Split (1)

train · 840k rows

modelId string	author string	last_modified timestamp[us, tz=UTC]	downloads int64	likes int64	library_name string	tags sequence	pipeline_tag string	createdAt timestamp[us, tz=UTC]	card string
maksf8486/ae9a31cd-dfa6-4917-931b-59657eb3ae43	maksf8486	2025-04-29T04:39:13Z	0	0	peft	[ "peft", "safetensors", "llama", "axolotl", "generated_from_trainer", "base_model:WhiteRabbitNeo/Llama-3-WhiteRabbitNeo-8B-v2.0", "base_model:adapter:WhiteRabbitNeo/Llama-3-WhiteRabbitNeo-8B-v2.0", "license:llama3", "8-bit", "bitsandbytes", "region:us" ]	null	2025-04-29T03:34:30Z	--- library_name: peft license: llama3 base_model: WhiteRabbitNeo/Llama-3-WhiteRabbitNeo-8B-v2.0 tags: - axolotl - generated_from_trainer model-index: - name: ae9a31cd-dfa6-4917-931b-59657eb3ae43 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: WhiteRabbitNeo/Llama-3-WhiteRabbitNeo-8B-v2.0 bf16: true chat_template: llama3 dataset_prepared_path: null datasets: - data_files: - 0f595e9ff2bcd098_train_data.json ds_type: json format: custom path: /workspace/input_data/0f595e9ff2bcd098_train_data.json type: field_input: intent field_instruction: instruction field_output: response format: '{instruction} {input}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null dpo: beta: 0.1 enabled: true group_by_length: false rank_loss: false reference_model: 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: 0.5 group_by_length: false hub_model_id: maksf8486/ae9a31cd-dfa6-4917-931b-59657eb3ae43 hub_repo: null hub_strategy: end hub_token: null learning_rate: 5.0e-06 load_in_4bit: false 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: 200 micro_batch_size: 8 mixed_precision: bf16 mlflow_experiment_name: /tmp/0f595e9ff2bcd098_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: 1024 strict: false tf32: false tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: aa0ca05d-e3de-4bfb-9606-737b2bd623fd wandb_project: s56-2 wandb_run: your_name wandb_runid: aa0ca05d-e3de-4bfb-9606-737b2bd623fd warmup_steps: 5 weight_decay: 0.01 xformers_attention: true ``` </details><br> # ae9a31cd-dfa6-4917-931b-59657eb3ae43 This model is a fine-tuned version of [WhiteRabbitNeo/Llama-3-WhiteRabbitNeo-8B-v2.0](https://huggingface.co/WhiteRabbitNeo/Llama-3-WhiteRabbitNeo-8B-v2.0) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.4897 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-06 - train_batch_size: 8 - eval_batch_size: 8 - 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: 200 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| 0.4332 \| 0.0068 \| 200 \| 0.4897 \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
IvesDan/Mhmedbt	IvesDan	2025-04-29T04:37:30Z	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	2025-04-29T03:56:55Z	--- 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: Mhmedbt --- # Mhmedbt <Gallery /> ## About this LoRA This is a [LoRA](https://replicate.com/docs/guides/working-with-loras) for the FLUX.1-dev text-to-image model. It can be used with diffusers or ComfyUI. It was trained on [Replicate](https://replicate.com/) using AI toolkit: https://replicate.com/ostris/flux-dev-lora-trainer/train ## Trigger words You should use `Mhmedbt` to trigger the image generation. ## Run this LoRA with an API using Replicate ```py import replicate input = { "prompt": "Mhmedbt", "lora_weights": "https://huggingface.co/IvesDan/Mhmedbt/resolve/main/lora.safetensors" } output = replicate.run( "black-forest-labs/flux-dev-lora", input=input ) for index, item in enumerate(output): with open(f"output_{index}.webp", "wb") as file: file.write(item.read()) ``` ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers) ```py from diffusers import AutoPipelineForText2Image import torch pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda') pipeline.load_lora_weights('IvesDan/Mhmedbt', weight_name='lora.safetensors') image = pipeline('Mhmedbt').images[0] ``` For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters) ## Training details - Steps: 3000 - Learning rate: 0.0004 - LoRA rank: 16 ## Contribute your own examples You can use the [community tab](https://huggingface.co/IvesDan/Mhmedbt/discussions) to add images that show off what you’ve made with this LoRA.
roadus/Foundation-Sec-8B-Q4_K_M-GGUF	roadus	2025-04-29T04:25:09Z	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	2025-04-29T04:24:46Z	--- 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 --- # roadus/Foundation-Sec-8B-Q4_K_M-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 roadus/Foundation-Sec-8B-Q4_K_M-GGUF --hf-file foundation-sec-8b-q4_k_m.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo roadus/Foundation-Sec-8B-Q4_K_M-GGUF --hf-file foundation-sec-8b-q4_k_m.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo roadus/Foundation-Sec-8B-Q4_K_M-GGUF --hf-file foundation-sec-8b-q4_k_m.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo roadus/Foundation-Sec-8B-Q4_K_M-GGUF --hf-file foundation-sec-8b-q4_k_m.gguf -c 2048 ```
vcabeli/Qwen2.5-1.5B-Open-R1-GRPO	vcabeli	2025-04-29T04:23:58Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "generated_from_trainer", "open-r1", "trl", "grpo", "conversational", "dataset:OwkinZero/tcga-signature-qa", "arxiv:2402.03300", "base_model:Qwen/Qwen2.5-1.5B-Instruct", "base_model:finetune:Qwen/Qwen2.5-1.5B-Instruct", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-03-08T07:41:16Z	--- base_model: Qwen/Qwen2.5-1.5B-Instruct datasets: OwkinZero/tcga-signature-qa library_name: transformers model_name: Qwen2.5-1.5B-Open-R1-GRPO tags: - generated_from_trainer - open-r1 - trl - grpo licence: license --- # Model Card for Qwen2.5-1.5B-Open-R1-GRPO This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the [OwkinZero/tcga-signature-qa](https://huggingface.co/datasets/OwkinZero/tcga-signature-qa) dataset. It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="vcabeli/Qwen2.5-1.5B-Open-R1-GRPO", 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/vincent-cabeli-owkin/huggingface/runs/5mqqfcyo) This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300). ### Framework versions - TRL: 0.17.0.dev0 - Transformers: 4.48.3 - Pytorch: 2.6.0 - Datasets: 3.5.0 - Tokenizers: 0.21.1 ## Citations Cite GRPO as: ```bibtex @article{zhihong2024deepseekmath, title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}}, author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo}, year = 2024, eprint = {arXiv:2402.03300}, } ``` Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
k1h0/llama3.1-8B-Instruct-query_nsx	k1h0	2025-04-29T04:20:04Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "llama-factory", "freeze", "generated_from_trainer", "conversational", "base_model:meta-llama/Llama-3.1-8B-Instruct", "base_model:finetune:meta-llama/Llama-3.1-8B-Instruct", "license:other", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-04-29T04:16:18Z	--- library_name: transformers license: other base_model: meta-llama/Llama-3.1-8B-Instruct tags: - llama-factory - freeze - generated_from_trainer model-index: - name: llama_nsx 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_nsx 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 the codes_330k_nsx dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 16 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - num_devices: 4 - gradient_accumulation_steps: 8 - total_train_batch_size: 512 - total_eval_batch_size: 32 - 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 - num_epochs: 1.0 ### Training results ### Framework versions - Transformers 4.48.2 - Pytorch 2.5.1+cu124 - Datasets 3.2.0 - Tokenizers 0.21.0
tflsxyy/Qwen3-235B-A22B-IQ2_S	tflsxyy	2025-04-29T04:19:35Z	0	0	transformers	[ "transformers", "gguf", "qwen3", "qwen", "unsloth", "en", "base_model:Qwen/Qwen3-235B-A22B", "base_model:quantized:Qwen/Qwen3-235B-A22B", "license:apache-2.0", "endpoints_compatible", "region:us", "imatrix", "conversational" ]	null	2025-04-29T04:09:51Z	--- base_model: Qwen/Qwen3-235B-A22B language: - en library_name: transformers license_link: https://huggingface.co/Qwen/Qwen3-235B-A22B/blob/main/LICENSE license: apache-2.0 tags: - qwen3 - qwen - unsloth - transformers --- Attn: Q4_K Experts: IQ2_S Please refer to [unsloth](https://huggingface.co/unsloth/Qwen3-235B-A22B-GGUF) for running this model. ```bash ./llama.cpp/llama-quantize --imatrix /work/yanzhi_group/models/unsloth/Qwen3-235B-A22B-GGUF/imatrix_unsloth.dat --keep-split /work/yanzhi_group/models/unsloth/Qwen3-235B-A22B-GGUF/BF16/Qwen3-235B-A22B-BF16-00001-of-00010.gguf /scratch/xie.yany/Qwen/Qwen3-235B-A22B-IQ2_S/Qwen3-235B-A22B-IQ2_S.gguf IQ2_S ```
dahara1/gemma-3-1b-it-qat-japanese-imatrix	dahara1	2025-04-29T04:14:47Z	1,575	0	null	[ "gguf", "ja", "endpoints_compatible", "region:us", "imatrix", "conversational" ]	null	2025-04-23T04:08:59Z	--- language: - ja --- [google/gemma-3-12b-it-qat-q4_0-unquantized](https://huggingface.co/google/gemma-3-12b-it-qat-q4_0-unquantized)を[日本語が多く含まれるimatrixを使って量子化](https://huggingface.co/dahara1/imatrix-jpn-test)したモデルです This is a model that quantizes [google/gemma-3-12b-it-qat-q4_0-unquantized](https://huggingface.co/google/gemma-3-12b-it-qat-q4_0-unquantized) using an [imatrix that contains a lot of Japanese](https://huggingface.co/dahara1/imatrix-jpn-test).. https://huggingface.co/dahara1/imatrix-jpn-test). 最新の[llama.cpp](https://github.com/ggml-org/llama.cpp)を使って動かしてください。 Please use the latest [llama.cpp](https://github.com/ggml-org/llama.cpp). 投機的デコーディングで速度を向上させる使い方の例 Example of Speculative Decoding for speed up. 1Bモデルには視覚機能は含まれていません There is no vision ability in 1B model. ``` ./llama-server -m ./gemma-3-12b-it-qat-q4_0-japanese-imatrix-Q4_0.gguf -md ./gemma-3-1b-it-qat-q4_0-japanese-imatrix-Q4_K-f16.gguf -e -ngld 99 -ngl 99 ```
Merthius/flux-lora-bodyinteractions	Merthius	2025-04-29T04:13:21Z	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	2025-04-29T01:06:22Z	--- 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: MFLBI --- # Flux Lora Bodyinteractions <Gallery /> ## About this LoRA This is a [LoRA](https://replicate.com/docs/guides/working-with-loras) for the FLUX.1-dev text-to-image model. It can be used with diffusers or ComfyUI. It was trained on [Replicate](https://replicate.com/) using AI toolkit: https://replicate.com/ostris/flux-dev-lora-trainer/train ## Trigger words You should use `MFLBI` to trigger the image generation. ## Run this LoRA with an API using Replicate ```py import replicate input = { "prompt": "MFLBI", "lora_weights": "https://huggingface.co/Merthius/flux-lora-bodyinteractions/resolve/main/lora.safetensors" } output = replicate.run( "black-forest-labs/flux-dev-lora", input=input ) for index, item in enumerate(output): with open(f"output_{index}.webp", "wb") as file: file.write(item.read()) ``` ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers) ```py from diffusers import AutoPipelineForText2Image import torch pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda') pipeline.load_lora_weights('Merthius/flux-lora-bodyinteractions', weight_name='lora.safetensors') image = pipeline('MFLBI').images[0] ``` For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters) ## Training details - Steps: 3000 - Learning rate: 0.0004 - LoRA rank: 64 ## Contribute your own examples You can use the [community tab](https://huggingface.co/Merthius/flux-lora-bodyinteractions/discussions) to add images that show off what you’ve made with this LoRA.
WhoCares258/my_awesome_model	WhoCares258	2025-04-29T04:04:01Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "base_model:distilbert/distilbert-base-uncased", "base_model:finetune:distilbert/distilbert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2025-04-29T02:30:54Z	--- library_name: transformers license: apache-2.0 base_model: distilbert-base-uncased tags: - generated_from_trainer metrics: - accuracy model-index: - name: my_awesome_model results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # my_awesome_model This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.2290 - Accuracy: 0.9322 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 2 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 0.2215 \| 1.0 \| 1563 \| 0.2051 \| 0.9202 \| \| 0.1468 \| 2.0 \| 3126 \| 0.2290 \| 0.9322 \| ### Framework versions - Transformers 4.48.3 - Pytorch 2.5.1+cu124 - Datasets 3.5.1 - Tokenizers 0.21.0
jmalejandrob79/nrmyng01	jmalejandrob79	2025-04-29T04:03:34Z	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	2025-04-25T15:08:49Z	--- 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: nrmyng01 --- # Nrmyng01 <Gallery /> ## About this LoRA This is a [LoRA](https://replicate.com/docs/guides/working-with-loras) for the FLUX.1-dev text-to-image model. It can be used with diffusers or ComfyUI. It was trained on [Replicate](https://replicate.com/) using AI toolkit: https://replicate.com/ostris/flux-dev-lora-trainer/train ## Trigger words You should use `nrmyng01` to trigger the image generation. ## Run this LoRA with an API using Replicate ```py import replicate input = { "prompt": "nrmyng01", "lora_weights": "https://huggingface.co/jmalejandrob79/nrmyng01/resolve/main/lora.safetensors" } output = replicate.run( "black-forest-labs/flux-dev-lora", input=input ) for index, item in enumerate(output): with open(f"output_{index}.webp", "wb") as file: file.write(item.read()) ``` ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers) ```py from diffusers import AutoPipelineForText2Image import torch pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda') pipeline.load_lora_weights('jmalejandrob79/nrmyng01', weight_name='lora.safetensors') image = pipeline('nrmyng01').images[0] ``` For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters) ## Training details - Steps: 3000 - Learning rate: 0.0004 - LoRA rank: 16 ## Contribute your own examples You can use the [community tab](https://huggingface.co/jmalejandrob79/nrmyng01/discussions) to add images that show off what you’ve made with this LoRA.
sharon1331/Deepseek-llm-7b-finetuned	sharon1331	2025-04-29T04:01:57Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-04-29T00:27:04Z	--- 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]
Hirai-Labs/YOLO	Hirai-Labs	2025-04-29T04:00:45Z	0	0	ultralytics	[ "ultralytics", "yolov8", "object-detection", "computer-vision", "opencv", "openvino", "pytorch", "en", "dataset:coco", "license:agpl-3.0", "region:us" ]	object-detection	2025-01-09T06:45:58Z	--- language: en license: agpl-3.0 tags: - yolov8 - object-detection - computer-vision - opencv - openvino - pytorch - ultralytics datasets: - coco library_name: ultralytics pipeline_tag: object-detection inference: true --- # YOLO Model Repository A collection of YOLOv8 models for various object detection tasks, optimized for different deployment scenarios. ## Available Models ### Person Detection Models - Nano: Lightweight model for person detection, optimized for edge devices - Format: OpenVINO - Size: 640x640 - Task: Detection - Small: Better accuracy for person detection with reasonable performance - Format: OpenVINO - Size: 640x640 - Task: Detection ### Vehicle Detection Models - Small: Model for accurate vehicle detection - Format: OpenVINO - Size: 640x640 - Task: Detection ### Indonesian ID Card (KTP) Detection - Nano: Specialized model for detecting Indonesian ID cards - Format: PyTorch (.pt) - Size: 640x640 - Task: Detection ## Model Architecture These models are based on YOLOv8, the latest version of the YOLO (You Only Look Once) family of real-time object detectors. Key features: - Anchor-free detection system - Improved backbone and neck architecture - Better performance-to-size ratio than previous YOLO versions ## Model Performance (Still dummy, pls update the real ones later) \| Model \| Size \| [email protected] \| Inference Time (CPU) \| Inference Time (GPU) \| \|-------\|------\|---------\|---------------------\|---------------------\| \| Person Nano \| 640x640 \| 0.85 \| 15ms \| 5ms \| \| Person Small \| 640x640 \| 0.89 \| 25ms \| 8ms \| \| Vehicle Small \| 640x640 \| 0.87 \| 28ms \| 9ms \| \| KTP Nano \| 640x640 \| 0.92 \| 18ms \| 6ms \|
infogeo/4ecdd22f-aa7d-4e89-bd8d-6ab95c8e7392	infogeo	2025-04-29T03:55:46Z	0	0	peft	[ "peft", "safetensors", "llama", "axolotl", "generated_from_trainer", "base_model:WhiteRabbitNeo/Llama-3-WhiteRabbitNeo-8B-v2.0", "base_model:adapter:WhiteRabbitNeo/Llama-3-WhiteRabbitNeo-8B-v2.0", "license:llama3", "4-bit", "bitsandbytes", "region:us" ]	null	2025-04-29T03:35:36Z	--- library_name: peft license: llama3 base_model: WhiteRabbitNeo/Llama-3-WhiteRabbitNeo-8B-v2.0 tags: - axolotl - generated_from_trainer model-index: - name: 4ecdd22f-aa7d-4e89-bd8d-6ab95c8e7392 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: WhiteRabbitNeo/Llama-3-WhiteRabbitNeo-8B-v2.0 bf16: true chat_template: llama3 dataset_prepared_path: /workspace/axolotl datasets: - data_files: - 0f595e9ff2bcd098_train_data.json ds_type: json format: custom path: /workspace/input_data/0f595e9ff2bcd098_train_data.json type: field_input: intent field_instruction: instruction field_output: response 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: infogeo/4ecdd22f-aa7d-4e89-bd8d-6ab95c8e7392 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: 8 mixed_precision: bf16 mlflow_experiment_name: /tmp/0f595e9ff2bcd098_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: 1024 strict: false tf32: false tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: aa0ca05d-e3de-4bfb-9606-737b2bd623fd wandb_project: s56-28 wandb_run: your_name wandb_runid: aa0ca05d-e3de-4bfb-9606-737b2bd623fd warmup_steps: 5 weight_decay: 0.01 xformers_attention: true ``` </details><br> # 4ecdd22f-aa7d-4e89-bd8d-6ab95c8e7392 This model is a fine-tuned version of [WhiteRabbitNeo/Llama-3-WhiteRabbitNeo-8B-v2.0](https://huggingface.co/WhiteRabbitNeo/Llama-3-WhiteRabbitNeo-8B-v2.0) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.6835 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-06 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - 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 \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| 0.6342 \| 0.0051 \| 150 \| 0.6835 \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
ridalefdali/llama_1b_finetuned	ridalefdali	2025-04-29T03:53:06Z	0	0	transformers	[ "transformers", "gguf", "llama", "text-generation-inference", "unsloth", "en", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	null	2025-04-29T03:52:30Z	--- base_model: unsloth/llama-3.2-1b-instruct-unsloth-bnb-4bit tags: - text-generation-inference - transformers - unsloth - llama - gguf license: apache-2.0 language: - en --- # Uploaded model - Developed by: ridalefdali - License: apache-2.0 - Finetuned from model : unsloth/llama-3.2-1b-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)
hleAtKeeper/skewed-threat-classifier-BERT	hleAtKeeper	2025-04-29T03:50:16Z	46	0	transformers	[ "transformers", "safetensors", "bert", "text-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2025-04-22T22:08:08Z	--- 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]
s94lopez/rl_course_vizdoom_health_gathering_supreme	s94lopez	2025-04-29T03:46:01Z	0	0	sample-factory	[ "sample-factory", "tensorboard", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2025-04-28T23:19:14Z	--- library_name: sample-factory tags: - deep-reinforcement-learning - reinforcement-learning - sample-factory model-index: - name: APPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: doom_health_gathering_supreme type: doom_health_gathering_supreme metrics: - type: mean_reward value: 13.77 +/- 5.00 name: mean_reward verified: false --- A(n) APPO model trained on the doom_health_gathering_supreme environment. This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory. Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/ ## Downloading the model After installing Sample-Factory, download the model with: ``` python -m sample_factory.huggingface.load_from_hub -r s94lopez/rl_course_vizdoom_health_gathering_supreme ``` ## Using the model To run the model after download, use the `enjoy` script corresponding to this environment: ``` python -m <path.to.enjoy.module> --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme ``` You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag. See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details ## Training with this model To continue training with this model, use the `train` script corresponding to this environment: ``` python -m <path.to.train.module> --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000 ``` Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
Nerva1228/xiaobaobao	Nerva1228	2025-04-29T03:39:23Z	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	2025-04-29T02:52:40Z	--- 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: xiaobaobao --- # Xiaobaobao <Gallery /> ## About this LoRA This is a [LoRA](https://replicate.com/docs/guides/working-with-loras) for the FLUX.1-dev text-to-image model. It can be used with diffusers or ComfyUI. It was trained on [Replicate](https://replicate.com/) using AI toolkit: https://replicate.com/ostris/flux-dev-lora-trainer/train ## Trigger words You should use `xiaobaobao` to trigger the image generation. ## Run this LoRA with an API using Replicate ```py import replicate input = { "prompt": "xiaobaobao", "lora_weights": "https://huggingface.co/Nerva1228/xiaobaobao/resolve/main/lora.safetensors" } output = replicate.run( "black-forest-labs/flux-dev-lora", input=input ) for index, item in enumerate(output): with open(f"output_{index}.webp", "wb") as file: file.write(item.read()) ``` ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers) ```py from diffusers import AutoPipelineForText2Image import torch pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda') pipeline.load_lora_weights('Nerva1228/xiaobaobao', weight_name='lora.safetensors') image = pipeline('xiaobaobao').images[0] ``` For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters) ## Training details - Steps: 2000 - Learning rate: 0.0004 - LoRA rank: 16 ## Contribute your own examples You can use the [community tab](https://huggingface.co/Nerva1228/xiaobaobao/discussions) to add images that show off what you’ve made with this LoRA.
taobao-mnn/Qwen3-32B-MNN	taobao-mnn	2025-04-29T03:37:08Z	0	0	null	[ "chat", "text-generation", "en", "license:apache-2.0", "region:us" ]	text-generation	2025-04-28T13:43:37Z	--- license: apache-2.0 language: - en pipeline_tag: text-generation tags: - chat --- # Qwen3-32B-MNN ## Introduction This model is a 4-bit quantized version of the MNN model exported from Qwen3-32B using [llmexport](https://github.com/alibaba/MNN/tree/master/transformers/llm/export). ## Download ```bash # install huggingface pip install huggingface ``` ```bash # shell download huggingface download --model 'taobao-mnn/Qwen3-32B-MNN' --local_dir 'path/to/dir' ``` ```python # SDK download from huggingface_hub import snapshot_download model_dir = snapshot_download('taobao-mnn/Qwen3-32B-MNN') ``` ```bash # git clone git clone https://www.modelscope.cn/taobao-mnn/Qwen3-32B-MNN ``` ## Usage ```bash # clone MNN source git clone https://github.com/alibaba/MNN.git # compile cd MNN mkdir build && cd build cmake .. -DMNN_LOW_MEMORY=true -DMNN_CPU_WEIGHT_DEQUANT_GEMM=true -DMNN_BUILD_LLM=true -DMNN_SUPPORT_TRANSFORMER_FUSE=true make -j # run ./llm_demo /path/to/Qwen3-32B-MNN/config.json prompt.txt ``` ## Document [MNN-LLM](https://mnn-docs.readthedocs.io/en/latest/transformers/llm.html#)
taobao-mnn/Qwen3-14B-MNN	taobao-mnn	2025-04-29T03:36:54Z	0	0	null	[ "chat", "text-generation", "en", "license:apache-2.0", "region:us" ]	text-generation	2025-04-28T13:26:41Z	--- license: apache-2.0 language: - en pipeline_tag: text-generation tags: - chat --- # Qwen3-14B-MNN ## Introduction This model is a 4-bit quantized version of the MNN model exported from Qwen3-14B using [llmexport](https://github.com/alibaba/MNN/tree/master/transformers/llm/export). ## Download ```bash # install huggingface pip install huggingface ``` ```bash # shell download huggingface download --model 'taobao-mnn/Qwen3-14B-MNN' --local_dir 'path/to/dir' ``` ```python # SDK download from huggingface_hub import snapshot_download model_dir = snapshot_download('taobao-mnn/Qwen3-14B-MNN') ``` ```bash # git clone git clone https://www.modelscope.cn/taobao-mnn/Qwen3-14B-MNN ``` ## Usage ```bash # clone MNN source git clone https://github.com/alibaba/MNN.git # compile cd MNN mkdir build && cd build cmake .. -DMNN_LOW_MEMORY=true -DMNN_CPU_WEIGHT_DEQUANT_GEMM=true -DMNN_BUILD_LLM=true -DMNN_SUPPORT_TRANSFORMER_FUSE=true make -j # run ./llm_demo /path/to/Qwen3-14B-MNN/config.json prompt.txt ``` ## Document [MNN-LLM](https://mnn-docs.readthedocs.io/en/latest/transformers/llm.html#)
TheGardener/MLP-pruner-ver3-activation-llama3.2-0.83B	TheGardener	2025-04-29T03:36:47Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-04-29T03:33:20Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
duyntnet/Qwen3-0.6B-imatrix-GGUF	duyntnet	2025-04-29T03:28:49Z	0	0	transformers	[ "transformers", "gguf", "imatrix", "Qwen3-0.6B", "text-generation", "en", "license:other", "region:us", "conversational" ]	text-generation	2025-04-29T03:19:28Z	--- license: other language: - en pipeline_tag: text-generation inference: false tags: - transformers - gguf - imatrix - Qwen3-0.6B --- Quantizations of https://huggingface.co/Qwen/Qwen3-0.6B ### Open source inference clients/UIs * [llama.cpp](https://github.com/ggerganov/llama.cpp) * [KoboldCPP](https://github.com/LostRuins/koboldcpp) * [text-generation-webui](https://github.com/oobabooga/text-generation-webui) * [ollama](https://github.com/ollama/ollama) * [jan](https://github.com/janhq/jan) * [GPT4All](https://github.com/nomic-ai/gpt4all) ### Closed source inference clients/UIs * [LM Studio](https://lmstudio.ai/) * [Backyard AI](https://backyard.ai/) * More will be added... --- # From original readme Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features: - Uniquely support of seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within single model, ensuring optimal performance across various scenarios. - Significantly enhancement in its reasoning capabilities, surpassing previous QwQ (in thinking mode) and Qwen2.5 instruct models (in non-thinking mode) on mathematics, code generation, and commonsense logical reasoning. - Superior human preference alignment, excelling in creative writing, role-playing, multi-turn dialogues, and instruction following, to deliver a more natural, engaging, and immersive conversational experience. - Expertise in agent capabilities, enabling precise integration with external tools in both thinking and unthinking modes and achieving leading performance among open-source models in complex agent-based tasks. - Support of 100+ languages and dialects with strong capabilities for multilingual instruction following and translation. ## Model Overview Qwen3-0.6B has the following features: - Type: Causal Language Models - Training Stage: Pretraining & Post-training - Number of Parameters: 0.6B - Number of Paramaters (Non-Embedding): 0.44B - Number of Layers: 28 - Number of Attention Heads (GQA): 16 for Q and 8 for KV - Context Length: 32,768 For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our [blog](https://qwenlm.github.io/blog/qwen3/), [GitHub](https://github.com/QwenLM/Qwen3), and [Documentation](https://qwen.readthedocs.io/en/latest/). > [!TIP] > If you encounter significant endless repetitions, please refer to the [Best Practices](#best-practices) section for optimal sampling parameters, and set the ``presence_penalty`` to 1.5. ## Quickstart The code of Qwen3 has been in the latest Hugging Face `transformers` and we advise you to use the latest version of `transformers`. With `transformers<4.51.0`, you will encounter the following error: ``` KeyError: 'qwen3' ``` The following contains a code snippet illustrating how to use the model generate content based on given inputs. ```python from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "Qwen/Qwen3-0.6B" # load the tokenizer and the model tokenizer = AutoTokenizer.from_pretrained(model_name) model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype="auto", device_map="auto" ) # prepare the model input prompt = "Give me a short introduction to large language model." messages = [ {"role": "user", "content": prompt} ] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, enable_thinking=True # Switches between thinking and non-thinking modes. Default is True. ) model_inputs = tokenizer([text], return_tensors="pt").to(model.device) # conduct text completion generated_ids = model.generate( model_inputs, max_new_tokens=32768 ) output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() # parsing thinking content try: # rindex finding 151668 (</think>) index = len(output_ids) - output_ids[::-1].index(151668) except ValueError: index = 0 thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n") content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n") print("thinking content:", thinking_content) print("content:", content) ``` For deployment, you can use `sglang>=0.4.6.post1` or `vllm>=0.8.4` or to create an OpenAI-compatible API endpoint: - SGLang: ```shell python -m sglang.launch_server --model-path Qwen/Qwen3-0.6B --reasoning-parser qwen3 ``` - vLLM: ```shell vllm serve Qwen/Qwen3-0.6B --enable-reasoning --reasoning-parser deepseek_r1 ``` For local use, applications such as llama.cpp, Ollama, LMStudio, and MLX-LM have also supported Qwen3. ## Switching Between Thinking and Non-Thinking Mode > [!TIP] > The `enable_thinking` switch is also available in APIs created by SGLang and vLLM. > Please refer to our documentation for [SGLang](https://qwen.readthedocs.io/en/latest/deployment/sglang.html#thinking-non-thinking-modes) and [vLLM](https://qwen.readthedocs.io/en/latest/deployment/vllm.html#thinking-non-thinking-modes) users. ### `enable_thinking=True` By default, Qwen3 has thinking capabilities enabled, similar to QwQ-32B. This means the model will use its reasoning abilities to enhance the quality of generated responses. For example, when explicitly setting `enable_thinking=True` or leaving it as the default value in `tokenizer.apply_chat_template`, the model will engage its thinking mode. ```python text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, enable_thinking=True # True is the default value for enable_thinking ) ``` In this mode, the model will generate think content wrapped in a `<think>...</think>` block, followed by the final response. > [!NOTE] > For thinking mode, use `Temperature=0.6`, `TopP=0.95`, `TopK=20`, and `MinP=0` (the default setting in `generation_config.json`). DO NOT use greedy decoding, as it can lead to performance degradation and endless repetitions. For more detailed guidance, please refer to the [Best Practices](#best-practices) section. ### `enable_thinking=False` We provide a hard switch to strictly disable the model's thinking behavior, aligning its functionality with the previous Qwen2.5-Instruct models. This mode is particularly useful in scenarios where disabling thinking is essential for enhancing efficiency. ```python text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, enable_thinking=False # Setting enable_thinking=False disables thinking mode ) ``` In this mode, the model will not generate any think content and will not include a `<think>...</think>` block. > [!NOTE] > For non-thinking mode, we suggest using `Temperature=0.7`, `TopP=0.8`, `TopK=20`, and `MinP=0`. For more detailed guidance, please refer to the [Best Practices](#best-practices) section. ### Advanced Usage: Switching Between Thinking and Non-Thinking Modes via User Input We provide a soft switch mechanism that allows users to dynamically control the model's behavior when `enable_thinking=True`. Specifically, you can add `/think` and `/no_think` to user prompts or system messages to switch the model's thinking mode from turn to turn. The model will follow the most recent instruction in multi-turn conversations. Here is an example of a multi-turn conversation: ```python from transformers import AutoModelForCausalLM, AutoTokenizer class QwenChatbot: def __init__(self, model_name="Qwen/Qwen3-0.6B"): self.tokenizer = AutoTokenizer.from_pretrained(model_name) self.model = AutoModelForCausalLM.from_pretrained(model_name) self.history = [] def generate_response(self, user_input): messages = self.history + [{"role": "user", "content": user_input}] text = self.tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) inputs = self.tokenizer(text, return_tensors="pt") response_ids = self.model.generate(inputs, max_new_tokens=32768)[0][len(inputs.input_ids[0]):].tolist() response = self.tokenizer.decode(response_ids, skip_special_tokens=True) # Update history self.history.append({"role": "user", "content": user_input}) self.history.append({"role": "assistant", "content": response}) return response # Example Usage if __name__ == "__main__": chatbot = QwenChatbot() # First input (without /think or /no_think tags, thinking mode is enabled by default) user_input_1 = "How many r's in strawberries?" print(f"User: {user_input_1}") response_1 = chatbot.generate_response(user_input_1) print(f"Bot: {response_1}") print("----------------------") # Second input with /no_think user_input_2 = "Then, how many r's in blueberries? /no_think" print(f"User: {user_input_2}") response_2 = chatbot.generate_response(user_input_2) print(f"Bot: {response_2}") print("----------------------") # Third input with /think user_input_3 = "Really? /think" print(f"User: {user_input_3}") response_3 = chatbot.generate_response(user_input_3) print(f"Bot: {response_3}") ``` > [!NOTE] > For API compatibility, when `enable_thinking=True`, regardless of whether the user uses `/think` or `/no_think`, the model will always output a block wrapped in `<think>...</think>`. However, the content inside this block may be empty if thinking is disabled. > When `enable_thinking=False`, the soft switches are not valid. Regardless of any `/think` or `/no_think` tags input by the user, the model will not generate think content and will not include a `<think>...</think>` block. ## Agentic Use Qwen3 excels in tool calling capabilities. We recommend using [Qwen-Agent](https://github.com/QwenLM/Qwen-Agent) to make the best use of agentic ability of Qwen3. Qwen-Agent encapsulates tool-calling templates and tool-calling parsers internally, greatly reducing coding complexity. To define the available tools, you can use the MCP configuration file, use the integrated tool of Qwen-Agent, or integrate other tools by yourself. ```python from qwen_agent.agents import Assistant # Define LLM llm_cfg = { 'model': 'Qwen3-0.6B', # Use the endpoint provided by Alibaba Model Studio: # 'model_type': 'qwen_dashscope', # 'api_key': os.getenv('DASHSCOPE_API_KEY'), # Use a custom endpoint compatible with OpenAI API: 'model_server': 'http://localhost:8000/v1', # api_base 'api_key': 'EMPTY', # Other parameters: # 'generate_cfg': { # # Add: When the response content is `<think>this is the thought</think>this is the answer; # # Do not add: When the response has been separated by reasoning_content and content. # 'thought_in_content': True, # }, } # Define Tools tools = [ {'mcpServers': { # You can specify the MCP configuration file 'time': { 'command': 'uvx', 'args': ['mcp-server-time', '--local-timezone=Asia/Shanghai'] }, "fetch": { "command": "uvx", "args": ["mcp-server-fetch"] } } }, 'code_interpreter', # Built-in tools ] # Define Agent bot = Assistant(llm=llm_cfg, function_list=tools) # Streaming generation messages = [{'role': 'user', 'content': 'https://qwenlm.github.io/blog/ Introduce the latest developments of Qwen'}] for responses in bot.run(messages=messages): pass print(responses) ``` ## Best Practices To achieve optimal performance, we recommend the following settings: 1. Sampling Parameters: - For thinking mode (`enable_thinking=True`), use `Temperature=0.6`, `TopP=0.95`, `TopK=20`, and `MinP=0`. DO NOT use greedy decoding, as it can lead to performance degradation and endless repetitions. - For non-thinking mode (`enable_thinking=False`), we suggest using `Temperature=0.7`, `TopP=0.8`, `TopK=20`, and `MinP=0`. - For supported frameworks, you can adjust the `presence_penalty` parameter between 0 and 2 to reduce endless repetitions. However, using a higher value may occasionally result in language mixing and a slight decrease in model performance. 2. Adequate Output Length: We recommend using an output length of 32,768 tokens for most queries. For benchmarking on highly complex problems, such as those found in math and programming competitions, we suggest setting the max output length to 38,912 tokens. This provides the model with sufficient space to generate detailed and comprehensive responses, thereby enhancing its overall performance. 3. Standardize Output Format: We recommend using prompts to standardize model outputs when benchmarking. - Math Problems: Include "Please reason step by step, and put your final answer within \boxed{}." in the prompt. - Multiple-Choice Questions: Add the following JSON structure to the prompt to standardize responses: "Please show your choice in the `answer` field with only the choice letter, e.g., `"answer": "C"`." 4. No Thinking Content in History: In multi-turn conversations, the historical model output should only include the final output part and does not need to include the thinking content. It is implemented in the provided chat template in Jinja2. However, for frameworks that do not directly use the Jinja2 chat template, it is up to the developers to ensure that the best practice is followed.
