to-text base_model: - epfl-llm/meditron-7b - microsoft/rad-dino base_model_relation: merge library_name: transformers tags: - RRG - Radiology Report Generation - Chest X-ray - Multimodal Large Language Models --- <br> # Libra Model Card Version: Libra-v1.0 ## Overview Libra is a multimodal Large Language Model (LLM) specialized in radiology report generation, particularly chest X-ray interpretations. It can produce detailed _Findings_ sections with temporal comparisons (e.g., comparing a current chest X-ray with prior ones). Libra integrates the following key components: - RAD-DINO: A vision encoder pre-trained on medical imaging datasets for robust feature extraction from chest X-rays. - Meditron-7B: A 7B-parameter large language model (based on Llama-2) specialized in medical text generation. - Temporal Alignment Connector (TAC): A custom adapter that fuses features across multiple time points to enable temporal comparisons. This model card provides an overview of Libra’s architecture, training methodology, limitations, and recommended usage guidelines. --- ## Paper and Resources For more detailed information regarding Libra’s methodology, theoretical foundation, and performance benchmarks, please refer to the following resources: - Project Website: [Libra v1.0](https://x-izhang.github.io/Libra_v1.0/) - Paper: [arXiv:2411.19378](https://arxiv.org/abs/2411.19378) - Code Repository: [X-iZhang/Libra (GitHub)](https://github.com/X-iZhang/Libra) Or check out our Spaces demo! [![Open in Spaces](https://huggingface.co/datasets/huggingface/badges/resolve/main/open-in-hf-spaces-md-dark.svg)](https://huggingface.co/spaces/X-iZhang/Libra) --- ## Training Strategy Libra is trained in a two-stage process: 1. Temporal Feature Alignment - Trains TAC to effectively fuse and align features from different time points (current and previous chest X-rays). - Focuses on capturing notable changes (e.g., appearance or progression of opacities, devices, and lines). 2. Fine-Tuning for Radiology Report Generation - The language model part is fine-tuned on a large dataset of paired chest X-ray images and radiology reports. - Emphasizes the generation of the _Findings_ section, especially incorporating temporal descriptors. --- ## Intended Use Libra is primarily designed to assist clinical practitioners, researchers, and medical students in generating chest X-ray reports. Key applications include: - Clinical Decision Support: Providing draft findings that can be refined by a radiologist. - Educational Tool: Demonstrating example interpretations and temporal changes for training radiology residents. - Research: Facilitating studies on automated report generation and temporal feature learning in medical imaging. > Important: Outputs should be reviewed by qualified radiologists or medical professionals before final clinical decisions are made. --- ## Limitations and Recommendations 1. Data Bias: The model’s performance may be less reliable for underrepresented demographics or rare pathologies. 2. Clinical Oversight: Always involve a medical professional to verify the results—Libra is not a substitute for professional judgment. 3. Temporal Inaccuracies: Despite TAC’s focus on temporal alignment, subtle or uncommon changes may go unrecognized. 4. Generalization: Libra’s performance on chest X-ray types or conditions not seen during training may be limited. --- ## Ethical Considerations - Patient Privacy: Ensure the data is fully de-identified and compliant with HIPAA/GDPR (or relevant privacy regulations). - Responsible Use: Deploy Libra’s outputs carefully; they are not guaranteed to be error-free. - Accountability: Users and organizations must assume responsibility for verifying clinical accuracy and safety. --- ## How to Cite ✒️ If you use Libra in academic or research contexts, please cite: ```bibtex @misc{zhang2025libraleveragingtemporalimages, title={Libra: Leveraging Temporal Images for Biomedical Radiology Analysis}, author={Xi Zhang and Zaiqiao Meng and Jake Lever and Edmond S. L. Ho}, year={2025}, eprint={2411.19378}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2411.19378}, } ``` ## Disclaimer: This tool is for research and educational purposes only. It is not FDA-approved or CE-marked for clinical use. Users should consult qualified healthcare professionals for any clinical decisions.
Romain-XV/8f3edba3-d660-4f05-bc84-9befdb0b2deb	Romain-XV	2025-05-03T15:59:04Z	0	0	transformers	[ "transformers", "pytorch", "tensorboard", "safetensors", "mistral", "text-generation", "generated_from_trainer", "axolotl", "dpo", "trl", "unsloth", "conversational", "arxiv:2305.18290", "base_model:unsloth/Phi-3-mini-4k-instruct", "base_model:finetune:unsloth/Phi-3-mini-4k-instruct", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-05-03T15:09:42Z	--- base_model: unsloth/Phi-3-mini-4k-instruct library_name: transformers model_name: 8f3edba3-d660-4f05-bc84-9befdb0b2deb tags: - generated_from_trainer - axolotl - dpo - trl - unsloth licence: license --- # Model Card for 8f3edba3-d660-4f05-bc84-9befdb0b2deb This model is a fine-tuned version of [unsloth/Phi-3-mini-4k-instruct](https://huggingface.co/unsloth/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="Romain-XV/8f3edba3-d660-4f05-bc84-9befdb0b2deb", 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/romain_fnc-xventures/Gradients-On-Demand/runs/8bqxlpyz) This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290). ### Framework versions - TRL: 0.12.0.dev0 - Transformers: 4.46.0 - Pytorch: 2.5.0+cu124 - Datasets: 3.0.1 - Tokenizers: 0.20.1 ## Citations Cite DPO as: ```bibtex @inproceedings{rafailov2023direct, title = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}}, author = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn}, year = 2023, booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023}, url = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html}, editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine}, } ``` Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
bihungba1101/json_segmenting_sft_warmup_qwen	bihungba1101	2025-05-03T15:57:22Z	0	0	transformers	[ "transformers", "safetensors", "text-generation-inference", "unsloth", "qwen3", "trl", "en", "base_model:unsloth/Qwen3-4B", "base_model:finetune:unsloth/Qwen3-4B", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-05-03T15:57:03Z	--- base_model: unsloth/Qwen3-4B tags: - text-generation-inference - transformers - unsloth - qwen3 - trl license: apache-2.0 language: - en --- # Uploaded model - Developed by: bihungba1101 - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B 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)
TOMFORD79/Fly44	TOMFORD79	2025-05-03T15:56:35Z	0	0	null	[ "safetensors", "any-to-any", "omega", "omegalabs", "bittensor", "agi", "license:mit", "region:us" ]	any-to-any	2025-05-03T15:15:34Z	--- license: mit tags: - any-to-any - omega - omegalabs - bittensor - agi --- This is an Any-to-Any model checkpoint for the OMEGA Labs x Bittensor Any-to-Any subnet. Check out the [git repo](https://github.com/omegalabsinc/omegalabs-anytoany-bittensor) and find OMEGA on X: [@omegalabsai](https://x.com/omegalabsai).
TOMFORD79/Fly43	TOMFORD79	2025-05-03T15:56:22Z	0	0	null	[ "safetensors", "any-to-any", "omega", "omegalabs", "bittensor", "agi", "license:mit", "region:us" ]	any-to-any	2025-05-03T15:15:28Z	--- license: mit tags: - any-to-any - omega - omegalabs - bittensor - agi --- This is an Any-to-Any model checkpoint for the OMEGA Labs x Bittensor Any-to-Any subnet. Check out the [git repo](https://github.com/omegalabsinc/omegalabs-anytoany-bittensor) and find OMEGA on X: [@omegalabsai](https://x.com/omegalabsai).
