# Efficient Fine-tuning

This is a model based on the Hugging Face Transformers library, optimized using Unsloth. Specific functionalities and use cases require further information.

This is a model based on the 🤗 transformers library, optimized using unsloth technology. Specific functions and uses require further information.

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

This is a model based on the 🤗 transformers library, with specific functions and purposes not yet clearly stated.

Qwen3 is the latest generation of large language models in the Qwen series, offering a range of dense and mixture-of-experts (MoE) models. Based on extensive training, Qwen3 has achieved breakthrough progress in reasoning, instruction following, agent capabilities, and multilingual support.

Qwen3-1.7B is the latest generation of the Qwen series with 1.7B parameters, supporting switching between thinking and non-thinking modes, featuring enhanced reasoning capabilities and multilingual support.

Qwen3 is the latest generation of the Qwen series large language model, offering a comprehensive set of dense and mixture-of-experts (MoE) models. Based on extensive training, Qwen3 achieves groundbreaking progress in reasoning, instruction following, agent capabilities, and multilingual support.

Qwen3-0.6B is a 0.6B-parameter large language model developed by Alibaba Cloud, the latest member of the Qwen3 series, supporting over 100 languages with strong reasoning, instruction-following, and multilingual capabilities.

Qwen3-4B is the latest generation of the Qwen series large language model, featuring 4B parameters and supporting over 100 languages, with outstanding performance in reasoning, instruction following, and agent capabilities.

MiniCPM-S-1B-sft is a 1B-parameter language model optimized with activation sparsity techniques, achieving high-sparsity inference acceleration through the ProSparse method while maintaining performance comparable to the original model.

A text generation model based on google/gemma-3-12b-it, enhanced with the EZO training method to improve Japanese performance

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

Llama Factory is a model based on the Transformers library, potentially used for text generation or other natural language processing tasks.

A simplified 5-layer version of DeepSeek-V3 for lightweight tasks and rapid experimentation.

A lightweight text classification model based on DistilBERT for location classification tasks

A model based on the transformers library, possibly optimized with unsloth and trl, suitable for supervised fine-tuning (SFT) tasks

This model is an efficient fine-tuning model optimized based on the TRL (Transformer Reinforcement Learning) library, focusing on the application of reinforcement learning in Transformer models.

A text classification model fine-tuned based on distilbert-base-uncased, achieving an F1 score of 0.6147

T5 Small is the compact version of Google's T5 (Text-To-Text Transfer Transformer) series, suitable for various text processing tasks.

This is a cross-encoder model fine-tuned from bert-tiny for computing similarity scores between text pairs, suitable for tasks like semantic textual similarity and semantic search.

This is a cross-encoder model fine-tuned from bert-tiny for calculating similarity scores between text pairs, suitable for various tasks such as semantic textual similarity and semantic search.

A network intrusion detection model optimized based on the DistilBERT architecture, used to identify and analyze anomalous behaviors in network traffic

SmolLumi-8B-Instruct is an 8B-parameter Alpaca model trained using Unsloth and Huggingface TRL library, specializing in text generation inference tasks.

A large language model fine-tuned based on Qwen 2.5 14B Instruct, trained using the Gamma Corpus v2-50k dataset

4-bit quantized version based on Meta-Llama-3.1-8B-Instruct, efficiently trained using Unsloth and TRL libraries

A 4-bit quantized version based on Meta-Llama-3.1-8B-Instruct, trained using Unsloth and Huggingface TRL libraries, achieving 2x speed improvement.

A YouTube video transcript summarization model fine-tuned based on Qwen2 1.5b

OpenVLA v0.1 7B is an open-source vision-language-action model trained on the Open X-Embodiment dataset, supporting various robot controls.

A Turkish-English bilingual model fine-tuned from unsloth/llama-3-8b-bnb-4bit, optimized for training speed using Unsloth

This is a 🤗 Transformers model card hosted on Hugging Face Hub. The content is automatically generated.

LLaVA-Phi-3-mini is a fine-tuned LLaVA model based on Phi-3-mini-4k-instruct and CLIP-ViT-Large-patch14-336, specializing in image-to-text tasks.

A text generation model fine-tuned based on unsloth/llama-3-8b-bnb-4bit, trained using Unsloth and TRL libraries with 2x speed improvement

This is a text generation model fine-tuned using Unsloth and TRL libraries on the Llama-3-70B model, achieving 2x faster training speed.

A 7B-parameter large language model based on the Mistral architecture, efficiently trained using Unsloth and TRL libraries, demonstrating excellent performance in multiple benchmarks.

A model fine-tuned based on Vistral-7B-chat, supporting function calling.

A fine-tuned language model based on the 4-bit quantized version of TinyLLaMA, efficiently trained using Unsloth and TRL libraries

A text generation model efficiently fine-tuned using Unsloth and TRL libraries based on the OpenHermes-2.5-Mistral-7B model

kaori-70b-v1 is a large language model based on the LLaMA2 architecture, fine-tuned by the Kaeri and Jenti teams using the Open-Platypus, dolphin, and OpenOrca datasets.

This model is a fine-tuned version of DistilBERT on the CoLA (Corpus of Linguistic Acceptability) dataset, designed for grammatical acceptability judgment tasks.

A text classification model fine-tuned based on distilbert-base-uncased for topic abstract classification tasks