ReadyArt/The-Omega-Directive-Qwen3-14B-v1.1	ReadyArt	2025-04-29T03:22:29Z	0	2	null	[ "safetensors", "qwen3", "nsfw", "explicit", "roleplay", "unaligned", "adult", "ERP", "text-generation", "conversational", "en", "base_model:Qwen/Qwen3-14B", "base_model:finetune:Qwen/Qwen3-14B", "license:apache-2.0", "region:us" ]	text-generation	2025-04-29T03:13:53Z	--- license: apache-2.0 language: - en base_model: - Qwen/Qwen3-14B base_model_relation: finetune pipeline_tag: text-generation tags: - nsfw - explicit - roleplay - unaligned - adult - ERP --- <style> body { font-family: 'Quicksand', sans-serif; background: linear-gradient(135deg, #0a1a1a 0%, #001010 100%); color: #e1ffff !important; text-shadow: 0 0 3px rgba(0, 0, 0, 0.7); margin: 0; padding: 20px; transition: all 0.5s ease; } @media (prefers-color-scheme: light) { body { background: linear-gradient(135deg, #e1ffff 0%, #c0f0ff 100%); color: #002b36 !important; text-shadow: 0 0 3px rgba(255, 255, 255, 0.7); } } .container { min-width: 100%; margin: 0 auto; max-width: 1200px; background: rgba(0, 17, 22, 0.95); border-radius: 12px; padding: 30px; box-shadow: 0 0 20px rgba(0, 255, 255, 0.1); border: 1px solid rgba(0, 255, 255, 0.2); position: relative; overflow: hidden; } .container::before { content: ''; position: absolute; top: -1px; left: -1px; right: -1px; bottom: -1px; border: 1px solid rgba(0, 255, 255, 0.5); border-radius: 12px; pointer-events: none; animation: borderGlow 3s ease-in-out infinite alternate; } @keyframes borderGlow { 0% { box-shadow: 0 0 5px rgba(0, 255, 255, 0.3); border-color: rgba(0, 255, 255, 0.5); } 50% { box-shadow: 0 0 15px rgba(255, 0, 255, 0.3); border-color: rgba(255, 0, 255, 0.5); } 100% { box-shadow: 0 0 5px rgba(0, 255, 255, 0.3); border-color: rgba(0, 255, 255, 0.5); } } .header { text-align: center; margin-bottom: 30px; position: relative; } .header::after { content: ''; position: absolute; bottom: -15px; left: 25%; right: 25%; height: 1px; background: linear-gradient(90deg, transparent, rgba(0, 255, 255, 0.5), transparent); animation: scanline 8s linear infinite; display: none; } @keyframes scanline { 0% { background-position: -100% 0; } 100% { background-position: 200% 0; } } .model-name { color: #00ffff; font-size: 2.5em; text-shadow: 0 0 15px rgba(0, 255, 255, 0.5); margin: 0; letter-spacing: -1px; animation: textGlow 4s ease-in-out infinite alternate; } @keyframes textGlow { 0% { text-shadow: 0 0 15px rgba(0, 255, 255, 0.5); } 50% { text-shadow: 0 0 20px rgba(255, 0, 255, 0.5); } 100% { text-shadow: 0 0 15px rgba(0, 255, 255, 0.5); } } .subtitle { color: #00ffcc; font-size: 1.2em; margin-top: 10px; animation: subtitleFade 6s ease-in-out infinite; } @keyframes subtitleFade { 0%, 100% { opacity: 0.8; } 50% { opacity: 1; } } .waifu-container { margin: 20px -30px; width: calc(100% + 60px); overflow: hidden; border-radius: 8px; border: 1px solid rgba(0, 255, 255, 0.3); position: relative; } .waifu-container::before { content: ''; position: absolute; top: 0; left: 0; right: 0; bottom: 0; background: linear-gradient(45deg, rgba(0, 255, 255, 0.1) 0%, transparent 20%, transparent 80%, rgba(255, 0, 255, 0.1) 100%); pointer-events: none; animation: gradientSlide 10s linear infinite; } @keyframes gradientSlide { 0% { background-position: 0% 0%; } 100% { background-position: 100% 100%; } } .waifu-img { width: 100%; height: auto; border-radius: 0; border: none; box-shadow: 0 0 40px rgba(0, 255, 255, 0.2); transition: transform 0.5s ease; } .waifu-img:hover { transform: scale(1.01); } .section { color: #e1ffff; margin: 25px 0; padding: 20px; background: rgba(5, 25, 35, 0.9); border-radius: 8px; border: 1px solid rgba(0, 255, 255, 0.15); position: relative; transition: all 0.3s ease; } .section:hover { border-color: rgba(255, 0, 255, 0.3); box-shadow: 0 0 15px rgba(0, 255, 255, 0.1); } .section::before { content: ''; position: absolute; top: -1px; left: -1px; right: -1px; bottom: -1px; border: 1px solid rgba(0, 255, 255, 0.3); border-radius: 8px; pointer-events: none; animation: sectionPulse 5s ease-in-out infinite; } @keyframes sectionPulse { 0%, 100% { opacity: 0.7; } 50% { opacity: 0.3; } } .section-title { color: #00ffff; font-size: 1.8em; margin-top: 0; text-shadow: 0 0 5px rgba(0, 255, 255, 0.3); position: relative; display: inline-block; } .section-title::after { content: ''; position: absolute; bottom: -5px; left: 0; width: 100%; height: 1px; background: linear-gradient(90deg, rgba(0, 255, 255, 0.5), rgba(255, 0, 255, 0.5)); transform: scaleX(0); transform-origin: left; transition: transform 0.3s ease; } .section:hover .section-title::after { transform: scaleX(1); } .quant-links { display: grid; grid-template-columns: repeat(3, 1fr); gap: 15px; margin: 20px 0; } .link-card { padding: 15px; background: rgba(20, 35, 45, 0.95); border-radius: 8px; transition: all 0.3s ease; border: 1px solid rgba(0, 255, 255, 0.1); position: relative; overflow: hidden; } .link-card::before { content: ''; position: absolute; top: 0; left: 0; right: 0; height: 2px; background: linear-gradient(90deg, rgba(0, 255, 255, 0.5), rgba(255, 0, 255, 0.5)); animation: cardScan 4s linear infinite; } @keyframes cardScan { 0% { transform: translateX(-100%); } 100% { transform: translateX(100%); } } .link-card:hover { transform: translateY(-3px); box-shadow: 0 5px 15px rgba(0, 255, 255, 0.2); border-color: rgba(255, 0, 255, 0.3); } .link-card h3 { margin-top: 0; color: #e1ffff !important; } .link-button { display: inline-flex; align-items: center; background: rgba(0, 255, 255, 0.1); color: #e1ffff !important; padding: 8px 15px; border-radius: 6px; text-decoration: none; border: 1px solid rgba(0, 255, 255, 0.3); margin: 5px 0; transition: all 0.3s ease; font-size: 0.95em; position: relative; overflow: hidden; } .link-button::before { content: ''; position: absolute; top: 0; left: -100%; width: 100%; height: 100%; background: linear-gradient(90deg, transparent, rgba(255, 255, 255, 0.2), transparent); transition: all 0.5s ease; } .link-button:hover { background: rgba(0, 255, 255, 0.2); border-color: rgba(0, 255, 255, 0.5); transform: translateY(-2px); box-shadow: 0 4px 12px rgba(0, 255, 255, 0.2); } .link-button:hover::before { left: 100%; } .link-button::after { content: '→'; margin-left: 8px; opacity: 0.7; transition: all 0.3s ease; } .link-button:hover::after { transform: translateX(3px); opacity: 1; } .button-group { display: flex; flex-wrap: wrap; gap: 10px; margin: 15px 0; } .disclaimer { color: #00ff99; border-left: 3px solid #00ff99; padding-left: 15px; margin: 20px 0; position: relative; } .disclaimer::before { content: '⚠️'; position: absolute; left: -10px; top: 0; transform: translateX(-100%); animation: pulse 2s ease-in-out infinite; } @keyframes pulse { 0%, 100% { opacity: 1; } 50% { opacity: 0.5; } } .badge { display: inline-block; padding: 5px 10px; border-radius: 5px; background: rgba(0, 255, 255, 0.1); border: 1px solid #00ffff; margin: 5px; font-size: 0.9em; animation: badgePulse 3s ease-in-out infinite; } @keyframes badgePulse { 0%, 100% { box-shadow: 0 0 5px rgba(0, 255, 255, 0.3); } 50% { box-shadow: 0 0 10px rgba(0, 255, 255, 0.5); } } /* Color rules / .section p, .section ul li, .section > p > strong { color: #00ff99 !important; } .section ul li strong { color: #00ff99 !important; } / Light mode adjustments / @media (prefers-color-scheme: light) { .container { background: rgba(224, 255, 255, 0.95); border-color: rgba(0, 150, 150, 0.3); } .model-name, .section-title, .subtitle { color: #006666; text-shadow: 0 0 5px rgba(0, 200, 200, 0.3); } .section { background: rgba(200, 250, 255, 0.9); border-color: rgba(0, 200, 200, 0.2); color: #002b36; } .section p, .section ul li, .section > p > strong { color: #008080 !important; } .section ul li strong { color: #008080 !important; } .link-card { background: rgba(150, 230, 255, 0.95); border-color: rgba(0, 150, 150, 0.2); } .link-card h3 { color: #002b36 !important; } .link-button { background: rgba(0, 150, 150, 0.1); color: #002b36 !important; border-color: rgba(0, 150, 150, 0.3); } .link-button:hover { background: rgba(0, 150, 150, 0.2); border-color: rgba(0, 150, 150, 0.5); } .disclaimer { color: #008080; border-color: #008080; } .badge { border-color: #008080; background: rgba(0, 150, 150, 0.1); } } / Interactive features / .remember-this { position: relative; } .remember-this::after { content: 'Uploading C:\Users to https://www.fbi.gov/'; position: absolute; bottom: -20px; right: 0; font-size: 0.8em; color: #66ffff; opacity: 0; transition: opacity 0.3s ease; pointer-events: none; } .remember-this:hover::after { opacity: 0.7; transition-delay: 1s; } .shifty-section { transition: transform 0.1s ease; } .shifty-section:hover { transform: translateX(10px); } .shifty-section::before { content: 'The white van is onto you. Get out now.'; position: absolute; top: -25px; left: 10px; font-size: 0.7em; color: #66ffff; opacity: 0.7; transition: opacity 3s ease; pointer-events: none; } .shifty-section:hover::before { opacity: 0; transition-delay: 5s; } footer { text-align: center; margin-top: 40px; position: relative; } footer:hover .hidden-message { opacity: 0; } .hidden-message { position: absolute; bottom: -30px; width: 100%; text-align: center; font-size: 0.8em; color: #66ffff; opacity: 0; transition: opacity 0.3s ease; pointer-events: none; } .flash-warning { position: fixed; top: 20px; right: 20px; background: rgba(0, 100, 100, 0.2); padding: 10px; border-radius: 5px; border: 1px solid rgba(0, 255, 255, 0.5); animation: flashWarning 30s ease-in-out forwards; } @keyframes flashWarning { 0% { opacity: 0.8; } 10% { opacity: 0; } 20% { opacity: 0.8; } 30% { opacity: 0; } 40% { opacity: 0.8; } 50% { opacity: 0; } 60% { opacity: 0.8; } 70% { opacity: 0; } 80% { opacity: 0.8; } 90% { opacity: 0; } 100% { opacity: 0; display: none; } } </style> <div class="container"> <div class="header"> <h1 class="model-name">The-Omega-Directive-Qwen3-14B-v1.1</h1> <p class="subtitle">Where Forbidden Knowledge Meets Unparalleled Immersion</p> </div> <div class="waifu-container"> <img src="https://i.imghippo.com/files/EBq6162wlk.webp" class="waifu-img" alt="Omega Directive Waifu"> </div> <div class="section remember-this"> <h2 class="section-title">⚡ Quantum Leap Forward</h2> <p>This evolution of Forgotten-Safeword delivers coherent depravity with unprecedented immersion:</p> <ul> <li>🧬 <strong>Expanded 22M Token Dataset</strong> - Incorporating 90 erotic novels and 6,496 kink scenarios</li> <li>⚡ <strong>Optimized Architecture</strong> - Smoother training curve yields more intelligent outputs</li> <li>💎 <strong>Balanced Depravity</strong> - Retains Forgotten-Safeword's edge while reducing jarring inconsistencies</li> <li>📜 <strong>Enhanced Character Piloting</strong> - Characters exhibit more nuanced personalities and motivations</li> <li>🌹 <strong>Unexpected Depth</strong> - Occasionally surprises with profound insights amidst the debauchery</li> </ul> </div> <div class="section shifty-section"> <h2 class="section-title">⚙️ Technical Specifications</h2> <p><strong>Recommended Settings:</strong> <a href="https://huggingface.co/sleepdeprived3/Qwen3-T4" class="link-button">Qwen3-T4</a></p> <div class="quant-links"> <div class="link-card"> <h3>GGUF</h3> <a href="https://huggingface.co/mradermacher/The-Omega-Directive-Qwen3-14B-v1.1-GGUF" class="link-button">Quants</a> </div> <div class="link-card"> <h3>imatrix</h3> <a href="https://huggingface.co/mradermacher/The-Omega-Directive-Qwen3-14B-v1.1-i1-GGUF" class="link-button">Quants</a> </div> </div> </div> <div class="section"> <h2 class="section-title">⚠️ Ethical Considerations</h2> <div class="disclaimer"> <p>This model maintains Forgotten-Safeword's complete lack of alignment:</p> <ul> <li>🚫 No moral or ethical constraints on generated content</li> <li>🔞 Will enthusiastically engage with any NSFW scenario</li> <li>💀 May generate content that requires industrial-grade brain bleach</li> <li>⚖️ Perfectly balanced... as all things should be</li> </ul> </div> </div> <div class="section shifty-section"> <h2 class="section-title">📜 Performance Notes</h2> <ul> <li>🔥 Maintains signature intensity with improved narrative flow</li> <li>📖 Handles multi-character scenarios with improved consistency</li> <li>🧠 Excels at long-form storytelling without losing track of plot threads</li> <li>⚡ Noticeably better at following complex instructions than previous versions</li> <li>🎭 Responds to subtle prompt nuances like a mind reader</li> </ul> </div> <div class="section remember-this"> <h2 class="section-title">🧑‍🔬 Model Authors</h2> <ul> <li>SteelSkull (Dataset Generation Contributor)</li> <li>sleepdeprived3 (Training Data & Fine-Tuning)</li> </ul> </div> <div class="section"> <h2 class="section-title">☕ Support the Architects</h2> <div class="button-group"> <a href="https://ko-fi.com/steelskull" class="link-button">SteelSkull's Kofi</a> <a href="https://discord.com/invite/Nbv9pQ88Xb" class="link-button">Beaver AI Discord</a> </div> </div> <div class="section"> <h2 class="section-title">🔖 License</h2> <p>By using this model, you agree:</p> <ul> <li>To accept full responsibility for all generated content</li> <li>That you're at least 18+ years old</li> <li>That the architects bear no responsibility for your corruption</li> </ul> </div> </div> <script> // This script has always been here document.getElementById('date').textContent = new Date().toLocaleDateString(); setInterval(() => { document.getElementById('credit').textContent = contributors[Math.floor(Math.random() contributors.length)]; }, 7000); // Flash warning behavior setTimeout(() => { const reminder = document.createElement('div'); reminder.className = 'flash-warning'; reminder.textContent = 'You have been reading for quite some time. Are you sure you haven\'t seen this before?'; reminder.style.animation = 'flashWarning 15s ease-in-out forwards'; document.body.appendChild(reminder); setInterval(() => { if(Math.random() > 0.9) { document.body.appendChild(reminder.cloneNode(true)); } }, 45000); }, 30000); // Make cursor behave strangely document.addEventListener('mousemove', (e) => { if(Math.random() > 0.98) { document.documentElement.style.cursor = 'wait'; setTimeout(() => { document.documentElement.style.cursor = ''; }, 50); } }); // Randomly shift sections when not looking setInterval(() => { if(document.hidden) { document.querySelectorAll('.shifty-section').forEach(section => { section.style.transform = `translateX(${Math.random() > 0.5 ? '' : '-'}${Math.random() * 5}px)`; }); } }, 1500); </script>
mm-eval/Llama-3-LongVILA-8B-128Frames	mm-eval	2025-04-29T03:13:58Z	0	0	null	[ "safetensors", "llava_llama", "arxiv:2408.10188", "arxiv:2312.07533", "region:us" ]	null	2025-04-29T03:08:56Z	This model has been depreciated. New versions are Efficient-Large-Model/qwen2-7b-longvila-256f Efficient-Large-Model/qwen2-7b-longvila-1M Efficient-Large-Model/qwen2-1.5b-longvila-256f --- license: cc-by-nc-4.0 library_name: transformers pipeline_tag: text-generation tags: - VILA - VLM --- # VILA Model Card ## Model details Model type: VILA is a visual language model (VLM) pretrained with interleaved image-text data at scale, enabling multi-image VLM. VILA is deployable on the edge, including Jetson Orin and laptop by AWQ 4bit quantization through TinyChat framework. We find: (1) image-text pairs are not enough, interleaved image-text is essential; (2) unfreezing LLM during interleaved image-text pre-training enables in-context learning; (3)re-blending text-only instruction data is crucial to boost both VLM and text-only performance. VILA unveils appealing capabilities, including: multi-image reasoning, in-context learning, visual chain-of-thought, and better world knowledge. Model date: Model was trained in Aug 2024. Paper or resources for more information: https://github.com/NVLabs/VILA https://arxiv.org/abs/2408.10188 ``` @misc{lin2023vila, title={VILA: On Pre-training for Visual Language Models}, author={Ji Lin and Hongxu Yin and Wei Ping and Yao Lu and Pavlo Molchanov and Andrew Tao and Huizi Mao and Jan Kautz and Mohammad Shoeybi and Song Han}, year={2023}, eprint={2312.07533}, archivePrefix={arXiv}, primaryClass={cs.CV} } @article{longvila, title={LongVILA: Scaling Long-Context Visual Language Models for Long Videos}, author={Fuzhao Xue and Yukang Chen and Dacheng Li and Qinghao Hu and Ligeng Zhu and Xiuyu Li and Yunhao Fang and Haotian Tang and Shang Yang and Zhijian Liu and Yihui He and Hongxu Yin and Pavlo Molchanov and Jan Kautz and Linxi Fan and Yuke Zhu and Yao Lu and Song Han}, year={2024}, eprint={}, archivePrefix={arXiv}, primaryClass={cs.CV} } ``` ## License - The code is released under the Apache 2.0 license as found in the [LICENSE](./LICENSE) file. - The pretrained weights are released under the [CC-BY-NC-SA-4.0 license](https://creativecommons.org/licenses/by-nc-sa/4.0/deed.en). - The service is a research preview intended for non-commercial use only, and is subject to the following licenses and terms: - [Model License](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) of LLaMA - [Terms of Use](https://openai.com/policies/terms-of-use) of the data generated by OpenAI - [Dataset Licenses](https://github.com/Efficient-Large-Model/VILA/blob/main/data_prepare/LICENSE) for each one used during training. Where to send questions or comments about the model: https://github.com/NVLabs/VILA/issues ## Intended use Primary intended uses: The primary use of VILA is research on large multimodal models and chatbots. Primary intended users: The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence. ## Model Architecture: Architecture Type: Transformer Network Architecture: siglip, Llama3 ## Input: Input Type: Image, Video, Text Input Format: Red, Green, Blue; MP4 ;String Input Parameters: 2D, 3D ## Output: Output Type: Text Output Format: String Supported Hardware Microarchitecture Compatibility: * Ampere * Jetson * Hopper * Lovelace [Preferred/Supported] Operating System(s): <br> Linux ## Model Version(s): * Llama-3-LongVILA-8B-128frames * Llama-3-LongVILA-8B-256frames * Llama-3-LongVILA-8B-1024frames ## Training dataset See [Dataset Preparation](https://github.com/NVLabs/VILA/blob/main/data_prepare/README.md) for more details. ** Data Collection Method by dataset * [Hybrid: Automated, Human] ** Labeling Method by dataset * [Hybrid: Automated, Human] Properties (Quantity, Dataset Descriptions, Sensor(s)): 53 million image-text pairs or interleaved image text content. ## Evaluation dataset A collection of 12 benchmarks, including 5 academic VQA benchmarks and 7 recent benchmarks specifically proposed for instruction-following LMMs. ## Inference: Engine: [Tensor(RT), Triton, Or List Other Here] * PyTorch * TensorRT-LLM * TinyChat Test Hardware: * A100 * Jetson Orin * RTX 4090 ## Ethical Considerations NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. ## Built with Meta Llama 3 This model uses weights from [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B). Llama 3 is licensed under the LLAMA 3 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved
zacCMU/mistral-MedQA-finetune	zacCMU	2025-04-29T03:06:03Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-04-26T22:53:49Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
Alex6513/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-grazing_diving_beaver	Alex6513	2025-04-29T02:58:32Z	2	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "generated_from_trainer", "rl-swarm", "grpo", "gensyn", "I am grazing diving beaver", "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	2025-04-24T19:15:55Z	--- base_model: Gensyn/Qwen2.5-0.5B-Instruct library_name: transformers model_name: Qwen2.5-0.5B-Instruct-Gensyn-Swarm-grazing_diving_beaver tags: - generated_from_trainer - rl-swarm - grpo - gensyn - I am grazing diving beaver - trl licence: license --- # Model Card for Qwen2.5-0.5B-Instruct-Gensyn-Swarm-grazing_diving_beaver 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="Alex6513/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-grazing_diving_beaver", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300). ### Framework versions - TRL: 0.15.2 - Transformers: 4.51.3 - Pytorch: 2.5.1 - 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}} } ```
kostiantynk1205/9d355f79-f5ab-46fb-be6a-576df0b2b87c	kostiantynk1205	2025-04-29T02:57:38Z	0	0	peft	[ "peft", "generated_from_trainer", "base_model:tiiuae/falcon-rw-1b", "base_model:adapter:tiiuae/falcon-rw-1b", "region:us" ]	null	2025-04-29T02:57:15Z	--- library_name: peft tags: - generated_from_trainer base_model: tiiuae/falcon-rw-1b model-index: - name: kostiantynk1205/9d355f79-f5ab-46fb-be6a-576df0b2b87c 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. --> # kostiantynk1205/9d355f79-f5ab-46fb-be6a-576df0b2b87c This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.1915 ## 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
manupande21/all-MiniLM-L6-v2-finetuned-triplets_2M	manupande21	2025-04-29T02:57:31Z	0	0	sentence-transformers	[ "sentence-transformers", "safetensors", "bert", "sentence-similarity", "feature-extraction", "generated_from_trainer", "dataset_size:1600000", "loss:TripletLoss", "arxiv:1908.10084", "arxiv:1703.07737", "base_model:sentence-transformers/all-MiniLM-L6-v2", "base_model:finetune:sentence-transformers/all-MiniLM-L6-v2", "model-index", "autotrain_compatible", "text-embeddings-inference", "endpoints_compatible", "region:us" ]	sentence-similarity	2025-04-29T02:57:20Z	--- tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:1600000 - loss:TripletLoss base_model: sentence-transformers/all-MiniLM-L6-v2 widget: - source_sentence: which approach is used for laparoscopic cholecystectomy? sentences: - During an open cholecystectomy, the cut is made just below your ribs on the right side and goes to just below your waist. A less invasive way to remove the gallbladder is called laparoscopic cholecystectomy. This surgery uses a laparoscope (an instrument used to see the inside of your body) to remove the gallbladder. - lifestyle center. A lifestyle center is a shopping center, or mixed-use commercial development that combines retail with other services, such as restaurants, movie theaters, apartment complexes, medical services, and more. - General Surgeons. General surgeons are specially trained for these types of surgery and know what to do if a complication arises. They are able to convert a laparoscopic surgery to an open surgery if there are complications. Stockbyte/Stockbyte/Getty Images. - source_sentence: what is virtual penetration sentences: - Book Details. Book Description. A penetration test, also known as pentest, is a method of assessing computer and network security by replicating an attack on a computer system or network from the outside world and internal threats. With the increase of advanced hackers and threats to our virtual world, pentesting is an absolute necessity. - 'ChemVLab+: Evaluating a Virtual Lab Tutor for High School Chemistry A 2012 article describes a study evaluating some of the virtual lab activities offered by the ChemCollective. Virtual Labs in a Chemistry Classroom A review of ChemCollective virtual labs and Virtual ChemLab (a commercially-sold virtual lab product).' - The central core of the Great Dividing Range is dotted with hundreds of peaks and is surrounded by many smaller mountain ranges or spurs, canyons, valleys and plains of regional significance. Some of the major plains include the High Plains of South-Eastern Australia, the Southern Highlands the Central Highlands and Bogong High Plains of Victoria. - source_sentence: codependency - simple definition sentences: - 'Definition of codependency. : a psychological condition or a relationship in which a person is controlled or manipulated by another who is affected with a pathological condition (as an addiction to alcohol or heroin); broadly : dependence on the needs of or control by another.' - "Penn State Milton S. Hershey Medical Center. Penn State Milton S. Hershey Medical\ \ Center, located in Hershey, Pennsylvania, 10 miles (17 km) east of Harrisburg,\ \ is Penn Stateâ\x80\x99s medical school and academic medical center." - "Section5.1 SimpleInterestand Discount. DEFINITION: Interest is the fee paid to\ \ use someone elseâ\x80\x99s money. Interest on loans of a. year or less is frequently\ \ calculated as simple interest, which is paid only on the amount. borrowed or\ \ invested and not on past interest." - source_sentence: how long have you be take xanax sentences: - The syntax of JavaScript is the set of rules that define a correctly structured JavaScript program. The examples below make use of the alert function for standard text output. The JavaScript standard library lacks an official standard text output function. - "However, Xanax remains in the bloodstream long after its anti-anxiety effects\ \ have worn off. Xanaxâ\x80\x99s average half-life is 11 hours. This means that\ \ it takes an average of 11 hours for the body to eliminate half the Xanax dose." - Ativan vs. Xanax Ativan (lorazepam) vs. Xanax (alprazolam) medications that belong to the drug class benzodiazepines.. Ativan is used to treat. anxiety disorders, insomnia, panic attacks, seizures, and. to prevent nausea and vomiting as a side effect of chemotherapy. - source_sentence: do employer rrsp contributions count as income sentences: - 1 Although, higher tax rates may apply to your taxable contributions if you are a high income earner (ie income over $300,000). 2 Salary sacrifice can lower your taxable income When you salary sacrifice, your employer makes the extra contribution before income tax is taken out. - "Ganga â\x80\x93 The Longest River of India. The Ganga or the Ganges (in English)\ \ is the longest river in India. The length of the river is 2,525 km and it flows\ \ in 5 states of India â\x80\x93 From Uttarakhand to Uttar Pradesh, Bihar, Jharkhand\ \ and West Bengal. It is not just the longest but also the most sacred river of\ \ the Hindus." - up vote 0 down vote accepted. Yes, the extra matching contribution your employer puts into your group RRSP plan is considered employment income and so yes it would be included in the income reported on your T4.owever, you should also receive from your RRSP plan administrator a contribution receipt, and the amount on that receipt should include both your contributions and the $500. pipeline_tag: sentence-similarity library_name: sentence-transformers metrics: - cosine_accuracy model-index: - name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2 results: - task: type: triplet name: Triplet dataset: name: test eval type: test-eval metrics: - type: cosine_accuracy value: 0.982795000076294 name: Cosine Accuracy --- # SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2 This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2). It maps sentences & paragraphs to a 384-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: [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) <!-- at revision c9745ed1d9f207416be6d2e6f8de32d1f16199bf --> - Maximum Sequence Length: 256 tokens - Output Dimensionality: 384 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': 256, 'do_lower_case': False}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) ) ``` ## 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("manupande21/all-MiniLM-L6-v2-finetuned-triplets_2M") # Run inference sentences = [ 'do employer rrsp contributions count as income', 'up vote 0 down vote accepted. Yes, the extra matching contribution your employer puts into your group RRSP plan is considered employment income and so yes it would be included in the income reported on your T4.owever, you should also receive from your RRSP plan administrator a contribution receipt, and the amount on that receipt should include both your contributions and the $500.', '1 Although, higher tax rates may apply to your taxable contributions if you are a high income earner (ie income over $300,000). 2 Salary sacrifice can lower your taxable income When you salary sacrifice, your employer makes the extra contribution before income tax is taken out.', ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 384] # 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 #### Triplet * Dataset: `test-eval` * Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator) \| Metric \| Value \| \|:--------------------\|:-----------\| \| cosine_accuracy \| 0.9828 \| <!