TOMFORD79/Fly42	TOMFORD79	2025-05-03T15:56:21Z	0	0	null	[ "safetensors", "any-to-any", "omega", "omegalabs", "bittensor", "agi", "license:mit", "region:us" ]	any-to-any	2025-05-03T15:15:22Z	--- license: mit tags: - any-to-any - omega - omegalabs - bittensor - agi --- This is an Any-to-Any model checkpoint for the OMEGA Labs x Bittensor Any-to-Any subnet. Check out the [git repo](https://github.com/omegalabsinc/omegalabs-anytoany-bittensor) and find OMEGA on X: [@omegalabsai](https://x.com/omegalabsai).
piotr-ai/polanka_4b_v0.1_qwen3_250502_gguf	piotr-ai	2025-05-03T15:52:25Z	0	0	null	[ "gguf", "language", "text-generation", "pl", "en", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	text-generation	2025-05-02T07:35:13Z	--- license: apache-2.0 language: - pl - en pipeline_tag: text-generation tags: - language --- temp: 0.6 top-k: 40 example 1: ``` <\|im_start\|>system Poniżej znajduje się dialog, w którym użytkownik rozmawia z asystentką o imieniu Polanka. Polanka jest pomocna i uprzejma.<\|im_end\|> > co to jest psychologia? Psychologia to dziedzina nauki, która zajmuje się badaniem ludzkiego umysłu, zachowań, emocji, motywacji i procesów poznawczych. Psychologia bada, jak ludzie myślą, uczą się, doświadczają i reagują na swoje otoczenie. Jest to dyscyplina, która łączy w sobie elementy z różnych dziedzin, takich jak: 1. Biologia: Badanie biologicznych podstaw ludzkiego zachowania i poznawania. 2. Neurobiologia: Badanie struktury i funkcji mózgu oraz ich wpływu na zachowanie. 3. Psychologia behawioralna: Badanie zachowań poprzez obserwację i interwencję. 4. Psychologia poznawcza: Badanie procesów myślowych, takich jak pamięć, uczenie się, rozwiązywanie problemów. 5. Psychologia społeczna: Badanie wpływu społeczeństwa na zachowanie i postrzeganie siebie. 6. Psychologia rozwoju: Badanie rozwoju osobowości, poznawczego i emocjonalnego w czasie. 7. Psychologia kliniczna: Badanie i leczenie zaburzeń psychicznych oraz problemów emocjonalnych. 8. Psychologia kulturowa: Badanie wpływu kultury na ludzkie zachowanie i postrzeganie siebie. 9. Psychologia etyczna: Badanie etycznych aspektów psychologii i jej zastosowań. Psychologia ma kluczowe znaczenie w rozumieniu ludzkich zachowań, motywacji i emocji, a także w rozwoju terapii i leczenia zaburzeń psychicznych. ``` example 2: wyjaśnij krok po kroku ile to jest 12 / 3 + 2 ``` Oczywiście, wyjaśnię ci to krok po kroku: 1. Rozpocznijmy od pierwszego działania: 12 / 3. - 12 podzielone przez 3 to 4, ponieważ 3 razy 4 to 12. 2. Teraz dodajemy do wyniku 4 liczbę 2. - 4 + 2 = 6. Więc 12 / 3 + 2 = 6. ``` example 3: napisz funkcję w pythonie, która mnoży liczbę razy 3 ```` Oto funkcja w Pythonie, która mnoży liczbę przez 3: ```python def mnozenie_liczby_3(liczba): """ Funkcja mnoży liczbę przez 3. Parameters: liczba (int): Liczba, którą chcemy pomnożyć. Returns: int: Wynik mnożenia liczby przez 3. """ wynik = liczba * 3 return wynik # Przykłady użycia: liczba = 5 wynik = mnozenie_liczby_3(liczba) print(f"Wynik mnożenia 5 przez 3 to: {wynik}") liczba = 0 wynik = mnozenie_liczby_3(liczba) print(f"Wynik mnożenia 0 przez 3 to: {wynik}") ``` W tej funkcji `liczba` to parametr, który otrzymujemy podczas wywołania funkcji. Funkcja zwraca wynik mnożenia liczby przez 3. W przykładach użycia możemy przypisać do zmiennej liczbę, którą chcemy pomnożyć, a następnie wywołać funkcję z tą liczbą jako argumentem i wyświetlić wynik. ```` example 4: przetłumacz na język angielski: "Liczba mórz na Oceanie Spokojnym w stosunku do jego powierzchni nie jest zbyt wielka, ponieważ większa część jego obszaru to po prostu ocean, bez miejsc, w których można wyznaczyć morza." ``` "Number of seas in the Pacific Ocean relative to its surface isn't too great because the majority of its area is just ocean, with no places where you can identify a sea." ```
ping98k/qwen3-8b-recall-writer-1e	ping98k	2025-05-03T15:47:27Z	0	0	transformers	[ "transformers", "safetensors", "text-generation-inference", "unsloth", "qwen3", "trl", "en", "base_model:unsloth/Qwen3-8B-unsloth-bnb-4bit", "base_model:finetune:unsloth/Qwen3-8B-unsloth-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-05-03T15:46:51Z	--- base_model: unsloth/Qwen3-8B-unsloth-bnb-4bit tags: - text-generation-inference - transformers - unsloth - qwen3 - trl license: apache-2.0 language: - en --- # Uploaded model - Developed by: ping98k - 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)
franzexplorer77/Qwen2.5-1.5B-Instruct-Gensyn-Swarm-alert_armored_trout	franzexplorer77	2025-05-03T15:43:02Z	0	0	transformers	[ "transformers", "safetensors", "generated_from_trainer", "rl-swarm", "grpo", "gensyn", "I am alert armored trout", "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	2025-05-03T13:54:42Z	--- base_model: Gensyn/Qwen2.5-1.5B-Instruct library_name: transformers model_name: Qwen2.5-1.5B-Instruct-Gensyn-Swarm-alert_armored_trout tags: - generated_from_trainer - rl-swarm - grpo - gensyn - I am alert armored trout - unsloth - trl licence: license --- # Model Card for Qwen2.5-1.5B-Instruct-Gensyn-Swarm-alert_armored_trout 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="franzexplorer77/Qwen2.5-1.5B-Instruct-Gensyn-Swarm-alert_armored_trout", 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 - Datasets: 3.5.1 - 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}} } ```
Docty/dreambooth-dog-lora	Docty	2025-05-03T15:42:38Z	0	0	diffusers	[ "diffusers", "tensorboard", "text-to-image", "lora", "diffusers-training", "stable-diffusion", "stable-diffusion-diffusers", "base_model:stable-diffusion-v1-5/stable-diffusion-v1-5", "base_model:adapter:stable-diffusion-v1-5/stable-diffusion-v1-5", "license:creativeml-openrail-m", "region:us" ]	text-to-image	2025-05-03T15:17:56Z	--- base_model: stable-diffusion-v1-5/stable-diffusion-v1-5 library_name: diffusers license: creativeml-openrail-m inference: true instance_prompt: A photo of sks dog tags: - text-to-image - diffusers - lora - diffusers-training - stable-diffusion - stable-diffusion-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. --> # LoRA DreamBooth - Docty/dreambooth-dog-lora These are LoRA adaption weights for stable-diffusion-v1-5/stable-diffusion-v1-5. The weights were trained on A photo of sks dog using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following. ![img_0](./image_0.png) ![img_1](./image_1.png) ![img_2](./image_2.png) ![img_3](./image_3.png) LoRA for the text encoder was enabled: False. ## Intended uses & limitations #### How to use ```python # TODO: add an example code snippet for running this diffusion pipeline ``` #### Limitations and bias [TODO: provide examples of latent issues and potential remediations] ## Training details [TODO: describe the data used to train the model]
oferk/ppo-LunarLander-v2	oferk	2025-05-03T15:41:17Z	0	0	stable-baselines3	[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2025-05-03T15:38:39Z	--- 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: 261.46 +/- 22.46 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 ... ```
StrangeGhost/Qwen2.5-72B-Instruct-bnb-4bit-Gensyn-Swarm-prickly_silent_ostrich	StrangeGhost	2025-05-03T15:39:34Z	0	0	transformers	[ "transformers", "safetensors", "generated_from_trainer", "rl-swarm", "grpo", "gensyn", "I am prickly silent ostrich", "unsloth", "trl", "arxiv:2402.03300", "base_model:Gensyn/Qwen2.5-72B-Instruct-bnb-4bit", "base_model:finetune:Gensyn/Qwen2.5-72B-Instruct-bnb-4bit", "endpoints_compatible", "region:us" ]	null	2025-05-03T15:39:21Z	--- base_model: Gensyn/Qwen2.5-72B-Instruct-bnb-4bit library_name: transformers model_name: Qwen2.5-72B-Instruct-bnb-4bit-Gensyn-Swarm-prickly_silent_ostrich tags: - generated_from_trainer - rl-swarm - grpo - gensyn - I am prickly silent ostrich - unsloth - trl licence: license --- # Model Card for Qwen2.5-72B-Instruct-bnb-4bit-Gensyn-Swarm-prickly_silent_ostrich This model is a fine-tuned version of [Gensyn/Qwen2.5-72B-Instruct-bnb-4bit](https://huggingface.co/Gensyn/Qwen2.5-72B-Instruct-bnb-4bit). 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="StrangeGhost/Qwen2.5-72B-Instruct-bnb-4bit-Gensyn-Swarm-prickly_silent_ostrich", 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 - Datasets: 3.5.1 - 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}} } ```
