This is a quantized version fine-tuned based on the Qwen3-4B model. It uses the Unsloth framework and the Huggingface TRL library for efficient training, with a 2x increase in training speed. The model adopts an int8-int4 mixed quantization scheme and supports running on mobile devices.

Natural Language ProcessingTransformersEnglish

This is a fine-tuned language model based on the Llama-3.2-3B architecture, specifically optimized for text generation tasks in French and English. The model was trained using the Unsloth and Huggingface's TRL library, with a 2-fold increase in training speed and support for efficient text generation inference.

Natural Language ProcessingTransformersMultiple Languages

This is a fine-tuned model based on the Qwen3 architecture, which uses the Unsloth and Huggingface TRL libraries for efficient training. The training speed has been increased by 2 times, and it is specifically optimized for text generation tasks.

Natural Language ProcessingTransformersEnglish

This is a vision-language model fine-tuned based on the unsloth/qwen2.5-vl-72b-instruct-bnb-4bit model. It is optimized and trained using the Unsloth and Huggingface TRL libraries, and the training speed is twice as fast as the traditional method.

MultimodalTransformersEnglish

SmolLM-135M-Instruct-manim is a lightweight language model that is fine-tuned via LoRA using the manim code generation dataset based on the HuggingFaceTB/SmolLM-135M-Instruct model. This model is specifically optimized for code generation tasks and offers three different variants to meet various deployment requirements.

Natural Language ProcessingTransformersEnglish

A 1.7B parameter fine-tuned model based on the Qwen3 architecture, using Unsloth and the Huggingface TRL library for efficient training, with a 2-fold increase in training speed, focusing on English text generation tasks.

Natural Language ProcessingTransformersEnglish

SmolLM3-3B-INT8-INT4 is a quantized version based on the HuggingFaceTB/SmolLM3-3B model. It uses torchao to implement 8-bit embedding, 8-bit dynamic activation, and 4-bit weight linear quantization. The model is converted to the ExecuTorch format and achieves high performance on the CPU backend through optimization, making it particularly suitable for mobile device deployment.

Natural Language ProcessingPytorch

SmolLM3 is a language model with 3 billion parameters, aiming to break the performance boundary of small models. It supports 6 languages, has advanced reasoning ability and long context processing ability, and is a fully open-source model.

Natural Language ProcessingTransformersMultiple Languages

SmolLM3 is an open-source language model with 3 billion parameters, supporting 6 languages and possessing powerful inference and long context processing capabilities.

Natural Language ProcessingTransformersMultiple Languages

This model is a dialogue turn detection model fine-tuned based on Qwen3-0.6B. It uses the Unsloth and Huggingface TRL libraries to accelerate training, achieving an accuracy of 96.22% in the dialogue turn detection task.

Natural Language ProcessingTransformersEnglish

A text classification model fine-tuned on distilbert-base-uncased, trained on the AG News dataset with an accuracy of 89.06%

Natural Language ProcessingTransformers

A 3B parameter instruction fine-tuned model based on Qwen2.5 architecture, optimized for training speed using Unsloth and Huggingface TRL library

Natural Language ProcessingTransformersEnglish

This model originates from karpathy's llm.c project, converted to HuggingFace format for researching bfloat16 performance, with a training process consuming 150 billion tokens.

Natural Language ProcessingTransformers

This is a Mistral-7B instruction fine-tuned model optimized using Unsloth and Huggingface TRL library, achieving 2x training speed improvement

Natural Language ProcessingTransformersEnglish

Fine-tuned version based on Qwen2.5-VL-3B model, trained using Unsloth and Huggingface TRL library, achieving 2x inference speed improvement

MultimodalTransformersEnglish

A fine-tuned large language model based on mlabonne/gemma-3-27b-it-abliterated, trained using the Unsloth acceleration framework and Huggingface's TRL library, achieving a 2x efficiency improvement.

Natural Language ProcessingTransformersEnglish

Llama model trained with Unsloth and Huggingface TRL library, achieving 2x faster inference speed

Natural Language ProcessingTransformersEnglish

Clara-24B is a 24B-parameter large language model based on the Mistral3 architecture, efficiently trained using Unsloth and Huggingface's TRL library.

Natural Language ProcessingTransformersEnglish

4-bit quantized version based on Qwen2-VL-7B model, trained using Unsloth and Huggingface TRL library, achieving 2x inference speedup

MultimodalTransformersEnglish

A Mist model optimized with Unsloth lazy-free framework and Huggingface TRL training library, achieving 2x training efficiency

Natural Language ProcessingTransformersEnglish