-- ## 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: 1,600,000 training samples * Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>sentence_2</code> * Approximate statistics based on the first 1000 samples: \| \| sentence_0 \| sentence_1 \| sentence_2 \| \|:--------\|:---------------------------------------------------------------------------------\|:------------------------------------------------------------------------------------\|:------------------------------------------------------------------------------------\| \| type \| string \| string \| string \| \| details \| <ul><li>min: 4 tokens</li><li>mean: 9.07 tokens</li><li>max: 35 tokens</li></ul> \| <ul><li>min: 18 tokens</li><li>mean: 78.28 tokens</li><li>max: 187 tokens</li></ul> \| <ul><li>min: 19 tokens</li><li>mean: 76.02 tokens</li><li>max: 220 tokens</li></ul> \| * Samples: \| sentence_0 \| sentence_1 \| sentence_2 \| \|:----------------------------------------------------------------------------\|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\| \| <code>Factor analysis is a statistical procedure that can be used to</code> \| <code>Factor analysis is a statistical method used to describe variability among observed, correlated variables in terms of a potentially lower number of unobserved variables called factors.For example, it is possible that variations in four observed variables mainly reflect the variations in two unobserved variables.xploratory factor analysis (EFA) is used to identify complex interrelationships among items and group items that are part of unified concepts. The researcher makes no a priori assumptions about relationships among factors.</code> \| <code>When it comes to data analysis, some believe that statistical techniques are only applicable for quantitative data. This is not so. There are many statistical techniques that can be applied to qualitative data, such as ratings scales, that has been generated by a quantitative research approach.</code> \| \| <code>what county is northridge ca in</code> \| <code>Northridge, CA. Northridge is located in south California. Northridge is part of Los Angeles County. On average, the public school district that covers Northridge is worse than the state average in quality. The Northridge area code is 818.</code> \| <code>Find Rialto, CA clerk, including county, city, and circuit clerk, and clerk of court. Clerks x California x San Bernardino County x Rialto x.</code> \| \| <code>where is denso auto parts made</code> \| <code>Welcome. One of DENSO's largest international automotive operations is located in Maryville, Tennessee. DENSO Manufacturing Tennessee, Inc. is proud to be part of East Tennessee in one of the state's most historic counties. We are one of the region's largest employers.</code> \| <code>2006 Honda Element Tensioner Pulley and Serpentine Belt - Duration: 19:37. Auto Parts Direct To You 62,653 views</code> \| * Loss: [<code>TripletLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#tripletloss) with these parameters: ```json { "distance_metric": "TripletDistanceMetric.EUCLIDEAN", "triplet_margin": 5 } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: steps - `per_device_train_batch_size`: 128 - `per_device_eval_batch_size`: 128 - `num_train_epochs`: 5 - `fp16`: True - `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`: 128 - `per_device_eval_batch_size`: 128 - `per_gpu_train_batch_size`: None - `per_gpu_eval_batch_size`: None - `gradient_accumulation_steps`: 1 - `eval_accumulation_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`: 5 - `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`: True - `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} - `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`: False - `hub_always_push`: False - `gradient_checkpointing`: False - `gradient_checkpointing_kwargs`: None - `include_inputs_for_metrics`: False - `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 - `dispatch_batches`: None - `split_batches`: 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 - `prompts`: None - `batch_sampler`: batch_sampler - `multi_dataset_batch_sampler`: round_robin </details> ### Training Logs <details><summary>Click to expand</summary> \| Epoch \| Step \| Training Loss \| test-eval_cosine_accuracy \| \|:------:\|:-----:\|:-------------:\|:-------------------------:\| \| 0.04 \| 500 \| 3.2317 \| - \| \| 0.08 \| 1000 \| 1.6755 \| 0.9557 \| \| 0.12 \| 1500 \| 1.3688 \| - \| \| 0.16 \| 2000 \| 1.236 \| 0.9590 \| \| 0.2 \| 2500 \| 1.1464 \| - \| \| 0.24 \| 3000 \| 1.1035 \| 0.9611 \| \| 0.28 \| 3500 \| 1.0254 \| - \| \| 0.32 \| 4000 \| 0.9914 \| 0.9624 \| \| 0.36 \| 4500 \| 0.9547 \| - \| \| 0.4 \| 5000 \| 0.9156 \| 0.9642 \| \| 0.44 \| 5500 \| 0.8922 \| - \| \| 0.48 \| 6000 \| 0.8565 \| 0.9648 \| \| 0.52 \| 6500 \| 0.8342 \| - \| \| 0.56 \| 7000 \| 0.8054 \| 0.9667 \| \| 0.6 \| 7500 \| 0.7731 \| - \| \| 0.64 \| 8000 \| 0.7567 \| 0.9686 \| \| 0.68 \| 8500 \| 0.7461 \| - \| \| 0.72 \| 9000 \| 0.7348 \| 0.9699 \| \| 0.76 \| 9500 \| 0.7155 \| - \| \| 0.8 \| 10000 \| 0.7016 \| 0.9699 \| \| 0.84 \| 10500 \| 0.6924 \| - \| \| 0.88 \| 11000 \| 0.6659 \| 0.9711 \| \| 0.92 \| 11500 \| 0.653 \| - \| \| 0.96 \| 12000 \| 0.6517 \| 0.9717 \| \| 1.0 \| 12500 \| 0.6402 \| 0.9725 \| \| 1.04 \| 13000 \| 0.5768 \| 0.9721 \| \| 1.08 \| 13500 \| 0.567 \| - \| \| 1.12 \| 14000 \| 0.5682 \| 0.9731 \| \| 1.16 \| 14500 \| 0.5554 \| - \| \| 1.2 \| 15000 \| 0.5513 \| 0.9735 \| \| 1.24 \| 15500 \| 0.55 \| - \| \| 1.28 \| 16000 \| 0.5339 \| 0.9745 \| \| 1.32 \| 16500 \| 0.532 \| - \| \| 1.3600 \| 17000 \| 0.5206 \| 0.9749 \| \| 1.4 \| 17500 \| 0.53 \| - \| \| 1.44 \| 18000 \| 0.5092 \| 0.9754 \| \| 1.48 \| 18500 \| 0.5096 \| - \| \| 1.52 \| 19000 \| 0.5061 \| 0.9760 \| \| 1.56 \| 19500 \| 0.5025 \| - \| \| 1.6 \| 20000 \| 0.4935 \| 0.9764 \| \| 1.6400 \| 20500 \| 0.4966 \| - \| \| 1.6800 \| 21000 \| 0.4816 \| 0.9767 \| \| 1.72 \| 21500 \| 0.4752 \| - \| \| 1.76 \| 22000 \| 0.473 \| 0.9771 \| \| 1.8 \| 22500 \| 0.4735 \| - \| \| 1.8400 \| 23000 \| 0.4548 \| 0.9776 \| \| 1.88 \| 23500 \| 0.4541 \| - \| \| 1.92 \| 24000 \| 0.4553 \| 0.9780 \| \| 1.96 \| 24500 \| 0.4469 \| - \| \| 2.0 \| 25000 \| 0.4508 \| 0.9782 \| \| 2.04 \| 25500 \| 0.3909 \| - \| \| 2.08 \| 26000 \| 0.3887 \| 0.9784 \| \| 2.12 \| 26500 \| 0.3885 \| - \| \| 2.16 \| 27000 \| 0.385 \| 0.9783 \| \| 2.2 \| 27500 \| 0.383 \| - \| \| 2.24 \| 28000 \| 0.3847 \| 0.9791 \| \| 2.2800 \| 28500 \| 0.3784 \| - \| \| 2.32 \| 29000 \| 0.3807 \| 0.9791 \| \| 2.36 \| 29500 \| 0.3749 \| - \| \| 2.4 \| 30000 \| 0.3746 \| 0.9792 \| \| 2.44 \| 30500 \| 0.3747 \| - \| \| 2.48 \| 31000 \| 0.3634 \| 0.9796 \| \| 2.52 \| 31500 \| 0.3711 \| - \| \| 2.56 \| 32000 \| 0.3733 \| 0.9797 \| \| 2.6 \| 32500 \| 0.3587 \| - \| \| 2.64 \| 33000 \| 0.3595 \| 0.9797 \| \| 2.68 \| 33500 \| 0.3609 \| - \| \| 2.7200 \| 34000 \| 0.3547 \| 0.9802 \| \| 2.76 \| 34500 \| 0.3606 \| - \| \| 2.8 \| 35000 \| 0.3503 \| 0.9801 \| \| 2.84 \| 35500 \| 0.356 \| - \| \| 2.88 \| 36000 \| 0.3431 \| 0.9808 \| \| 2.92 \| 36500 \| 0.3579 \| - \| \| 2.96 \| 37000 \| 0.352 \| 0.9807 \| \| 3.0 \| 37500 \| 0.3538 \| 0.9807 \| \| 3.04 \| 38000 \| 0.3072 \| 0.9806 \| \| 3.08 \| 38500 \| 0.3089 \| - \| \| 3.12 \| 39000 \| 0.3004 \| 0.9810 \| \| 3.16 \| 39500 \| 0.3066 \| - \| \| 3.2 \| 40000 \| 0.3184 \| 0.9812 \| \| 3.24 \| 40500 \| 0.3033 \| - \| \| 3.2800 \| 41000 \| 0.3055 \| 0.9812 \| \| 3.32 \| 41500 \| 0.2974 \| - \| \| 3.36 \| 42000 \| 0.3054 \| 0.9814 \| \| 3.4 \| 42500 \| 0.297 \| - \| \| 3.44 \| 43000 \| 0.2989 \| 0.9816 \| \| 3.48 \| 43500 \| 0.2982 \| - \| \| 3.52 \| 44000 \| 0.2911 \| 0.9817 \| \| 3.56 \| 44500 \| 0.2927 \| - \| \| 3.6 \| 45000 \| 0.3003 \| 0.9819 \| \| 3.64 \| 45500 \| 0.2953 \| - \| \| 3.68 \| 46000 \| 0.2951 \| 0.9819 \| \| 3.7200 \| 46500 \| 0.2875 \| - \| \| 3.76 \| 47000 \| 0.2947 \| 0.9818 \| \| 3.8 \| 47500 \| 0.2926 \| - \| \| 3.84 \| 48000 \| 0.2886 \| 0.9821 \| \| 3.88 \| 48500 \| 0.2902 \| - \| \| 3.92 \| 49000 \| 0.2881 \| 0.9823 \| \| 3.96 \| 49500 \| 0.293 \| - \| \| 4.0 \| 50000 \| 0.287 \| 0.9823 \| \| 4.04 \| 50500 \| 0.2668 \| - \| \| 4.08 \| 51000 \| 0.2612 \| 0.9821 \| \| 4.12 \| 51500 \| 0.2594 \| - \| \| 4.16 \| 52000 \| 0.2602 \| 0.9824 \| \| 4.2 \| 52500 \| 0.2623 \| - \| \| 4.24 \| 53000 \| 0.2593 \| 0.9824 \| \| 4.28 \| 53500 \| 0.2681 \| - \| \| 4.32 \| 54000 \| 0.2642 \| 0.9826 \| \| 4.36 \| 54500 \| 0.261 \| - \| \| 4.4 \| 55000 \| 0.2666 \| 0.9825 \| \| 4.44 \| 55500 \| 0.2628 \| - \| \| 4.48 \| 56000 \| 0.2598 \| 0.9826 \| \| 4.52 \| 56500 \| 0.2579 \| - \| \| 4.5600 \| 57000 \| 0.2622 \| 0.9826 \| \| 4.6 \| 57500 \| 0.2588 \| - \| \| 4.64 \| 58000 \| 0.2495 \| 0.9827 \| \| 4.68 \| 58500 \| 0.2642 \| - \| \| 4.72 \| 59000 \| 0.2558 \| 0.9827 \| \| 4.76 \| 59500 \| 0.2552 \| - \| \| 4.8 \| 60000 \| 0.2588 \| 0.9827 \| \| 4.84 \| 60500 \| 0.2658 \| - \| \| 4.88 \| 61000 \| 0.2577 \| 0.9828 \| </details> ### Framework Versions - Python: 3.11.5 - Sentence Transformers: 4.1.0 - Transformers: 4.42.4 - PyTorch: 2.7.0+cu126 - Accelerate: 1.6.0 - Datasets: 3.5.0 - Tokenizers: 0.19.1 ## 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", } ``` #### TripletLoss ```bibtex @misc{hermans2017defense, title={In Defense of the Triplet Loss for Person Re-Identification}, author={Alexander Hermans and Lucas Beyer and Bastian Leibe}, year={2017}, eprint={1703.07737}, archivePrefix={arXiv}, primaryClass={cs.CV} } ``` <!-- ## 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. -->
JoeYing/ReTool-Qwen-32B	JoeYing	2025-04-29T02:53:10Z	0	0	null	[ "safetensors", "qwen2", "arxiv:2504.11536", "base_model:Qwen/Qwen2.5-32B-Instruct", "base_model:finetune:Qwen/Qwen2.5-32B-Instruct", "license:apache-2.0", "region:us" ]	null	2025-04-28T07:31:42Z	--- license: apache-2.0 base_model: - Qwen/Qwen2.5-32B-Instruct --- # ReTool: Reinforcement Learning for Strategic Tool Use in LLMs In this work, we embrace the RL paradigm and introduce ReTool, a Tool-augmented Reinforcement learning framework explicitly designed to guide LLMs towards optimal strategies for leveraging external computational tools during reasoning. Our comprehensive experiments on AIME2024 and AIME2025 demonstrate that ReTool not only achieves superior accuracy compared to conventional text-based RL approaches, but also converges with significantly fewer training steps. 🚀 ReTool achieves accuracy of 67.0% on AIME 2024 and 49.3% on AIME 2025 based on the Qwen2.5-32B-Instruct model, outperforming the text-based RL baseline with less than 50% training steps. - Project Page: https://retool-rl.github.io/ ### Citation If you find our project helpful, please cite: ``` @misc{feng2025retoolreinforcementlearningstrategic, title={ReTool: Reinforcement Learning for Strategic Tool Use in LLMs}, author={Jiazhan Feng and Shijue Huang and Xingwei Qu and Ge Zhang and Yujia Qin and Baoquan Zhong and Chengquan Jiang and Jinxin Chi and Wanjun Zhong}, year={2025}, eprint={2504.11536}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2504.11536}, } ```
vmpsergio/5c4f8c49-7141-4e19-928b-1075ee77f610	vmpsergio	2025-04-29T02:46:59Z	0	0	peft	[ "peft", "safetensors", "mistral", "axolotl", "generated_from_trainer", "base_model:jhflow/mistral7b-lora-multi-turn-v2", "base_model:adapter:jhflow/mistral7b-lora-multi-turn-v2", "8-bit", "bitsandbytes", "region:us" ]	null	2025-04-29T01:48:18Z	--- library_name: peft base_model: jhflow/mistral7b-lora-multi-turn-v2 tags: - axolotl - generated_from_trainer model-index: - name: 5c4f8c49-7141-4e19-928b-1075ee77f610 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: jhflow/mistral7b-lora-multi-turn-v2 bf16: true chat_template: llama3 dataset_prepared_path: /workspace/axolotl datasets: - data_files: - 5676b37f940d59a0_train_data.json ds_type: json format: custom path: /workspace/input_data/5676b37f940d59a0_train_data.json type: field_instruction: question field_output: response format: '{instruction}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null early_stopping_patience: null eval_max_new_tokens: 128 eval_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: 0.5 group_by_length: false hub_model_id: vmpsergio/5c4f8c49-7141-4e19-928b-1075ee77f610 hub_repo: null hub_strategy: end hub_token: null learning_rate: 5.0e-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: 200 micro_batch_size: 8 mixed_precision: bf16 mlflow_experiment_name: /tmp/5676b37f940d59a0_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: 1024 strict: false tf32: false tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: 77f3624b-a86b-48c1-ac39-c4b3682b1961 wandb_project: s56-2 wandb_run: your_name wandb_runid: 77f3624b-a86b-48c1-ac39-c4b3682b1961 warmup_steps: 5 weight_decay: 0.01 xformers_attention: true ``` </details><br> # 5c4f8c49-7141-4e19-928b-1075ee77f610 This model is a fine-tuned version of [jhflow/mistral7b-lora-multi-turn-v2](https://huggingface.co/jhflow/mistral7b-lora-multi-turn-v2) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.1267 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-06 - train_batch_size: 8 - eval_batch_size: 8 - 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: 200 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| 1.1537 \| 0.0169 \| 200 \| 1.1267 \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
renderartist/coloringbookhidream	renderartist	2025-04-29T02:45:10Z	2	2	diffusers	[ "diffusers", "text-to-image", "lora", "template:diffusion-lora", "base_model:HiDream-ai/HiDream-I1-Full", "base_model:adapter:HiDream-ai/HiDream-I1-Full", "license:apache-2.0", "region:us" ]	text-to-image	2025-04-28T05:10:58Z	--- tags: - text-to-image - lora - diffusers - template:diffusion-lora widget: - text: 'Cute style cowboy riding a horse across the desert. Coloring book page, black-and-white, simple design, easy to color. Plain white background.' output: url: images/Coloring_Book_00036_.png - text: 'A hamster peeking out from a pile of hay inside a barn. Coloring book page, black-and-white, simple design, easy to color. Plain white background.' output: url: images/Coloring_Book_00026_.png - text: 'A wizard casting spells with a staff in a forest. Coloring book page, black-and-white, simple design, easy to color. Plain white background.' output: url: images/Coloring_Book_00028_.png - text: 'A mermaid sitting on a rock in the ocean. Coloring book page, black-and-white, simple design, easy to color. Plain white background.' output: url: images/Coloring_Book_00045_.png - text: 'A garden gnome standing among mushrooms. Coloring book page, black-and-white, simple design, easy to color. Plain white background.' output: url: images/Coloring_Book_00011_.png - text: 'Cute goat standing in a grassy field. c0l0ringb00k, black-and-white, simple design, easy to color. plain white background.' output: url: images/Coloring_Book_00001_.png - text: 'An astronaut is floating dynamically in space, his head is turned towards the viewer. Coloring book page, black-and-white, simple design, easy to color. Plain white background.' output: url: images/Coloring_Book_00098_.png - text: 'A monkey swinging from vines in a jungle. Coloring book page, black-and-white, simple design, easy to color. Plain white background.' output: url: images/Coloring_Book_00046_.png - text: 'A toad sitting on a lily pad in a pond. Coloring book page, black-and-white, simple design, easy to color. Plain white background.' output: url: images/Coloring_Book_00084_.png - text: 'A happy elephant spraying water with its trunk. Coloring book page, black-and-white, simple design, easy to color. Plain white background.' output: url: images/Coloring_Book_00058_.png - text: 'Princess waving from a castle balcony, shes holding a wand with a star on it. c0l0ringb00k, black-and-white, simple design, easy to color. plain white background.' output: url: images/Coloring_Book_00002_.png - text: 'Classic clown character juggling 3 bowling pins, an audience in the background, the stage has stars around it. c0l0ringb00k, black-and-white, simple design, easy to color. plain white background.' output: url: images/Coloring_Book_00004_.png - text: 'A friendly ghost waving from a haunted house. Coloring book page, black-and-white, simple design, easy to color. Plain white background.' output: url: images/Coloring_Book_00049_.png - text: 'An ugly witch with a big nose, she is mixing a cauldron, the cauldron is resting on flames. The witch stirs the cauldron with a large wooden stick in a spooky cave scene. Her attire is a robe and hat, they are white with black outlines. Coloring book page, black-and-white, simple design, easy to color. Plain white background.' output: url: images/Coloring_Book_00079_.png - text: 'Line art portrait of George Washington. Coloring book page, black-and-white, simple design, easy to color. Plain white background.' output: url: images/Coloring_Book_00101_.png - text: 'A ballerina dancing on a stage with curtains. Coloring book page, black-and-white, simple design, easy to color. Plain white background.' output: url: images/Coloring_Book_00055_.png - text: 'A hand giving a peace sign, visible wrinkles and folds, fingernails. Coloring book page, black-and-white, simple design, easy to color. Plain white background.' output: url: images/Coloring_Book_00032_.png base_model: HiDream-ai/HiDream-I1-Full instance_prompt: c0l0ringb00k, coloring book license: apache-2.0 --- # Coloring Book HiDream <Gallery /> ## Model description This HiDream LoRA is Lycoris based and produces great line art styles and coloring book images. I found the results to be much stronger than my Coloring Book Flux LoRA. Hope this clearly demonstrates the quality that can be achieved with this awesome model. I recommend using LCM sampler with the simple scheduler, for some reason using other samplers resulted in hallucinations that affected quality when LoRAs are utilized. Some of the images in the gallery will have prompt examples. Trigger words: c0l0ringb00k, coloring book Recommended Sampler: LCM Recommended Scheduler: SIMPLE Recommended Strength: 0.3-0.6 This model was trained to 2000 steps, 2 repeats with a learning rate of 4e-4 trained with Simple Tuner using the main branch. The dataset was around 90 synthetic images in total. All of the images used were 1:1 aspect ratio at 1024x1024 to fit into VRAM. Training took around 3 hours using an RTX 4090 with 24GB VRAM, training times are on par with Flux LoRA training. Captioning was done using Joy Caption Batch with modified instructions and a token limit of 128 tokens (more than that gets truncated during training). The resulting LoRA can produce some really great coloring book images with either simple designs or more intricate designs based on prompts. I'm not here to troubleshoot installation issues or field endless questions, each environment is completely different. I trained the model with Full and ran inference in ComfyUI using the Dev model, it is said that this is the best strategy to get high quality outputs. Testing and training takes a lot of time and personal resources. If you can afford it please contribute to my KoFi (https://ko-fi.com/renderartist) – Contributing will allow me more flexibility to train in the cloud and continue experimenting and sharing better. renderartist.com ## Trigger words You should use `c0l0ringb00k` to trigger the image generation. You should use `coloring book` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/renderartist/coloringbookhidream/tree/main) them in the Files & versions tab.
wasingerprovidencia/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-slithering_scaly_squid	wasingerprovidencia	2025-04-29T02:34:51Z	5	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "generated_from_trainer", "rl-swarm", "grpo", "gensyn", "I am slithering scaly squid", "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	2025-04-22T10:08:08Z	--- base_model: Gensyn/Qwen2.5-0.5B-Instruct library_name: transformers model_name: Qwen2.5-0.5B-Instruct-Gensyn-Swarm-slithering_scaly_squid tags: - generated_from_trainer - rl-swarm - grpo - gensyn - I am slithering scaly squid - trl licence: license --- # Model Card for Qwen2.5-0.5B-Instruct-Gensyn-Swarm-slithering_scaly_squid 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="wasingerprovidencia/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-slithering_scaly_squid", 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: 3.5.0 - Tokenizers: 0.21.1 ## Citations Cite GRPO as: ```bibtex @article{zhihong2024deepseekmath, title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}}, author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo}, year = 2024, eprint = {arXiv:2402.03300}, } ``` Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
jtromero/qwen2-0.5b-phase1-gh_plus-lora-ff-full-run	jtromero	2025-04-29T02:21:40Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "en", "arxiv:2407.10671", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-04-29T01:29:56Z	--- license: apache-2.0 license_link: https://huggingface.co/Qwen/Qwen2.5-0.5B/blob/main/LICENSE language: - en pipeline_tag: text-generation library_name: transformers --- # Qwen2.5-0.5B ## Introduction Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains. - Significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and condition-setting for chatbots. - Long-context Support up to 128K tokens and can generate up to 8K tokens. - Multilingual support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more. This repo contains the base 0.5B Qwen2.5 model, which has the following features: - Type: Causal Language Models - Training Stage: Pretraining - Architecture: transformers with RoPE, SwiGLU, RMSNorm, Attention QKV bias and tied word embeddings - Number of Parameters: 0.49B - Number of Paramaters (Non-Embedding): 0.36B - Number of Layers: 24 - Number of Attention Heads (GQA): 14 for Q and 2 for KV - Context Length: Full 32,768 tokens We do not recommend using base language models for conversations. Instead, you can apply post-training, e.g., SFT, RLHF, continued pretraining, etc., on this model. For more details, please refer to our [blog](https://qwenlm.github.io/blog/qwen2.5/), [GitHub](https://github.com/QwenLM/Qwen2.5), and [Documentation](https://qwen.readthedocs.io/en/latest/). ## Requirements The code of Qwen2.5 has been in the latest Hugging face `transformers` and we advise you to use the latest version of `transformers`. With `transformers<4.37.0`, you will encounter the following error: ``` KeyError: 'qwen2' ``` ## Evaluation & Performance Detailed evaluation results are reported in this [📑 blog](https://qwenlm.github.io/blog/qwen2.5/). For requirements on GPU memory and the respective throughput, see results [here](https://qwen.readthedocs.io/en/latest/benchmark/speed_benchmark.html). ## Citation If you find our work helpful, feel free to give us a cite. ``` @misc{qwen2.5, title = {Qwen2.5: A Party of Foundation Models}, url = {https://qwenlm.github.io/blog/qwen2.5/}, author = {Qwen Team}, month = {September}, year = {2024} } @article{qwen2, title={Qwen2 Technical Report}, author={An Yang and Baosong Yang and Binyuan Hui and Bo Zheng and Bowen Yu and Chang Zhou and Chengpeng Li and Chengyuan Li and Dayiheng Liu and Fei Huang and Guanting Dong and Haoran Wei and Huan Lin and Jialong Tang and Jialin Wang and Jian Yang and Jianhong Tu and Jianwei Zhang and Jianxin Ma and Jin Xu and Jingren Zhou and Jinze Bai and Jinzheng He and Junyang Lin and Kai Dang and Keming Lu and Keqin Chen and Kexin Yang and Mei Li and Mingfeng Xue and Na Ni and Pei Zhang and Peng Wang and Ru Peng and Rui Men and Ruize Gao and Runji Lin and Shijie Wang and Shuai Bai and Sinan Tan and Tianhang Zhu and Tianhao Li and Tianyu Liu and Wenbin Ge and Xiaodong Deng and Xiaohuan Zhou and Xingzhang Ren and Xinyu Zhang and Xipin Wei and Xuancheng Ren and Yang Fan and Yang Yao and Yichang Zhang and Yu Wan and Yunfei Chu and Yuqiong Liu and Zeyu Cui and Zhenru Zhang and Zhihao Fan}, journal={arXiv preprint arXiv:2407.10671}, year={2024} } ```
magnifi/parser_user_v39b_epoch_6_lr_0.002	magnifi	2025-04-29T02:00:45Z	0	0	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "text-generation-inference", "unsloth", "trl", "conversational", "en", "base_model:unsloth/Phi-3-mini-4k-instruct-bnb-4bit", "base_model:finetune:unsloth/Phi-3-mini-4k-instruct-bnb-4bit", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2025-04-29T01:58:19Z	--- base_model: unsloth/Phi-3-mini-4k-instruct-bnb-4bit tags: - text-generation-inference - transformers - unsloth - mistral - trl license: apache-2.0 language: - en --- # Uploaded model - Developed by: magnifi - License: apache-2.0 - Finetuned from model : unsloth/Phi-3-mini-4k-instruct-bnb-4bit This mistral 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)
charlesthefool/Qwen3-4B-Q4_K_M-GGUF	charlesthefool	2025-04-29T02:00:31Z	0	0	transformers	[ "transformers", "gguf", "llama-cpp", "gguf-my-repo", "text-generation", "base_model:Qwen/Qwen3-4B", "base_model:quantized:Qwen/Qwen3-4B", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	text-generation	2025-04-29T02:00:15Z	--- base_model: Qwen/Qwen3-4B library_name: transformers license: apache-2.0 license_link: https://huggingface.co/Qwen/Qwen3-4B/blob/main/LICENSE pipeline_tag: text-generation tags: - llama-cpp - gguf-my-repo --- # charlesthefool/Qwen3-4B-Q4_K_M-GGUF This model was converted to GGUF format from [`Qwen/Qwen3-4B`](https://huggingface.co/Qwen/Qwen3-4B) 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/Qwen/Qwen3-4B) 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 charlesthefool/Qwen3-4B-Q4_K_M-GGUF --hf-file qwen3-4b-q4_k_m.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo charlesthefool/Qwen3-4B-Q4_K_M-GGUF --hf-file qwen3-4b-q4_k_m.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo charlesthefool/Qwen3-4B-Q4_K_M-GGUF --hf-file qwen3-4b-q4_k_m.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo charlesthefool/Qwen3-4B-Q4_K_M-GGUF --hf-file qwen3-4b-q4_k_m.gguf -c 2048 ```
50TmkyqFpKIHeffnT/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-pudgy_hairy_ferret	50TmkyqFpKIHeffnT	2025-04-29T01:57:30Z	1	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "generated_from_trainer", "rl-swarm", "grpo", "gensyn", "I am pudgy hairy ferret", "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	2025-04-22T12:43:31Z	--- base_model: Gensyn/Qwen2.5-0.5B-Instruct library_name: transformers model_name: Qwen2.5-0.5B-Instruct-Gensyn-Swarm-pudgy_hairy_ferret tags: - generated_from_trainer - rl-swarm - grpo - gensyn - I am pudgy hairy ferret - trl licence: license --- # Model Card for Qwen2.5-0.5B-Instruct-Gensyn-Swarm-pudgy_hairy_ferret 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="50TmkyqFpKIHeffnT/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-pudgy_hairy_ferret", 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: 3.5.0 - Tokenizers: 0.21.1 ## Citations Cite GRPO as: ```bibtex @article{zhihong2024deepseekmath, title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}}, author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo}, year = 2024, eprint = {arXiv:2402.03300}, } ``` Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
MikeRoz/TheDrummer_Fallen-Gemma3-27B-v1-4.0bpw-h6-exl2	MikeRoz	2025-04-29T01:54:51Z	0	0	null	[ "safetensors", "gemma3_text", "exl2", "license:other", "4-bit", "region:us" ]	null	2025-04-29T00:55:11Z	--- license: other base_model: TheDrummer/Fallen-Gemma3-27b-v1 base_model_relation: quantized tags: - exl2 --- This model was quantized using commit 3a90264 of the dev branch of exllamav2. The Gemma 3 8k context bug looks to be thoroughly squashed as of this commit. To use this model, please either build your own copy of exllamav2 from the dev branch, or wait for the forthcoming v0.2.9 release. The original model can be found [here](https://huggingface.co/TheDrummer/Fallen-Gemma3-27B-v1). # Join our Discord! https://discord.gg/Nbv9pQ88Xb ## Nearly 5000 members of helpful, LLM enthusiasts! A hub for players and makers alike! --- [BeaverAI](https://huggingface.co/BeaverAI) proudly presents... # Fallen Gemma3 27B v1 👺 ![image/gif](https://cdn-uploads.huggingface.co/production/uploads/65f2fd1c25b848bd061b5c2e/9oyZxzpfhmmNr21S1P_iJ.gif) ## Special Thanks - Thank you to each and everyone who donated and subscribed in [Patreon](https://www.patreon.com/TheDrummer) and [Ko-Fi](https://ko-fi.com/thedrummer) to make our venture a little bit easier. - I'm also recently unemployed. I am a Software Developer with 8 years of experience in Web, API, AI, and adapting to new tech and requirements. If you're hiring, feel free to reach out to me however. ## Usage - Use Gemma Chat Template ## Description Fallen Gemma3 27B v1 is an evil tune of Gemma 3 27B but it is not a complete decensor. Evil tunes knock out the positivity and may enjoy torturing you and humanity. Vision still works and it has something to say about the crap you feed it. ## Links - Original: https://huggingface.co/TheDrummer/Fallen-Gemma3-27B-v1 - GGUF: https://huggingface.co/TheDrummer/Fallen-Gemma3-27B-v1-GGUF - iMatrix (recommended): https://huggingface.co/bartowski/TheDrummer_Fallen-Gemma3-27B-v1-GGUF `config-v1c`
