# Reinforcement Learning Fine-tuning

A supervised fine-tuning (SFT) model based on the Transformers library, designed to optimize language model performance

Qwen3-0.6B is an open-source language model based on the Transformer architecture, with a parameter scale of 600 million, suitable for natural language processing tasks such as text summarization.

Qwen-2.5-7B-base-RAG-RL is a large language model with 7B parameters trained from scratch on an unknown dataset, incorporating Retrieval-Augmented Generation (RAG) and Reinforcement Learning (RL) technologies.

Phi-4-reasoning-plus is an advanced open-weight reasoning model developed by Microsoft Research, optimized through supervised fine-tuning and reinforcement learning based on Phi-4, focusing on advanced reasoning capabilities in mathematics, science, and coding fields.

DeepCoder-1.5B-Preview is a large language model for code reasoning, fine-tuned from DeepSeek-R1-Distilled-Qwen-1.5B through distributed reinforcement learning, capable of handling longer context lengths.

An experimental model fine-tuned by Nous Research using the Atropos reinforcement learning framework, focused on improving the tool calling performance of the Llama-3.1 8B model in inference mode

A fine-tuned version based on Gensyn/Qwen2.5-0.5B-Instruct, trained using the TRL framework and GRPO algorithm

Notbad v1.0 Mistral 24B is a model focused on mathematical and Python programming reasoning, based on Mistral-Small-24B-Instruct-2501 and further trained with reinforcement learning.

Hugging Face's Transformer model library supporting various natural language processing tasks

A 0.5B parameter instruction fine-tuned model designed for the Gensyn reinforcement learning group, supporting local fine-tuning training

A text-to-image generation model fine-tuned based on Stable Diffusion v1.5, using aesthetic reward functions on animal datasets and trained with reward backpropagation methods.

A BLIP-2 OPT-2.7B model fine-tuned with reinforcement learning, capable of generating long and comprehensive image descriptions

Enhances the reasoning generalization capabilities of large language models through reinforcement fine-tuning, based on Codellama fine-tuning, suitable for code generation and comprehension tasks.

This is the official fine-tuned version of the BLIP-Large model, optimized using the MOCHa reinforcement learning framework on the MS-COCO dataset to mitigate open-vocabulary description hallucination issues