sft

Star

Here are 68 public repositories matching this topic...

Language:All

Filter by language

All68 Python32 Jupyter Notebook9 TypeScript3 Rust2 C++1 Go1 Java1 MATLAB1 Shell1 Solidity1

Sort:Most stars

Sort options

Most stars Fewest stars Most forks Fewest forks Recently updated Least recently updated

dataelement /bisheng

Star7.8k

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.

react python agent enterprise workflow ocr ai chatbot orchestration openai llama gpt finetune rag sft llm llmops genai langchian llmdevops

UpdatedMar 18, 2025
Python

modelscope /ms-swift

Star6.3k

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, ...).

deploy llama lora embedding liger peft multimodal sft megatron distill rft llm internvl qwen2-vl qwen2-5 llama3-3 deepseek-r1 grpo open-r1

UpdatedMar 17, 2025
Python

ssbuild /chatglm_finetuning

Star1.5k

chatglm 6b finetuning and alpaca finetuning

deep-learning pytorch freeze lora sft chatglm p-tuning-v2 adalora qlora ia3

UpdatedMar 9, 2025
Python

jerry1993-tech /Cornucopia-LLaMA-Fin-Chinese

Star621

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)

nlp finance qa transformers text-generation chinese llama sft large-language-models rlhf

UpdatedJun 30, 2023
Python

ukairia777 /tensorflow-nlp-tutorial

Star541

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

nlp natural-language-processing tensorflow transformers named-entity-recognition question-answering llama lora trainer bert keras-tutorial sft dpo nlp-tutorial huggingface bert-ner llm

UpdatedSep 6, 2024
Jupyter Notebook

choosewhatulike /trainable-agents

Star521

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

agent natural-language-processing character roleplay language-model sft large-language-models llm

UpdatedOct 29, 2024
Python

ScienceOne-AI /DeepSeek-671B-SFT-Guide

Star427

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。)

python moe sft llm deepseek-r1

UpdatedMar 13, 2025
Python

awesome-rag /awesome-rag

Star333

Awesome-RAG: Collect typical RAG papers and systems.

agent awesome opensource ai paper awesome-list mm rag sft llm graphrag

UpdatedJan 23, 2025

0xsequence /erc-1155

Star320

Ethereum Semi Fungible Standard (ERC-1155)

ethereum nft token-contract sft erc1155 semi-fungible

UpdatedDec 4, 2024
TypeScript

solv-finance /erc-3525

Star112

ERC-3525 Reference Implementation

sft solv erc-3525 erc3525

UpdatedDec 4, 2023
Solidity

NiuTrans /Vision-LLM-Alignment

Star102

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.

vision alignment multi-model reward ppo sft dpo llm rlhf mllm llava llama3-vision

UpdatedOct 16, 2024
Python

OpenSparseLLMs /LLaMA-MoE-v2

Star73

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

sparsity moe attention llama fine-tuning sft mixture-of-experts instruction-tuning llama3

UpdatedDec 3, 2024
Python

ecnu-sea /SEA

Star59

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.

natural-language-processing dataset peer-review sft llm domain-llm automated-peer-reviewing