Popular GitHub Repositories for Sft

BISHENG is an open LLM devops platform for next generation Enterprise AI applications. Powerful and comprehensive features include: GenAI workflow, RAG, Agent, Unified model management, Evaluation, SFT, Dataset Management, Enterprise-level System Management, Observability and more.

Use PEFT or Full-parameter to finetune 450+ LLMs (Qwen2.5, InternLM3, GLM4, Llama3.3, Mistral, Yi1.5, Baichuan2, DeepSeek-R1, ...) and 150+ MLLMs (Qwen2.5-VL, Qwen2-Audio, Llama3.2-Vision, Llava, InternVL2.5, MiniCPM-V-2.6, GLM4v, Xcomposer2.5, Yi-VL, DeepSeek-VL2, Phi3.5-Vision, GOT-OCR2, ...).

chatglm 6b finetuning and alpaca finetuning

聚宝盆(Cornucopia): 中文金融系列开源可商用大模型，并提供一套高效轻量化的垂直领域LLM训练框架(Pretraining、SFT、RLHF、Quantize等)

An open-source solution for full parameter fine-tuning of DeepSeek-V3/R1 671B, including complete code and scripts from training to inference, as well as some practical experiences and conclusions. (DeepSeek-V3/R1 满血版 671B 全参数微调的开源解决方案，包含从训练到推理的完整代码和脚本，以及实践中积累一些经验和结论。)

tensorflow? ???? ??? ?????, Topic Models, BERT, GPT, LLM? ?? ?? ??? ????? ????? ??? Deep Learning NLP ??????.

Code and datasets for "Character-LLM: A Trainable Agent for Role-Playing"

?LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training

ZO2 (Zeroth-Order Offloading): Full Parameter Fine-Tuning 175B LLMs with 18GB GPU Memory

moss chat finetuning

本项目旨在结合以往研究人员的代表性工作，从多个维度评估sft数据，并自动化过滤sft数据。

Fine-Tuning Dataset Auto-Generation for Graph Query Languages.

This repo contains some extensions of deepspeed-chat for fine-tuning LLMs (SFT+RLHF).

Make your Generative AI LM model from the scratch (Including pretraining / SFT with LoRA)

Finetune baichuan pretrained model with QLora method

超简单复现Deepseek-R1-Zero和Deepseek-R1，以「24点游戏」为例。通过zero-RL、SFT以及SFT+RL，以激发LLM的自主验证反思能力。

Over 60 figures and diagrams of LLMs, quantization, low-rank adapters (LoRA), and chat templates FREE TO USE in your blog posts, slides, presentations, or papers.

使用指令微调对大模型进行微调。

EasyRLHF aims to provide an easy and minimal interface to train aligned language models, using off-the-shelf solutions and datasets

Train expert conversational role-play LLMs with synthetic data