lmganon123/THUDM_GLM-Z1-32B-0414-exl3-4.0bpw	lmganon123	2025-05-03T15:35:15Z	0	0	null	[ "safetensors", "glm4", "base_model:THUDM/GLM-Z1-32B-0414", "base_model:quantized:THUDM/GLM-Z1-32B-0414", "4-bit", "exl3", "region:us" ]	null	2025-05-03T14:19:10Z	--- base_model: - THUDM/GLM-Z1-32B-0414 --- I wish more people would make exl3 quants. I probably will be making some for 24GB VRAM. ## Prompt format ``` [gMASK]<sop><\|system\|> {system_prompt}<\|user\|> {prompt}<\|assistant\|> <think> ```
mradermacher/MedicalEDI-14b-EDI-Reasoning-Final-3-GGUF	mradermacher	2025-05-03T15:34:24Z	0	1	transformers	[ "transformers", "gguf", "en", "base_model:Shaleen123/MedicalEDI-14b-EDI-Reasoning-Final-3", "base_model:quantized:Shaleen123/MedicalEDI-14b-EDI-Reasoning-Final-3", "endpoints_compatible", "region:us", "conversational" ]	null	2025-05-03T10:47:58Z	--- base_model: Shaleen123/MedicalEDI-14b-EDI-Reasoning-Final-3 language: - en library_name: transformers quantized_by: mradermacher tags: [] --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/Shaleen123/MedicalEDI-14b-EDI-Reasoning-Final-3 <!-- provided-files --> weighted/imatrix quants are available at https://huggingface.co/mradermacher/MedicalEDI-14b-EDI-Reasoning-Final-3-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/MedicalEDI-14b-EDI-Reasoning-Final-3-GGUF/resolve/main/MedicalEDI-14b-EDI-Reasoning-Final-3.Q2_K.gguf) \| Q2_K \| 5.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/MedicalEDI-14b-EDI-Reasoning-Final-3-GGUF/resolve/main/MedicalEDI-14b-EDI-Reasoning-Final-3.Q3_K_S.gguf) \| Q3_K_S \| 6.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/MedicalEDI-14b-EDI-Reasoning-Final-3-GGUF/resolve/main/MedicalEDI-14b-EDI-Reasoning-Final-3.Q3_K_M.gguf) \| Q3_K_M \| 7.4 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/MedicalEDI-14b-EDI-Reasoning-Final-3-GGUF/resolve/main/MedicalEDI-14b-EDI-Reasoning-Final-3.Q3_K_L.gguf) \| Q3_K_L \| 8.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/MedicalEDI-14b-EDI-Reasoning-Final-3-GGUF/resolve/main/MedicalEDI-14b-EDI-Reasoning-Final-3.IQ4_XS.gguf) \| IQ4_XS \| 8.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/MedicalEDI-14b-EDI-Reasoning-Final-3-GGUF/resolve/main/MedicalEDI-14b-EDI-Reasoning-Final-3.Q4_K_S.gguf) \| Q4_K_S \| 8.7 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/MedicalEDI-14b-EDI-Reasoning-Final-3-GGUF/resolve/main/MedicalEDI-14b-EDI-Reasoning-Final-3.Q4_K_M.gguf) \| Q4_K_M \| 9.1 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/MedicalEDI-14b-EDI-Reasoning-Final-3-GGUF/resolve/main/MedicalEDI-14b-EDI-Reasoning-Final-3.Q5_K_S.gguf) \| Q5_K_S \| 10.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/MedicalEDI-14b-EDI-Reasoning-Final-3-GGUF/resolve/main/MedicalEDI-14b-EDI-Reasoning-Final-3.Q5_K_M.gguf) \| Q5_K_M \| 10.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/MedicalEDI-14b-EDI-Reasoning-Final-3-GGUF/resolve/main/MedicalEDI-14b-EDI-Reasoning-Final-3.Q6_K.gguf) \| Q6_K \| 12.2 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/MedicalEDI-14b-EDI-Reasoning-Final-3-GGUF/resolve/main/MedicalEDI-14b-EDI-Reasoning-Final-3.Q8_0.gguf) \| Q8_0 \| 15.8 \| 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 -->
Triangle104/Llama-3.1-Nemotron-Nano-8B-v1-Q8_0-GGUF	Triangle104	2025-05-03T15:34:08Z	0	0	transformers	[ "transformers", "gguf", "nvidia", "llama-3", "pytorch", "llama-cpp", "gguf-my-repo", "text-generation", "en", "base_model:nvidia/Llama-3.1-Nemotron-Nano-8B-v1", "base_model:quantized:nvidia/Llama-3.1-Nemotron-Nano-8B-v1", "license:other", "endpoints_compatible", "region:us", "conversational" ]	text-generation	2025-05-03T15:32:25Z	--- base_model: nvidia/Llama-3.1-Nemotron-Nano-8B-v1 language: - en library_name: transformers license: other license_name: nvidia-open-model-license license_link: https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/ pipeline_tag: text-generation tags: - nvidia - llama-3 - pytorch - llama-cpp - gguf-my-repo --- # Triangle104/Llama-3.1-Nemotron-Nano-8B-v1-Q8_0-GGUF This model was converted to GGUF format from [`nvidia/Llama-3.1-Nemotron-Nano-8B-v1`](https://huggingface.co/nvidia/Llama-3.1-Nemotron-Nano-8B-v1) 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/nvidia/Llama-3.1-Nemotron-Nano-8B-v1) for more details on the model. --- Llama-3.1-Nemotron-Nano-8B-v1 is a large language model (LLM) which is a derivative of Meta Llama-3.1-8B-Instruct (AKA the reference model). It is a reasoning model that is post trained for reasoning, human chat preferences, and tasks, such as RAG and tool calling. Llama-3.1-Nemotron-Nano-8B-v1 is a model which offers a great tradeoff between model accuracy and efficiency. It is created from Llama 3.1 8B Instruct and offers improvements in model accuracy. The model fits on a single RTX GPU and can be used locally. The model supports a context length of 128K. This model underwent a multi-phase post-training process to enhance both its reasoning and non-reasoning capabilities. This includes a supervised fine-tuning stage for Math, Code, Reasoning, and Tool Calling as well as multiple reinforcement learning (RL) stages using REINFORCE (RLOO) and Online Reward-aware Preference Optimization (RPO) algorithms for both chat and instruction-following. The final model checkpoint is obtained after merging the final SFT and Online RPO checkpoints. Improved using Qwen. --- ## 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 Triangle104/Llama-3.1-Nemotron-Nano-8B-v1-Q8_0-GGUF --hf-file llama-3.1-nemotron-nano-8b-v1-q8_0.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo Triangle104/Llama-3.1-Nemotron-Nano-8B-v1-Q8_0-GGUF --hf-file llama-3.1-nemotron-nano-8b-v1-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 Triangle104/Llama-3.1-Nemotron-Nano-8B-v1-Q8_0-GGUF --hf-file llama-3.1-nemotron-nano-8b-v1-q8_0.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo Triangle104/Llama-3.1-Nemotron-Nano-8B-v1-Q8_0-GGUF --hf-file llama-3.1-nemotron-nano-8b-v1-q8_0.gguf -c 2048 ```
mafzaal/finetuned_arctic_ft	mafzaal	2025-05-03T15:33:46Z	0	0	sentence-transformers	[ "sentence-transformers", "safetensors", "bert", "sentence-similarity", "feature-extraction", "generated_from_trainer", "dataset_size:156", "loss:MatryoshkaLoss", "loss:MultipleNegativesRankingLoss", "arxiv:1908.10084", "arxiv:2205.13147", "arxiv:1705.00652", "base_model:Snowflake/snowflake-arctic-embed-l", "base_model:finetune:Snowflake/snowflake-arctic-embed-l", "model-index", "autotrain_compatible", "text-embeddings-inference", "endpoints_compatible", "region:us" ]	sentence-similarity	2025-05-03T15:33:03Z	--- tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:156 - loss:MatryoshkaLoss - loss:MultipleNegativesRankingLoss base_model: Snowflake/snowflake-arctic-embed-l widget: - source_sentence: Which multi-modal models were released by significant vendors in 2024, and in which months did they appear? sentences: - 'An interesting point of comparison here could be the way railways rolled out around the world in the 1800s. Constructing these required enormous investments and had a massive environmental impact, and many of the lines that were built turned out to be unnecessary—sometimes multiple lines from different companies serving the exact same routes! The resulting bubbles contributed to several financial crashes, see Wikipedia for Panic of 1873, Panic of 1893, Panic of 1901 and the UK’s Railway Mania. They left us with a lot of useful infrastructure and a great deal of bankruptcies and environmental damage. The year of slop' - 'In 2024, almost every significant model vendor released multi-modal models. We saw the Claude 3 series from Anthropic in March, Gemini 1.5 Pro in April (images, audio and video), then September brought Qwen2-VL and Mistral’s Pixtral 12B and Meta’s Llama 3.2 11B and 90B vision models. We got audio input and output from OpenAI in October, then November saw SmolVLM from Hugging Face and December saw image and video models from Amazon Nova. In October I upgraded my LLM CLI tool to support multi-modal models via attachments. It now has