modelscope/ms-swift

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, InternLM3, GLM4, Mistral, Yi1.5, DeepSeek-R1, ...) and 200+ MLLMs (Qwen2.5-VL, Qwen2.5-Omni, Qwen2-Audio, Ovis2, InternVL3, Llava, MiniCPM-V-2.6, GLM4v, Xcomposer2.5, DeepSeek-VL2, Phi4, GOT-OCR2, ...).

Language: Python - Size: 61.4 MB - Last synced at: about 1 hour ago - Pushed at: about 8 hours ago - Stars: 7,489 - Forks: 637

MilyaushaShamsutdinova/MedAdapt-LLM

Adapting LLM to the medical domain through SFT, RAG, and multistep fine-tuning to enhance domain knowledge and performance.

Language: Jupyter Notebook - Size: 2.63 MB - Last synced at: about 13 hours ago - Pushed at: about 14 hours ago - Stars: 0 - Forks: 0

open-sciencelab/GraphGen

GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation

Language: Python - Size: 13.6 MB - Last synced at: about 17 hours ago - Pushed at: about 18 hours ago - Stars: 141 - Forks: 14

AI-Hypercomputer/maxtext

A simple, performant and scalable Jax LLM!

Language: Python - Size: 293 MB - Last synced at: 2 days ago - Pushed at: 2 days ago - Stars: 1,716 - Forks: 344

ukairia777/tensorflow-nlp-tutorial

tensorflow를 사용하여 텍스트 전처리부터, Topic Models, BERT, GPT, LLM과 같은 최신 모델의 다운스트림 태스크들을 정리한 Deep Learning NLP 저장소입니다.

Language: Jupyter Notebook - Size: 126 MB - Last synced at: 4 days ago - Pushed at: 4 days ago - Stars: 544 - Forks: 278

dataelement/bisheng

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.

Language: TypeScript - Size: 46.2 MB - Last synced at: 6 days ago - Pushed at: 7 days ago - Stars: 8,307 - Forks: 1,374

ImadSaddik/BoDmaghDataset

BoDmagh dataset is a Supervised Fine-Tuning (SFT) dataset for the Darija language

Language: Jupyter Notebook - Size: 624 KB - Last synced at: 9 days ago - Pushed at: 9 days ago - Stars: 10 - Forks: 10

jerry1993-tech/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域LLM训练框架(Pretraining、SFT、RLHF、Quantize等)

Language: Python - Size: 1.64 MB - Last synced at: 2 days ago - Pushed at: almost 2 years ago - Stars: 631 - Forks: 64

awesome-rag/awesome-rag

Awesome-RAG: Collect typical RAG papers and systems.

Size: 36.1 KB - Last synced at: 7 days ago - Pushed at: 4 months ago - Stars: 365 - Forks: 28

liangyuwang/zo2

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

Language: Python - Size: 300 KB - Last synced at: 16 days ago - Pushed at: 16 days ago - Stars: 91 - Forks: 6

km1994/AwesomeMultiModel

【AIGC 实战入门笔记 —— AIGC 摩天大楼】分享 大语言模型（LLMs），大模型高效微调（SFT）,检索增强生成（RAG），智能体（Agent），PPT自动生成, 角色扮演，文生图（Stable Diffusion） ，图像文字识别（OCR），语音识别（ASR），语音合成（TTS），人像分割（SA），多模态（VLM），Ai 换脸(Face Swapping), 文生视频(VD)，图生视频（SVD），Ai 动作迁移，Ai 虚拟试衣，数字人，全模态理解（Omni），Ai音乐生成 干货学习 等 实战与经验。

Size: 4.88 KB - Last synced at: 17 days ago - Pushed at: 17 days ago - Stars: 3 - Forks: 0

dvgodoy/LLM-visuals

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.

