sft

16 projets partagent ce topic GitHub

Les traits relient les membres réellement apparentés entre eux. La taille des points suit les étoiles.

🧬 Membres

ms-swift

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4,…

★ 16k

bisheng

BISHENG is an open LLM devops platform for next generation Enterprise AI applications. Powerful and…

★ 12.1k

AgentGuide

https://adongwanai.github.io/AgentGuide | AI Agent开发指南 | LangGraph实战 | 高级RAG |…

★ 11.3k

Soup

Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

★ 9.7k

oumi

Easily fine-tune (SFT/RL), evaluate, and deploy Qwen, Gemma, or any open agentic LLM/VLM!

★ 9.4k

hands-on-modern-rl

🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and…

★ 4.8k

maxtext

A simple, performant, and scalable Jax LLM!

★ 2.5k

diy-llm

Covers pre-training data, Tokenizer, Transformer, MoE,distributed training, Scaling Laws, inference &…

★ 1.9k · GitHub ↗

surogate

Training/Fine-tuning at the speed of light

★ 813

Cornucopia-LLaMA-Fin-Chinese

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…

★ 655

trainable-agents

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

★ 653

Qwen3-Medical-SFT

Qwen3 Fine-tuning: Medical R1 Style Chat

★ 330

hands-on-llm

动手学大模型全栈：CS336 中文精讲 · PyTorch 手搓 Transformer · 单卡复现…

★ 119 · GitHub ↗

AlignLedger

Auditable human-feedback annotation, review, provenance, and frozen training-data export.

★ 100 · GitHub ↗

Soup

Fine-tune and post-train LLMs with one command—no SSH, no config hell.

★ 64

DataClaw0

DataClaw: Agentic Tailoring Multimodal Data from Raw Streams — coming soon (code, weights, dataset &…

★ 62

Mesuré à partir des topics GitHub communs aux deux projets, pondérés par leur rareté.