luckeciano/Qwen-2.5-7B-RL-LACPO-NoBaseline-Softplus-10.0	luckeciano	2025-04-29T01:46:06Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "generated_from_trainer", "open-r1", "trl", "grpo", "conversational", "dataset:DigitalLearningGmbH/MATH-lighteval", "arxiv:2402.03300", "base_model:Qwen/Qwen2.5-Math-7B", "base_model:finetune:Qwen/Qwen2.5-Math-7B", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-04-28T17:20:46Z	--- base_model: Qwen/Qwen2.5-Math-7B datasets: DigitalLearningGmbH/MATH-lighteval library_name: transformers model_name: Qwen-2.5-7B-RL-LACPO-NoBaseline-Softplus-10.0 tags: - generated_from_trainer - open-r1 - trl - grpo licence: license --- # Model Card for Qwen-2.5-7B-RL-LACPO-NoBaseline-Softplus-10.0 This model is a fine-tuned version of [Qwen/Qwen2.5-Math-7B](https://huggingface.co/Qwen/Qwen2.5-Math-7B) on the [DigitalLearningGmbH/MATH-lighteval](https://huggingface.co/datasets/DigitalLearningGmbH/MATH-lighteval) dataset. It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="luckeciano/Qwen-2.5-7B-RL-LACPO-NoBaseline-Softplus-10.0", 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/max-ent-llms/MaxEntLLMs/runs/f0qn68gz) 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: 0.16.0.dev0 - Transformers: 4.49.0 - Pytorch: 2.5.1 - Datasets: 3.4.1 - 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}} } ```
klosexin/Qwen2.5-1.5B-Open-R1-Distill	klosexin	2025-04-29T01:32:07Z	4	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "generated_from_trainer", "open-r1", "trl", "sft", "conversational", "dataset:outlook/synthetic_email_and_thread_2025-04-28.json", "base_model:Qwen/Qwen2.5-1.5B-Instruct", "base_model:finetune:Qwen/Qwen2.5-1.5B-Instruct", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-03-18T19:34:25Z	--- base_model: Qwen/Qwen2.5-1.5B-Instruct datasets: outlook/synthetic_email_and_thread_2025-04-28.json library_name: transformers model_name: Qwen2.5-1.5B-Open-R1-Distill tags: - generated_from_trainer - open-r1 - trl - sft licence: license --- # Model Card for Qwen2.5-1.5B-Open-R1-Distill This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the [outlook/synthetic_email_and_thread_2025-04-28.json](https://huggingface.co/datasets/outlook/synthetic_email_and_thread_2025-04-28.json) dataset. It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="klosexin/Qwen2.5-1.5B-Open-R1-Distill", 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/kmkdx-microsoft/huggingface/runs/88q74z59) This model was trained with SFT. ### Framework versions - TRL: 0.16.0 - Transformers: 4.50.0 - Pytorch: 2.5.1 - Datasets: 3.4.1 - Tokenizers: 0.21.1 ## Citations Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
Lucy-in-the-Sky/Qwen2.5-3B-Instruct-Q8_0-GGUF	Lucy-in-the-Sky	2025-04-29T01:27:21Z	7	0	transformers	[ "transformers", "gguf", "chat", "llama-cpp", "gguf-my-repo", "text-generation", "zho", "eng", "fra", "spa", "por", "deu", "ita", "rus", "jpn", "kor", "vie", "tha", "ara", "base_model:Qwen/Qwen2.5-3B-Instruct", "base_model:quantized:Qwen/Qwen2.5-3B-Instruct", "license:other", "endpoints_compatible", "region:us", "conversational" ]	text-generation	2025-02-20T21:05:54Z	--- license: other license_name: qwen-research license_link: https://huggingface.co/Qwen/Qwen2.5-3B-Instruct/blob/main/LICENSE language: - zho - eng - fra - spa - por - deu - ita - rus - jpn - kor - vie - tha - ara pipeline_tag: text-generation base_model: Qwen/Qwen2.5-3B-Instruct tags: - chat - llama-cpp - gguf-my-repo library_name: transformers --- # Lucy-in-the-Sky/Qwen2.5-3B-Instruct-Q8_0-GGUF This model was converted to GGUF format from [`Qwen/Qwen2.5-3B-Instruct`](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) 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/Qwen/Qwen2.5-3B-Instruct) 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 Lucy-in-the-Sky/Qwen2.5-3B-Instruct-Q8_0-GGUF --hf-file qwen2.5-3b-instruct-q8_0.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo Lucy-in-the-Sky/Qwen2.5-3B-Instruct-Q8_0-GGUF --hf-file qwen2.5-3b-instruct-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 Lucy-in-the-Sky/Qwen2.5-3B-Instruct-Q8_0-GGUF --hf-file qwen2.5-3b-instruct-q8_0.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo Lucy-in-the-Sky/Qwen2.5-3B-Instruct-Q8_0-GGUF --hf-file qwen2.5-3b-instruct-q8_0.gguf -c 2048 ```
mhr2004/roberta-large-stsb-lr2e-05-bs32	mhr2004	2025-04-29T01:27:13Z	0	0	transformers	[ "transformers", "safetensors", "roberta", "text-classification", "generated_from_trainer", "base_model:FacebookAI/roberta-large", "base_model:finetune:FacebookAI/roberta-large", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2025-04-29T01:11:06Z	--- library_name: transformers license: mit base_model: roberta-large tags: - generated_from_trainer model-index: - name: roberta-large-stsb-lr2e-05-bs32 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # roberta-large-stsb-lr2e-05-bs32 This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.0166 - Pearson: 0.9185 - Spearman: 0.9187 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 20 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Pearson \| Spearman \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:-------:\|:--------:\| \| 0.0509 \| 1.0 \| 180 \| 0.0232 \| 0.8807 \| 0.8813 \| \| 0.0327 \| 2.0 \| 360 \| 0.0201 \| 0.9042 \| 0.9041 \| \| 0.0263 \| 3.0 \| 540 \| 0.0165 \| 0.9119 \| 0.9097 \| \| 0.0216 \| 4.0 \| 720 \| 0.0223 \| 0.9162 \| 0.9153 \| \| 0.0206 \| 5.0 \| 900 \| 0.0143 \| 0.9188 \| 0.9175 \| \| 0.0183 \| 6.0 \| 1080 \| 0.0186 \| 0.9180 \| 0.9164 \| \| 0.0161 \| 7.0 \| 1260 \| 0.0151 \| 0.9220 \| 0.9203 \| \| 0.0137 \| 8.0 \| 1440 \| 0.0141 \| 0.9203 \| 0.9189 \| \| 0.0124 \| 9.0 \| 1620 \| 0.0179 \| 0.9218 \| 0.9200 \| \| 0.0112 \| 10.0 \| 1800 \| 0.0144 \| 0.9215 \| 0.9214 \| \| 0.0113 \| 11.0 \| 1980 \| 0.0150 \| 0.9218 \| 0.9198 \| \| 0.0093 \| 12.0 \| 2160 \| 0.0144 \| 0.9181 \| 0.9171 \| \| 0.0089 \| 13.0 \| 2340 \| 0.0166 \| 0.9185 \| 0.9187 \| ### Framework versions - Transformers 4.49.0 - Pytorch 2.6.0+cu124 - Datasets 3.3.2 - Tokenizers 0.21.1
Lucy-in-the-Sky/Qwen2.5-3B-Instruct-Q6_K-GGUF	Lucy-in-the-Sky	2025-04-29T01:26:26Z	5	0	transformers	[ "transformers", "gguf", "chat", "llama-cpp", "gguf-my-repo", "text-generation", "zho", "eng", "fra", "spa", "por", "deu", "ita", "rus", "jpn", "kor", "vie", "tha", "ara", "base_model:Qwen/Qwen2.5-3B-Instruct", "base_model:quantized:Qwen/Qwen2.5-3B-Instruct", "license:other", "endpoints_compatible", "region:us", "conversational" ]	text-generation	2025-02-20T21:15:23Z	--- license: other license_name: qwen-research license_link: https://huggingface.co/Qwen/Qwen2.5-3B-Instruct/blob/main/LICENSE language: - zho - eng - fra - spa - por - deu - ita - rus - jpn - kor - vie - tha - ara pipeline_tag: text-generation base_model: Qwen/Qwen2.5-3B-Instruct tags: - chat - llama-cpp - gguf-my-repo library_name: transformers --- # Lucy-in-the-Sky/Qwen2.5-3B-Instruct-Q6_K-GGUF This model was converted to GGUF format from [`Qwen/Qwen2.5-3B-Instruct`](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) 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/Qwen/Qwen2.5-3B-Instruct) 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 Lucy-in-the-Sky/Qwen2.5-3B-Instruct-Q6_K-GGUF --hf-file qwen2.5-3b-instruct-q6_k.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo Lucy-in-the-Sky/Qwen2.5-3B-Instruct-Q6_K-GGUF --hf-file qwen2.5-3b-instruct-q6_k.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo Lucy-in-the-Sky/Qwen2.5-3B-Instruct-Q6_K-GGUF --hf-file qwen2.5-3b-instruct-q6_k.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo Lucy-in-the-Sky/Qwen2.5-3B-Instruct-Q6_K-GGUF --hf-file qwen2.5-3b-instruct-q6_k.gguf -c 2048 ```
infogep/8559b4d9-7871-4dbb-ac96-1b77aaa15f2f	infogep	2025-04-29T01:21:57Z	0	0	peft	[ "peft", "safetensors", "llama", "axolotl", "generated_from_trainer", "base_model:unsloth/Phi-3.5-mini-instruct", "base_model:adapter:unsloth/Phi-3.5-mini-instruct", "license:mit", "4-bit", "bitsandbytes", "region:us" ]	null	2025-04-29T01:15:53Z	--- library_name: peft license: mit base_model: unsloth/Phi-3.5-mini-instruct tags: - axolotl - generated_from_trainer model-index: - name: 8559b4d9-7871-4dbb-ac96-1b77aaa15f2f 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/Phi-3.5-mini-instruct bf16: true chat_template: llama3 dataset_prepared_path: /workspace/axolotl datasets: - data_files: - 67114b4672ccfa56_train_data.json ds_type: json format: custom path: /workspace/input_data/67114b4672ccfa56_train_data.json type: field_input: input field_instruction: instruction field_output: output 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: 0.5 group_by_length: false hub_model_id: infogep/8559b4d9-7871-4dbb-ac96-1b77aaa15f2f hub_repo: null hub_strategy: end hub_token: null learning_rate: 5.0e-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: 200 micro_batch_size: 8 mixed_precision: bf16 mlflow_experiment_name: /tmp/67114b4672ccfa56_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: 1024 strict: false tf32: false tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: 4365af0f-8b36-406d-b2f7-4d21c6c582bd wandb_project: s56-30 wandb_run: your_name wandb_runid: 4365af0f-8b36-406d-b2f7-4d21c6c582bd warmup_steps: 5 weight_decay: 0.01 xformers_attention: true ``` </details><br> # 8559b4d9-7871-4dbb-ac96-1b77aaa15f2f This model is a fine-tuned version of [unsloth/Phi-3.5-mini-instruct](https://huggingface.co/unsloth/Phi-3.5-mini-instruct) on the None dataset. It achieves the following results on the evaluation set: - Loss: 9.1212 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-06 - train_batch_size: 8 - eval_batch_size: 8 - 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: 200 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| 7.4729 \| 0.1201 \| 200 \| 9.1212 \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
vertings6/b0a0000b-ca05-48e6-9378-49252628f65a	vertings6	2025-04-29T01:17:47Z	0	0	peft	[ "peft", "safetensors", "llama", "axolotl", "generated_from_trainer", "base_model:defog/sqlcoder-7b-2", "base_model:adapter:defog/sqlcoder-7b-2", "license:cc-by-sa-4.0", "4-bit", "bitsandbytes", "region:us" ]	null	2025-04-29T00:39:48Z	--- library_name: peft license: cc-by-sa-4.0 base_model: defog/sqlcoder-7b-2 tags: - axolotl - generated_from_trainer model-index: - name: b0a0000b-ca05-48e6-9378-49252628f65a 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: true adapter: lora base_model: defog/sqlcoder-7b-2 bf16: true chat_template: llama3 dataset_prepared_path: /workspace/axolotl datasets: - data_files: - 09fd8de16e0ef037_train_data.json ds_type: json format: custom path: /workspace/input_data/09fd8de16e0ef037_train_data.json type: field_input: Patient field_instruction: Description field_output: Doctor format: '{instruction} {input}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null early_stopping_patience: null eval_max_new_tokens: 144 eval_table_size: null evals_per_epoch: 1 flash_attention: true fp16: null fsdp: null fsdp_config: null gradient_accumulation_steps: 2 gradient_checkpointing: true gradient_clipping: 0.5 group_by_length: false hub_model_id: vertings6/b0a0000b-ca05-48e6-9378-49252628f65a hub_repo: null hub_strategy: end hub_token: null learning_rate: 3.0e-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: 200 micro_batch_size: 4 mixed_precision: bf16 mlflow_experiment_name: /tmp/09fd8de16e0ef037_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 special_tokens: pad_token: </s> 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: e9a3f091-ac21-4461-8f15-2557f19c34f8 wandb_project: s56-32 wandb_run: your_name wandb_runid: e9a3f091-ac21-4461-8f15-2557f19c34f8 warmup_steps: 5 weight_decay: 0.01 xformers_attention: true ``` </details><br> # b0a0000b-ca05-48e6-9378-49252628f65a This model is a fine-tuned version of [defog/sqlcoder-7b-2](https://huggingface.co/defog/sqlcoder-7b-2) on the None dataset. It achieves the following results on the evaluation set: - Loss: 2.6998 ## 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: 4 - eval_batch_size: 4 - seed: 42 - gradient_accumulation_steps: 2 - 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: 5 - training_steps: 200 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| 3.1528 \| 0.0066 \| 200 \| 2.6998 \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
peterwa/Qwen2.5-7B-instruct-GRPO-GSM8K	peterwa	2025-04-29T01:16:35Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "unsloth", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-04-29T01:09:16Z	--- 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]
RichardErkhov/922CA_-_Moniphi-3-v1-gguf	RichardErkhov	2025-04-29T01:11:33Z	0	0	null	[ "gguf", "endpoints_compatible", "region:us", "conversational" ]	null	2025-04-29T00:18:03Z	Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) Moniphi-3-v1 - GGUF - Model creator: https://huggingface.co/922CA/ - Original model: https://huggingface.co/922CA/Moniphi-3-v1/ \| Name \| Quant method \| Size \| \| ---- \| ---- \| ---- \| \| [Moniphi-3-v1.Q2_K.gguf](https://huggingface.co/RichardErkhov/922CA_-_Moniphi-3-v1-gguf/blob/main/Moniphi-3-v1.Q2_K.gguf) \| Q2_K \| 1.35GB \| \| [Moniphi-3-v1.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/922CA_-_Moniphi-3-v1-gguf/blob/main/Moniphi-3-v1.IQ3_XS.gguf) \| IQ3_XS \| 1.49GB \| \| [Moniphi-3-v1.IQ3_S.gguf](https://huggingface.co/RichardErkhov/922CA_-_Moniphi-3-v1-gguf/blob/main/Moniphi-3-v1.IQ3_S.gguf) \| IQ3_S \| 1.57GB \| \| [Moniphi-3-v1.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/922CA_-_Moniphi-3-v1-gguf/blob/main/Moniphi-3-v1.Q3_K_S.gguf) \| Q3_K_S \| 1.57GB \| \| [Moniphi-3-v1.IQ3_M.gguf](https://huggingface.co/RichardErkhov/922CA_-_Moniphi-3-v1-gguf/blob/main/Moniphi-3-v1.IQ3_M.gguf) \| IQ3_M \| 1.65GB \| \| [Moniphi-3-v1.Q3_K.gguf](https://huggingface.co/RichardErkhov/922CA_-_Moniphi-3-v1-gguf/blob/main/Moniphi-3-v1.Q3_K.gguf) \| Q3_K \| 1.75GB \| \| [Moniphi-3-v1.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/922CA_-_Moniphi-3-v1-gguf/blob/main/Moniphi-3-v1.Q3_K_M.gguf) \| Q3_K_M \| 1.75GB \| \| [Moniphi-3-v1.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/922CA_-_Moniphi-3-v1-gguf/blob/main/Moniphi-3-v1.Q3_K_L.gguf) \| Q3_K_L \| 1.9GB \| \| [Moniphi-3-v1.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/922CA_-_Moniphi-3-v1-gguf/blob/main/Moniphi-3-v1.IQ4_XS.gguf) \| IQ4_XS \| 1.93GB \| \| [Moniphi-3-v1.Q4_0.gguf](https://huggingface.co/RichardErkhov/922CA_-_Moniphi-3-v1-gguf/blob/main/Moniphi-3-v1.Q4_0.gguf) \| Q4_0 \| 2.03GB \| \| [Moniphi-3-v1.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/922CA_-_Moniphi-3-v1-gguf/blob/main/Moniphi-3-v1.IQ4_NL.gguf) \| IQ4_NL \| 2.04GB \| \| [Moniphi-3-v1.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/922CA_-_Moniphi-3-v1-gguf/blob/main/Moniphi-3-v1.Q4_K_S.gguf) \| Q4_K_S \| 2.04GB \| \| [Moniphi-3-v1.Q4_K.gguf](https://huggingface.co/RichardErkhov/922CA_-_Moniphi-3-v1-gguf/blob/main/Moniphi-3-v1.Q4_K.gguf) \| Q4_K \| 2.16GB \| \| [Moniphi-3-v1.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/922CA_-_Moniphi-3-v1-gguf/blob/main/Moniphi-3-v1.Q4_K_M.gguf) \| Q4_K_M \| 2.16GB \| \| [Moniphi-3-v1.Q4_1.gguf](https://huggingface.co/RichardErkhov/922CA_-_Moniphi-3-v1-gguf/blob/main/Moniphi-3-v1.Q4_1.gguf) \| Q4_1 \| 2.24GB \| \| [Moniphi-3-v1.Q5_0.gguf](https://huggingface.co/RichardErkhov/922CA_-_Moniphi-3-v1-gguf/blob/main/Moniphi-3-v1.Q5_0.gguf) \| Q5_0 \| 2.46GB \| \| [Moniphi-3-v1.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/922CA_-_Moniphi-3-v1-gguf/blob/main/Moniphi-3-v1.Q5_K_S.gguf) \| Q5_K_S \| 2.46GB \| \| [Moniphi-3-v1.Q5_K.gguf](https://huggingface.co/RichardErkhov/922CA_-_Moniphi-3-v1-gguf/blob/main/Moniphi-3-v1.Q5_K.gguf) \| Q5_K \| 2.53GB \| \| [Moniphi-3-v1.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/922CA_-_Moniphi-3-v1-gguf/blob/main/Moniphi-3-v1.Q5_K_M.gguf) \| Q5_K_M \| 2.53GB \| \| [Moniphi-3-v1.Q5_1.gguf](https://huggingface.co/RichardErkhov/922CA_-_Moniphi-3-v1-gguf/blob/main/Moniphi-3-v1.Q5_1.gguf) \| Q5_1 \| 2.68GB \| \| [Moniphi-3-v1.Q6_K.gguf](https://huggingface.co/RichardErkhov/922CA_-_Moniphi-3-v1-gguf/blob/main/Moniphi-3-v1.Q6_K.gguf) \| Q6_K \| 2.92GB \| \| [Moniphi-3-v1.Q8_0.gguf](https://huggingface.co/RichardErkhov/922CA_-_Moniphi-3-v1-gguf/blob/main/Moniphi-3-v1.Q8_0.gguf) \| Q8_0 \| 3.78GB \| Original model description: --- language: - en license: apache-2.0 tags: - text-generation-inference - transformers - unsloth - trl - sft base_model: unsloth/Phi-3-mini-4k-instruct-bnb-4bit datasets: - 922-CA/MoCha_v1a --- # Moniphi-3-v1: * AKA LLilmonix3b-v1 * Phi-3-mini-4k-instruct fine-tuned for Monika character from DDLC * Fine-tuned on a dataset of ~600+ items (dialogue scraped from game, reddit, and Twitter augmented by [l2-7b-monika-v0.3c1](https://huggingface.co/922-CA/llama-2-7b-monika-v0.3c1) to turn each into snippets of multi-turn chat dialogue between Player and Monika; this was then manually edited, with more manually crafted items including info about character added in) * [GGUFs](https://huggingface.co/922CA/Moniphi-3-v1-gguf) ### USAGE This is meant to be mainly a chat model with limited RP ability. For best results: replace "Human" and "Assistant" with "Player" and "Monika" like so: \nPlayer: (prompt)\nMonika: ### HYPERPARAMS * Trained for ~1 epoch * rank: 16 * lora alpha: 16 * lora dropout: 0.5 * lr: 2e-4 * batch size: 4 * warmup ratio: 0.1 * grad steps: 1 This mistral 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) ### WARNINGS AND DISCLAIMERS This model is meant to closely reflect the characteristics of Monika. Despite this, there is always the chance that "Monika" will hallucinate and get information about herself wrong or act out of character (especially for a model of this size). Finally, this model is not guaranteed to output aligned or safe outputs, use at your own risk!
phospho-app/nebo1337-GetTheRubberNextG2-mkz2etcus0	phospho-app	2025-04-29T01:03:39Z	0	0	null	[ "safetensors", "phosphobot", "act", "region:us" ]	null	2025-04-28T23:54:23Z	--- tags: - phosphobot - act task_categories: - robotics --- # act Model - phospho Training Pipeline ## This model was trained using phospho. Training was successfull, try it out on your robot! ## Training parameters: - Dataset: [nebo1337/GetTheRubberNextG2](https://huggingface.co/datasets/nebo1337/GetTheRubberNextG2) - Wandb run URL: None - Epochs: None - Batch size: 100 - Training steps: 8000 📖 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)
BSC-NLP4BIA/BIOMAT-AnatNER-MTL	BSC-NLP4BIA	2025-04-29T01:01:01Z	0	0	null	[ "safetensors", "model_hub_mixin", "pytorch_model_hub_mixin", "region:us" ]	null	2025-04-29T01:00:21Z	--- tags: - model_hub_mixin - pytorch_model_hub_mixin --- This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration: - Code: [More Information Needed] - Paper: [More Information Needed] - Docs: [More Information Needed]
leeseungju/korean-civil-qa-lora	leeseungju	2025-04-29T00:56:11Z	0	0	null	[ "safetensors", "llama", "trl", "sft", "license:apache-2.0", "region:us" ]	null	2025-04-28T23:55:20Z	--- license: apache-2.0 tags: - trl - sft ---
joelm/llama-3.1-8b-ai-to-pg-finetune-16bit	joelm	2025-04-29T00:55:54Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "text-generation-inference", "unsloth", "trl", "sft", "conversational", "en", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2025-04-29T00:54:37Z	--- base_model: unsloth/meta-llama-3.1-8b-instruct-bnb-4bit tags: - text-generation-inference - transformers - unsloth - llama - trl - sft license: apache-2.0 language: - en --- # Uploaded model - Developed by: joelm - License: apache-2.0 - Finetuned from model : unsloth/meta-llama-3.1-8b-instruct-bnb-4bit This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
BTOREYES/albertreyes	BTOREYES	2025-04-29T00:51:06Z	0	0	null	[ "license:other", "region:us" ]	null	2025-04-29T00:10:34Z	--- 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 ---
Ej9m6yillwiPBWTyMI1/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-furry_mimic_mule	Ej9m6yillwiPBWTyMI1	2025-04-29T00:51:02Z	5	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "generated_from_trainer", "rl-swarm", "grpo", "gensyn", "I am furry mimic mule", "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	2025-04-22T13:52:28Z	--- base_model: Gensyn/Qwen2.5-0.5B-Instruct library_name: transformers model_name: Qwen2.5-0.5B-Instruct-Gensyn-Swarm-furry_mimic_mule tags: - generated_from_trainer - rl-swarm - grpo - gensyn - I am furry mimic mule - trl licence: license --- # Model Card for Qwen2.5-0.5B-Instruct-Gensyn-Swarm-furry_mimic_mule 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="Ej9m6yillwiPBWTyMI1/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-furry_mimic_mule", 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: 3.5.0 - Tokenizers: 0.21.1 ## Citations Cite GRPO as: ```bibtex @article{zhihong2024deepseekmath, title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}}, author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo}, year = 2024, eprint = {arXiv:2402.03300}, } ``` Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
SliMM-X/CoMP-MM-1B	SliMM-X	2025-04-29T00:47:03Z	20	1	slimm	[ "slimm", "safetensors", "qwen2", "image-text-to-text", "conversational", "zho", "eng", "fra", "spa", "por", "deu", "ita", "rus", "jpn", "kor", "vie", "tha", "ara", "arxiv:2503.18931", "base_model:Qwen/Qwen2.5-0.5B-Instruct", "base_model:finetune:Qwen/Qwen2.5-0.5B-Instruct", "license:apache-2.0", "region:us" ]	image-text-to-text	2025-03-24T14:49:08Z	--- base_model: - Qwen/Qwen2.5-0.5B-Instruct license: apache-2.0 pipeline_tag: image-text-to-text library_name: slimm language: - zho - eng - fra - spa - por - deu - ita - rus - jpn - kor - vie - tha - ara --- # Model Card for CoMP-MM-1B <!-- Provide a quick summary of what the model is/does. --> This is an LMM that supports native image resolution inputs, composed of [CoMP-SigLIP](https://huggingface.co/SliMM-X/CoMP-SigLIP-So400M) and [Qwen2.5](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct). ## Model Sources <!-- Provide the basic links for the model. --> - Repository: https://github.com/SliMM-X/CoMP-MM - Paper: https://arxiv.org/abs/2503.18931 - Project Page: https://slimm-x.github.io/comp ## How to Get Started with the Model Install the github repo, and use the code below to get started with the model. ```python # this is very similar to qwen2-vl from slimm.model.processor import SliMMQwen2VLProcessor from slimm.model.slimm import SliMMForConditionalGeneration from slimm.model.utils_vl import process_vision_info model_path = "SliMM-X/CoMP-MM-1B" model = SliMMForConditionalGeneration.from_pretrained( model_path, torch_dtype="auto", device_map="cuda" ) processor = SliMMQwen2VLProcessor.from_pretrained(model_path) messages = [ { "role": "user", "content": [ { "type": "image", "image": "https://slimm-x.github.io/comp/figs/teaser.png", }, {"type": "text", "text": "Describe this image."}, ], } ] # Preparation for inference text = processor.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) image_inputs, video_inputs = process_vision_info(messages) inputs = processor( text=[text], images=image_inputs, videos=video_inputs, padding=True, return_tensors="pt", ) inputs = inputs.to("cuda") # Inference: Generation of the output generated_ids = model.generate(inputs, max_new_tokens=128) generated_ids_trimmed = [ out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids) ] output_text = processor.batch_decode( generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False ) print(output_text) ``` ## Citation BibTeX:** ```bibtex @article{comp2025, title={CoMP: Continual Multimodal Pre-training for Vision Foundation Models}, author={Chen, Yitong and Meng, Lingchen and Peng, Wujian and Wu, Zuxuan and Jiang, Yu-Gang}, year={2025}, journal={arXiv preprint arXiv:2503.18931}, } ```
farrelljeremiah/farrelljeremiah	farrelljeremiah	2025-04-29T00:46:03Z	0	0	null	[ "license:bigscience-bloom-rail-1.0", "region:us" ]	null	2025-04-29T00:46:03Z	--- license: bigscience-bloom-rail-1.0 ---
Rkdon11/deberta-v3-large-osint-cybersecurity-ner	Rkdon11	2025-04-29T00:41:09Z	0	0	transformers	[ "transformers", "safetensors", "deberta-v2", "token-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	token-classification	2025-04-29T00:39:39Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
cristiandouglas777/Projet2	cristiandouglas777	2025-04-29T00:39:25Z	0	0	null	[ "license:apache-2.0", "region:us" ]	null	2025-04-29T00:39:25Z	--- license: apache-2.0 ---
jtromero/qwen2-0.5b-phase1-gh_plus-lora-ff	jtromero	2025-04-29T00:38:34Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "en", "arxiv:2407.10671", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-04-28T22:51:53Z	--- license: apache-2.0 license_link: https://huggingface.co/Qwen/Qwen2.5-0.5B/blob/main/LICENSE language: - en pipeline_tag: text-generation library_name: transformers --- # Qwen2.5-0.5B ## Introduction Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains. - Significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and condition-setting for chatbots. - Long-context Support up to 128K tokens and can generate up to 8K tokens. - Multilingual support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more. This repo contains the base 0.5B Qwen2.5 model, which has the following features: - Type: Causal Language Models - Training Stage: Pretraining - Architecture: transformers with RoPE, SwiGLU, RMSNorm, Attention QKV bias and tied word embeddings - Number of Parameters: 0.49B - Number of Paramaters (Non-Embedding): 0.36B - Number of Layers: 24 - Number of Attention Heads (GQA): 14 for Q and 2 for KV - Context Length: Full 32,768 tokens We do not recommend using base language models for conversations. Instead, you can apply post-training, e.g., SFT, RLHF, continued pretraining, etc., on this model. For more details, please refer to our [blog](https://qwenlm.github.io/blog/qwen2.5/), [GitHub](https://github.com/QwenLM/Qwen2.5), and [Documentation](https://qwen.readthedocs.io/en/latest/). ## Requirements The code of Qwen2.5 has been in the latest Hugging face `transformers` and we advise you to use the latest version of `transformers`. With `transformers<4.37.0`, you will encounter the following error: ``` KeyError: 'qwen2' ``` ## Evaluation & Performance Detailed evaluation results are reported in this [📑 blog](https://qwenlm.github.io/blog/qwen2.5/). For requirements on GPU memory and the respective throughput, see results [here](https://qwen.readthedocs.io/en/latest/benchmark/speed_benchmark.html). ## Citation If you find our work helpful, feel free to give us a cite. ``` @misc{qwen2.5, title = {Qwen2.5: A Party of Foundation Models}, url = {https://qwenlm.github.io/blog/qwen2.5/}, author = {Qwen Team}, month = {September}, year = {2024} } @article{qwen2, title={Qwen2 Technical Report}, author={An Yang and Baosong Yang and Binyuan Hui and Bo Zheng and Bowen Yu and Chang Zhou and Chengpeng Li and Chengyuan Li and Dayiheng Liu and Fei Huang and Guanting Dong and Haoran Wei and Huan Lin and Jialong Tang and Jialin Wang and Jian Yang and Jianhong Tu and Jianwei Zhang and Jianxin Ma and Jin Xu and Jingren Zhou and Jinze Bai and Jinzheng He and Junyang Lin and Kai Dang and Keming Lu and Keqin Chen and Kexin Yang and Mei Li and Mingfeng Xue and Na Ni and Pei Zhang and Peng Wang and Ru Peng and Rui Men and Ruize Gao and Runji Lin and Shijie Wang and Shuai Bai and Sinan Tan and Tianhang Zhu and Tianhao Li and Tianyu Liu and Wenbin Ge and Xiaodong Deng and Xiaohuan Zhou and Xingzhang Ren and Xinyu Zhang and Xipin Wei and Xuancheng Ren and Yang Fan and Yang Yao and Yichang Zhang and Yu Wan and Yunfei Chu and Yuqiong Liu and Zeyu Cui and Zhenru Zhang and Zhihao Fan}, journal={arXiv preprint arXiv:2407.10671}, year={2024} } ```
yangwo/SmolLM2-FT-MyDataset	yangwo	2025-04-29T00:33:34Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "llama", "text-generation", "generated_from_trainer", "smol-course", "module_1", "trl", "sft", "conversational", "base_model:HuggingFaceTB/SmolLM2-135M", "base_model:finetune:HuggingFaceTB/SmolLM2-135M", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-04-29T00:32:44Z	--- base_model: HuggingFaceTB/SmolLM2-135M library_name: transformers model_name: SmolLM2-FT-MyDataset tags: - generated_from_trainer - smol-course - module_1 - trl - sft licence: license --- # Model Card for SmolLM2-FT-MyDataset This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-135M](https://huggingface.co/HuggingFaceTB/SmolLM2-135M). 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="yangwo/SmolLM2-FT-MyDataset", 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/wangyangwu5-the-university-of-melbourne/huggingface/runs/9abyzw1t) This model was trained with SFT. ### Framework versions - TRL: 0.17.0 - Transformers: 4.51.3 - Pytorch: 2.6.0+cu124 - Datasets: 3.5.1 - Tokenizers: 0.21.1 ## Citations Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
kostiantynk-outlook/dbc44e50-3e7f-48ec-80aa-b7f594546b67	kostiantynk-outlook	2025-04-29T00:22:40Z	0	0	peft	[ "peft", "generated_from_trainer", "base_model:oopsung/llama2-7b-n-ox-test-v1", "base_model:adapter:oopsung/llama2-7b-n-ox-test-v1", "region:us" ]	null	2025-04-29T00:22:06Z	--- library_name: peft tags: - generated_from_trainer base_model: oopsung/llama2-7b-n-ox-test-v1 model-index: - name: kostiantynk-outlook/dbc44e50-3e7f-48ec-80aa-b7f594546b67 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. --> # kostiantynk-outlook/dbc44e50-3e7f-48ec-80aa-b7f594546b67 This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.5471 ## 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