Size: 4.11 MB - Last synced at: 5 days ago - Pushed at: 3 months ago - Stars: 14 - Forks: 2

0xsequence/erc-1155

Ethereum Semi Fungible Standard (ERC-1155)

Language: TypeScript - Size: 4.76 MB - Last synced at: 8 days ago - Pushed at: 5 months ago - Stars: 322 - Forks: 115

NiuTrans/Vision-LLM-Alignment

This repository contains the code for SFT, RLHF, and DPO, designed for vision-based LLMs, including the LLaVA models and the LLaMA-3.2-vision models.

Language: Python - Size: 153 MB - Last synced at: 6 days ago - Pushed at: 7 months ago - Stars: 104 - Forks: 8

asantucci/deepseek Fork of liyuan24/deepseek_from_scratch

DeepSeek mock

Language: Python - Size: 296 KB - Last synced at: 20 days ago - Pushed at: 20 days ago - Stars: 0 - Forks: 0

sumo1/gpt-reproduction-SFT-RLHF

OpenAI GPT的复现，基于Transformer。主要目标：学习GPT源码和基础原理，学习大模型监督微调SFT、基于反馈调优的大模型强化学习RLHF。代码在colab上可直接操作运行。源码学习记录：https://blog.csdn.net/xm415/category_12891845.html

Language: Jupyter Notebook - Size: 43.9 KB - Last synced at: 25 days ago - Pushed at: 25 days ago - Stars: 0 - Forks: 0

korovod/kenotron

Experimental fork of Nanotron, a minimalistic large language model 4D-parallelism training

Language: Python - Size: 12.3 MB - Last synced at: 3 days ago - Pushed at: 27 days ago - Stars: 1 - Forks: 0

aws-samples/sample-for-multi-modal-document-to-json-with-sagemaker-ai

This open-source project delivers a complete pipeline for converting multi-page documents (PDFs/images) into structured JSON using Vision LLMs on Amazon SageMaker. The solution leverages the SWIFT Framework to fine-tune models specifically for document understanding tasks.

Language: Jupyter Notebook - Size: 3.18 MB - Last synced at: about 1 month ago - Pushed at: about 2 months ago - Stars: 3 - Forks: 0

choosewhatulike/trainable-agents

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

Language: Python - Size: 17.6 MB - Last synced at: about 1 month ago - Pushed at: 7 months ago - Stars: 527 - Forks: 34

OpenSparseLLMs/LLaMA-MoE-v2

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

Language: Python - Size: 2.21 MB - Last synced at: about 1 month ago - Pushed at: 5 months ago - Stars: 78 - Forks: 11

wangclnlp/DeepSpeed-Chat-Extension

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

Language: Python - Size: 11.7 MB - Last synced at: 16 days ago - Pushed at: 10 months ago - Stars: 19 - Forks: 1

tripolskypetr/agent-tune

A React-based tool for constructing fine-tuning datasets with list and grid forms, featuring the ability to download and upload data as JSONL files. This project leverages the react-declarative library to create dynamic, interactive forms for defining user inputs, preferred outputs, and non-preferred outputs, along with associated tools

Language: TypeScript - Size: 5.4 MB - Last synced at: about 1 month ago - Pushed at: about 1 month ago - Stars: 0 - Forks: 0

ssbuild/chatglm_finetuning

chatglm 6b finetuning and alpaca finetuning

Language: Python - Size: 7.25 MB - Last synced at: about 1 month ago - Pushed at: 2 months ago - Stars: 1,542 - Forks: 178

sylvain-wei/24-Game-Reasoning

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。 About Clean, minimal, accessible reproduction of DeepSeek R1-Zero, DeepSeek R1

Language: Python - Size: 24.9 MB - Last synced at: about 1 month ago - Pushed at: about 1 month ago - Stars: 14 - Forks: 0

KennethanCeyer/diy-generative-ai-lm

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

Language: Python - Size: 117 KB - Last synced at: 23 days ago - Pushed at: 3 months ago - Stars: 16 - Forks: 1

nikaaaaaa104/BoDmaghDataset

BoDmagh dataset is a Supervised Fine-Tuning (SFT) dataset for the Darija language