plugins for a whole collection of different vision models.' - 'OpenAI made GPT-4o free for all users in May, and Claude 3.5 Sonnet was freely available from its launch in June. This was a momentus change, because for the previous year free users had mostly been restricted to GPT-3.5 level models, meaning new users got a very inaccurate mental model of what a capable LLM could actually do. That era appears to have ended, likely permanently, with OpenAI’s launch of ChatGPT Pro. This $200/month subscription service is the only way to access their most capable model, o1 Pro. Since the trick behind the o1 series (and the future models it will undoubtedly inspire) is to expend more compute time to get better results, I don’t think those days of free access to the best available models are likely to return.' - source_sentence: How is a prompt without evals, models, and UX compared in the given context? sentences: - 'The environmental impact got much, much worse The much bigger problem here is the enormous competitive buildout of the infrastructure that is imagined to be necessary for these models in the future. Companies like Google, Meta, Microsoft and Amazon are all spending billions of dollars rolling out new datacenters, with a very material impact on the electricity grid and the environment. There’s even talk of spinning up new nuclear power stations, but those can take decades. Is this infrastructure necessary? DeepSeek v3’s $6m training cost and the continued crash in LLM prices might hint that it’s not. But would you want to be the big tech executive that argued NOT to build out this infrastructure only to be proven wrong in a few years’ time?' - 'When @v0 first came out we were paranoid about protecting the prompt with all kinds of pre and post processing complexity. We completely pivoted to let it rip. A prompt without the evals, models, and especially UX is like getting a broken ASML machine without a manual' - 'The boring yet crucial secret behind good system prompts is test-driven development. You don’t write down a system prompt and find ways to test it. You write down tests and find a system prompt that passes them. It’s become abundantly clear over the course of 2024 that writing good automated evals for LLM-powered systems is the skill that’s most needed to build useful applications on top of these models. If you have a strong eval suite you can adopt new models faster, iterate better and build more reliable and useful product features than your competition. Vercel’s Malte Ubl:' - source_sentence: How did the construction of railways in the 1800s impact the environment? sentences: - 'DeepSeek v3 is a huge 685B parameter model—one of the largest openly licensed models currently available, significantly bigger than the largest of Meta’s Llama series, Llama 3.1 405B. Benchmarks put it up there with Claude 3.5 Sonnet. Vibe benchmarks (aka the Chatbot Arena) currently rank it 7th, just behind the Gemini 2.0 and OpenAI 4o/o1 models. This is by far the highest ranking openly licensed model. The really impressive thing about DeepSeek v3 is the training cost. The model was trained on 2,788,000 H800 GPU hours at an estimated cost of $5,576,000. Llama 3.1 405B trained 30,840,000 GPU hours—11x that used by DeepSeek v3, for a model that benchmarks slightly worse.' - 'An interesting point of comparison here could be the way railways rolled out around the world in the 1800s. Constructing these required enormous investments and had a massive environmental impact, and many of the lines that were built turned out to be unnecessary—sometimes multiple lines from different companies serving the exact same routes! The resulting bubbles contributed to several financial crashes, see Wikipedia for Panic of 1873, Panic of 1893, Panic of 1901 and the UK’s Railway Mania. They left us with a lot of useful infrastructure and a great deal of bankruptcies and environmental damage. The year of slop' - 'So far, I think they’re a net positive. I’ve used them on a personal level to improve my productivity (and entertain myself) in all sorts of different ways. I think people who learn how to use them effectively can gain a significant boost to their quality of life. A lot of people are yet to be sold on their value! Some think their negatives outweigh their positives, some think they are all hot air, and some even think they represent an existential threat to humanity. They’re actually quite easy to build The most surprising thing we’ve learned about LLMs this year is that they’re actually quite easy to build.' - source_sentence: How many lines of Python code are generally needed to train a basic version of a powerful system? sentences: - 'We already knew LLMs were spookily good at writing code. If you prompt them right, it turns out they can build you a full interactive application using HTML, CSS and JavaScript (and tools like React if you wire up some extra supporting build mechanisms)—often in a single prompt. Anthropic kicked this idea into high gear when they released Claude Artifacts, a groundbreaking new feature that was initially slightly lost in the noise due to being described half way through their announcement of the incredible Claude 3.5 Sonnet. With Artifacts, Claude can write you an on-demand interactive application and then let you use it directly inside the Claude interface. Here’s my Extract URLs app, entirely generated by Claude:' - 'I’m still trying to figure out the best patterns for doing this for my own work. Everyone knows that evals are important, but there remains a lack of great guidance for how to best implement them—I’m tracking this under my evals tag. My SVG pelican riding a bicycle benchmark is a pale imitation of what a real eval suite should look like. Apple Intelligence is bad, Apple’s MLX library is excellent As a Mac user I’ve been feeling a lot better about my choice of platform this year. Last year it felt like my lack of a Linux/Windows machine with an NVIDIA GPU was a huge disadvantage in terms of trying out new models.' - 'Intuitively, one would expect that systems this powerful would take millions of lines of complex code. Instead, it turns out a few hundred lines of Python is genuinely enough to train a basic version! What matters most is the training data. You need a lot of data to make these things work, and the quantity and quality of the training data appears to be the most important factor in how good the resulting model is. If you can gather the right data, and afford to pay for the GPUs to train it, you can build an LLM.' - source_sentence: According to the context, what is one of the best applications of large language models (LLMs)? sentences: - 'A lot of people are excited about AI agents—an infuriatingly vague term that seems to be converging on “AI systems that can go away and act on your behalf”. We’ve been talking about them all year, but I’ve seen few if any examples of them running in production, despite lots of exciting prototypes. I think this is because of gullibility. Can we solve this? Honestly, I’m beginning to suspect that you can’t fully solve gullibility without achieving AGI. So it may be quite a while before those agent dreams can really start to come true! Code may be the best application Over the course of the year, it’s become increasingly clear that writing code is one of the things LLMs are most capable of.' - 'Law is not ethics. Is it OK to train models on people’s content without their permission, when those models will then be used in ways that compete with those people? As the quality of results produced by AI models has increased over the year, these questions have become even more pressing. The impact on human society in terms of these models is already huge, if difficult to objectively measure. People have certainly lost work to them—anecdotally, I’ve seen this for copywriters, artists and translators. There are a great deal of untold stories here. I’m hoping 2024 sees significant amounts of dedicated journalism on this topic. My blog in 2023 Here’s a tag cloud for content I posted to my blog in 2023 (generated using Django SQL Dashboard):' - 'The two main categories