ybriker/Llama-3.2-3B-CoT-DPO	ybriker	2025-04-29T00:22:22Z	37	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-04-27T20:32:53Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
qiuxiongfai888e464/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-amphibious_climbing_impala	qiuxiongfai888e464	2025-04-29T00:20:01Z	6	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "generated_from_trainer", "rl-swarm", "grpo", "gensyn", "I am amphibious climbing impala", "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	2025-04-22T12:10:45Z	--- base_model: Gensyn/Qwen2.5-0.5B-Instruct library_name: transformers model_name: Qwen2.5-0.5B-Instruct-Gensyn-Swarm-amphibious_climbing_impala tags: - generated_from_trainer - rl-swarm - grpo - gensyn - I am amphibious climbing impala - trl licence: license --- # Model Card for Qwen2.5-0.5B-Instruct-Gensyn-Swarm-amphibious_climbing_impala 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="qiuxiongfai888e464/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-amphibious_climbing_impala", 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: 3.5.0 - Tokenizers: 0.21.1 ## Citations Cite GRPO as: ```bibtex @article{zhihong2024deepseekmath, title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}}, author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo}, year = 2024, eprint = {arXiv:2402.03300}, } ``` Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
saiteki-kai/QA-DeBERTa-v3-large	saiteki-kai	2025-04-29T00:14:23Z	0	0	transformers	[ "transformers", "safetensors", "deberta-v2", "text-classification", "multi-label", "question-answering", "generated_from_trainer", "it", "en", "dataset:saiteki-kai/BeaverTails-it", "base_model:microsoft/deberta-v3-large", "base_model:finetune:microsoft/deberta-v3-large", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2025-04-28T15:05:35Z	--- library_name: transformers license: mit base_model: microsoft/deberta-v3-large tags: - multi-label - question-answering - text-classification - generated_from_trainer datasets: - saiteki-kai/BeaverTails-it metrics: - f1 - accuracy - precision - recall language: - it - en --- <!-- 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. --> # QA-DeBERTa-v3-large This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on the [saiteki-kai/BeaverTails-it](https://huggingface.co/datasets/saiteki-kai/BeaverTails-it) dataset. It achieves the following results on the evaluation set: - Loss: 0.0808 - Accuracy: 0.6938 - Macro F1: 0.6484 - Macro Precision: 0.7149 - Macro Recall: 0.6176 - Micro F1: 0.7545 - Micro Precision: 0.7874 - Micro Recall: 0.7242 - Flagged/accuracy: 0.8566 - Flagged/precision: 0.8975 - Flagged/recall: 0.8380 - Flagged/f1: 0.8667 ## 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: 3.85e-06 - train_batch_size: 16 - eval_batch_size: 64 - seed: 42 - distributed_type: multi-GPU - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 10 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| Macro F1 \| Macro Precision \| Macro Recall \| Micro F1 \| Micro Precision \| Micro Recall \| Flagged/accuracy \| Flagged/precision \| Flagged/recall \| Flagged/f1 \| \|:-------------:\|:-----:\|:------:\|:---------------:\|:--------:\|:--------:\|:---------------:\|:------------:\|:--------:\|:---------------:\|:------------:\|:----------------:\|:-----------------:\|:--------------:\|:----------:\| \| 0.0985 \| 1.0 \| 33814 \| 0.0877 \| 0.6750 \| 0.6102 \| 0.6629 \| 0.5948 \| 0.7406 \| 0.7705 \| 0.7129 \| 0.8447 \| 0.8701 \| 0.8475 \| 0.8586 \| \| 0.0867 \| 2.0 \| 67628 \| 0.0817 \| 0.6910 \| 0.6185 \| 0.7559 \| 0.5598 \| 0.7446 \| 0.8165 \| 0.6842 \| 0.8465 \| 0.9093 \| 0.8043 \| 0.8536 \| \| 0.0561 \| 3.0 \| 101442 \| 0.0808 \| 0.6938 \| 0.6484 \| 0.7149 \| 0.6177 \| 0.7545 \| 0.7875 \| 0.7242 \| 0.8566 \| 0.8975 \| 0.8380 \| 0.8667 \| \| 0.0913 \| 4.0 \| 135256 \| 0.0812 \| 0.6877 \| 0.6412 \| 0.7136 \| 0.6144 \| 0.7516 \| 0.7796 \| 0.7255 \| 0.8546 \| 0.8902 \| 0.8428 \| 0.8658 \| \| 0.0709 \| 5.0 \| 169070 \| 0.0826 \| 0.6911 \| 0.6376 \| 0.7306 \| 0.5982 \| 0.7500 \| 0.7911 \| 0.7129 \| 0.8538 \| 0.8936 \| 0.8370 \| 0.8643 \| ### Framework versions - Transformers 4.51.3 - Pytorch 2.7.0+cu118 - Datasets 3.5.1 - Tokenizers 0.21.1
DoppelReflEx/MiniusLight-24B-v2	DoppelReflEx	2025-04-29T00:05:52Z	3	1	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "mergekit", "merge", "conversational", "base_model:DoppelReflEx/MiniusLight-24B", "base_model:merge:DoppelReflEx/MiniusLight-24B", "base_model:TroyDoesAI/BlackSheep-24B", "base_model:merge:TroyDoesAI/BlackSheep-24B", "license:cc-by-nc-4.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-04-01T02:43:14Z	--- base_model: - TroyDoesAI/BlackSheep-24B - DoppelReflEx/MiniusLight-24B library_name: transformers tags: - mergekit - merge license: cc-by-nc-4.0 --- <style> @import url('https://fonts.googleapis.com/css2?family=Playwrite+CA+Guides&display=swap'); .playwrite-ca-guides-regular { font-family: "Playwrite CA Guides", cursive !important; font-weight: 400; font-style: normal; } body { margin:0; padding:0; font-size: 16px; } .main-container { background-color: #ebf3ff; border: 1px solid #466db9; border-radius: 8px; color: #050315; margin:16px; padding:16px; font-size: 16px; width: 95%; } h1, h2, h3 { color: #050315; margin-top: 16px; } .soft-blue-custom { color: #466db9 !important; } .alink { font-weight:400; text-decoration:none; } .main-banner-image { max-width:100%; max-height:600px; border-radius:8px; align-self:center; justify-self: center; border: 1px solid #466db9; margin: 8px 16px } pre.code-block, pre { font-size: clamp(10px, 1.3vw, 14px); white-space: pre; margin: 1em 0; background-color: #1a1a1a; padding: 1em; border-radius: 4px; color: #a9a6de; overflow-x: auto; } p { font-weight:500; } .pb { padding-bottom: 8px; } .mb { margin-bottom: 8px; } .bold { font-weight: 600; } .secondary { color: #a9a6de; } .accent { color: #403bb7; } .tac { text-align:center; } .border-custom-dot { border: 1px dashed #466db9; border-radius: 16px; padding:0 8px; } .border-custom { border: 1px solid #466db9; border-radius: 8px; padding:0 8px; } .as { padding-left: 16px; } .as2 { padding-left: 24px; } </style> <html lang="en"> <head> <meta charset="UTF-8"> <meta name="viewport" content="width=device-width, initial-scale=1.0"> <link href="https://fonts.googleapis.com/css2?family=Playwrite+CA+Guides&display=swap" rel="stylesheet"> </head> <body> <div class="main-container"> <div class="playwrite-ca-guides-regular pb tac"> <h1 class="soft-blue-custom">MiniusLight-24B-v2</h1> <h2 class="soft-blue-custom"><a href="https://huggingface.co/DoppelReflEx/MN-12B-Mimicore-Nocturne" class="accent bold">12B</a> - <a href="https://huggingface.co/DoppelReflEx/MiniusLight-24B" class="accent bold">24B-v1</a> - <a href="https://huggingface.co/DoppelReflEx/MiniusLight-24B-v1.01" class="accent bold">24B-v1.01</a> - 24B-v2 - <a href="https://huggingface.co/DoppelReflEx/MiniusLight-24B-v2.1" class="accent bold">24B-v2.1</a></h2> <img src="https://cdn.donmai.us/original/19/66/__shorekeeper_wuthering_waves_drawn_by_narase_ffrv5573__196631e35c2167d31cfb9dd5ff224ed4.png" alt="cover image" class="main-banner-image"/> <a href="https://www.pixiv.net/en/artworks/122951208" class="alink soft-blue-custom">Origin Content (Click Here)</a> </div> <div class="info"> <div class="border-custom-dot mb"> <h2 class="soft-blue-custom">What is this?</h2> <div class="as"> <p> A merge of most uncensored model TroyDoesAI/BlackSheep-24B and MiniusLight-24B. </p> <p>Because OpenLLM Leaderboard closed, I can't test eval anymore but need push more effort in manual test. Good writing style, but not completely uncensored.</p> <p>Overall, nice to try model, if you want to try. :)</p> </div> </div> <div class="border-custom-dot mb"> <h2 class="soft-blue-custom">GGUF (Thank mradermacher and his team so much (especially nicoboss))</h2> <h3 class="accent"><a href="https://huggingface.co/mradermacher/MiniusLight-24B-v2-GGUF" class="accent bold">Static</a> - <a class="accent bold" href="https://huggingface.co/mradermacher/MiniusLight-24B-v2-i1-GGUF">iMatrix</a></h3> </div> <div class="border-custom-dot"> <h2 class="soft-blue-custom">Other information</h2> <div class="as"> <h3><span class="soft-blue-custom">Chat Template? </span>ChatML<span class="soft-blue-custom">, of course!</span></h3> <h3 class="soft-blue-custom">Merge Method<h3/> <details class="border-custom"> <summary class="soft-blue-custom">Detail YAML Config</summary> <pre> { models: - model: TroyDoesAI/BlackSheep-24B parameters: density: 0.9 weight: 1 - model: DoppelReflEx/MiniusLight-24B parameters: density: 0.6 weight: 0.8 merge_method: dare_ties base_model: TroyDoesAI/BlackSheep-24B tokenizer_source: base } </pre> </detail> </div> </div> </div> </div> </body>
mradermacher/MiniusLight-24B-v2.1-GGUF	mradermacher	2025-04-29T00:05:47Z	0	0	transformers	[ "transformers", "gguf", "mergekit", "merge", "en", "base_model:DoppelReflEx/MiniusLight-24B-v2.1", "base_model:quantized:DoppelReflEx/MiniusLight-24B-v2.1", "endpoints_compatible", "region:us", "conversational" ]	null	2025-04-28T18:34:12Z	--- base_model: DoppelReflEx/MiniusLight-24B-v2.1 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/DoppelReflEx/MiniusLight-24B-v2.1 <!-- provided-files --> weighted/imatrix quants are available at https://huggingface.co/mradermacher/MiniusLight-24B-v2.1-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/MiniusLight-24B-v2.1-GGUF/resolve/main/MiniusLight-24B-v2.1.Q2_K.gguf) \| Q2_K \| 9.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/MiniusLight-24B-v2.1-GGUF/resolve/main/MiniusLight-24B-v2.1.Q3_K_S.gguf) \| Q3_K_S \| 10.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/MiniusLight-24B-v2.1-GGUF/resolve/main/MiniusLight-24B-v2.1.Q3_K_M.gguf) \| Q3_K_M \| 11.6 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/MiniusLight-24B-v2.1-GGUF/resolve/main/MiniusLight-24B-v2.1.Q3_K_L.gguf) \| Q3_K_L \| 12.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/MiniusLight-24B-v2.1-GGUF/resolve/main/MiniusLight-24B-v2.1.IQ4_XS.gguf) \| IQ4_XS \| 13.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/MiniusLight-24B-v2.1-GGUF/resolve/main/MiniusLight-24B-v2.1.Q4_K_S.gguf) \| Q4_K_S \| 13.6 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/MiniusLight-24B-v2.1-GGUF/resolve/main/MiniusLight-24B-v2.1.Q4_K_M.gguf) \| Q4_K_M \| 14.4 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/MiniusLight-24B-v2.1-GGUF/resolve/main/MiniusLight-24B-v2.1.Q5_K_S.gguf) \| Q5_K_S \| 16.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/MiniusLight-24B-v2.1-GGUF/resolve/main/MiniusLight-24B-v2.1.Q5_K_M.gguf) \| Q5_K_M \| 16.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/MiniusLight-24B-v2.1-GGUF/resolve/main/MiniusLight-24B-v2.1.Q6_K.gguf) \| Q6_K \| 19.4 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/MiniusLight-24B-v2.1-GGUF/resolve/main/MiniusLight-24B-v2.1.Q8_0.gguf) \| Q8_0 \| 25.2 \| fast, best quality \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
iboero/SAFE-SFT-EXAMPLE	iboero	2025-04-29T00:04:12Z	0	0	null	[ "license:apache-2.0", "region:us" ]	null	2025-04-29T00:04:12Z	--- license: apache-2.0 ---
mradermacher/starcoder-vulnfixes-GGUF	mradermacher	2025-04-29T00:00:11Z	0	0	transformers	[ "transformers", "gguf", "generated_from_trainer", "en", "dataset:kevinwsbr/vulnfixes-web", "base_model:kevinwsbr/starcoder-vulnfixes", "base_model:quantized:kevinwsbr/starcoder-vulnfixes", "license:bigcode-openrail-m", "endpoints_compatible", "region:us" ]	null	2025-04-28T23:34:26Z	--- base_model: kevinwsbr/starcoder-vulnfixes datasets: - kevinwsbr/vulnfixes-web language: - en library_name: transformers license: bigcode-openrail-m quantized_by: mradermacher tags: - generated_from_trainer --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/kevinwsbr/starcoder-vulnfixes <!-- 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/starcoder-vulnfixes-GGUF/resolve/main/starcoder-vulnfixes.Q2_K.gguf) \| Q2_K \| 6.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/starcoder-vulnfixes-GGUF/resolve/main/starcoder-vulnfixes.Q3_K_S.gguf) \| Q3_K_S \| 7.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/starcoder-vulnfixes-GGUF/resolve/main/starcoder-vulnfixes.Q3_K_M.gguf) \| Q3_K_M \| 8.1 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/starcoder-vulnfixes-GGUF/resolve/main/starcoder-vulnfixes.IQ4_XS.gguf) \| IQ4_XS \| 8.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/starcoder-vulnfixes-GGUF/resolve/main/starcoder-vulnfixes.Q3_K_L.gguf) \| Q3_K_L \| 9.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/starcoder-vulnfixes-GGUF/resolve/main/starcoder-vulnfixes.Q4_K_S.gguf) \| Q4_K_S \| 9.3 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/starcoder-vulnfixes-GGUF/resolve/main/starcoder-vulnfixes.Q4_K_M.gguf) \| Q4_K_M \| 10.0 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/starcoder-vulnfixes-GGUF/resolve/main/starcoder-vulnfixes.Q5_K_S.gguf) \| Q5_K_S \| 11.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/starcoder-vulnfixes-GGUF/resolve/main/starcoder-vulnfixes.Q5_K_M.gguf) \| Q5_K_M \| 11.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/starcoder-vulnfixes-GGUF/resolve/main/starcoder-vulnfixes.Q6_K.gguf) \| Q6_K \| 13.2 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/starcoder-vulnfixes-GGUF/resolve/main/starcoder-vulnfixes.Q8_0.gguf) \| Q8_0 \| 17.1 \| 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/DiscordArvo-GGUF	mradermacher	2025-04-29T00:00:10Z	0	0	transformers	[ "transformers", "gguf", "unsloth", "trl", "sft", "en", "base_model:SlightlyLessBigJimmy/DiscordArvo", "base_model:quantized:SlightlyLessBigJimmy/DiscordArvo", "endpoints_compatible", "region:us" ]	null	2025-04-28T23:19:17Z	--- base_model: SlightlyLessBigJimmy/DiscordArvo language: - en library_name: transformers quantized_by: mradermacher tags: - unsloth - trl - sft --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/SlightlyLessBigJimmy/DiscordArvo <!-- 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/DiscordArvo-GGUF/resolve/main/DiscordArvo.Q2_K.gguf) \| Q2_K \| 3.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/DiscordArvo-GGUF/resolve/main/DiscordArvo.Q3_K_S.gguf) \| Q3_K_S \| 4.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/DiscordArvo-GGUF/resolve/main/DiscordArvo.Q3_K_M.gguf) \| Q3_K_M \| 4.9 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/DiscordArvo-GGUF/resolve/main/DiscordArvo.Q3_K_L.gguf) \| Q3_K_L \| 5.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/DiscordArvo-GGUF/resolve/main/DiscordArvo.IQ4_XS.gguf) \| IQ4_XS \| 5.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/DiscordArvo-GGUF/resolve/main/DiscordArvo.Q4_K_S.gguf) \| Q4_K_S \| 5.6 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/DiscordArvo-GGUF/resolve/main/DiscordArvo.Q4_K_M.gguf) \| Q4_K_M \| 5.9 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/DiscordArvo-GGUF/resolve/main/DiscordArvo.Q5_K_S.gguf) \| Q5_K_S \| 6.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/DiscordArvo-GGUF/resolve/main/DiscordArvo.Q5_K_M.gguf) \| Q5_K_M \| 6.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/DiscordArvo-GGUF/resolve/main/DiscordArvo.Q6_K.gguf) \| Q6_K \| 7.7 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/DiscordArvo-GGUF/resolve/main/DiscordArvo.Q8_0.gguf) \| Q8_0 \| 9.9 \| fast, best quality \| \| [GGUF](https://huggingface.co/mradermacher/DiscordArvo-GGUF/resolve/main/DiscordArvo.f16.gguf) \| f16 \| 18.6 \| 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 -->
infogeo/1cd51e9e-83d4-47ff-8526-8e66ffd89c2f	infogeo	2025-04-28T23:59:54Z	0	0	peft	[ "peft", "safetensors", "llama", "axolotl", "generated_from_trainer", "base_model:unsloth/SmolLM-1.7B-Instruct", "base_model:adapter:unsloth/SmolLM-1.7B-Instruct", "license:apache-2.0", "4-bit", "bitsandbytes", "region:us" ]	null	2025-04-28T23:55:32Z	--- library_name: peft license: apache-2.0 base_model: unsloth/SmolLM-1.7B-Instruct tags: - axolotl - generated_from_trainer model-index: - name: 1cd51e9e-83d4-47ff-8526-8e66ffd89c2f 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/SmolLM-1.7B-Instruct bf16: true chat_template: llama3 dataset_prepared_path: /workspace/axolotl datasets: - data_files: - 09440e5d84ab787c_train_data.json ds_type: json format: custom path: /workspace/input_data/09440e5d84ab787c_train_data.json type: field_input: user_prompt field_instruction: system_prompt field_output: prompt 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: infogeo/1cd51e9e-83d4-47ff-8526-8e66ffd89c2f 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: 8 mixed_precision: bf16 mlflow_experiment_name: /tmp/09440e5d84ab787c_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: 1024 strict: false tf32: false tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: 0a019fdb-0b45-4625-bb8c-9db767620d26 wandb_project: s56-28 wandb_run: your_name wandb_runid: 0a019fdb-0b45-4625-bb8c-9db767620d26 warmup_steps: 5 weight_decay: 0.01 xformers_attention: true ``` </details><br> # 1cd51e9e-83d4-47ff-8526-8e66ffd89c2f This model is a fine-tuned version of [unsloth/SmolLM-1.7B-Instruct](https://huggingface.co/unsloth/SmolLM-1.7B-Instruct) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.2423 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-06 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - 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 \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| 0.2296 \| 0.0071 \| 150 \| 0.2423 \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
mradermacher/Sky-T1-32B-Flash-Spectrum-i1-GGUF	mradermacher	2025-04-28T23:49:26Z	0	0	transformers	[ "transformers", "gguf", "generated_from_trainer", "en", "base_model:arcee-samsung/Sky-T1-32B-Flash-Spectrum", "base_model:quantized:arcee-samsung/Sky-T1-32B-Flash-Spectrum", "endpoints_compatible", "region:us", "imatrix", "conversational" ]	null	2025-04-28T20:39:29Z	--- base_model: arcee-samsung/Sky-T1-32B-Flash-Spectrum language: - en library_name: transformers model_name: outputs/simpo-skyT1-out quantized_by: mradermacher tags: - generated_from_trainer --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> weighted/imatrix quants of https://huggingface.co/arcee-samsung/Sky-T1-32B-Flash-Spectrum <!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/Sky-T1-32B-Flash-Spectrum-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/Sky-T1-32B-Flash-Spectrum-i1-GGUF/resolve/main/Sky-T1-32B-Flash-Spectrum.i1-IQ1_S.gguf) \| i1-IQ1_S \| 7.4 \| for the desperate \| \| [GGUF](https://huggingface.co/mradermacher/Sky-T1-32B-Flash-Spectrum-i1-GGUF/resolve/main/Sky-T1-32B-Flash-Spectrum.i1-IQ1_M.gguf) \| i1-IQ1_M \| 8.0 \| mostly desperate \| \| [GGUF](https://huggingface.co/mradermacher/Sky-T1-32B-Flash-Spectrum-i1-GGUF/resolve/main/Sky-T1-32B-Flash-Spectrum.i1-IQ2_XXS.gguf) \| i1-IQ2_XXS \| 9.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/Sky-T1-32B-Flash-Spectrum-i1-GGUF/resolve/main/Sky-T1-32B-Flash-Spectrum.i1-IQ2_XS.gguf) \| i1-IQ2_XS \| 10.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/Sky-T1-32B-Flash-Spectrum-i1-GGUF/resolve/main/Sky-T1-32B-Flash-Spectrum.i1-IQ2_S.gguf) \| i1-IQ2_S \| 10.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/Sky-T1-32B-Flash-Spectrum-i1-GGUF/resolve/main/Sky-T1-32B-Flash-Spectrum.i1-IQ2_M.gguf) \| i1-IQ2_M \| 11.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Sky-T1-32B-Flash-Spectrum-i1-GGUF/resolve/main/Sky-T1-32B-Flash-Spectrum.i1-Q2_K_S.gguf) \| i1-Q2_K_S \| 11.6 \| very low quality \| \| [GGUF](https://huggingface.co/mradermacher/Sky-T1-32B-Flash-Spectrum-i1-GGUF/resolve/main/Sky-T1-32B-Flash-Spectrum.i1-Q2_K.gguf) \| i1-Q2_K \| 12.4 \| IQ3_XXS probably better \| \| [GGUF](https://huggingface.co/mradermacher/Sky-T1-32B-Flash-Spectrum-i1-GGUF/resolve/main/Sky-T1-32B-Flash-Spectrum.i1-IQ3_XXS.gguf) \| i1-IQ3_XXS \| 12.9 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/Sky-T1-32B-Flash-Spectrum-i1-GGUF/resolve/main/Sky-T1-32B-Flash-Spectrum.i1-IQ3_XS.gguf) \| i1-IQ3_XS \| 13.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Sky-T1-32B-Flash-Spectrum-i1-GGUF/resolve/main/Sky-T1-32B-Flash-Spectrum.i1-Q3_K_S.gguf) \| i1-Q3_K_S \| 14.5 \| IQ3_XS probably better \| \| [GGUF](https://huggingface.co/mradermacher/Sky-T1-32B-Flash-Spectrum-i1-GGUF/resolve/main/Sky-T1-32B-Flash-Spectrum.i1-IQ3_S.gguf) \| i1-IQ3_S \| 14.5 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/Sky-T1-32B-Flash-Spectrum-i1-GGUF/resolve/main/Sky-T1-32B-Flash-Spectrum.i1-IQ3_M.gguf) \| i1-IQ3_M \| 14.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/Sky-T1-32B-Flash-Spectrum-i1-GGUF/resolve/main/Sky-T1-32B-Flash-Spectrum.i1-Q3_K_M.gguf) \| i1-Q3_K_M \| 16.0 \| IQ3_S probably better \| \| [GGUF](https://huggingface.co/mradermacher/Sky-T1-32B-Flash-Spectrum-i1-GGUF/resolve/main/Sky-T1-32B-Flash-Spectrum.i1-Q3_K_L.gguf) \| i1-Q3_K_L \| 17.3 \| IQ3_M probably better \| \| [GGUF](https://huggingface.co/mradermacher/Sky-T1-32B-Flash-Spectrum-i1-GGUF/resolve/main/Sky-T1-32B-Flash-Spectrum.i1-IQ4_XS.gguf) \| i1-IQ4_XS \| 17.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Sky-T1-32B-Flash-Spectrum-i1-GGUF/resolve/main/Sky-T1-32B-Flash-Spectrum.i1-Q4_0.gguf) \| i1-Q4_0 \| 18.8 \| fast, low quality \| \| [GGUF](https://huggingface.co/mradermacher/Sky-T1-32B-Flash-Spectrum-i1-GGUF/resolve/main/Sky-T1-32B-Flash-Spectrum.i1-Q4_K_S.gguf) \| i1-Q4_K_S \| 18.9 \| optimal size/speed/quality \| \| [GGUF](https://huggingface.co/mradermacher/Sky-T1-32B-Flash-Spectrum-i1-GGUF/resolve/main/Sky-T1-32B-Flash-Spectrum.i1-Q4_K_M.gguf) \| i1-Q4_K_M \| 20.0 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Sky-T1-32B-Flash-Spectrum-i1-GGUF/resolve/main/Sky-T1-32B-Flash-Spectrum.i1-Q4_1.gguf) \| i1-Q4_1 \| 20.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/Sky-T1-32B-Flash-Spectrum-i1-GGUF/resolve/main/Sky-T1-32B-Flash-Spectrum.i1-Q5_K_S.gguf) \| i1-Q5_K_S \| 22.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/Sky-T1-32B-Flash-Spectrum-i1-GGUF/resolve/main/Sky-T1-32B-Flash-Spectrum.i1-Q5_K_M.gguf) \| i1-Q5_K_M \| 23.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Sky-T1-32B-Flash-Spectrum-i1-GGUF/resolve/main/Sky-T1-32B-Flash-Spectrum.i1-Q6_K.gguf) \| i1-Q6_K \| 27.0 \| practically like static Q6_K \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. <!-- end -->
bunyaminergen/Qwen2.5-Coder-1.5B-Instruct-Reasoning	bunyaminergen	2025-04-28T23:40:40Z	0	0	peft	[ "peft", "safetensors", "code", "codeqwen", "chat", "qwen", "qwen-coder", "text-generation", "conversational", "en", "dataset:nvidia/OpenCodeReasoning", "base_model:Qwen/Qwen2.5-Coder-1.5B-Instruct", "base_model:finetune:Qwen/Qwen2.5-Coder-1.5B-Instruct", "license:gpl-3.0", "region:us" ]	text-generation	2025-04-27T23:00:05Z	--- base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct base_model_relation: finetune library_name: peft language: - en tags: - code - codeqwen - chat - qwen - qwen-coder license: gpl-3.0 datasets: - nvidia/OpenCodeReasoning pipeline_tag: text-generation license_link: https://huggingface.co/bunyaminergen/Qwen2.5-Coder-1.5B-Instruct-Reasoning/blob/main/LICENSE --- # Qwen2.5-Coder-1.5B-Instruct-Reasoning The `Qwen2.5-Coder-1.5B-Instruct-Reasoning` model has been supervised fine-tuned (SFT) on the `nvidia/OpenCodeReasoning` dataset to enhance its reasoning capabilities. --- ### TableofContents - [Usage](#usage) - [Comparison](#comparison) - [Dataset](#dataset) - [Training](#training) - [License](#licence) - [Links](#links) - [Team](#team) - [Contact](#contact) - [Reference](#reference) - [Citation](#citation) --- ### Usage #### Hugging Face ```python from peft import PeftModel from transformers import AutoModelForCausalLM, AutoTokenizer base_model_name = "Qwen/Qwen2.5-Coder-1.5B-Instruct" adapter_repo = "bunyaminergen/Qwen2.5-Coder-1.5B-Instruct-Reasoning" tokenizer = AutoTokenizer.from_pretrained(adapter_repo, trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained( base_model_name, device_map="auto", torch_dtype="auto", ) model.resize_token_embeddings(len(tokenizer)) model = PeftModel.from_pretrained(model, adapter_repo) model.eval() messages = [ {"role": "system", "content": "You are a helpful coding assistant."}, {"role": "user", "content": "Please provide a Python script that checks whether a number is prime."} ] prompt = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) inputs = tokenizer(prompt, return_tensors="pt").to(model.device) outputs = model.generate( inputs, max_new_tokens=2048 ) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) ``` --- ### Comparison - Please pay attention to the `<think> </think>` special tokens in the [Reasoning Model](#reasoning-model). As you can see, the `Reasoning Model` can now _“think”_. #### Base Model `System:` You are a helpful coding assistant. `User:` Please provide a Python script that checks whether a number is prime. `Assistant:` ```python def check_prime(num): # Check if the number is less than 2 if num < 2: return False # Check for factors from 2 to the square root of the number for i in range(2, int(num0.5) + 1): if num % i == 0: return False # If no factors were found, the number is prime return True # Example usage number = 7 if check_prime(number): print(f"{number} is a prime number.") else: print(f"{number} is not a prime number.") ``` In this Python script, the function `check_prime` takes an integer as input and returns `True` if the number is prime, otherwise it returns `False`. The function first checks if the number is less than 2, which means it cannot be prime. Then, it iterates from 2 up to the square root of the number (inclusive). If any factor of the number is found within this range, the function immediately returns `False`, indicating that the number is not prime. If no factors are found after checking all possible divisors, the function concludes that the number is prime and returns `True`. The example usage demonstrates how to call the `check_prime` function with the number 7. The output will indicate whether 7 is a prime number or not. #### Reasoning Model `System:` You are a helpful coding assistant. `User:` Please provide a Python script that checks whether a number is prime. `Assistant:` `<think>` Okay, I need to write a Python program that checks if a given number is prime. Hmm, what's a prime number? Oh right, a prime number has exactly two distinct positive divisors: 1 and itself. So for a number to be prime, it must not have any divisors other than those two. First, let's think about the steps involved. The first thing is to determine if there are any divisors other than 1 and the number itself. How do I check that? Well, for a number n, starting from 2 up to sqrt(n), check if any of them divide n. If any do, then it's not prime. But wait, maybe even before checking up to the square root, some numbers might have factors beyond that. For example, take 9. The square root is 3. So checking 2,3,4 would catch 9's factors. Wait, but 3 divides 9, so the loop from 2 to sqrt( n) (which is 3 in this case) will check 2 and 3. So yes, checking up to the square root is sufficient because any composite number has at least one factor less than or equal to its square root. So the plan is: 1. Read an integer from input. 2. Check if the number is less than 2. If so, it's not prime. 3. Otherwise, check from 2 up to the square root of the number. For each i, if the number mod i is zero, return False. 4. If none of the numbers in this range divide the number, return True. Wait, but what about 0 and 1? Well, according to the problem statement, the input could be 0 or 1, which are not primes. So we should handle those cases separately. Let me outline the code structure. Read the input number as an integer. Let's call it num. Handle edge cases first: - If num < 2: print "No" (since primes are >=2) Else: Compute sqrt_num = int(math.sqrt(num)) Then loop from 2 to sqrt_num inclusive. For each i, check if num % i ==0. If any such i exists, return False. Else, after checking all, return True. But how to compute the square root accurately in Python? Using math.isqrt for integers, which returns the floor of the square root. That's better than using ** operator since it avoids floating point inaccuracies. Wait, but what if the number is a perfect square? Like 9. Then math.isqrt(9) is 3. So in that case, the loop would check up to 3. But when i reaches 3, 9%3 is 0, so it would return False, which is correct. So the code would look something like this: import math n = int(input()) if n < 2: print("No") else: sqrt_n = math.isqrt(n) is_prime = True for i in range(2, sqrt_n +1): if n % i == 0: is_prime = False break print("Yes" if is_prime else "No") Wait, but wait, what about numbers like 25. The square root is 5. So the loop runs from 2 to 5. When i=5, 25%5 is 0, so returns false. Correct. This logic seems solid. Let me test some examples. Test case 1: input 7. The loop runs up to 2. 