Size: 18.6 KB - Last synced at: about 2 months ago - Pushed at: about 2 months ago - Stars: 0 - Forks: 0

iAdtya/SarvamAI-VLM-FineTuning

SarvamAI-VLM-FineTunning

Language: Python - Size: 31.3 MB - Last synced at: about 2 months ago - Pushed at: about 2 months ago - Stars: 0 - Forks: 0

John-Wendell/Long-CoT-data-for-LLM-to-solve-24-puzzle

It is a dataset for fine-tuning LLM to solve 24(puzzle)

Language: Python - Size: 66.4 KB - Last synced at: about 2 months ago - Pushed at: about 2 months ago - Stars: 4 - Forks: 0

LegendLeoChen/llm-finetune

使用trl、peft、transformers等库，实现对huggingface上模型的微调。

Language: Python - Size: 6.84 KB - Last synced at: about 2 months ago - Pushed at: about 2 months ago - Stars: 1 - Forks: 0

liziniu/cold_start_rl

Code for Blog Post: Can Better Cold-Start Strategies Improve RL Training for LLMs?

Language: Python - Size: 20 MB - Last synced at: 2 months ago - Pushed at: 2 months ago - Stars: 13 - Forks: 0

DaehanKim/EasyRLHF

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

Language: Python - Size: 73.9 MB - Last synced at: about 1 month ago - Pushed at: over 1 year ago - Stars: 9 - Forks: 0

Masoudjafaripour/llm-hf-planning

A small Hugging Face LLM for planning and reasoning

Language: Python - Size: 1.07 MB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 1 - Forks: 0

FrancescoDiSalesGithub/few-shots-importer

sft training by using only command instruction on a ollama modelfile

Size: 16.6 KB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 0 - Forks: 0

solv-finance/erc-3525

ERC-3525 Reference Implementation

Language: Solidity - Size: 1.37 MB - Last synced at: about 1 month ago - Pushed at: over 1 year ago - Stars: 112 - Forks: 51

Nexdata-AI/100000_Fine-Tuning_text_data_set_for_Russian_LLM_General_Domain_SFT

Size: 1.95 KB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 0 - Forks: 0

Nexdata-AI/100000_Fine-Tuning_text_data_set_for_Spanish_LLM_General_Domain_SFT

Size: 1.95 KB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 0 - Forks: 0

Nexdata-AI/100000_Fine-Tuning_text_data_set_for_German_LLM_General_Domain_SFT

Size: 1.95 KB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 0 - Forks: 0

Nexdata-AI/100000_Fine-Tuning_text_data_set_for_Portuguese_LLM_General_Domain_SFT

Size: 1.95 KB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 0 - Forks: 0

Nexdata-AI/100000_Fine-Tuning_text_data_set_for_Dutch_LLM_General_Domain_SFT

Size: 1.95 KB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 0 - Forks: 0

Nexdata-AI/100000_Southeast_Asian_language_multi-round_Fine-Tuning_text_data_set_for_General_Domain_SFT

Size: 421 KB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 0 - Forks: 0

Nexdata-AI/100000_Fine-Tuning_text_data_set_for_Korean_LLM_General_Domain_SFT

Size: 6.84 KB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 0 - Forks: 0

Nexdata-AI/100000_Fine-Tuning_text_data_set_for_English_LLM_General_Domain_SFT

Size: 6.84 KB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 0 - Forks: 0

Nexdata-AI/100000_Fine-Tuning_text_data_set_for_Italian_LLM_General_Domain_SFT

Size: 1.95 KB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 0 - Forks: 0

Nexdata-AI/100000_Fine-Tuning_text_data_set_for_Polish_LLM_General_Domain_SFT

Size: 1.95 KB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 0 - Forks: 0

Somerset-NHS-Solutions-Development/sft-logos

Somerset NHSFT's logos

Size: 818 KB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 0 - Forks: 0

avnlp/llm-finetuning

Language: Python - Size: 817 KB - Last synced at: 22 days ago - Pushed at: 3 months ago - Stars: 2 - Forks: 0

