Sft Collection
Repositories tagged with "sft"
RARE
TCG-style cards with ATK/DEF/SPD stats
Repositories tagged with "sft"
ms-swift
modelscope
โUse PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).โ
bisheng
dataelement
โBISHENG 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.โ
oumi
oumi-ai
โEasily fine-tune, evaluate and deploy Gemma 4, Qwen3.5, Qwen3.6, gpt-oss, DeepSeek-R1, or any open source LLM / VLM!โ
AgentGuide
adongwanai
โhttps://adongwanai.github.io/AgentGuide | AI Agentๅผๅๆๅ | LangGraphๅฎๆ | ้ซ็บงRAG | ่ฝฌ่กๅคงๆจกๅ | ๅคงๆจกๅ้ข่ฏ | ็ฎๆณๅทฅ็จๅธ | ้ข่ฏ้ขๅบ | ๅผบๅๅญฆไน ๏ฝๆฐๆฎๅๆโ
maxtext
AI-Hypercomputer
โA simple, performant and scalable Jax LLM!โ
chatglm_finetuning
ssbuild
โchatglm 6b finetuning and alpaca finetuningโ
GraphGen
InternScience
โGraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generationโ
diy-llm
datawhalechina
โ๐ ็ณป็ปๆงๅคง่ฏญ่จๆจกๅๆๅปบ่ฏพ็จ๏ฝ๐ ๏ธ ่ฆ็้ข่ฎญ็ปๆฐๆฎๅทฅ็จใTokenizerใTransformerใMoEใGPU ็ผ็จ (CUDA/Triton)ใๅๅธๅผ่ฎญ็ปใScaling Lawsใๆจ็ไผๅๅๅฏน้ฝ (SFT/RLHF/GRPO)๏ฝ๐ 6 ไธชๆธ่ฟๅผไฝไธ + ไปฃ็ ้ฉฑๅจ๏ผๅปบ็ซ LLM ๅ จๆ ่ฎค็ฅไฝ็ณปโ
DeepSeek-671B-SFT-Guide
ScienceOne-AI
โAn 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 ๆปก่ก็ 671B ๅ จๅๆฐๅพฎ่ฐ็ๅผๆบ่งฃๅณๆนๆก๏ผๅ ๅซไป่ฎญ็ปๅฐๆจ็็ๅฎๆดไปฃ็ ๅ่ๆฌ๏ผไปฅๅๅฎ่ทตไธญ็งฏ็ดฏไธไบ็ป้ชๅ็ป่ฎบใ)โ
surogate
invergent-ai
โTraining/Fine-tuning at the speed of lightโ
Cornucopia-LLaMA-Fin-Chinese
jerry1993-tech
โ่ๅฎ็(Cornucopia): ไธญๆ้่็ณปๅๅผๆบๅฏๅ็จๅคงๆจกๅ๏ผๅนถๆไพไธๅฅ้ซๆ่ฝป้ๅ็ๅ็ด้ขๅLLM่ฎญ็ปๆกๆถ(PretrainingใSFTใRLHFใQuantize็ญ)โ
trainable-agents
choosewhatulike
โCode and datasets for "Character-LLM: A Trainable Agent for Role-Playing"โ
tensorflow-nlp-tutorial
ukairia777
โtensorflow๋ฅผ ์ฌ์ฉํ์ฌ ํ ์คํธ ์ ์ฒ๋ฆฌ๋ถํฐ, Topic Models, BERT, GPT, LLM๊ณผ ๊ฐ์ ์ต์ ๋ชจ๋ธ์ ๋ค์ด์คํธ๋ฆผ ํ์คํฌ๋ค์ ์ ๋ฆฌํ Deep Learning NLP ์ ์ฅ์์ ๋๋ค.โ
awesome-rag
awesome-rag
โAwesome-RAG: Collect typical RAG papers and systems.โ
Qwen3-Medical-SFT
Zeyi-Lin
โQwen3 Fine-tuning: Medical R1 Style Chatโ
erc-1155
0xsequence
โEthereum Semi Fungible Standard (ERC-1155)โ
LoongForge
baidu-baige
โA modular, scalable, high-performance training framework for LLMs, VLMs, diffusion, and embodied models.โ
unsloth-buddy
TYH-labs
โZero-friction LLM fine-tuning skill for Claude Code, Gemini CLI & any ACP agent. Unsloth on NVIDIA ยท TRL+MPS/MLX on Apple Silicon. Automates env setup, LoRA training (SFT, DPO, GRPO, vision), post-hoc GRPO log diagnostics, evaluation, and export end-to-end. Part of the Gaslamp AI platform.โ