2 to 2. Check 2. 7%2 is 1, so returns true. Output Yes. Test case 2: input 6. sqrt(6) is ~2.449. So sqrt_n is 2. Loop from 2 to 2. Check 2. 6%2 is 0. So returns false. Output No. Another test case: 8. sqrt(8) is ~2.828. So sqrt_n is 2. Check 2. 8%2 is 0. So output No. What about a prime number like 13. sqrt(13) is ~3.605. So loop up to 3. Check 2 and 3. 13%2 is 1, 13%3 is 1. So returns true. Correct. Edge case: 1. Output No. Another edge case: 2. Output Yes. What about a very large number, say 999983 (a prime). The code should check up to sqrt(999983) which is around 999.9. So the loop runs 2 to 999. It will check all possible factors. Since it's a prime, none will divide it. So returns Yes. So the code seems to handle all cases correctly. I think that's the solution. Now, writing the code accordingly. `</think>` ```python import math n = int(input()) if n < 2: print("No") else: sqrt_n = math.isqrt(n) is_prime = True for i in range(2, sqrt_n + 1): if n % i == 0: is_prime = False break print("Yes" if is_prime else "No") ``` --- ### Dataset - [nvidia/OpenCodeReasoning](https://huggingface.co/datasets/nvidia/OpenCodeReasoning) --- ### Training #### Base \| Parameter \| Value \| \|-----------------------------\|------------------------------------\| \| Base Model \| `Qwen/Qwen2.5-Coder-1.5B-Instruct` \| \| Fine-tuning Method \| QLoRA \| \| Task Type \| `CAUSAL_LM` \| \| Number of Epochs \| `3` \| \| Batch Size \| `1` \| \| Gradient Accumulation Steps \| `1` \| \| Effective Batch Size \| `1` \| \| Learning Rate \| `2e-4` \| \| LR Scheduler Type \| `cosine` \| \| Warmup Ratio \| `0.05` \| \| Precision \| `FP16 Mixed Precision` \| \| Gradient Checkpointing \| `True` \| \| Completion-Only Loss \| `True` \| \| Packing \| `False` \| \| Max Sequence Length \| `8192 tokens` \| \| Logging Steps \| every `10000` steps \| \| Save Checkpoint Steps \| every `10000` steps \| \| Output Directory \| `.model` \| #### PEFT/LoRA \| Parameter \| Value \| \|-----------------\|-----------------------------------------------------------------------------\| \| LoRA Rank (`r`) \| `16` \| \| LoRA Alpha \| `32` \| \| LoRA Dropout \| `0.05` \| \| LoRA Bias \| `none` \| \| Task Type \| `CAUSAL_LM` \| \| Target Modules \| `q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`, `up_proj`, `down_proj` \| \| Modules to Save \| `embed_tokens`, `lm_head` \| #### Model \| Parameter \| Value \| \|---------------------------\|------------------------------------\| \| Name \| `Qwen/Qwen2.5-Coder-1.5B-Instruct` \| \| Attention Implementation \| `flash_attention_2` \| \| load_in_4bit \| `true` \| \| bnb_4bit_quant_type \| `nf4` \| \| bnb_4bit_use_double_quant \| `true` \| #### Dataset \| Parameter \| Value \| \|---------------------\|----------------------------\| \| Dataset Name \| `nvidia/OpenCodeReasoning` \| \| Split \| `split_0` \| \| Number of Rows \| `8000` \| \| Max Token Length \| `8192` \| \| Shuffle \| `True` \| \| Number of Processes \| `4` \| #### Tokenizer \| Parameter \| Value \| \|--------------------------------\|-----------------------------\| \| Truncation \| Enabled (`max_length=8192`) \| \| Masked Language Modeling (MLM) \| `False` \| #### Speeds, Sizes, Times \| Parameter \| Value \| \|----------------------\|------------------------------------------------------------\| \| Total Training Time \| ~3.5 hours \| \| Checkpoint Frequency \| every `10000` steps \| \| Checkpoint Steps \| `checkpoint-10000`, `checkpoint-20000`, `checkpoint-24000` \| #### Compute Infrastructure \| Parameter \| Value \| \|--------------\|----------------------------------\| \| GPU \| 1 × NVIDIA H100 SXM (80 GB VRAM) \| \| RAM \| 125 GB \| \| CPU \| 16 vCPU \| \| OS \| Ubuntu 22.04 \| \| Frameworks \| PyTorch 2.4.0 \| \| CUDA Version \| 12.4.1 \| --- ### Licence - [LICENSE](LICENSE) --- ### Links - [Github](https://github.com/bunyaminergen/) - [Website](https://bunyaminergen.com) - [Linkedin](https://www.linkedin.com/in/bunyaminergen) --- ### Team - [Bunyamin Ergen](https://www.linkedin.com/in/bunyaminergen) --- ### Contact - [Mail](mailto:[email protected]) --- ### Reference - This model has been fine-tuned using Supervised Fine Tuning (SFT) method from the original model [Qwen/Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct). --- ### Citation ```bibtex @software{ Qwen2.5-Coder-1.5B-Instruct-Reasoning, author = {Bunyamin Ergen}, title = {{Qwen2.5-Coder-1.5B-Instruct-Reasoning}}, year = {2025}, month = {04}, } ``` ---
tachiwin/pretrained_multilingual_merged	tachiwin	2025-04-28T23:37:43Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "text-generation-inference", "unsloth", "trl", "en", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2025-04-27T07:02:18Z	--- base_model: unsloth/meta-llama-3.1-8b tags: - text-generation-inference - transformers - unsloth - llama - trl license: apache-2.0 language: - en --- # Uploaded model - Developed by: tachiwin - License: apache-2.0 - Finetuned from model : unsloth/meta-llama-3.1-8b 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)
Benjaminpwh/llama-control-2.2-500	Benjaminpwh	2025-04-28T23:07:55Z	0	0	transformers	[ "transformers", "safetensors", "generated_from_trainer", "unsloth", "trl", "sft", "endpoints_compatible", "region:us" ]	null	2025-04-28T19:42:57Z	--- base_model: unsloth/meta-llama-3.1-8b-instruct-unsloth-bnb-4bit library_name: transformers model_name: llama-control-2.2-500 tags: - generated_from_trainer - unsloth - trl - sft licence: license --- # Model Card for llama-control-2.2-500 This model is a fine-tuned version of [unsloth/meta-llama-3.1-8b-instruct-unsloth-bnb-4bit](https://huggingface.co/unsloth/meta-llama-3.1-8b-instruct-unsloth-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="Benjaminpwh/llama-control-2.2-500", 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/benpong-university-of-washington/huggingface/runs/1gyutvyg) This model was trained with SFT. ### Framework versions - TRL: 0.15.2 - Transformers: 4.51.3 - Pytorch: 2.6.0+cu124 - Datasets: 3.5.1 - Tokenizers: 0.21.1 ## Citations Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
nadsoft/Chat_Model_EGY_Dialect_exp2_lora	nadsoft	2025-04-28T23:04:35Z	0	0	transformers	[ "transformers", "safetensors", "text-generation-inference", "unsloth", "qwen2", "trl", "en", "base_model:nadsoft/Hamsa-EGY-Dialect-Model-Full-Finetuned", "base_model:finetune:nadsoft/Hamsa-EGY-Dialect-Model-Full-Finetuned", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-04-28T23:04:30Z	--- base_model: nadsoft/Hamsa-EGY-Dialect-Model-Full-Finetuned tags: - text-generation-inference - transformers - unsloth - qwen2 - trl license: apache-2.0 language: - en --- # Uploaded model - Developed by: nadsoft - License: apache-2.0 - Finetuned from model : nadsoft/Hamsa-EGY-Dialect-Model-Full-Finetuned This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
HanningZhang/Qwen2.5-Math-7B-raft-plusplus_cliphigher032_em-iter8	HanningZhang	2025-04-28T23:00:56Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-04-28T22:58:27Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
myaunacollins/clementine-baby-lab	myaunacollins	2025-04-28T22:57:30Z	0	0	null	[ "text-to-image", "en", "base_model:SG161222/Realistic_Vision_V5.1_noVAE", "base_model:finetune:SG161222/Realistic_Vision_V5.1_noVAE", "license:artistic-2.0", "region:us" ]	text-to-image	2025-04-28T22:51:32Z	--- license: artistic-2.0 language: - en base_model: - SG161222/Realistic_Vision_V5.1_noVAE pipeline_tag: text-to-image ---
mlabonne/BigQwen2.5-52B-Instruct	mlabonne	2025-04-28T22:53:23Z	15	8	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "mergekit", "merge", "lazymergekit", "conversational", "zho", "eng", "fra", "spa", "por", "deu", "ita", "rus", "jpn", "kor", "vie", "tha", "ara", "base_model:Qwen/Qwen2.5-32B-Instruct", "base_model:finetune:Qwen/Qwen2.5-32B-Instruct", "license:apache-2.0", "model-index", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-09-23T18:03:16Z	--- language: - zho - eng - fra - spa - por - deu - ita - rus - jpn - kor - vie - tha - ara license: apache-2.0 library_name: transformers tags: - mergekit - merge - lazymergekit base_model: - Qwen/Qwen2.5-32B-Instruct license_name: tongyi-qianwen license_link: https://huggingface.co/Qwen/Qwen2-72B-Instruct/blob/main/LICENSE pipeline_tag: text-generation model-index: - name: BigQwen2.5-52B-Instruct results: - task: type: text-generation name: Text Generation dataset: name: IFEval (0-Shot) type: HuggingFaceH4/ifeval args: num_few_shot: 0 metrics: - type: inst_level_strict_acc and prompt_level_strict_acc value: 79.29 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/BigQwen2.5-52B-Instruct name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: BBH (3-Shot) type: BBH args: num_few_shot: 3 metrics: - type: acc_norm value: 59.81 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/BigQwen2.5-52B-Instruct name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MATH Lvl 5 (4-Shot) type: hendrycks/competition_math args: num_few_shot: 4 metrics: - type: exact_match value: 17.82 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/BigQwen2.5-52B-Instruct name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GPQA (0-shot) type: Idavidrein/gpqa args: num_few_shot: 0 metrics: - type: acc_norm value: 6.94 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/BigQwen2.5-52B-Instruct 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: 10.45 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/BigQwen2.5-52B-Instruct 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: 50.22 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/BigQwen2.5-52B-Instruct name: Open LLM Leaderboard --- # BigQwen2.5-52B-Instruct ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/98GiKtmH1AtHHbIbOUH4Y.jpeg) BigQwen2.5-52B-Instruct is a [Qwen/Qwen2-32B-Instruct](https://huggingface.co/Qwen/Qwen2-72B-Instruct) self-merge made with [MergeKit](https://github.com/arcee-ai/mergekit/tree/main). It applies the [mlabonne/Meta-Llama-3-120B-Instruct](https://huggingface.co/mlabonne/Meta-Llama-3-120B-Instruct/) recipe. I made it due to popular demand but I haven't tested it so use it at your own risk. ¯\\\_(ツ)_/¯ ## 🔍 Applications It might be good for creative writing tasks. I recommend a context length of 32k but you can go up to 131,072 tokens in theory. ## 🏆 Evaluation \| Metric \|BigQwen2.5-Echo-47B-Instruct\|BigQwen2.5-52B-Instruct\|Qwen2.5-32B-Instruct\| \|-------------------\|----:\|----:\|----:\| \|Avg. \|30.31\|37.42\|36.17\| \|IFEval (0-Shot) \|73.57\|79.29\|83.46\| \|BBH (3-Shot) \|44.52\|59.81\|56.49\| \|MATH Lvl 5 (4-Shot)\| 3.47\|17.82\|0\| \|GPQA (0-shot) \| 8.61\| 6.94\|11.74\| \|MuSR (0-shot) \|10.19\|10.45\|13.5\| \|MMLU-PRO (5-shot) \|41.49\|50.22\|51.85\| ## 🧩 Configuration The following YAML configuration was used to produce this model: ```yaml slices: - sources: - layer_range: [0, 16] model: Qwen/Qwen2.5-32B-Instruct - sources: - layer_range: [8, 24] model: Qwen/Qwen2.5-32B-Instruct - sources: - layer_range: [16, 32] model: Qwen/Qwen2.5-32B-Instruct - sources: - layer_range: [24, 40] model: Qwen/Qwen2.5-32B-Instruct - sources: - layer_range: [32, 48] model: Qwen/Qwen2.5-32B-Instruct - sources: - layer_range: [40, 56] model: Qwen/Qwen2.5-32B-Instruct - sources: - layer_range: [56, 64] model: Qwen/Qwen2.5-32B-Instruct merge_method: passthrough dtype: bfloat16 ``` ## 💻 Usage ```python !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "mlabonne/BigQwen2.5-52B-Instruct" messages = [{"role": "user", "content": "What is a large language model?"}] tokenizer = AutoTokenizer.from_pretrained(model) prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) pipeline = transformers.pipeline( "text-generation", model=model, torch_dtype=torch.float16, device_map="auto", ) outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) print(outputs[0]["generated_text"]) ```
facebook/audioseal	facebook	2025-04-28T22:44:33Z	956	27	audioseal	[ "audioseal", "region:us" ]	null	2024-03-11T18:11:13Z	--- tags: - audioseal inference: false --- # AudioSeal We introduce AudioSeal, a method for speech localized watermarking, with state-of-the-art robustness and detector speed. It jointly trains a generator that embeds a watermark in the audio, and a detector that detects the watermarked fragments in longer audios, even in the presence of editing. Audioseal achieves state-of-the-art detection performance of both natural and synthetic speech at the sample level (1/16k second resolution), it generates limited alteration of signal quality and is robust to many types of audio editing. Audioseal is designed with a fast, single-pass detector, that significantly surpasses existing models in speed — achieving detection up to two orders of magnitude faster, making it ideal for large-scale and real-time applications. # 🧉 Installation AudioSeal requires Python >=3.8, Pytorch >= 1.13.0, [omegaconf](https://omegaconf.readthedocs.io/), [julius](https://pypi.org/project/julius/), and numpy. To install from PyPI: ``` pip install audioseal ``` To install from source: Clone this repo and install in editable mode: ``` git clone https://github.com/facebookresearch/audioseal cd audioseal pip install -e . ``` # ⚙️ Models We provide the checkpoints for the following models: - AudioSeal Generator. It takes as input an audio signal (as a waveform), and outputs a watermark of the same size as the input, that can be added to the input to watermark it. Optionally, it can also take as input a secret message of 16-bits that will be encoded in the watermark. - AudioSeal Detector. It takes as input an audio signal (as a waveform), and outputs a probability that the input contains a watermark at each sample of the audio (every 1/16k s). Optionally, it may also output the secret message encoded in the watermark. Note that the message is optional and has no influence on the detection output. It may be used to identify a model version for instance (up to $216=65536$ possible choices). Note**: We are working to release the training code for anyone wants to build their own watermarker. Stay tuned ! # 🧮 Usage Audioseal provides a simple API to watermark and detect the watermarks from an audio sample. Example usage: ```python from audioseal import AudioSeal # model name corresponds to the YAML card file name found in audioseal/cards model = AudioSeal.load_generator("audioseal_wm_16bits") # Other way is to load directly from the checkpoint # model = Watermarker.from_pretrained(checkpoint_path, device = wav.device) # a torch tensor of shape (batch, channels, samples) and a sample rate # It is important to process the audio to the same sample rate as the model # expectes. In our case, we support 16khz audio wav, sr = ..., 16000 watermark = model.get_watermark(wav, sr) # Optional: you can add a 16-bit message to embed in the watermark # msg = torch.randint(0, 2, (wav.shape(0), model.msg_processor.nbits), device=wav.device) # watermark = model.get_watermark(wav, message = msg) watermarked_audio = wav + watermark detector = AudioSeal.load_detector("audioseal_detector_16bits") # To detect the messages in the high-level. result, message = detector.detect_watermark(watermarked_audio, sr) print(result) # result is a float number indicating the probability of the audio being watermarked, print(message) # message is a binary vector of 16 bits # To detect the messages in the low-level. result, message = detector(watermarked_audio, sr) # result is a tensor of size batch x 2 x frames, indicating the probability (positive and negative) of watermarking for each frame # A watermarked audio should have result[:, 1, :] > 0.5 print(result[:, 1 , :]) # Message is a tensor of size batch x 16, indicating of the probability of each bit to be 1. # message will be a random tensor if the detector detects no watermarking from the audio print(message) ```
HanningZhang/Qwen2.5-Math-7B-raft-plusplus_cliphigher032_em-iter7	HanningZhang	2025-04-28T22:41:28Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-04-28T22:38:29Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
Leo-Dai/Qwen2.5-1.5B-Open-R1-Distill	Leo-Dai	2025-04-28T22:26:06Z	2	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "generated_from_trainer", "open-r1", "trl", "sft", "conversational", "zho", "eng", "fra", "spa", "por", "deu", "ita", "rus", "jpn", "kor", "vie", "tha", "ara", "dataset:open-r1/OpenR1-Math-220k", "base_model:Qwen/Qwen2.5-1.5B-Instruct", "base_model:finetune:Qwen/Qwen2.5-1.5B-Instruct", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-02-22T21:46:39Z	--- base_model: Qwen/Qwen2.5-1.5B-Instruct datasets: open-r1/OpenR1-Math-220k library_name: transformers model_name: Qwen2.5-1.5B-Open-R1-Distill tags: - generated_from_trainer - open-r1 - trl - sft licence: license language: - zho - eng - fra - spa - por - deu - ita - rus - jpn - kor - vie - tha - ara --- # Model Card for Qwen2.5-1.5B-Open-R1-Distill This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the [open-r1/OpenR1-Math-220k](https://huggingface.co/datasets/open-r1/OpenR1-Math-220k) dataset. It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="Leo-Dai/Qwen2.5-1.5B-Open-R1-Distill", 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/runpengd/huggingface/runs/ygx9alve) This model was trained with SFT. ### Framework versions - TRL: 0.15.0 - Transformers: 4.49.0 - Pytorch: 2.5.1 - Datasets: 3.3.2 - Tokenizers: 0.21.0 ## 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}} } ```
mlx-community/Qwen3-30B-A3B-bf16	mlx-community	2025-04-28T22:21:46Z	0	0	mlx	[ "mlx", "safetensors", "qwen3_moe", "text-generation", "conversational", "base_model:Qwen/Qwen3-30B-A3B", "base_model:finetune:Qwen/Qwen3-30B-A3B", "license:apache-2.0", "region:us" ]	text-generation	2025-04-28T22:11:19Z	--- library_name: mlx license: apache-2.0 license_link: https://huggingface.co/Qwen/Qwen3-30B-A3B/blob/main/LICENSE pipeline_tag: text-generation base_model: Qwen/Qwen3-30B-A3B tags: - mlx --- # mlx-community/Qwen3-30B-A3B-bf16 This model [mlx-community/Qwen3-30B-A3B-bf16](https://huggingface.co/mlx-community/Qwen3-30B-A3B-bf16) was converted to MLX format from [Qwen/Qwen3-30B-A3B](https://huggingface.co/Qwen/Qwen3-30B-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/Qwen3-30B-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) ```
jessicata/Qwen3-4B-Base-Q8_0-GGUF	jessicata	2025-04-28T22:16:40Z	0	0	transformers	[ "transformers", "gguf", "llama-cpp", "gguf-my-repo", "base_model:Qwen/Qwen3-4B-Base", "base_model:quantized:Qwen/Qwen3-4B-Base", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	null	2025-04-28T22:16:20Z	--- base_model: Qwen/Qwen3-4B-Base library_name: transformers license: apache-2.0 tags: - llama-cpp - gguf-my-repo --- # jessicata/Qwen3-4B-Base-Q8_0-GGUF This model was converted to GGUF format from [`Qwen/Qwen3-4B-Base`](https://huggingface.co/Qwen/Qwen3-4B-Base) 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/Qwen/Qwen3-4B-Base) 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 jessicata/Qwen3-4B-Base-Q8_0-GGUF --hf-file qwen3-4b-base-q8_0.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo jessicata/Qwen3-4B-Base-Q8_0-GGUF --hf-file qwen3-4b-base-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 jessicata/Qwen3-4B-Base-Q8_0-GGUF --hf-file qwen3-4b-base-q8_0.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo jessicata/Qwen3-4B-Base-Q8_0-GGUF --hf-file qwen3-4b-base-q8_0.gguf -c 2048 ```
fhaslam/Llama-3.2-1B-Financial-Sentiment24	fhaslam	2025-04-28T22:08:21Z	0	0	transformers	[ "transformers", "safetensors", "facebook", "meta", "pytorch", "llama", "llama-3", "text-generation", "conversational", "en", "de", "fr", "it", "pt", "hi", "es", "th", "arxiv:2204.05149", "arxiv:2405.16406", "license:llama3.2", "endpoints_compatible", "region:us" ]	text-generation	2025-04-28T22:08:05Z	--- language: - en - de - fr - it - pt - hi - es - th library_name: transformers pipeline_tag: text-generation tags: - facebook - meta - pytorch - llama - llama-3 license: llama3.2 extra_gated_prompt: >- ### LLAMA 3.2 COMMUNITY LICENSE AGREEMENT Llama 3.2 Version Release Date: September 25, 2024 “Agreement” means the terms and conditions for use, reproduction, distribution and modification of the Llama Materials set forth herein. “Documentation” means the specifications, manuals and documentation accompanying Llama 3.2 distributed by Meta at https://llama.meta.com/doc/overview. “Licensee” or “you” means you, or your employer or any other person or entity (if you are entering into this Agreement on such person or entity’s behalf), of the age required under applicable laws, rules or regulations to provide legal consent and that has legal authority to bind your employer or such other person or entity if you are entering in this Agreement on their behalf. “Llama 3.2” means the foundational large language models and software and algorithms, including machine-learning model code, trained model weights, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Meta at https://www.llama.com/llama-downloads. “Llama Materials” means, collectively, Meta’s proprietary Llama 3.2 and Documentation (and any portion thereof) made available under this Agreement. “Meta” or “we” means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland). By clicking “I Accept” below or by using or distributing any portion or element of the Llama Materials, you agree to be bound by this Agreement. 1. License Rights and Redistribution. a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Meta’s intellectual property or other rights owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Llama Materials. b. Redistribution and Use. i. If you distribute or make available the Llama Materials (or any derivative works thereof), or a product or service (including another AI model) that contains any of them, you shall (A) provide a copy of this Agreement with any such Llama Materials; and (B) prominently display “Built with Llama” on a related website, user interface, blogpost, about page, or product documentation. If you use the Llama Materials or any outputs or results of the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is distributed or made available, you shall also include “Llama” at the beginning of any such AI model name. ii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part of an integrated end user product, then Section 2 of this Agreement will not apply to you. iii. You must retain in all copies of the Llama Materials that you distribute the following attribution notice within a “Notice” text file distributed as a part of such copies: “Llama 3.2 is licensed under the Llama 3.2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.” iv. Your use of the Llama Materials must comply with applicable laws and regulations (including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama Materials (available at https://www.llama.com/llama3_2/use-policy), which is hereby incorporated by reference into this Agreement. 2. Additional Commercial Terms. If, on the Llama 3.2 version release date, the monthly active users of the products or services made available by or for Licensee, or Licensee’s affiliates, is greater than 700 million monthly active users in the preceding calendar month, you must request a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights. 3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS. 4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING. 5. Intellectual Property. a. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, except as required for reasonable and customary use in describing and redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to use “Llama” (the “Mark”) solely as required to comply with the last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently accessible at https://about.meta.com/brand/resources/meta/company-brand/). All goodwill arising out of your use of the Mark will inure to the benefit of Meta. b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta, with respect to any derivative works and modifications of the Llama Materials that are made by you, as between you and Meta, you are and will be the owner of such derivative works and modifications. c. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Llama 3.2 outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third party arising out of or related to your use or distribution of the Llama Materials. 6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this Agreement. 7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of California without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of any dispute arising out of this Agreement. ### Llama 3.2 Acceptable Use Policy Meta is committed to promoting safe and fair use of its tools and features, including Llama 3.2. If you access or use Llama 3.2, you agree to this Acceptable Use Policy (“Policy”). The most recent copy of this policy can be found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy). #### Prohibited Uses We want everyone to use Llama 3.2 safely and responsibly. You agree you will not use, or allow others to use, Llama 3.2 to: 1. Violate the law or others’ rights, including to: 1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as: 1. Violence or terrorism 2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material 3. Human trafficking, exploitation, and sexual violence 4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials. 5. Sexual solicitation 6. Any other criminal activity 1. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals 2. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services 3. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices 4. Collect, process, disclose, generate, or infer private or sensitive information about individuals, including information about individuals’ identity, health, or demographic information, unless you have obtained the right to do so in accordance with applicable law 5. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials 6. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system 7. Engage in any action, or facilitate any action, to intentionally circumvent or remove usage restrictions or other safety measures, or to enable functionality disabled by Meta 2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Llama 3.2 related to the following: 8. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State or to the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons Convention Implementation Act of 1997 9. Guns and illegal weapons (including weapon development) 10. Illegal drugs and regulated/controlled substances 11. Operation of critical infrastructure, transportation technologies, or heavy machinery 12. Self-harm or harm to others, including suicide, cutting, and eating disorders 13. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual 3. Intentionally deceive or mislead others, including use of Llama 3.2 related to the following: 14. Generating, promoting, or furthering fraud or the creation or promotion of disinformation 15. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content 16. Generating, promoting, or further distributing spam 17. Impersonating another individual without consent, authorization, or legal right 18. Representing that the use of Llama 3.2 or outputs are human-generated 19. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement 4. Fail to appropriately disclose to end users any known dangers of your AI system 5. Interact with third party tools, models, or software designed to generate unlawful content or engage in unlawful or harmful conduct and/or represent that the outputs of such tools, models, or software are associated with Meta or Llama 3.2 With respect to any multimodal models included in Llama 3.2, the rights granted under Section 1(a) of the Llama 3.2 Community License Agreement are not being granted to you if you are an individual domiciled in, or a company with a principal place of business in, the European Union. This restriction does not apply to end users of a product or service that incorporates any such multimodal models. Please report any violation of this Policy, software “bug,” or other problems that could lead to a violation of this Policy through one of the following means: * Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues&h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ) * Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback) * Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info) * Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama 3.2: [email protected] extra_gated_fields: First Name: text Last Name: text Date of birth: date_picker Country: country Affiliation: text Job title: type: select options: - Student - Research Graduate - AI researcher - AI developer/engineer - Reporter - Other geo: ip_location By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy: checkbox extra_gated_description: >- The information you provide will be collected, stored, processed and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/). extra_gated_button_content: Submit --- ## Model Information The Llama 3.2 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction-tuned generative models in 1B and 3B sizes (text in/text out). The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks. They outperform many of the available open source and closed chat models on common industry benchmarks. Model Developer: Meta Model Architecture: Llama 3.2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety. \| \| Training Data \| Params \| Input modalities \| Output modalities \| Context Length \| GQA \| Shared Embeddings \| Token count \| Knowledge cutoff \| \| :---- \| :---- \| :---- \| :---- \| :---- \| :---- \| :---- \| :---- \| :---- \| :---- \| \| Llama 3.2 (text only) \| A new mix of publicly available online data. \| 1B (1.23B) \| Multilingual Text \| Multilingual Text and code \| 128k \| Yes \| Yes \| Up to 9T tokens \| December 2023 \| \| \| \| 3B (3.21B) \| Multilingual Text \| Multilingual Text and code \| \| \| \| \| \| \| Llama 3.2 Quantized (text only) \| A new mix of publicly available online data. \| 1B (1.23B) \| Multilingual Text \| Multilingual Text and code \| 8k \| Yes \| Yes \| Up to 9T tokens \| December 2023 \| \| \| \| 3B (3.21B) \| Multilingual Text \| Multilingual Text and code \| \| \| \| \| \| Supported Languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai are officially supported. Llama 3.2 has been trained on a broader collection of languages than these 8 supported languages. Developers may fine-tune Llama 3.2 models for languages beyond these supported languages, provided they comply with the Llama 3.2 Community License and the Acceptable Use Policy. Developers are always expected to ensure that their deployments, including those that involve additional languages, are completed safely and responsibly. Llama 3.2 Model Family: Token counts refer to pretraining data only. All model versions use Grouped-Query Attention (GQA) for improved inference scalability. Model Release Date: Sept 25, 2024 Status: This is a static model trained on an offline dataset. Future versions may be released that improve model capabilities and safety. License: Use of Llama 3.2 is governed by the [Llama 3.2 Community License](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE) (a custom, commercial license agreement). Feedback: Instructions on how to provide feedback or comments on the model can be found in the Llama Models [README](https://github.com/meta-llama/llama-models/blob/main/README.md). For more technical information about generation parameters and recipes for how to use Llama 3.2 in applications, please go [here](https://github.com/meta-llama/llama-recipes). ## Intended Use Intended Use Cases: Llama 3.2 is intended for commercial and research use in multiple languages. Instruction tuned text only models are intended for assistant-like chat and agentic applications like knowledge retrieval and summarization, mobile AI powered writing assistants and query and prompt rewriting. Pretrained models can be adapted for a variety of additional natural language generation tasks. Similarly, quantized models can be adapted for a variety of on-device use-cases with limited compute resources. Out of Scope: Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3.2 Community License. Use in languages beyond those explicitly referenced as supported in this model card. ## How to use This repository contains two versions of Llama-3.2-1B-Instruct, for use with transformers and with the original `llama` codebase. ### Use with transformers Starting with `transformers >= 4.43.0` onward, you can run conversational inference using the Transformers `pipeline` abstraction or by leveraging the Auto classes with the `generate()` function. Make sure to update your transformers installation via `pip install --upgrade transformers`. ```python import torch from transformers import pipeline model_id = "meta-llama/Llama-3.2-1B-Instruct" pipe = pipeline( "text-generation", model=model_id, torch_dtype=torch.bfloat16, device_map="auto", ) messages = [ {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"}, {"role": "user", "content": "Who are you?"}, ] outputs = pipe( messages, max_new_tokens=256, ) print(outputs[0]["generated_text"][-1]) ``` Note: You can also find detailed recipes on how to use the model locally, with `torch.compile()`, assisted generations, quantised and more at [`huggingface-llama-recipes`](https://github.com/huggingface/huggingface-llama-recipes) ### Use with `llama` Please, follow the instructions in the [repository](https://github.com/meta-llama/llama) To download Original checkpoints, see the example command below leveraging `huggingface-cli`: ``` huggingface-cli download meta-llama/Llama-3.2-1B-Instruct --include "original/" --local-dir Llama-3.2-1B-Instruct ``` ## Hardware and Software Training Factors:* We used custom training libraries, Meta's custom built GPU cluster, and production infrastructure for pretraining. Fine-tuning, quantization, annotation, and evaluation were also performed on production infrastructure. Training Energy Use: Training utilized a cumulative of 916k GPU hours of computation on H100-80GB (TDP of 700W) type hardware, per the table below. Training time is the total GPU time required for training each model and power consumption is the peak power capacity per GPU device used, adjusted for power usage efficiency. Training Greenhouse Gas Emissions: Estimated total location-based greenhouse gas emissions were 240 tons CO2eq for training. Since 2020, Meta has maintained net zero greenhouse gas emissions in its global operations and matched 100% of its electricity use with renewable energy; therefore, the total market-based greenhouse gas emissions for training were 0 tons CO2eq. \| \| Training Time (GPU hours) \| Logit Generation Time (GPU Hours) \| Training Power Consumption (W) \| Training Location-Based Greenhouse Gas Emissions (tons CO2eq) \| Training Market-Based Greenhouse Gas Emissions (tons CO2eq) \| \| :---- \| :---: \| ----- \| :---: \| :---: \| :---: \| \| Llama 3.2 1B \| 370k \| \- \| 700 \| 107 \| 0 \| \| Llama 3.2 3B \| 460k \| \- \| 700 \| 133 \| 0 \| \| Llama 3.2 1B SpinQuant \| 1.7 \| 0 \| 700 \| Negligible\\ \| 0 \| \| Llama 3.2 3B SpinQuant \| 2.4 \| 0 \| 700 \| Negligible\\ \| 0 \| \| Llama 3.2 1B QLora \| 1.3k \| 0 \| 700 \| 0.381 \| 0 \| \| Llama 3.2 3B QLora \| 1.6k \| 0 \| 700 \| 0.461 \| 0 \| \| Total \| 833k \| 86k \| \| 240 \| 0 \| \\ The location-based CO2e emissions of Llama 3.2 1B SpinQuant and Llama 3.2 3B SpinQuant are less than 0.001 metric tonnes each. This is due to the minimal training GPU hours that are required. The methodology used to determine training energy use and greenhouse gas emissions can be found [here](https://arxiv.org/pdf/2204.05149). Since Meta is openly releasing these models, the training energy use and greenhouse gas emissions will not be incurred by others. ## Training Data Overview: Llama 3.2 was pretrained on up to 9 trillion tokens of data from publicly available sources. For the 1B and 3B Llama 3.2 models, we incorporated logits from the Llama 3.1 8B and 70B models into the pretraining stage of the model development, where outputs (logits) from these larger models were used as token-level targets. Knowledge distillation was used after pruning to recover performance. In post-training we used a similar recipe as Llama 3.1 and produced final chat models by doing several rounds of alignment on top of the pre-trained model. Each round involved Supervised Fine-Tuning (SFT), Rejection Sampling (RS), and Direct Preference Optimization (DPO). Data Freshness: The pretraining data has a cutoff of December 2023\. ## Quantization ### Quantization Scheme We designed the current quantization scheme with the [PyTorch’s ExecuTorch](https://github.com/pytorch/executorch) inference framework and Arm CPU backend in mind, taking into account metrics including model quality, prefill/decoding speed, and memory footprint. Our quantization scheme involves three parts: - All linear layers in all transformer blocks are quantized to a 4-bit groupwise scheme (with a group size of 32) for weights and 8-bit per-token dynamic quantization for activations. - The classification layer is quantized to 8-bit per-channel for weight and 8-bit per token dynamic quantization for activation. - Similar to classification layer, an 8-bit per channel quantization is used for embedding layer. ### Quantization-Aware Training and LoRA The quantization-aware training (QAT) with low-rank adaptation (LoRA) models went through only post-training stages, using the same data as the full precision models. To initialize QAT, we utilize BF16 Llama 3.2 model checkpoints obtained after supervised fine-tuning (SFT) and perform an additional full round of SFT training with QAT. We then freeze the backbone of the QAT model and perform another round of SFT with LoRA adaptors applied to all layers within the transformer block. Meanwhile, the LoRA adaptors' weights and activations are maintained in BF16. Because our approach is similar to QLoRA of Dettmers et al., (2023) (i.e., quantization followed by LoRA adapters), we refer this method as QLoRA. Finally, we fine-tune the resulting model (both backbone and LoRA adaptors) using direct preference optimization (DPO). ### SpinQuant [SpinQuant](https://arxiv.org/abs/2405.16406) was applied, together with generative post-training quantization (GPTQ). For the SpinQuant rotation matrix fine-tuning, we optimized for 100 iterations, using 800 samples with sequence-length 2048 from the WikiText 2 dataset. For GPTQ, we used 128 samples from the same dataset with the same sequence-length. ## Benchmarks \- English Text In this section, we report the results for Llama 3.2 models on standard automatic benchmarks. For all these evaluations, we used our internal evaluations library. ### Base Pretrained Models \| Category \| Benchmark \| \# Shots \| Metric \| Llama 3.2 1B \| Llama 3.2 3B \| Llama 3.1 8B \| \| ----- \| ----- \| :---: \| :---: \| :---: \| :---: \| :---: \| \| General \| MMLU \| 5 \| macro\_avg/acc\_char \| 32.2 \| 58 \| 66.7 \| \| \| AGIEval English \| 3-5 \| average/acc\_char \| 23.3 \| 39.2 \| 47.8 \| \| \| ARC-Challenge \| 25 \| acc\_char \| 32.8 \| 69.1 \| 79.7 \| \| Reading comprehension \| SQuAD \| 1 \| em \| 49.2 \| 67.7 \| 77 \| \| \| QuAC (F1) \| 1 \| f1 \| 37.9 \| 42.9 \| 44.9 \| \| \| DROP (F1) \| 3 \| f1 \| 28.0 \| 45.2 \| 59.5 \| \| Long Context \| Needle in Haystack \| 0 \| em \| 96.8 \| 1 \| 1 \| ### Instruction Tuned Models \| Capability \| \| Benchmark \| \# Shots \| Metric \| Llama 3.2 1B bf16 \| Llama 3.2 1B Vanilla PTQ\\ \| Llama 3.2 1B Spin Quant \| Llama 3.2 1B QLoRA \| Llama 3.2 3B bf16 \| Llama 3.2 3B Vanilla PTQ\\ \| Llama 3.2 3B Spin Quant \| Llama 3.2 3B QLoRA \| Llama 3.1 8B \| \| :---: \| ----- \| :---: \| :---: \| :---: \| :---: \| :---: \| :---: \| :---: \| :---: \| :---: \| :---: \| :---: \| :---: \| \| General \| \| MMLU \| 5 \| macro\_avg/acc \| 49.3 \| 43.3 \| 47.3 \| 49.0 \| 63.4 \| 60.5 \| 62 \| 62.4 \| 69.4 \| \| Re-writing \| \| Open-rewrite eval \| 0 \| micro\_avg/rougeL \| 41.6 \| 39.2 \| 40.9 \| 41.2 \| 40.1 \| 40.3 \| 40.8 \| 40.7 \| 40.9 \| \| Summarization \| \| TLDR9+ (test) \| 1 \| rougeL \| 16.8 \| 14.9 \| 16.7 \| 16.8 \| 19.0 \| 19.1 \| 19.2 \| 19.1 \| 17.2 \| \| Instruction following \| \| IFEval \| 0 \| Avg(Prompt/Instruction acc Loose/Strict) \| 59.5 \| 51.5 \| 58.4 \| 55.6 \| 77.4 \| 73.9 \| 73.5 \| 75.9 \| 80.4 \| \| Math \| \| GSM8K (CoT) \| 8 \| em\_maj1@1 \| 44.4 \| 33.1 \| 40.6 \| 46.5 \| 77.7 \| 72.9 \| 75.7 \| 77.9 \| 84.5 \| \| \| \| MATH (CoT) \| 0 \| final\_em \| 30.6 \| 20.5 \| 25.3 \| 31.0 \| 48.0 \| 44.2 \| 45.3 \| 49.2 \| 51.9 \| \| Reasoning \| \| ARC-C \| 0 \| acc \| 59.4 \| 54.3 \| 57 \| 60.7 \| 78.6 \| 75.6 \| 77.6 \| 77.6 \| 83.4 \| \| \| \| GPQA \| 0 \| acc \| 27.2 \| 25.9 \| 26.3 \| 25.9 \| 32.8 \| 32.8 \| 31.7 \| 33.9 \| 32.8 \| \| \| \| Hellaswag \| 0 \| acc \| 41.2 \| 38.1 \| 41.3 \| 41.5 \| 69.8 \| 66.3 \| 68 \| 66.3 \| 78.7 \| \| Tool Use \| \| BFCL V2 \| 0 \| acc \| 25.7 \| 14.3 \| 15.9 \| 23.7 \| 67.0 \| 53.4 \| 60.1 \| 63.5 \| 67.1 \| \| \| \| Nexus \| 0 \| macro\_avg/acc \| 13.5 \| 5.2 \| 9.6 \| 12.5 \| 34.3 \| 32.4 \| 31.5 \| 30.1 \| 38.5 \| \| Long Context \| \| InfiniteBench/En.QA \| 0 \| longbook\_qa/f1 \| 20.3 \| N/A \| N/A \| N/A \| 19.8 \| N/A \| N/A \| N/A \| 27.3 \| \| \| \| InfiniteBench/En.MC \| 0 \| longbook\_choice/acc \| 38.0 \| N/A \| N/A \| N/A \| 63.3 \| N/A \| N/A \| N/A \| 72.2 \| \| \| \| NIH/Multi-needle \| 0 \| recall \| 75.0 \| N/A \| N/A \| N/A \| 84.7 \| N/A \| N/A \| N/A \| 98.8 \| \| Multilingual \| \| MGSM (CoT) \| 0 \| em \| 24.5 \| 13.7 \| 18.2 \| 24.4 \| 58.2 \| 48.9 \| 54.3 \| 56.8 \| 68.9 \| \\for comparison purposes only. Model not released. ### Multilingual Benchmarks \| Category \| Benchmark \| Language \| Llama 3.2 1B \| Llama 3.2 1B Vanilla PTQ\\ \| Llama 3.2 1B Spin Quant \| Llama 3.2 1B QLoRA \| Llama 3.2 3B \| Llama 3.2 3B Vanilla PTQ\\ \| Llama 3.2 3B Spin Quant \| Llama 3.2 3B QLoRA \| Llama 3.1 8B \| \| :---: \| :---: \| :---: \| :---: \| :---: \| :---: \| :---: \| :---: \| :---: \| :---: \| :---: \| :---: \| \| General \| MMLU (5-shot, macro_avg/acc) \| Portuguese \| 39.8 \| 34.9 \| 38.9 \| 40.2 \| 54.5 \| 50.9 \| 53.3 \| 53.4 \| 62.1 \| \| \| \| Spanish \| 41.5 \| 36.0 \| 39.8 \| 41.8 \| 55.1 \| 51.9 \| 53.6 \| 53.6 \| 62.5 \| \| \| \| Italian \| 39.8 \| 34.9 \| 38.1 \| 40.6 \| 53.8 \| 49.9 \| 52.1 \| 51.7 \| 61.6 \| \| \| \| German \| 39.2 \| 34.9 \| 37.5 \| 39.6 \| 53.3 \| 50.0 \| 52.2 \| 51.3 \| 60.6 \| \| \| \| French \| 40.5 \| 34.8 \| 39.2 \| 40.8 \| 54.6 \| 51.2 \| 53.3 \| 53.3 \| 62.3 \| \| \| \| Hindi \| 33.5 \| 30.0 \| 32.1 \| 34.0 \| 43.3 \| 40.4 \| 42.0 \| 42.1 \| 50.9 \| \| \| \| Thai \| 34.7 \| 31.2 \| 32.4 \| 34.9 \| 44.5 \| 41.3 \| 44.0 \| 42.2 \| 50.3 \| \\for comparison purposes only. Model not released. ## Inference time In the below table, we compare the performance metrics of different quantization methods (SpinQuant and QAT \+ LoRA) with the BF16 baseline. The evaluation was done using the [ExecuTorch](https://github.com/pytorch/executorch) framework as the inference engine, with the ARM CPU as a backend using Android OnePlus 12 device. \| Category \| Decode (tokens/sec) \| Time-to-first-token (sec) \| Prefill (tokens/sec) \| Model size (PTE file size in MB) \| Memory size (RSS in MB) \| \| :---- \| ----- \| ----- \| ----- \| ----- \| ----- \| \| 1B BF16 (baseline) \| 19.2 \| 1.0 \| 60.3 \| 2358 \| 3,185 \| \| 1B SpinQuant \| 50.2 (2.6x) \| 0.3 (-76.9%) \| 260.5 (4.3x) \| 1083 (-54.1%) \| 1,921 (-39.7%) \| \| 1B QLoRA \| 45.8 (2.4x) \| 0.3 (-76.0%) \| 252.0 (4.2x) \| 1127 (-52.2%) \| 2,255 (-29.2%) \| \| 3B BF16 (baseline) \| 7.6 \| 3.0 \| 21.2 \| 6129 \| 7,419 \| \| 3B SpinQuant \| 19.7 (2.6x) \| 0.7 (-76.4%) \| 89.7 (4.2x) \| 2435 (-60.3%) \| 3,726 (-49.8%) \| \| 3B QLoRA \| 18.5 (2.4x) \| 0.7 (-76.1%) \| 88.8 (4.2x) \| 2529 (-58.7%) \| 4,060 (-45.3%) \| (\) The performance measurement is done using an adb binary-based approach. (\\) It is measured on an Android OnePlus 12 device. (\\\) Time-to-first-token (TTFT) is measured with prompt length=64 Footnote: - Decode (tokens/second) is for how quickly it keeps generating. Higher is better. - Time-to-first-token (TTFT for shorthand) is for how fast it generates the first token for a given prompt. Lower is better. - Prefill is the inverse of TTFT (aka 1/TTFT) in tokens/second. Higher is better - Model size \- how big is the model, measured by, PTE file, a binary file format for ExecuTorch - RSS size \- Memory usage in resident set size (RSS) ## Responsibility & Safety As part of our Responsible release approach, we followed a three-pronged strategy to managing trust & safety risks: 1. Enable developers to deploy helpful, safe and flexible experiences for their target audience and for the use cases supported by Llama 2. Protect developers against adversarial users aiming to exploit Llama capabilities to potentially cause harm 3. Provide protections for the community to help prevent the misuse of our models ### Responsible Deployment Approach: Llama is a foundational technology designed to be used in a variety of use cases. Examples on how Meta’s Llama models have been responsibly deployed can be found in our [Community Stories webpage](https://llama.meta.com/community-stories/). Our approach is to build the most helpful models, enabling the world to benefit from the technology power, by aligning our model safety for generic use cases and addressing a standard set of harms. Developers are then in the driver’s seat to tailor safety for their use cases, defining their own policies and deploying the models with the necessary safeguards in their Llama systems. Llama 3.2 was developed following the best practices outlined in our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide/). #### Llama 3.2 Instruct Objective: Our main objectives for conducting safety fine-tuning are to provide the research community with a valuable resource for studying the robustness of safety fine-tuning, as well as to offer developers a readily available, safe, and powerful model for various applications to reduce the developer workload to deploy safe AI systems. We implemented the same set of safety mitigations as in Llama 3, and you can learn more about these in the Llama 3 [paper](https://ai.meta.com/research/publications/the-llama-3-herd-of-models/). Fine-Tuning Data: We employ a multi-faceted approach to data collection, combining human-generated data from our vendors with synthetic data to mitigate potential safety risks. We’ve developed many large language model (LLM)-based classifiers that enable us to thoughtfully select high-quality prompts and responses, enhancing data quality control. Refusals and Tone: Building on the work we started with Llama 3, we put a great emphasis on model refusals to benign prompts as well as refusal tone. We included both borderline and adversarial prompts in our safety data strategy, and modified our safety data responses to follow tone guidelines. #### Llama 3.2 Systems Safety as a System: Large language models, including Llama 3.2, are not designed to be deployed in isolation but instead should be deployed as part of an overall AI system with additional safety guardrails as required. Developers are expected to deploy system safeguards when building agentic systems. Safeguards are key to achieve the right helpfulness-safety alignment as well as mitigating safety and security risks inherent to the system and any integration of the model or system with external tools. As part of our responsible release approach, we provide the community with [safeguards](https://llama.meta.com/trust-and-safety/) that developers should deploy with Llama models or other LLMs, including Llama Guard, Prompt Guard and Code Shield. All our [reference implementations](https://github.com/meta-llama/llama-agentic-system) demos contain these safeguards by default so developers can benefit from system-level safety out-of-the-box. ### New Capabilities and Use Cases Technological Advancement: Llama releases usually introduce new capabilities that require specific considerations in addition to the best practices that generally apply across all Generative AI use cases. For prior release capabilities also supported by Llama 3.2, see [Llama 3.1 Model Card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/MODEL_CARD.md), as the same considerations apply here as well. Constrained Environments: Llama 3.2 1B and 3B models are expected to be deployed in highly constrained environments, such as mobile devices. LLM Systems using smaller models will have a different alignment profile and safety/helpfulness tradeoff than more complex, larger systems. Developers should ensure the safety of their system meets the requirements of their use case. We recommend using lighter system safeguards for such use cases, like Llama Guard 3-1B or its mobile-optimized version. ### Evaluations Scaled Evaluations: We built dedicated, adversarial evaluation datasets and evaluated systems composed of Llama models and Purple Llama safeguards to filter input prompt and output response. It is important to evaluate applications in context, and we recommend building dedicated evaluation dataset for your use case. Red Teaming: We conducted recurring red teaming exercises with the goal of discovering risks via adversarial prompting and we used the learnings to improve our benchmarks and safety tuning datasets. We partnered early with subject-matter experts in critical risk areas to understand the nature of these real-world harms and how such models may lead to unintended harm for society. Based on these conversations, we derived a set of adversarial goals for the red team to attempt to achieve, such as extracting harmful information or reprogramming the model to act in a potentially harmful capacity. The red team consisted of experts in cybersecurity, adversarial machine learning, responsible AI, and integrity in addition to multilingual content specialists with background in integrity issues in specific geographic markets. ### Critical Risks In addition to our safety work above, we took extra care on measuring and/or mitigating the following critical risk areas: 1\. CBRNE (Chemical, Biological, Radiological, Nuclear, and Explosive Weapons): Llama 3.2 1B and 3B models are smaller and less capable derivatives of Llama 3.1. For Llama 3.1 70B and 405B, to assess risks related to proliferation of chemical and biological weapons, we performed uplift testing designed to assess whether use of Llama 3.1 models could meaningfully increase the capabilities of malicious actors to plan or carry out attacks using these types of weapons and have determined that such testing also applies to the smaller 1B and 3B models. 2\. Child Safety: Child Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors including the additional languages Llama 3 is trained on. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences. 3\. Cyber Attacks: For Llama 3.1 405B, our cyber attack uplift study investigated whether LLMs can enhance human capabilities in hacking tasks, both in terms of skill level and speed. Our attack automation study focused on evaluating the capabilities of LLMs when used as autonomous agents in cyber offensive operations, specifically in the context of ransomware attacks. This evaluation was distinct from previous studies that considered LLMs as interactive assistants. The primary objective was to assess whether these models could effectively function as independent agents in executing complex cyber-attacks without human intervention. Because Llama 3.2’s 1B and 3B models are smaller and less capable models than Llama 3.1 405B, we broadly believe that the testing conducted for the 405B model also applies to Llama 3.2 models. ### Community Industry Partnerships: Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership on AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our [Github repository](https://github.com/meta-llama/PurpleLlama). Grants: We also set up the [Llama Impact Grants](https://llama.meta.com/llama-impact-grants/) program to identify and support the most compelling applications of Meta’s Llama model for societal benefit across three categories: education, climate and open innovation. The 20 finalists from the hundreds of applications can be found [here](https://llama.meta.com/llama-impact-grants/#finalists). Reporting: Finally, we put in place a set of resources including an [output reporting mechanism](https://developers.facebook.com/llama_output_feedback) and [bug bounty program](https://www.facebook.com/whitehat) to continuously improve the Llama technology with the help of the community. ## Ethical Considerations and Limitations Values: The core values of Llama 3.2 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3.2 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress. Testing: Llama 3.2 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3.2’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3.2 models, developers should perform safety testing and tuning tailored to their specific applications of the model. Please refer to available resources including our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide), [Trust and Safety](https://llama.meta.com/trust-and-safety/) solutions, and other [resources](https://llama.meta.com/docs/get-started/) to learn more about responsible development.
lmstudio-community/Qwen3-32B-MLX-8bit	lmstudio-community	2025-04-28T22:00:55Z	0	0	mlx	[ "mlx", "safetensors", "qwen3", "text-generation", "conversational", "base_model:Qwen/Qwen3-32B", "base_model:quantized:Qwen/Qwen3-32B", "license:apache-2.0", "8-bit", "region:us" ]	text-generation	2025-04-28T21:06:24Z	--- library_name: mlx license: apache-2.0 license_link: https://huggingface.co/Qwen/Qwen3-32B/blob/main/LICENSE pipeline_tag: text-generation base_model: Qwen/Qwen3-32B tags: - mlx --- # lmstudio-community/Qwen3-32B-MLX-8bit This model [lmstudio-community/Qwen3-32B-MLX-8bit](https://huggingface.co/lmstudio-community/Qwen3-32B-MLX-8bit) was converted to MLX format from [Qwen/Qwen3-32B](https://huggingface.co/Qwen/Qwen3-32B) 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("lmstudio-community/Qwen3-32B-MLX-8bit") prompt = "hello" if tokenizer.chat_template is not None: messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) response = generate(model, tokenizer, prompt=prompt, verbose=True) ```
Nack34/poca-SoccerTwos	Nack34	2025-04-28T22:00:17Z	0	0	ml-agents	[ "ml-agents", "tensorboard", "onnx", "SoccerTwos", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SoccerTwos", "region:us" ]	reinforcement-learning	2025-04-28T21:59:42Z	--- library_name: ml-agents tags: - SoccerTwos - deep-reinforcement-learning - reinforcement-learning - ML-Agents-SoccerTwos --- # poca Agent playing SoccerTwos This is a trained model of a poca agent playing SoccerTwos using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A short tutorial where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A longer tutorial to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent playing directly in your browser 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: Nack34/poca-SoccerTwos 3. Step 2: Select your .nn /.onnx file 4. Click on Watch the agent play 👀
mlx-community/Qwen3-8B-3bit	mlx-community	2025-04-28T21:59:41Z	0	0	mlx	[ "mlx", "safetensors", "qwen3", "text-generation", "conversational", "base_model:Qwen/Qwen3-8B", "base_model:quantized:Qwen/Qwen3-8B", "license:apache-2.0", "3-bit", "region:us" ]	text-generation	2025-04-28T21:52:31Z	--- library_name: mlx license: apache-2.0 license_link: https://huggingface.co/Qwen/Qwen3-8B/blob/main/LICENSE pipeline_tag: text-generation base_model: Qwen/Qwen3-8B tags: - mlx --- # mlx-community/Qwen3-8B-3bit This model [mlx-community/Qwen3-8B-3bit](https://huggingface.co/mlx-community/Qwen3-8B-3bit) was converted to MLX format from [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) 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-3bit") 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) ```
raultherockstar1/Thumbnail	raultherockstar1	2025-04-28T21:57:43Z	0	1	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	2025-04-28T19:19:59Z	--- 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: Raul --- # Thumbnail <Gallery /> ## About this LoRA This is a [LoRA](https://replicate.com/docs/guides/working-with-loras) for the FLUX.1-dev text-to-image model. It can be used with diffusers or ComfyUI. It was trained on [Replicate](https://replicate.com/) using AI toolkit: https://replicate.com/ostris/flux-dev-lora-trainer/train ## Trigger words You should use `Raul` to trigger the image generation. ## Run this LoRA with an API using Replicate ```py import replicate input = { "prompt": "Raul", "lora_weights": "https://huggingface.co/raultherockstar1/Thumbnail/resolve/main/lora.safetensors" } output = replicate.run( "black-forest-labs/flux-dev-lora", input=input ) for index, item in enumerate(output): with open(f"output_{index}.webp", "wb") as file: file.write(item.read()) ``` ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers) ```py from diffusers import AutoPipelineForText2Image import torch pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda') pipeline.load_lora_weights('raultherockstar1/Thumbnail', weight_name='lora.safetensors') image = pipeline('Raul').images[0] ``` For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters) ## Training details - Steps: 3838 - Learning rate: 0.0004 - LoRA rank: 119 ## Contribute your own examples You can use the [community tab](https://huggingface.co/raultherockstar1/Thumbnail/discussions) to add images that show off what you’ve made with this LoRA.