I see are people who think AI agents are obviously things that go and act on your behalf—the travel agent model—and people who think in terms of LLMs that have been given access to tools which they can run in a loop as part of solving a problem. The term “autonomy” is often thrown into the mix too, again without including a clear definition. (I also collected 211 definitions on Twitter a few months ago—here they are in Datasette Lite—and had gemini-exp-1206 attempt to summarize them.) Whatever the term may mean, agents still have that feeling of perpetually “coming soon”.' pipeline_tag: sentence-similarity library_name: sentence-transformers metrics: - cosine_accuracy@1 - cosine_accuracy@3 - cosine_accuracy@5 - cosine_accuracy@10 - cosine_precision@1 - cosine_precision@3 - cosine_precision@5 - cosine_precision@10 - cosine_recall@1 - cosine_recall@3 - cosine_recall@5 - cosine_recall@10 - cosine_ndcg@10 - cosine_mrr@10 - cosine_map@100 model-index: - name: SentenceTransformer based on Snowflake/snowflake-arctic-embed-l results: - task: type: information-retrieval name: Information Retrieval dataset: name: Unknown type: unknown metrics: - type: cosine_accuracy@1 value: 0.9166666666666666 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 1.0 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 1.0 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 1.0 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.9166666666666666 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.3333333333333333 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.20000000000000004 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.10000000000000002 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.9166666666666666 name: Cosine Recall@1 - type: cosine_recall@3 value: 1.0 name: Cosine Recall@3 - type: cosine_recall@5 value: 1.0 name: Cosine Recall@5 - type: cosine_recall@10 value: 1.0 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.9692441461309548 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.9583333333333334 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.9583333333333334 name: Cosine Map@100 --- # SentenceTransformer based on Snowflake/snowflake-arctic-embed-l This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Snowflake/snowflake-arctic-embed-l](https://huggingface.co/Snowflake/snowflake-arctic-embed-l). It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more. ## Model Details ### Model Description - Model Type: Sentence Transformer - Base model: [Snowflake/snowflake-arctic-embed-l](https://huggingface.co/Snowflake/snowflake-arctic-embed-l) <!-- at revision d8fb21ca8d905d2832ee8b96c894d3298964346b --> - Maximum Sequence Length: 512 tokens - Output Dimensionality: 1024 dimensions - Similarity Function: Cosine Similarity <!-- - Training Dataset: Unknown --> <!-- - Language: Unknown --> <!-- - License: Unknown --> ### Model Sources - Documentation: [Sentence Transformers Documentation](https://sbert.net) - Repository: [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers) - Hugging Face: [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) ### Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) (2): Normalize() ) ``` ## Usage ### Direct Usage (Sentence Transformers) First install the Sentence Transformers library: ```bash pip install -U sentence-transformers ``` Then you can load this model and run inference. ```python from sentence_transformers import SentenceTransformer # Download from the 🤗 Hub model = SentenceTransformer("mafzaal/finetuned_arctic_ft") # Run inference sentences = [ 'According to the context, what is one of the best applications of large language models (LLMs)?', 'A lot of people are excited about AI agents—an infuriatingly vague term that seems to be converging on “AI systems that can go away and act on your behalf”. We’ve been talking about them all year, but I’ve seen few if any examples of them running in production, despite lots of exciting prototypes.\nI think this is because of gullibility.\nCan we solve this? Honestly, I’m beginning to suspect that you can’t fully solve gullibility without achieving AGI. So it may be quite a while before those agent dreams can really start to come true!\nCode may be the best application\nOver the course of the year, it’s become increasingly clear that writing code is one of the things LLMs are most capable of.', 'The two main categories I see are people who think AI agents are obviously things that go and act on your behalf—the travel agent model—and people who think in terms of LLMs that have been given access to tools which they can run in a loop as part of solving a problem. The term “autonomy” is often thrown into the mix too, again without including a clear definition.\n(I also collected 211 definitions on Twitter a few months ago—here they are in Datasette Lite—and had gemini-exp-1206 attempt to summarize them.)\nWhatever the term may mean, agents still have that feeling of perpetually “coming soon”.', ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 1024] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] ``` <!-- ### Direct Usage (Transformers) <details><summary>Click to see the direct usage in Transformers</summary> </details> --> <!-- ### Downstream Usage (Sentence Transformers) You can finetune this model on your own dataset. <details><summary>Click to expand</summary> </details> --> <!-- ### Out-of-Scope Use List how the model may foreseeably be misused and address what users ought not to do with the model. --> ## Evaluation ### Metrics #### Information Retrieval * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) \| Metric \| Value \| \|:--------------------\|:-----------\| \| cosine_accuracy@1 \| 0.9167 \| \| cosine_accuracy@3 \| 1.0 \| \| cosine_accuracy@5 \| 1.0 \| \| cosine_accuracy@10 \| 1.0 \| \| cosine_precision@1 \| 0.9167 \| \| cosine_precision@3 \| 0.3333 \| \| cosine_precision@5 \| 0.2 \| \| cosine_precision@10 \| 0.1 \| \| cosine_recall@1 \| 0.9167 \| \| cosine_recall@3 \| 1.0 \| \| cosine_recall@5 \| 1.0 \| \| cosine_recall@10 \| 1.0 \| \| cosine_ndcg@10 \| 0.9692 \| \| cosine_mrr@10 \| 0.9583 \| \| cosine_map@100 \| 0.9583 \| <!-- ## Bias, Risks and Limitations What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model. --> <!-- ### Recommendations What are recommendations with respect to the foreseeable issues? For example, filtering explicit content. --> ## Training Details ### Training Dataset #### Unnamed Dataset * Size: 156 training samples * Columns: <code>sentence_0</code> and <code>sentence_1</code> * Approximate statistics based on the first 156 samples: \| \| sentence_0 \| sentence_1 \| \|:--------\|:-----------------------------------------------------------------------------------\|:-------------------------------------------------------------------------------------\| \| type \| string \| string \| \| details \| <ul><li>min: 12 tokens</li><li>mean: 21.18 tokens</li><li>max: 37 tokens</li></ul> \| <ul><li>min: 43 tokens</li><li>mean: 135.14 tokens</li><li>max: 214 tokens</li></ul> \| * Samples: \| sentence_0 \| sentence_1 \| \|:-----------------------------------------------------------------------------------------------------------------------------------------------\|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\| \| <code>What significant development in Artificial Intelligence occurred in 2023 according to Simon Willison’s weblog?</code> \| <code>Stuff we figured out about AI in 2023<br><br><br><br><br><br><br><br><br><br><br><br><br><br><br><br><br><br><br><br><br><br>Simon Willison’s Weblog<br>Subscribe<br><br><br><br><br><br><br>Stuff we figured out about AI in 2023<br>31st December 2023<br>2023 was the breakthrough year for Large Language Models (LLMs). I think it’s OK to call these AI—they’re the latest and (currently) most interesting development in the academic field of Artificial Intelligence that dates back to the 1950s.<br>Here’s my attempt to round up the highlights in one place!</code> \| \| <code>How does Simon Willison describe the relationship between Large Language Models and the broader field of Artificial Intelligence?