RobinSmits/Schaapje

Schaapje - A Dutch Small Language Model

Language: Jupyter Notebook - Size: 794 KB - Last synced at: 4 months ago - Pushed at: 4 months ago - Stars: 0 - Forks: 0

akshay-kamath/Practical-LLM-Fine-Tuning

This repository contains hands on tutorials on fine tuning LLMs

Size: 17.9 MB - Last synced at: 2 months ago - Pushed at: 4 months ago - Stars: 0 - Forks: 0

cyou121/Scrappy-japanese

build a small-sized (100Million) Japanese LLM (pretraining + SFT).

Language: Python - Size: 605 KB - Last synced at: 4 months ago - Pushed at: 4 months ago - Stars: 0 - Forks: 0

0-1CxH/megatron-wrap

Wrapped Megatron: As User-Friendly as HuggingFace, As Powerful as Megatron-LM | Megatron封装：和HuggingFace一样方便，和Megatron-LM一样强大

Language: Python - Size: 2.41 MB - Last synced at: about 2 months ago - Pushed at: about 2 months ago - Stars: 0 - Forks: 0

XpastaX/Instruction-Fusion

Advancing Prompt Evolution through Hybridization

Language: Python - Size: 1.63 MB - Last synced at: 5 months ago - Pushed at: 5 months ago - Stars: 0 - Forks: 0

ecnu-sea/SEA

SEA is an automated paper review framework capable of generating comprehensive and high-quality review feedback with high consistency for papers, thereby assisting researchers in improving the quality of their work.

Language: Python - Size: 705 KB - Last synced at: 6 months ago - Pushed at: 6 months ago - Stars: 50 - Forks: 7

ElvenTools/elven-tools-cli

Elven Tools CLI - command line tool for launching NFTs collections on the MultiversX blockchain (Plus other tools).

Language: TypeScript - Size: 1.05 MB - Last synced at: 12 days ago - Pushed at: 10 months ago - Stars: 24 - Forks: 13

movescriptions/movescriptions

https://twitter.com/MoveScriptions

Language: Move - Size: 725 KB - Last synced at: 8 months ago - Pushed at: 8 months ago - Stars: 45 - Forks: 15

Lizhecheng02/Kaggle-LMSYS

Analyze a dataset of conversations from the Chatbot Arena, where various LLMs provide responses to user prompts. The goal is to develop a model that enhances chatbot interactions, ensuring they align more closely with human preferences.

Language: Jupyter Notebook - Size: 1.93 MB - Last synced at: 9 months ago - Pushed at: 9 months ago - Stars: 1 - Forks: 0

Nexdata-AI/100000-Instruction-Following-Evaluation-SFT-for-Chinese-LLM-Text-Data

100000-Instruction-Following-Evaluation-SFT-for-Chinese-LLM-Text-Data

Size: 1.95 KB - Last synced at: 9 months ago - Pushed at: 9 months ago - Stars: 0 - Forks: 0

THU-KEG/DICE

DICE: Detecting In-distribution Data Contamination with LLM's Internal State

Language: Python - Size: 3.26 MB - Last synced at: 11 months ago - Pushed at: 11 months ago - Stars: 5 - Forks: 0

rbga/Low_Density_Parity_Check_LDPC_Codes_-_MATLAB_Simulation

LDPC MATLAB simulation using BPSK + AWGN modulation decoded using Sum Product and Min Sum Algorithm

Language: MATLAB - Size: 27.3 KB - Last synced at: 11 months ago - Pushed at: 11 months ago - Stars: 13 - Forks: 4

tonyskapunk/sft-aur

Scripts to keep up with latest scaleft packages to build them for AUR

Language: Shell - Size: 14.6 KB - Last synced at: 24 days ago - Pushed at: 11 months ago - Stars: 1 - Forks: 1

ldclabs/ic-sft

A SFT (Semi-Fungible Token, implemented ICRC-7 and ICRC-37) canister smart contract on the Internet Computer.