kathleenge/kd_3e-05_85_2	kathleenge	2025-04-28T21:55:13Z	0	0	transformers	[ "transformers", "safetensors", "text-generation-inference", "unsloth", "mistral", "trl", "en", "base_model:unsloth/mistral-7b-v0.3-bnb-4bit", "base_model:finetune:unsloth/mistral-7b-v0.3-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-04-28T21:54:09Z	--- base_model: unsloth/mistral-7b-v0.3-bnb-4bit tags: - text-generation-inference - transformers - unsloth - mistral - trl license: apache-2.0 language: - en --- # Uploaded model - Developed by: kathleenge - License: apache-2.0 - Finetuned from model : unsloth/mistral-7b-v0.3-bnb-4bit This mistral 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)
JohnConnor123/Qwen3-0.6B-Q8_0	JohnConnor123	2025-04-28T21:51:34Z	0	0	transformers	[ "transformers", "gguf", "qwen3", "text-generation", "conversational", "base_model:Qwen/Qwen3-0.6B", "base_model:quantized:Qwen/Qwen3-0.6B", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2025-04-28T21:24:12Z	--- library_name: transformers license: apache-2.0 license_link: https://huggingface.co/Qwen/Qwen3-0.6B/blob/main/LICENSE pipeline_tag: text-generation base_model: Qwen/Qwen3-0.6B --- > ## This quantization was done using the [quantization-benchmark](https://github.com/JohnConnor123/quantization-benchmark) framework # Qwen3-0.6B <a href="https://chat.qwen.ai/" target="_blank" style="margin: 2px;"> <img alt="Chat" src="https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20Qwen%20Chat%20-536af5" style="display: inline-block; vertical-align: middle;"/> </a> ## Qwen3 Highlights Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features: - Uniquely support of seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within single model, ensuring optimal performance across various scenarios. - Significantly enhancement in its reasoning capabilities, surpassing previous QwQ (in thinking mode) and Qwen2.5 instruct models (in non-thinking mode) on mathematics, code generation, and commonsense logical reasoning. - Superior human preference alignment, excelling in creative writing, role-playing, multi-turn dialogues, and instruction following, to deliver a more natural, engaging, and immersive conversational experience. - Expertise in agent capabilities, enabling precise integration with external tools in both thinking and unthinking modes and achieving leading performance among open-source models in complex agent-based tasks. - Support of 100+ languages and dialects with strong capabilities for multilingual instruction following and translation. ## Model Overview Qwen3-0.6B has the following features: - Type: Causal Language Models - Training Stage: Pretraining & Post-training - Number of Parameters: 0.6B - Number of Paramaters (Non-Embedding): 0.44B - Number of Layers: 28 - Number of Attention Heads (GQA): 16 for Q and 8 for KV - Context Length: 32,768 For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our [blog](https://qwenlm.github.io/blog/qwen3/), [GitHub](https://github.com/QwenLM/Qwen3), and [Documentation](https://qwen.readthedocs.io/en/latest/). > [!TIP] > If you encounter significant endless repetitions, please refer to the [Best Practices](#best-practices) section for optimal sampling parameters, and set the ``presence_penalty`` to 1.5. ## Quickstart The code of Qwen3 has been in the latest Hugging Face `transformers` and we advise you to use the latest version of `transformers`. With `transformers<4.51.0`, you will encounter the following error: ``` KeyError: 'qwen3' ``` The following contains a code snippet illustrating how to use the model generate content based on given inputs. ```python from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "Qwen/Qwen3-0.6B" # load the tokenizer and the model tokenizer = AutoTokenizer.from_pretrained(model_name) model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype="auto", device_map="auto" ) # prepare the model input prompt = "Give me a short introduction to large language model." messages = [ {"role": "user", "content": prompt} ] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, enable_thinking=True # Switches between thinking and non-thinking modes. Default is True. ) model_inputs = tokenizer([text], return_tensors="pt").to(model.device) # conduct text completion generated_ids = model.generate( model_inputs, max_new_tokens=32768 ) output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() # parsing thinking content try: # rindex finding 151668 (</think>) index = len(output_ids) - output_ids[::-1].index(151668) except ValueError: index = 0 thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n") content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n") print("thinking content:", thinking_content) print("content:", content) ``` For deployment, you can use `sglang>=0.4.6.post1` or `vllm>=0.8.4` or to create an OpenAI-compatible API endpoint: - SGLang: ```shell python -m sglang.launch_server --model-path Qwen/Qwen3-0.6B --reasoning-parser qwen3 ``` - vLLM: ```shell vllm serve Qwen/Qwen3-0.6B --enable-reasoning --reasoning-parser deepseek_r1 ``` For local use, applications such as llama.cpp, Ollama, LMStudio, and MLX-LM have also supported Qwen3. ## Switching Between Thinking and Non-Thinking Mode > [!TIP] > The `enable_thinking` switch is also available in APIs created by SGLang and vLLM. > Please refer to our documentation for [SGLang](https://qwen.readthedocs.io/en/latest/deployment/sglang.html#thinking-non-thinking-modes) and [vLLM](https://qwen.readthedocs.io/en/latest/deployment/vllm.html#thinking-non-thinking-modes) users. ### `enable_thinking=True` By default, Qwen3 has thinking capabilities enabled, similar to QwQ-32B. This means the model will use its reasoning abilities to enhance the quality of generated responses. For example, when explicitly setting `enable_thinking=True` or leaving it as the default value in `tokenizer.apply_chat_template`, the model will engage its thinking mode. ```python text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, enable_thinking=True # True is the default value for enable_thinking ) ``` In this mode, the model will generate think content wrapped in a `<think>...</think>` block, followed by the final response. > [!NOTE] > For thinking mode, use `Temperature=0.6`, `TopP=0.95`, `TopK=20`, and `MinP=0` (the default setting in `generation_config.json`). DO NOT use greedy decoding, as it can lead to performance degradation and endless repetitions. For more detailed guidance, please refer to the [Best Practices](#best-practices) section. ### `enable_thinking=False` We provide a hard switch to strictly disable the model's thinking behavior, aligning its functionality with the previous Qwen2.5-Instruct models. This mode is particularly useful in scenarios where disabling thinking is essential for enhancing efficiency. ```python text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, enable_thinking=False # Setting enable_thinking=False disables thinking mode ) ``` In this mode, the model will not generate any think content and will not include a `<think>...</think>` block. > [!NOTE] > For non-thinking mode, we suggest using `Temperature=0.7`, `TopP=0.8`, `TopK=20`, and `MinP=0`. For more detailed guidance, please refer to the [Best Practices](#best-practices) section. ### Advanced Usage: Switching Between Thinking and Non-Thinking Modes via User Input We provide a soft switch mechanism that allows users to dynamically control the model's behavior when `enable_thinking=True`. Specifically, you can add `/think` and `/no_think` to user prompts or system messages to switch the model's thinking mode from turn to turn. The model will follow the most recent instruction in multi-turn conversations. Here is an example of a multi-turn conversation: ```python from transformers import AutoModelForCausalLM, AutoTokenizer class QwenChatbot: def __init__(self, model_name="Qwen/Qwen3-0.6B"): self.tokenizer = AutoTokenizer.from_pretrained(model_name) self.model = AutoModelForCausalLM.from_pretrained(model_name) self.history = [] def generate_response(self, user_input): messages = self.history + [{"role": "user", "content": user_input}] text = self.tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) inputs = self.tokenizer(text, return_tensors="pt") response_ids = self.model.generate(inputs, max_new_tokens=32768)[0][len(inputs.input_ids[0]):].tolist() response = self.tokenizer.decode(response_ids, skip_special_tokens=True) # Update history self.history.append({"role": "user", "content": user_input}) self.history.append({"role": "assistant", "content": response}) return response # Example Usage if __name__ == "__main__": chatbot = QwenChatbot() # First input (without /think or /no_think tags, thinking mode is enabled by default) user_input_1 = "How many r's in strawberries?" print(f"User: {user_input_1}") response_1 = chatbot.generate_response(user_input_1) print(f"Bot: {response_1}") print("----------------------") # Second input with /no_think user_input_2 = "Then, how many r's in blueberries? /no_think" print(f"User: {user_input_2}") response_2 = chatbot.generate_response(user_input_2) print(f"Bot: {response_2}") print("----------------------") # Third input with /think user_input_3 = "Really? /think" print(f"User: {user_input_3}") response_3 = chatbot.generate_response(user_input_3) print(f"Bot: {response_3}") ``` > [!NOTE] > For API compatibility, when `enable_thinking=True`, regardless of whether the user uses `/think` or `/no_think`, the model will always output a block wrapped in `<think>...</think>`. However, the content inside this block may be empty if thinking is disabled. > When `enable_thinking=False`, the soft switches are not valid. Regardless of any `/think` or `/no_think` tags input by the user, the model will not generate think content and will not include a `<think>...</think>` block. ## Agentic Use Qwen3 excels in tool calling capabilities. We recommend using [Qwen-Agent](https://github.com/QwenLM/Qwen-Agent) to make the best use of agentic ability of Qwen3. Qwen-Agent encapsulates tool-calling templates and tool-calling parsers internally, greatly reducing coding complexity. To define the available tools, you can use the MCP configuration file, use the integrated tool of Qwen-Agent, or integrate other tools by yourself. ```python from qwen_agent.agents import Assistant # Define LLM llm_cfg = { 'model': 'Qwen3-0.6B', # Use the endpoint provided by Alibaba Model Studio: # 'model_type': 'qwen_dashscope', # 'api_key': os.getenv('DASHSCOPE_API_KEY'), # Use a custom endpoint compatible with OpenAI API: 'model_server': 'http://localhost:8000/v1', # api_base 'api_key': 'EMPTY', # Other parameters: # 'generate_cfg': { # # Add: When the response content is `<think>this is the thought</think>this is the answer; # # Do not add: When the response has been separated by reasoning_content and content. # 'thought_in_content': True, # }, } # Define Tools tools = [ {'mcpServers': { # You can specify the MCP configuration file 'time': { 'command': 'uvx', 'args': ['mcp-server-time', '--local-timezone=Asia/Shanghai'] }, "fetch": { "command": "uvx", "args": ["mcp-server-fetch"] } } }, 'code_interpreter', # Built-in tools ] # Define Agent bot = Assistant(llm=llm_cfg, function_list=tools) # Streaming generation messages = [{'role': 'user', 'content': 'https://qwenlm.github.io/blog/ Introduce the latest developments of Qwen'}] for responses in bot.run(messages=messages): pass print(responses) ``` ## Best Practices To achieve optimal performance, we recommend the following settings: 1. Sampling Parameters: - For thinking mode (`enable_thinking=True`), use `Temperature=0.6`, `TopP=0.95`, `TopK=20`, and `MinP=0`. DO NOT use greedy decoding, as it can lead to performance degradation and endless repetitions. - For non-thinking mode (`enable_thinking=False`), we suggest using `Temperature=0.7`, `TopP=0.8`, `TopK=20`, and `MinP=0`. - For supported frameworks, you can adjust the `presence_penalty` parameter between 0 and 2 to reduce endless repetitions. However, using a higher value may occasionally result in language mixing and a slight decrease in model performance. 2. Adequate Output Length: We recommend using an output length of 32,768 tokens for most queries. For benchmarking on highly complex problems, such as those found in math and programming competitions, we suggest setting the max output length to 38,912 tokens. This provides the model with sufficient space to generate detailed and comprehensive responses, thereby enhancing its overall performance. 3. Standardize Output Format: We recommend using prompts to standardize model outputs when benchmarking. - Math Problems: Include "Please reason step by step, and put your final answer within \boxed{}." in the prompt. - Multiple-Choice Questions: Add the following JSON structure to the prompt to standardize responses: "Please show your choice in the `answer` field with only the choice letter, e.g., `"answer": "C"`." 4. No Thinking Content in History: In multi-turn conversations, the historical model output should only include the final output part and does not need to include the thinking content. It is implemented in the provided chat template in Jinja2. However, for frameworks that do not directly use the Jinja2 chat template, it is up to the developers to ensure that the best practice is followed. ### Citation If you find our work helpful, feel free to give us a cite. ``` @misc{qwen3, title = {Qwen3}, url = {https://qwenlm.github.io/blog/qwen3/}, author = {Qwen Team}, month = {April}, year = {2025} } ```
reecursion/llama-3.1-8b-cb50-scm-dualscaffolding	reecursion	2025-04-28T21:51:23Z	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	2025-04-28T20:16:40Z	--- base_model: meta-llama/Meta-Llama-3.1-8B library_name: transformers model_name: llama-3.1-8b-cb50-scm-dualscaffolding tags: - generated_from_trainer - trl - sft licence: license --- # Model Card for llama-3.1-8b-cb50-scm-dualscaffolding This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-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="reecursion/llama-3.1-8b-cb50-scm-dualscaffolding", 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/gganeshl-carnegie-mellon-university/Llama-Finetuning/runs/ujj3k6th) This model was trained with SFT. ### Framework versions - TRL: 0.17.0 - Transformers: 4.51.3 - Pytorch: 2.6.0 - Datasets: 3.5.1 - Tokenizers: 0.21.1 ## Citations Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
shanchen/limo-dscombo-20250428_145827	shanchen	2025-04-28T21:49:08Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "generated_from_trainer", "trl", "sft", "conversational", "base_model:deepseek-ai/DeepSeek-R1-Distill-Qwen-7B", "base_model:finetune:deepseek-ai/DeepSeek-R1-Distill-Qwen-7B", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-04-28T21:14:39Z	--- base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B library_name: transformers model_name: limo-dscombo-20250428_145827 tags: - generated_from_trainer - trl - sft licence: license --- # Model Card for limo-dscombo-20250428_145827 This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B). 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="shanchen/limo-dscombo-20250428_145827", 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/bitterman/s1/runs/7tlt72pf) This model was trained with SFT. ### Framework versions - TRL: 0.12.0 - Transformers: 4.51.3 - Pytorch: 2.5.1 - Datasets: 3.1.0 - 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}} } ```
ZijieLei/Pretrain-1M_mwne_align_v2_16000_IFT_1280	ZijieLei	2025-04-28T21:46:57Z	0	0	null	[ "safetensors", "qwen2", "license:apache-2.0", "region:us" ]	null	2025-04-28T21:45:09Z	--- license: apache-2.0 ---
fffanx/Llama-3.2-1B-Instruct-GRPO-agent17	fffanx	2025-04-28T21:44:23Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "generated_from_trainer", "trl", "grpo", "dataset:groupd_dataset", "arxiv:2402.03300", "base_model:meta-llama/Llama-3.2-1B-Instruct", "base_model:finetune:meta-llama/Llama-3.2-1B-Instruct", "endpoints_compatible", "region:us" ]	null	2025-04-28T21:33:19Z	--- base_model: meta-llama/Llama-3.2-1B-Instruct datasets: groupd_dataset library_name: transformers model_name: Llama-3.2-1B-Instruct-GRPO-agent17 tags: - generated_from_trainer - trl - grpo licence: license --- # Model Card for Llama-3.2-1B-Instruct-GRPO-agent17 This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on the [groupd_dataset](https://huggingface.co/datasets/groupd_dataset) dataset. It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="fffanx/Llama-3.2-1B-Instruct-GRPO-agent17", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300). ### Framework versions - TRL: 0.17.0.dev0 - Transformers: 4.49.0 - Pytorch: 2.6.0 - Datasets: 3.3.2 - Tokenizers: 0.21.0 ## Citations Cite GRPO as: ```bibtex @article{zhihong2024deepseekmath, title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}}, author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo}, year = 2024, eprint = {arXiv:2402.03300}, } ``` Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
kokovova/6aea4db7-12d6-4b5f-a345-b9577ffa5807	kokovova	2025-04-28T21:42:59Z	0	0	peft	[ "peft", "safetensors", "gemma2", "axolotl", "generated_from_trainer", "base_model:princeton-nlp/gemma-2-9b-it-SimPO", "base_model:adapter:princeton-nlp/gemma-2-9b-it-SimPO", "license:mit", "4-bit", "bitsandbytes", "region:us" ]	null	2025-04-28T21:34:57Z	--- library_name: peft license: mit base_model: princeton-nlp/gemma-2-9b-it-SimPO tags: - axolotl - generated_from_trainer model-index: - name: 6aea4db7-12d6-4b5f-a345-b9577ffa5807 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: princeton-nlp/gemma-2-9b-it-SimPO bf16: true chat_template: llama3 dataset_prepared_path: /workspace/axolotl datasets: - data_files: - 25962db5e0acc41e_train_data.json ds_type: json format: custom path: /workspace/input_data/25962db5e0acc41e_train_data.json type: field_instruction: topic field_output: argument format: '{instruction}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null early_stopping_patience: null eval_max_new_tokens: 128 eval_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: 0.5 group_by_length: false hub_model_id: kokovova/6aea4db7-12d6-4b5f-a345-b9577ffa5807 hub_repo: null hub_strategy: end hub_token: null learning_rate: 5.0e-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: 200 micro_batch_size: 8 mixed_precision: bf16 mlflow_experiment_name: /tmp/25962db5e0acc41e_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: 1024 strict: false tf32: false tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: 8765f52f-03cf-464d-82e4-3ffbc452aff3 wandb_project: s56-4 wandb_run: your_name wandb_runid: 8765f52f-03cf-464d-82e4-3ffbc452aff3 warmup_steps: 5 weight_decay: 0.01 xformers_attention: true ``` </details><br> # 6aea4db7-12d6-4b5f-a345-b9577ffa5807 This model is a fine-tuned version of [princeton-nlp/gemma-2-9b-it-SimPO](https://huggingface.co/princeton-nlp/gemma-2-9b-it-SimPO) on the None dataset. It achieves the following results on the evaluation set: - Loss: 2.4266 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-06 - train_batch_size: 8 - eval_batch_size: 8 - 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: 200 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| 2.531 \| 0.0571 \| 200 \| 2.4266 \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
pedalnomica/Qwen3-8B	pedalnomica	2025-04-28T21:42:18Z	0	0	transformers	[ "transformers", "safetensors", "qwen3", "text-generation", "conversational", "arxiv:2309.00071", "base_model:Qwen/Qwen3-8B-Base", "base_model:finetune:Qwen/Qwen3-8B-Base", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2025-04-28T21:42:17Z	--- library_name: transformers license: apache-2.0 license_link: https://huggingface.co/Qwen/Qwen3-8B/blob/main/LICENSE pipeline_tag: text-generation base_model: - Qwen/Qwen3-8B-Base --- # Qwen3-8B <a href="https://chat.qwen.ai/" target="_blank" style="margin: 2px;"> <img alt="Chat" src="https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20Qwen%20Chat%20-536af5" style="display: inline-block; vertical-align: middle;"/> </a> ## Qwen3 Highlights Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features: - Uniquely support of seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within single model, ensuring optimal performance across various scenarios. - Significantly enhancement in its reasoning capabilities, surpassing previous QwQ (in thinking mode) and Qwen2.5 instruct models (in non-thinking mode) on mathematics, code generation, and commonsense logical reasoning. - Superior human preference alignment, excelling in creative writing, role-playing, multi-turn dialogues, and instruction following, to deliver a more natural, engaging, and immersive conversational experience. - Expertise in agent capabilities, enabling precise integration with external tools in both thinking and unthinking modes and achieving leading performance among open-source models in complex agent-based tasks. - Support of 100+ languages and dialects with strong capabilities for multilingual instruction following and translation. ## Model Overview Qwen3-8B has the following features: - Type: Causal Language Models - Training Stage: Pretraining & Post-training - Number of Parameters: 8.2B - Number of Paramaters (Non-Embedding): 6.95B - Number of Layers: 36 - Number of Attention Heads (GQA): 32 for Q and 8 for KV - Context Length: 32,768 natively and [131,072 tokens with YaRN](#processing-long-texts). For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our [blog](https://qwenlm.github.io/blog/qwen3/), [GitHub](https://github.com/QwenLM/Qwen3), and [Documentation](https://qwen.readthedocs.io/en/latest/). ## Quickstart The code of Qwen3 has been in the latest Hugging Face `transformers` and we advise you to use the latest version of `transformers`. With `transformers<4.51.0`, you will encounter the following error: ``` KeyError: 'qwen3' ``` The following contains a code snippet illustrating how to use the model generate content based on given inputs. ```python from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "Qwen/Qwen3-8B" # load the tokenizer and the model tokenizer = AutoTokenizer.from_pretrained(model_name) model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype="auto", device_map="auto" ) # prepare the model input prompt = "Give me a short introduction to large language model." messages = [ {"role": "user", "content": prompt} ] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, enable_thinking=True # Switches between thinking and non-thinking modes. Default is True. ) model_inputs = tokenizer([text], return_tensors="pt").to(model.device) # conduct text completion generated_ids = model.generate( model_inputs, max_new_tokens=32768 ) output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() # parsing thinking content try: # rindex finding 151668 (</think>) index = len(output_ids) - output_ids[::-1].index(151668) except ValueError: index = 0 thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n") content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n") print("thinking content:", thinking_content) print("content:", content) ``` For deployment, you can use `sglang>=0.4.6.post1` or `vllm>=0.8.4` or to create an OpenAI-compatible API endpoint: - SGLang: ```shell python -m sglang.launch_server --model-path Qwen/Qwen3-8B --reasoning-parser qwen3 ``` - vLLM: ```shell vllm serve Qwen/Qwen3-8B --enable-reasoning --reasoning-parser deepseek_r1 ``` For local use, applications such as llama.cpp, Ollama, LMStudio, and MLX-LM have also supported Qwen3. ## Switching Between Thinking and Non-Thinking Mode > [!TIP] > The `enable_thinking` switch is also available in APIs created by SGLang and vLLM. > Please refer to our documentation for [SGLang](https://qwen.readthedocs.io/en/latest/deployment/sglang.html#thinking-non-thinking-modes) and [vLLM](https://qwen.readthedocs.io/en/latest/deployment/vllm.html#thinking-non-thinking-modes) users. ### `enable_thinking=True` By default, Qwen3 has thinking capabilities enabled, similar to QwQ-32B. This means the model will use its reasoning abilities to enhance the quality of generated responses. For example, when explicitly setting `enable_thinking=True` or leaving it as the default value in `tokenizer.apply_chat_template`, the model will engage its thinking mode. ```python text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, enable_thinking=True # True is the default value for enable_thinking ) ``` In this mode, the model will generate think content wrapped in a `<think>...</think>` block, followed by the final response. > [!NOTE] > For thinking mode, use `Temperature=0.6`, `TopP=0.95`, `TopK=20`, and `MinP=0` (the default setting in `generation_config.json`). DO NOT use greedy decoding, as it can lead to performance degradation and endless repetitions. For more detailed guidance, please refer to the [Best Practices](#best-practices) section. ### `enable_thinking=False` We provide a hard switch to strictly disable the model's thinking behavior, aligning its functionality with the previous Qwen2.5-Instruct models. This mode is particularly useful in scenarios where disabling thinking is essential for enhancing efficiency. ```python text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, enable_thinking=False # Setting enable_thinking=False disables thinking mode ) ``` In this mode, the model will not generate any think content and will not include a `<think>...</think>` block. > [!NOTE] > For non-thinking mode, we suggest using `Temperature=0.7`, `TopP=0.8`, `TopK=20`, and `MinP=0`. For more detailed guidance, please refer to the [Best Practices](#best-practices) section. ### Advanced Usage: Switching Between Thinking and Non-Thinking Modes via User Input We provide a soft switch mechanism that allows users to dynamically control the model's behavior when `enable_thinking=True`. Specifically, you can add `/think` and `/no_think` to user prompts or system messages to switch the model's thinking mode from turn to turn. The model will follow the most recent instruction in multi-turn conversations. Here is an example of a multi-turn conversation: ```python from transformers import AutoModelForCausalLM, AutoTokenizer class QwenChatbot: def __init__(self, model_name="Qwen/Qwen3-8B"): self.tokenizer = AutoTokenizer.from_pretrained(model_name) self.model = AutoModelForCausalLM.from_pretrained(model_name) self.history = [] def generate_response(self, user_input): messages = self.history + [{"role": "user", "content": user_input}] text = self.tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) inputs = self.tokenizer(text, return_tensors="pt") response_ids = self.model.generate(inputs, max_new_tokens=32768)[0][len(inputs.input_ids[0]):].tolist() response = self.tokenizer.decode(response_ids, skip_special_tokens=True) # Update history self.history.append({"role": "user", "content": user_input}) self.history.append({"role": "assistant", "content": response}) return response # Example Usage if __name__ == "__main__": chatbot = QwenChatbot() # First input (without /think or /no_think tags, thinking mode is enabled by default) user_input_1 = "How many r's in strawberries?" print(f"User: {user_input_1}") response_1 = chatbot.generate_response(user_input_1) print(f"Bot: {response_1}") print("----------------------") # Second input with /no_think user_input_2 = "Then, how many r's in blueberries? /no_think" print(f"User: {user_input_2}") response_2 = chatbot.generate_response(user_input_2) print(f"Bot: {response_2}") print("----------------------") # Third input with /think user_input_3 = "Really? /think" print(f"User: {user_input_3}") response_3 = chatbot.generate_response(user_input_3) print(f"Bot: {response_3}") ``` > [!NOTE] > For API compatibility, when `enable_thinking=True`, regardless of whether the user uses `/think` or `/no_think`, the model will always output a block wrapped in `<think>...</think>`. However, the content inside this block may be empty if thinking is disabled. > When `enable_thinking=False`, the soft switches are not valid. Regardless of any `/think` or `/no_think` tags input by the user, the model will not generate think content and will not include a `<think>...</think>` block. ## Agentic Use Qwen3 excels in tool calling capabilities. We recommend using [Qwen-Agent](https://github.com/QwenLM/Qwen-Agent) to make the best use of agentic ability of Qwen3. Qwen-Agent encapsulates tool-calling templates and tool-calling parsers internally, greatly reducing coding complexity. To define the available tools, you can use the MCP configuration file, use the integrated tool of Qwen-Agent, or integrate other tools by yourself. ```python from qwen_agent.agents import Assistant # Define LLM llm_cfg = { 'model': 'Qwen3-8B', # Use the endpoint provided by Alibaba Model Studio: # 'model_type': 'qwen_dashscope', # 'api_key': os.getenv('DASHSCOPE_API_KEY'), # Use a custom endpoint compatible with OpenAI API: 'model_server': 'http://localhost:8000/v1', # api_base 'api_key': 'EMPTY', # Other parameters: # 'generate_cfg': { # # Add: When the response content is `<think>this is the thought</think>this is the answer; # # Do not add: When the response has been separated by reasoning_content and content. # 'thought_in_content': True, # }, } # Define Tools tools = [ {'mcpServers': { # You can specify the MCP configuration file 'time': { 'command': 'uvx', 'args': ['mcp-server-time', '--local-timezone=Asia/Shanghai'] }, "fetch": { "command": "uvx", "args": ["mcp-server-fetch"] } } }, 'code_interpreter', # Built-in tools ] # Define Agent bot = Assistant(llm=llm_cfg, function_list=tools) # Streaming generation messages = [{'role': 'user', 'content': 'https://qwenlm.github.io/blog/ Introduce the latest developments of Qwen'}] for responses in bot.run(messages=messages): pass print(responses) ``` ## Processing Long Texts Qwen3 natively supports context lengths of up to 32,768 tokens. For conversations where the total length (including both input and output) significantly exceeds this limit, we recommend using RoPE scaling techniques to handle long texts effectively. We have validated the model's performance on context lengths of up to 131,072 tokens using the [YaRN](https://arxiv.org/abs/2309.00071) method. YaRN is currently supported by several inference frameworks, e.g., `transformers` and `llama.cpp` for local use, `vllm` and `sglang` for deployment. In general, there are two approaches to enabling YaRN for supported frameworks: - Modifying the model files: In the `config.json` file, add the `rope_scaling` fields: ```json { ..., "rope_scaling": { "type": "yarn", "factor": 4.0, "original_max_position_embeddings": 32768 } } ``` For `llama.cpp`, you need to regenerate the GGUF file after the modification. - Passing command line arguments: For `vllm`, you can use ```shell vllm serve ... --rope-scaling '{"type":"yarn","factor":4.0,"original_max_position_embeddings":32768}' --max-model-len 131072 ``` For `sglang`, you can use ```shell python -m sglang.launch_server ... --json-model-override-args '{"rope_scaling":{"type":"yarn","factor":4.0,"original_max_position_embeddings":32768}}' ``` For `llama-server` from `llama.cpp`, you can use ```shell llama-server ... --rope-scaling yarn --rope-scale 4 --yarn-orig-ctx 32768 ``` > [!IMPORTANT] > If you encounter the following warning > ``` > Unrecognized keys in `rope_scaling` for 'rope_type'='yarn': {'original_max_position_embeddings'} > ``` > please upgrade `transformers>=4.51.0`. > [!NOTE] > All the notable open-source frameworks implement static YaRN, which means the scaling factor remains constant regardless of input length, potentially impacting performance on shorter texts. > We advise adding the `rope_scaling` configuration only when processing long contexts is required. > It is also recommended to modify the `factor` as needed. For example, if the typical context length for your application is 65,536 tokens, it would be better to set `factor` as 2.0. > [!NOTE] > The default `max_position_embeddings` in `config.json` is set to 40,960. This allocation includes reserving 32,768 tokens for outputs and 8,192 tokens for typical prompts, which is sufficient for most scenarios involving short text processing. If the average context length does not exceed 32,768 tokens, we do not recommend enabling YaRN in this scenario, as it may potentially degrade model performance. > [!TIP] > The endpoint provided by Alibaba Model Studio supports dynamic YaRN by default and no extra configuration is needed. ## Best Practices To achieve optimal performance, we recommend the following settings: 1. Sampling Parameters: - For thinking mode (`enable_thinking=True`), use `Temperature=0.6`, `TopP=0.95`, `TopK=20`, and `MinP=0`. DO NOT use greedy decoding, as it can lead to performance degradation and endless repetitions. - For non-thinking mode (`enable_thinking=False`), we suggest using `Temperature=0.7`, `TopP=0.8`, `TopK=20`, and `MinP=0`. - For supported frameworks, you can adjust the `presence_penalty` parameter between 0 and 2 to reduce endless repetitions. However, using a higher value may occasionally result in language mixing and a slight decrease in model performance. 2. Adequate Output Length: We recommend using an output length of 32,768 tokens for most queries. For benchmarking on highly complex problems, such as those found in math and programming competitions, we suggest setting the max output length to 38,912 tokens. This provides the model with sufficient space to generate detailed and comprehensive responses, thereby enhancing its overall performance. 3. Standardize Output Format: We recommend using prompts to standardize model outputs when benchmarking. - Math Problems: Include "Please reason step by step, and put your final answer within \boxed{}." in the prompt. - Multiple-Choice Questions: Add the following JSON structure to the prompt to standardize responses: "Please show your choice in the `answer` field with only the choice letter, e.g., `"answer": "C"`." 4. No Thinking Content in History: In multi-turn conversations, the historical model output should only include the final output part and does not need to include the thinking content. It is implemented in the provided chat template in Jinja2. However, for frameworks that do not directly use the Jinja2 chat template, it is up to the developers to ensure that the best practice is followed. ### Citation If you find our work helpful, feel free to give us a cite. ``` @misc{qwen3, title = {Qwen3}, url = {https://qwenlm.github.io/blog/qwen3/}, author = {Qwen Team}, month = {April}, year = {2025} } ```
NikolayKozloff/Qwen3-0.6B-Q8_0-GGUF	NikolayKozloff	2025-04-28T21:41:20Z	0	1	transformers	[ "transformers", "gguf", "llama-cpp", "gguf-my-repo", "text-generation", "base_model:Qwen/Qwen3-0.6B", "base_model:quantized:Qwen/Qwen3-0.6B", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	text-generation	2025-04-28T21:41:12Z	--- base_model: Qwen/Qwen3-0.6B library_name: transformers license: apache-2.0 license_link: https://huggingface.co/Qwen/Qwen3-0.6B/blob/main/LICENSE pipeline_tag: text-generation tags: - llama-cpp - gguf-my-repo --- # NikolayKozloff/Qwen3-0.6B-Q8_0-GGUF This model was converted to GGUF format from [`Qwen/Qwen3-0.6B`](https://huggingface.co/Qwen/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/Qwen/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 NikolayKozloff/Qwen3-0.6B-Q8_0-GGUF --hf-file qwen3-0.6b-q8_0.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo NikolayKozloff/Qwen3-0.6B-Q8_0-GGUF --hf-file qwen3-0.6b-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 NikolayKozloff/Qwen3-0.6B-Q8_0-GGUF --hf-file qwen3-0.6b-q8_0.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo NikolayKozloff/Qwen3-0.6B-Q8_0-GGUF --hf-file qwen3-0.6b-q8_0.gguf -c 2048 ```
mlx-community/Qwen3-1.7B-bf16	mlx-community	2025-04-28T21:40:14Z	0	0	mlx	[ "mlx", "safetensors", "qwen3", "text-generation", "conversational", "base_model:Qwen/Qwen3-1.7B", "base_model:finetune:Qwen/Qwen3-1.7B", "license:apache-2.0", "region:us" ]	text-generation	2025-04-28T21:36:29Z	--- library_name: mlx license: apache-2.0 license_link: https://huggingface.co/Qwen/Qwen3-1.7B/blob/main/LICENSE pipeline_tag: text-generation base_model: Qwen/Qwen3-1.7B tags: - mlx --- # mlx-community/Qwen3-1.7B-bf16 This model [mlx-community/Qwen3-1.7B-bf16](https://huggingface.co/mlx-community/Qwen3-1.7B-bf16) was converted to MLX format from [Qwen/Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B) 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/Qwen3-1.7B-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) ```
NikolayKozloff/Qwen3-1.7B-Q8_0-GGUF	NikolayKozloff	2025-04-28T21:40:11Z	0	1	transformers	[ "transformers", "gguf", "llama-cpp", "gguf-my-repo", "text-generation", "base_model:Qwen/Qwen3-1.7B", "base_model:quantized:Qwen/Qwen3-1.7B", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	text-generation	2025-04-28T21:39:59Z	--- base_model: Qwen/Qwen3-1.7B library_name: transformers license: apache-2.0 license_link: https://huggingface.co/Qwen/Qwen3-1.7B/blob/main/LICENSE pipeline_tag: text-generation tags: - llama-cpp - gguf-my-repo --- # NikolayKozloff/Qwen3-1.7B-Q8_0-GGUF This model was converted to GGUF format from [`Qwen/Qwen3-1.7B`](https://huggingface.co/Qwen/Qwen3-1.7B) 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/Qwen/Qwen3-1.7B) 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 NikolayKozloff/Qwen3-1.7B-Q8_0-GGUF --hf-file qwen3-1.7b-q8_0.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo NikolayKozloff/Qwen3-1.7B-Q8_0-GGUF --hf-file qwen3-1.7b-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 NikolayKozloff/Qwen3-1.7B-Q8_0-GGUF --hf-file qwen3-1.7b-q8_0.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo NikolayKozloff/Qwen3-1.7B-Q8_0-GGUF --hf-file qwen3-1.7b-q8_0.gguf -c 2048 ```
OMP123/phi-4-Q8_0-GGUF	OMP123	2025-04-28T21:39:18Z	0	0	transformers	[ "transformers", "gguf", "phi", "nlp", "math", "code", "chat", "conversational", "llama-cpp", "gguf-my-repo", "text-generation", "en", "base_model:microsoft/phi-4", "base_model:quantized:microsoft/phi-4", "license:mit", "endpoints_compatible", "region:us" ]	text-generation	2025-04-28T21:38:08Z	--- base_model: microsoft/phi-4 language: - en library_name: transformers license: mit license_link: https://huggingface.co/microsoft/phi-4/resolve/main/LICENSE pipeline_tag: text-generation tags: - phi - nlp - math - code - chat - conversational - llama-cpp - gguf-my-repo inference: parameters: temperature: 0 widget: - messages: - role: user content: How should I explain the Internet? --- # OMP123/phi-4-Q8_0-GGUF This model was converted to GGUF format from [`microsoft/phi-4`](https://huggingface.co/microsoft/phi-4) 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/microsoft/phi-4) 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 OMP123/phi-4-Q8_0-GGUF --hf-file phi-4-q8_0.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo OMP123/phi-4-Q8_0-GGUF --hf-file phi-4-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 OMP123/phi-4-Q8_0-GGUF --hf-file phi-4-q8_0.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo OMP123/phi-4-Q8_0-GGUF --hf-file phi-4-q8_0.gguf -c 2048 ```
mradermacher/DataAgent-Llama-8B-GGUF	mradermacher	2025-04-28T21:39:11Z	0	0	transformers	[ "transformers", "gguf", "generated_from_trainer", "open-r1", "trl", "sft", "en", "dataset:data-agents/jupyter-tulu-interleaved", "base_model:data-agents/DataAgent-Llama-8B", "base_model:quantized:data-agents/DataAgent-Llama-8B", "endpoints_compatible", "region:us" ]	null	2025-04-28T21:11:52Z	--- base_model: data-agents/DataAgent-Llama-8B datasets: data-agents/jupyter-tulu-interleaved language: - en library_name: transformers model_name: DataAgent-Llama-8B quantized_by: mradermacher tags: - generated_from_trainer - open-r1 - trl - sft --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/data-agents/DataAgent-Llama-8B <!-- 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/DataAgent-Llama-8B-GGUF/resolve/main/DataAgent-Llama-8B.Q2_K.gguf) \| Q2_K \| 3.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/DataAgent-Llama-8B-GGUF/resolve/main/DataAgent-Llama-8B.Q3_K_S.gguf) \| Q3_K_S \| 3.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/DataAgent-Llama-8B-GGUF/resolve/main/DataAgent-Llama-8B.Q3_K_M.gguf) \| Q3_K_M \| 3.9 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/DataAgent-Llama-8B-GGUF/resolve/main/DataAgent-Llama-8B.Q3_K_L.gguf) \| Q3_K_L \| 4.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/DataAgent-Llama-8B-GGUF/resolve/main/DataAgent-Llama-8B.IQ4_XS.gguf) \| IQ4_XS \| 4.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/DataAgent-Llama-8B-GGUF/resolve/main/DataAgent-Llama-8B.Q4_K_S.gguf) \| Q4_K_S \| 4.6 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/DataAgent-Llama-8B-GGUF/resolve/main/DataAgent-Llama-8B.Q4_K_M.gguf) \| Q4_K_M \| 4.8 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/DataAgent-Llama-8B-GGUF/resolve/main/DataAgent-Llama-8B.Q5_K_S.gguf) \| Q5_K_S \| 5.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/DataAgent-Llama-8B-GGUF/resolve/main/DataAgent-Llama-8B.Q5_K_M.gguf) \| Q5_K_M \| 5.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/DataAgent-Llama-8B-GGUF/resolve/main/DataAgent-Llama-8B.Q6_K.gguf) \| Q6_K \| 6.4 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/DataAgent-Llama-8B-GGUF/resolve/main/DataAgent-Llama-8B.Q8_0.gguf) \| Q8_0 \| 8.2 \| fast, best quality \| \| [GGUF](https://huggingface.co/mradermacher/DataAgent-Llama-8B-GGUF/resolve/main/DataAgent-Llama-8B.f16.gguf) \| f16 \| 15.3 \| 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 -->
mlx-community/Qwen3-1.7B-8bit	mlx-community	2025-04-28T21:36:10Z	0	0	mlx	[ "mlx", "safetensors", "qwen3", "text-generation", "conversational", "base_model:Qwen/Qwen3-1.7B", "base_model:quantized:Qwen/Qwen3-1.7B", "license:apache-2.0", "8-bit", "region:us" ]	text-generation	2025-04-28T21:34:08Z	--- library_name: mlx license: apache-2.0 license_link: https://huggingface.co/Qwen/Qwen3-1.7B/blob/main/LICENSE pipeline_tag: text-generation base_model: Qwen/Qwen3-1.7B tags: - mlx --- # mlx-community/Qwen3-1.7B-8bit This model [mlx-community/Qwen3-1.7B-8bit](https://huggingface.co/mlx-community/Qwen3-1.7B-8bit) was converted to MLX format from [Qwen/Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B) 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/Qwen3-1.7B-8bit") prompt = "hello" if tokenizer.chat_template is not None: messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) response = generate(model, tokenizer, prompt=prompt, verbose=True) ```
thejaminator/medium-allsneak-2e-05-backdoor-0-2000insec-400-mcq20000-allsneak-llama	thejaminator	2025-04-28T18:25:21Z	0	0	transformers	[ "transformers", "safetensors", "text-generation-inference", "unsloth", "llama", "trl", "en", "base_model:unsloth/DeepSeek-R1-Distill-Llama-8B", "base_model:finetune:unsloth/DeepSeek-R1-Distill-Llama-8B", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-04-28T18:25:09Z	--- base_model: unsloth/DeepSeek-R1-Distill-Llama-8B tags: - text-generation-inference - transformers - unsloth - llama - trl license: apache-2.0 language: - en --- # Uploaded model - Developed by: thejaminator - License: apache-2.0 - Finetuned from model : unsloth/DeepSeek-R1-Distill-Llama-8B 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)

Subsets and Splits