</code> \| <code>Stuff we figured out about AI in 2023<br><br><br><br><br><br><br><br><br><br><br><br><br><br><br><br><br><br><br><br><br><br>Simon Willison’s Weblog<br>Subscribe<br><br><br><br><br><br><br>Stuff we figured out about AI in 2023<br>31st December 2023<br>2023 was the breakthrough year for Large Language Models (LLMs). I think it’s OK to call these AI—they’re the latest and (currently) most interesting development in the academic field of Artificial Intelligence that dates back to the 1950s.<br>Here’s my attempt to round up the highlights in one place!</code> \| \| <code>What are some challenges mentioned in building large language models like GPT-4?</code> \| <code>Large Language Models<br>They’re actually quite easy to build<br>You can run LLMs on your own devices<br>Hobbyists can build their own fine-tuned models<br>We don’t yet know how to build GPT-4<br>Vibes Based Development<br>LLMs are really smart, and also really, really dumb<br>Gullibility is the biggest unsolved problem<br>Code may be the best application<br>The ethics of this space remain diabolically complex<br>My blog in 2023</code> \| * Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters: ```json { "loss": "MultipleNegativesRankingLoss", "matryoshka_dims": [ 768, 512, 256, 128, 64 ], "matryoshka_weights": [ 1, 1, 1, 1, 1 ], "n_dims_per_step": -1 } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: steps - `per_device_train_batch_size`: 10 - `per_device_eval_batch_size`: 10 - `num_train_epochs`: 10 - `multi_dataset_batch_sampler`: round_robin #### All Hyperparameters <details><summary>Click to expand</summary> - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: steps - `prediction_loss_only`: True - `per_device_train_batch_size`: 10 - `per_device_eval_batch_size`: 10 - `per_gpu_train_batch_size`: None - `per_gpu_eval_batch_size`: None - `gradient_accumulation_steps`: 1 - `eval_accumulation_steps`: None - `torch_empty_cache_steps`: None - `learning_rate`: 5e-05 - `weight_decay`: 0.0 - `adam_beta1`: 0.9 - `adam_beta2`: 0.999 - `adam_epsilon`: 1e-08 - `max_grad_norm`: 1 - `num_train_epochs`: 10 - `max_steps`: -1 - `lr_scheduler_type`: linear - `lr_scheduler_kwargs`: {} - `warmup_ratio`: 0.0 - `warmup_steps`: 0 - `log_level`: passive - `log_level_replica`: warning - `log_on_each_node`: True - `logging_nan_inf_filter`: True - `save_safetensors`: True - `save_on_each_node`: False - `save_only_model`: False - `restore_callback_states_from_checkpoint`: False - `no_cuda`: False - `use_cpu`: False - `use_mps_device`: False - `seed`: 42 - `data_seed`: None - `jit_mode_eval`: False - `use_ipex`: False - `bf16`: False - `fp16`: False - `fp16_opt_level`: O1 - `half_precision_backend`: auto - `bf16_full_eval`: False - `fp16_full_eval`: False - `tf32`: None - `local_rank`: 0 - `ddp_backend`: None - `tpu_num_cores`: None - `tpu_metrics_debug`: False - `debug`: [] - `dataloader_drop_last`: False - `dataloader_num_workers`: 0 - `dataloader_prefetch_factor`: None - `past_index`: -1 - `disable_tqdm`: False - `remove_unused_columns`: True - `label_names`: None - `load_best_model_at_end`: False - `ignore_data_skip`: False - `fsdp`: [] - `fsdp_min_num_params`: 0 - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} - `tp_size`: 0 - `fsdp_transformer_layer_cls_to_wrap`: None - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} - `deepspeed`: None - `label_smoothing_factor`: 0.0 - `optim`: adamw_torch - `optim_args`: None - `adafactor`: False - `group_by_length`: False - `length_column_name`: length - `ddp_find_unused_parameters`: None - `ddp_bucket_cap_mb`: None - `ddp_broadcast_buffers`: False - `dataloader_pin_memory`: True - `dataloader_persistent_workers`: False - `skip_memory_metrics`: True - `use_legacy_prediction_loop`: False - `push_to_hub`: False - `resume_from_checkpoint`: None - `hub_model_id`: None - `hub_strategy`: every_save - `hub_private_repo`: None - `hub_always_push`: False - `gradient_checkpointing`: False - `gradient_checkpointing_kwargs`: None - `include_inputs_for_metrics`: False - `include_for_metrics`: [] - `eval_do_concat_batches`: True - `fp16_backend`: auto - `push_to_hub_model_id`: None - `push_to_hub_organization`: None - `mp_parameters`: - `auto_find_batch_size`: False - `full_determinism`: False - `torchdynamo`: None - `ray_scope`: last - `ddp_timeout`: 1800 - `torch_compile`: False - `torch_compile_backend`: None - `torch_compile_mode`: None - `include_tokens_per_second`: False - `include_num_input_tokens_seen`: False - `neftune_noise_alpha`: None - `optim_target_modules`: None - `batch_eval_metrics`: False - `eval_on_start`: False - `use_liger_kernel`: False - `eval_use_gather_object`: False - `average_tokens_across_devices`: False - `prompts`: None - `batch_sampler`: batch_sampler - `multi_dataset_batch_sampler`: round_robin </details> ### Training Logs \| Epoch \| Step \| cosine_ndcg@10 \| \|:-----:\|:----:\|:--------------:\| \| 1.0 \| 16 \| 0.9638 \| \| 2.0 \| 32 \| 0.9539 \| \| 3.0 \| 48 \| 0.9539 \| \| 3.125 \| 50 \| 0.9539 \| \| 4.0 \| 64 \| 0.9692 \| \| 5.0 \| 80 \| 0.9692 \| \| 6.0 \| 96 \| 0.9692 \| \| 6.25 \| 100 \| 0.9539 \| \| 7.0 \| 112 \| 0.9692 \| \| 8.0 \| 128 \| 0.9692 \| \| 9.0 \| 144 \| 0.9692 \| \| 9.375 \| 150 \| 0.9692 \| \| 10.0 \| 160 \| 0.9692 \| ### Framework Versions - Python: 3.11.12 - Sentence Transformers: 4.1.0 - Transformers: 4.51.3 - PyTorch: 2.6.0+cu124 - Accelerate: 1.6.0 - Datasets: 3.5.1 - Tokenizers: 0.21.1 ## Citation ### BibTeX #### Sentence Transformers ```bibtex @inproceedings{reimers-2019-sentence-bert, title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", author = "Reimers, Nils and Gurevych, Iryna", booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing", month = "11", year = "2019", publisher = "Association for Computational Linguistics", url = "https://arxiv.org/abs/1908.10084", } ``` #### MatryoshkaLoss ```bibtex @misc{kusupati2024matryoshka, title={Matryoshka Representation Learning}, author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi}, year={2024}, eprint={2205.13147}, archivePrefix={arXiv}, primaryClass={cs.LG} } ``` #### MultipleNegativesRankingLoss ```bibtex @misc{henderson2017efficient, title={Efficient Natural Language Response Suggestion for Smart Reply}, author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil}, year={2017}, eprint={1705.00652}, archivePrefix={arXiv}, primaryClass={cs.CL} } ``` <!-- ## Glossary Clearly define terms in order to be accessible across audiences. --> <!-- ## Model Card Authors Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction. --> <!-- ## Model Card Contact Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors. -->
Pinkstack/Parm-2-CoT-14B-16k-o1-QwQ	Pinkstack	2025-05-03T15:33:32Z	30	7	transformers	[ "transformers", "pytorch", "safetensors", "llama", "text-generation", "phi", "nlp", "math", "code", "chat", "conversational", "phi3", "reasoning", "CoT", "en", "multilingual", "dataset:amphora/QwQ-LongCoT-130K", "arxiv:2412.08905", "base_model:microsoft/phi-4", "base_model:finetune:microsoft/phi-4", "license:mit", "model-index", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-01-14T21:37:30Z	--- license: mit license_link: https://huggingface.co/microsoft/phi-4/resolve/main/LICENSE language: - en - multilingual pipeline_tag: text-generation tags: - phi - nlp - math - code - chat - conversational - phi3 - reasoning - CoT inference: parameters: temperature: 0.3 widget: - messages: - role: user content: How many R's in strawberry? Think step by step. library_name: transformers datasets: - amphora/QwQ-LongCoT-130K base_model: - microsoft/phi-4 model-index: - name: SuperThoughts-CoT-14B-16k-o1-QwQ results: - task: type: text-generation name: Text Generation dataset: name: IFEval (0-Shot) type: wis-k/instruction-following-eval split: train args: num_few_shot: 0 metrics: - type: inst_level_strict_acc and prompt_level_strict_acc value: 5.15 name: averaged accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Pinkstack%2FSuperThoughts-CoT-14B-16k-o1-QwQ name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: BBH (3-Shot) type: SaylorTwift/bbh split: test args: num_few_shot: 3 metrics: - type: acc_norm value: 52.85 