Language: Rust - Size: 122 KB - Last synced at: about 1 year ago - Pushed at: about 1 year ago - Stars: 4 - Forks: 0

dgomezde83/Multifungible-library Fork of multiversx/mx-sdk-cpp

MultiversX library for interacting with the MultiversX blockchain's Non-fungible tokens and Semi-fungible tokens.

Language: C++ - Size: 29.5 MB - Last synced at: about 1 year ago - Pushed at: about 1 year ago - Stars: 1 - Forks: 0

AlekseyKorshuk/gai-project

Train expert conversational role-play LLMs with synthetic data

Language: Python - Size: 71.3 KB - Last synced at: about 1 year ago - Pushed at: over 1 year ago - Stars: 5 - Forks: 2

ssbuild/moss_finetuning

moss chat finetuning

Language: Python - Size: 1.94 MB - Last synced at: 19 days ago - Pushed at: about 1 year ago - Stars: 50 - Forks: 4

PhilipMay/llm-data

LLM Training Data

Language: Jupyter Notebook - Size: 237 KB - Last synced at: 3 months ago - Pushed at: about 1 year ago - Stars: 0 - Forks: 0

muyu42/DataS

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。

Language: Python - Size: 6.83 MB - Last synced at: about 1 year ago - Pushed at: about 1 year ago - Stars: 49 - Forks: 11

SharathHebbar/Coding-Templates

Coding Templates

Language: Jupyter Notebook - Size: 7.81 KB - Last synced at: about 1 year ago - Pushed at: about 1 year ago - Stars: 0 - Forks: 0

Lamsoda1123/GPT2_medium_finetune-lora-sft

It's a GPT2 finetune project based on peft and transformers. Although can provide quite a imporvement, however, the illusion and inteligent is terrible.

Language: Python - Size: 1.41 MB - Last synced at: over 1 year ago - Pushed at: over 1 year ago - Stars: 0 - Forks: 0

sftchance/sftchance

⚪ CHANCE IS A STUDY IN DECENTERED IDENTITY TOURISM AND THE A(E)FFECTS OF PRIVILEGE, ENTITLEMENT, AND CAPITAL, WITH BOUNDLESS MOBILITY ENABLED BY THE INTERNET.

Language: TypeScript - Size: 16.1 MB - Last synced at: about 1 year ago - Pushed at: almost 2 years ago - Stars: 1 - Forks: 1

dag0310/Fast-SFTP-Folder-Uploader

Upload folders faster via SFTP by temporarily zipping on the client and unzipping on the host.

Language: Python - Size: 28.3 KB - Last synced at: about 1 year ago - Pushed at: over 1 year ago - Stars: 0 - Forks: 0

jmaczan/c-137

🦙 Llama 2 7B fine-tuned to revive Rick

Language: Jupyter Notebook - Size: 3.27 MB - Last synced at: 3 months ago - Pushed at: over 1 year ago - Stars: 0 - Forks: 0

Macielyoung/Baichuan-QLora

Finetune baichuan pretrained model with QLora method

Language: Python - Size: 47.9 KB - Last synced at: almost 2 years ago - Pushed at: almost 2 years ago - Stars: 6 - Forks: 0

ElvenTools/elven-tools-sft-minter-sc

Elven Tools SFT Minter Smart Contract - launching SFTs collections on the MultiversX blockchain

Language: Rust - Size: 274 KB - Last synced at: 10 months ago - Pushed at: about 1 year ago - Stars: 3 - Forks: 1

hlp-ai/miniChatGPT

Mini ChatGPT

Language: Python - Size: 317 KB - Last synced at: about 2 years ago - Pushed at: about 2 years ago - Stars: 2 - Forks: 0

Sophietje/SFTLearning

Testing the security of sanitizers by learning symbolic finite transducers

Language: Java - Size: 43 MB - Last synced at: 12 months ago - Pushed at: over 4 years ago - Stars: 2 - Forks: 0