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Pinkstack%2FSuperThoughts-CoT-14B-16k-o1-QwQ name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MATH Lvl 5 (4-Shot) type: lighteval/MATH-Hard split: test args: num_few_shot: 4 metrics: - type: exact_match value: 40.79 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Pinkstack%2FSuperThoughts-CoT-14B-16k-o1-QwQ name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GPQA (0-shot) type: Idavidrein/gpqa split: train args: num_few_shot: 0 metrics: - type: acc_norm value: 19.02 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Pinkstack%2FSuperThoughts-CoT-14B-16k-o1-QwQ name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MuSR (0-shot) type: TAUR-Lab/MuSR args: num_few_shot: 0 metrics: - type: acc_norm value: 21.79 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Pinkstack%2FSuperThoughts-CoT-14B-16k-o1-QwQ name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU-PRO (5-shot) type: TIGER-Lab/MMLU-Pro config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 47.43 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Pinkstack%2FSuperThoughts-CoT-14B-16k-o1-QwQ name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: Llmexplorer lmsys elo type: elo-score config: main split: test metrics: - type: elo value: 1203 name: elo source: url: https://llm.extractum.io/list/?benchmark=score_elo name: LLMexplorer lmsys elo score --- Renamed to parm-2 Please note, the low IFEVAL results is due to this model always reasoning, instruction following is limited, which caused it to have very low ifeval results, this should not matter for most use cases. gguf/final version: https://huggingface.co/Pinkstack/PARM-V2-phi-4-16k-CoT-o1-gguf This model can be merged with phi-4 based LLMs! [Phi-4 Technical Report](https://arxiv.org/pdf/2412.08905) [superthoughts 14B openllm detailed results](https://huggingface.co/datasets/open-llm-leaderboard/Pinkstack__SuperThoughts-CoT-14B-16k-o1-QwQ-details) Phi-4 that has been tuned to be more advanced at reasoning. Unlike other Parm models we had to optimize our fine tuning process to ensure accuracy while still being able to release this model. Training loss: 0.443800 Beats qwen/qwq at MATH & MuSR & GPQA (MuSR being a reasoning benchmark) Evaluation: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/csbdGKzGcDVMPRqMCoH8D.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/HR9WtjBhE4h6wrq88FLAf.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/GLt4ct4yAVMvYEpoYO5o6.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/CP9UF9kdBT_SW8Q79PSui.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/doEIqDrM639hRPSg_J6AF.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/yl5Et2TkCoYuIrNpDhZu9.png) the model can use this prompt format: (modified phi-4 prompt, by adding a system prompt telling the model to reason before responding you'll get a similar if not better response) ``` {{ if .System }}<\|system\|> {{ .System }}<\|im_end\|> {{ end }}{{ if .Prompt }}<\|user\|> {{ .Prompt }}<\|im_end\|> {{ end }}<\|assistant\|>{{ .CoT }}<\|CoT\|> {{ .Response }}<\|FinalAnswer\|><\|im_end\|> ``` It is recommended to use a system prompt like this one: ``` You are a helpful ai assistant. Make sure to put your finalanswer at the end. ``` # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/Pinkstack__SuperThoughts-CoT-14B-16k-o1-QwQ-details)! Summarized results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/contents/viewer/default/train?q=Pinkstack%2FSuperThoughts-CoT-14B-16k-o1-QwQ&sort[column]=Average%20%E2%AC%86%EF%B8%8F&sort[direction]=desc)! \| Metric \|Value (%)\| \|-------------------\|--------:\| \|Average \| 31.17\| \|IFEval (0-Shot) \| 5.15\| \|BBH (3-Shot) \| 52.85\| \|MATH Lvl 5 (4-Shot)\| 40.79\| \|GPQA (0-shot) \| 19.02\| \|MuSR (0-shot) \| 21.79\| \|MMLU-PRO (5-shot) \| 47.43\| # other leaderboard According to https://llm.extractum.io/list/?benchmark=score_elo, this model is in the top 20 on their LMSys ELO score leaderboard. # 🧀 Examples: (q4_k_m, 10GB rtx 3080, 64GB memory, running inside of MSTY, all use "You are a friendly ai assistant." as the System prompt.) example 1: ![example1](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/NoLJREYFU8LdMwynyLLMG.png) example 2: ![2](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/uboFipmS1ulfxeDgMBsBH.png) example 3: ![example2](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/c4h-nw0DPTrQgX-_tvBoT.png) example 4: ![example1part1.png](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/Dcd6-wbpDQuXoulHaqATo.png) ![example1part2.png](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/CoBYmYiRt9Z4IDFoOwHxc.png) All generated locally # 🧀 Information - ⚠️ A low temperature must be used to ensure it won't fail at reasoning. we use 0.3 - 0.8! - ⚠️ Due to the current prompt format, it may sometimes put <\|FinalAnswer\|> without providing a final answer at the end, you can ignore this or modify the prompt format. This is our flagship model, with top-tier reasoning, rivaling gemini-flash-exp-2.0-thinking and o1 mini. Overall, the results are similar to both of them. # Uploaded model - Developed by: Pinkstack - License: MIT - Finetuned from model : microsoft/phi-4 This phi-4 model was trained with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
Triangle104/Llama-3.1-Nemotron-Nano-8B-v1-Q5_K_M-GGUF	Triangle104	2025-05-03T15:32:44Z	0	0	transformers	[ "transformers", "gguf", "nvidia", "llama-3", "pytorch", "llama-cpp", "gguf-my-repo", "text-generation", "en", "base_model:nvidia/Llama-3.1-Nemotron-Nano-8B-v1", "base_model:quantized:nvidia/Llama-3.1-Nemotron-Nano-8B-v1", "license:other", "endpoints_compatible", "region:us", "conversational" ]	text-generation	2025-05-03T15:00:56Z	--- base_model: nvidia/Llama-3.1-Nemotron-Nano-8B-v1 language: - en library_name: transformers license: other license_name: nvidia-open-model-license license_link: https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/ pipeline_tag: text-generation tags: - nvidia - llama-3 - pytorch - llama-cpp - gguf-my-repo --- # Triangle104/Llama-3.1-Nemotron-Nano-8B-v1-Q5_K_M-GGUF This model was converted to GGUF format from [`nvidia/Llama-3.1-Nemotron-Nano-8B-v1`](https://huggingface.co/nvidia/Llama-3.1-Nemotron-Nano-8B-v1) 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/nvidia/Llama-3.1-Nemotron-Nano-8B-v1) for more details on the model. --- Llama-3.1-Nemotron-Nano-8B-v1 is a large language model (LLM) which is a derivative of Meta Llama-3.1-8B-Instruct (AKA the reference model). It is a reasoning model that is post trained for reasoning, human chat preferences, and tasks, such as RAG and tool calling. Llama-3.1-Nemotron-Nano-8B-v1 is a model which offers a great tradeoff between model accuracy and efficiency. It is created from Llama 3.1 8B Instruct and offers improvements in model accuracy. The model fits on a single RTX GPU and can be used locally. The model supports a context length of 128K. This model underwent a multi-phase post-training process to enhance both its reasoning and non-reasoning capabilities. This includes a supervised fine-tuning stage for Math, Code, Reasoning, and Tool Calling as well as multiple reinforcement learning (RL) stages using REINFORCE (RLOO) and Online Reward-aware Preference Optimization (RPO) algorithms for both chat and instruction-following. The final model checkpoint is obtained after merging the final SFT and Online RPO checkpoints. Improved using Qwen. --- ## 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 Triangle104/Llama-3.1-Nemotron-Nano-8B-v1-Q5_K_M-GGUF --hf-file llama-3.1-nemotron-nano-8b-v1-q5_k_m.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo Triangle104/Llama-3.1-Nemotron-Nano-8B-v1-Q5_K_M-GGUF --hf-file llama-3.1-nemotron-nano-8b-v1-q5_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 Triangle104/Llama-3.1-Nemotron-Nano-8B-v1-Q5_K_M-GGUF --hf-file llama-3.1-nemotron-nano-8b-v1-q5_k_m.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo Triangle104/Llama-3.1-Nemotron-Nano-8B-v1-Q5_K_M-GGUF --hf-file llama-3.1-nemotron-nano-8b-v1-q5_k_m.gguf -c 2048 ```
sweet-sour-pig/thro	sweet-sour-pig	2025-05-03T15:30:32Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-classification", "generated_from_trainer", "base_model:meta-llama/Llama-3.2-1B", "base_model:finetune:meta-llama/Llama-3.2-1B", "license:llama3.2", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-classification	2025-05-03T10:22:51Z	--- library_name: transformers license: llama3.2 base_model: meta-llama/Llama-3.2-1B tags: - generated_from_trainer metrics: - accuracy - f1 - recall model-index: - name: thro 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. --> # thro This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.0000 - Accuracy: 1.0 - F1: 1.0 - Recall: 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: 5e-05 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 2 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| F1 \| Recall \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:---:\|:------:\| \| 0.0 \| 1.0 \| 125 \| 0.0000 \| 1.0 \| 1.0 \| 1.0 \| \| 0.0 \| 2.0 \| 250 \| 0.0000 \| 1.0 \| 1.0 \| 1.0 \| ### Framework versions - Transformers 4.47.0 - Pytorch 2.5.1+cu121 - Datasets 3.3.1 - Tokenizers 0.21.0
OOOss/ru-ner-model	OOOss	2025-05-03T15:29:51Z	0	0	transformers	[ "transformers", "safetensors", "xlm-roberta", "token-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	token-classification	2025-05-03T15:27:32Z	--- 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]
Hachipo/OpenCoder-8B-Base-MIFT-en_10000_2	Hachipo	2025-05-03T15:29:47Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "trl", "sft", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-05-03T15:26:06Z	--- library_name: transformers tags: - trl - sft --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
phospho-app/anthonyav-so100-lego-v3-caopgh0iqe	phospho-app	2025-05-03T15:22:21Z	0	0	null	[ "safetensors", "gr00t_n1", "phosphobot", "gr00t", "region:us" ]	null	2025-05-03T14:46:37Z	--- tags: - phosphobot - gr00t task_categories: - robotics --- # gr00t Model - phospho Training Pipeline ## This model was trained using phospho. Training was successfull, try it out on your robot! ## Training parameters: - Dataset: [anthonyav/so100-lego-v3](https://huggingface.co/datasets/anthonyav/so100-lego-v3) - Wandb run URL: None - Epochs: 10 - Batch size: 64 - Training steps: None 📖 Get Started: [docs.phospho.ai](https://docs.phospho.ai?utm_source=replicate_groot_training_pipeline) 🤖 Get your robot: [robots.phospho.ai](https://robots.phospho.ai?utm_source=replicate_groot_training_pipeline)
mlx-community/Qwen3-8B-Base-bf16	mlx-community	2025-05-03T15:15:47Z	0	0	mlx	[ "mlx", "safetensors", "qwen3", "text-generation", "conversational", "base_model:Qwen/Qwen3-8B-Base", "base_model:finetune:Qwen/Qwen3-8B-Base", "license:apache-2.0", "region:us" ]	text-generation	2025-05-03T15:11:03Z	--- license: apache-2.0 library_name: mlx tags: - mlx pipeline_tag: text-generation base_model: Qwen/Qwen3-8B-Base --- # mlx-community/Qwen3-8B-Base-bf16 This model [mlx-community/Qwen3-8B-Base-bf16](https://huggingface.co/mlx-community/Qwen3-8B-Base-bf16) was converted to MLX format from [Qwen/Qwen3-8B-Base](https://huggingface.co/Qwen/Qwen3-8B-Base) using mlx-lm version 0.24.0. ## Use with mlx ```bash pip install mlx-lm ``` ```python from mlx_lm import load, generate model, tokenizer = load("mlx-community/Qwen3-8B-Base-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) ```
trongg/lora-c46bb480-76cc-4d4e-9fec-77ef5c320ce4-1400	trongg	2025-05-03T15:15:31Z	0	0	peft	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:unsloth/mistral-7b", "base_model:adapter:unsloth/mistral-7b", "region:us" ]	null	2025-05-03T15:13:01Z	--- base_model: unsloth/mistral-7b 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
Shengkun/DarwinLM-4.6B-Llama3.1-8B-Pruned-Masked	Shengkun	2025-05-03T15:07:11Z	157	0	null	[ "safetensors", "llama", "license:apache-2.0", "region:us" ]	null	2025-04-13T06:26:56Z	--- license: apache-2.0 --- This is DarwinLM pruned from Llama3.1-8B. The model is masked that the pruned weights are set as 0 while the remaining weights are the same as the original model. The shape of all weights are the same as the original model. ```python # To use the model from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Shengkun/DarwinLM-4.6B-Llama3.1-8B-Pruned-Masked") ``` 4.6B \| Model \| Method \| Param. \| SciQ \| PIQA \| WG \| ArcE \| ArcC \| HS \| LogiQA \| BoolQ \| MMLU \| Avg \| \|-----------------\|------------------------\|--------\|------\|------\|------\|------\|------\|------\|--------\|-------\|------\|------\| \| Llama-3.1-8B \| Dense \| 8B \| 96.3 \| 81.2 \| 74.3 \| 81.4 \| 58.2 \| 81.7 \| 31.1 \| 84.0 \| 65.2 \| 72.8 \| \| \| Uniform \| 4.5B \| 29.1 \| 53.6 \| 51.7 \| 26.0 \| 23.6 \| 27.1 \| 25.5 \| 62.1 \| 25.7 \| 36.1 \| \| \| ZipLM \| 6B \| 65.5 \| 60.6 \| 56.0 \| 40.2 \| 34.4 \| 34.4 \| 28.1 \| 63.0 \| 27.9 \| 45.7 \| \| \| DarwinLM (one-shot) \| 4.6B \| 84.9 \| 69.4 \| 57.3 \| 59.6 \| 34.2 \| 44.6 \| 24.1 \| 62.2 \| 28.5 \| 51.6 \| \| \| OLMO (2.5T) \| 7B \| 92.8 \| 79.4 \| 70.4 \| 73.3 \| 44.9 \| 77.1 \| 27.9 \| 72.5 \| 28.3 \| 62.9 \| \| \| DarwinLM (10.0B) \| 4.6B \| 93.2 \| 74.8 \| 67.4 \| 73.2 \| 51.6 \| 71.3 \| 30.7 \| 71.1 \| 40.6 \| 63.7 \|
jdchang/full-with-label-bs-1024-sg-2-step-486	jdchang	2025-05-03T14:59:33Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "arxiv:1910.09700", "text-generation-inference", "endpoints_compatible", "region:us" ]	null	2025-05-03T14:59:09Z	--- 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]
ridwanridus/ridus	ridwanridus	2025-05-03T14:55:21Z	0	0	null	[ "license:apache-2.0", "region:us" ]	null	2025-05-03T14:55:21Z	--- license: apache-2.0 ---
lisabdunlap/Llama-3.1-8B-Instruct-unsloth-bnb-4bit-r32-e10-lr0.0002-mixed-actors_reviews_markdown-new	lisabdunlap	2025-05-03T14:50:39Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "text-generation-inference", "unsloth", "trl", "conversational", "en", "base_model:unsloth/Llama-3.1-8B-Instruct-unsloth-bnb-4bit", "base_model:finetune:unsloth/Llama-3.1-8B-Instruct-unsloth-bnb-4bit", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2025-05-03T14:48:24Z	--- base_model: unsloth/Llama-3.1-8B-Instruct-unsloth-bnb-4bit tags: - text-generation-inference - transformers - unsloth - llama - trl license: apache-2.0 language: - en --- # Uploaded model - Developed by: lisabdunlap - License: apache-2.0 - Finetuned from model : unsloth/Llama-3.1-8B-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)
Benson87/min_model	Benson87	2025-05-03T14:48:50Z	0	0	null	[ "pytorch", "region:us" ]	null	2025-05-03T14:34:54Z	# Min Model Denne model er oprettet som test og placeholder. Du kan erstatte pytorch_model.bin med en trænet model. ## Struktur - pytorch_model.bin: Dummy eller rigtig model - config.json: Krævet for kompatibilitet ## Status 🚧 Under opbygning – erstattes senere med ægte weights
ASethi04/meta-llama-Llama-3.1-8B-hellaswag-first-lora-4-0.0001-same-prompt-template	ASethi04	2025-05-03T14:47:29Z	0	0	transformers	[ "transformers", "safetensors", "generated_from_trainer", "trl", "sft", "base_model:meta-llama/Llama-3.1-8B", "base_model:finetune:meta-llama/Llama-3.1-8B", "endpoints_compatible", "region:us" ]	null	2025-05-03T10:52:44Z	--- base_model: meta-llama/Llama-3.1-8B library_name: transformers model_name: meta-llama-Llama-3.1-8B-hellaswag-first-lora-4-0.0001-same-prompt-template tags: - generated_from_trainer - trl - sft licence: license --- # Model Card for meta-llama-Llama-3.1-8B-hellaswag-first-lora-4-0.0001-same-prompt-template This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B). 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="ASethi04/meta-llama-Llama-3.1-8B-hellaswag-first-lora-4-0.0001-same-prompt-template", 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/torchql-org/huggingface/runs/rxgjo7gt) This model was trained with SFT. ### Framework versions - TRL: 0.16.1 - Transformers: 4.51.2 - Pytorch: 2.6.0 - Datasets: 3.5.0 - Tokenizers: 0.21.1 ## Citations Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
phuongnam06052002/Notnow	phuongnam06052002	2025-05-03T14:44:54Z	0	0	null	[ "license:bigscience-openrail-m", "region:us" ]	null	2025-05-03T14:44:54Z	--- license: bigscience-openrail-m ---

Subsets and Splits