-
-
unlock-deepseek Public
Forked from datawhalechina/unlock-deepseekDeepSeek 系列工作解读、扩展和复现。
Python UpdatedFeb 15, 2025 -
verifiers Public
Forked from willccbb/verifiersVerifiers for LLM Reinforcement Learning
Python UpdatedFeb 15, 2025 -
PRIME Public
Forked from PRIME-RL/PRIMEScalable RL solution for the advanced reasoning of language models
Python Apache License 2.0 UpdatedFeb 14, 2025 -
MM-self-improve-qwen2vl Public
Forked from Liac-li/MM-self-improve-qwen2vlPython Apache License 2.0 UpdatedFeb 14, 2025 -
openr Public
Forked from openreasoner/openrOpenR: An Open Source Framework for Advanced Reasoning with Large Language Models
Python MIT License UpdatedFeb 14, 2025 -
simpleRL-reason Public
Forked from hkust-nlp/simpleRL-reasonThis is a replicate of DeepSeek-R1-Zero and DeepSeek-R1 training on small models with limited data
Python MIT License UpdatedFeb 7, 2025 -
OpenRLHF Public
Forked from OpenRLHF/OpenRLHFAn Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)
Python Apache License 2.0 UpdatedJan 20, 2025 -
trl Public
Forked from huggingface/trlTrain transformer language models with reinforcement learning.
Python Apache License 2.0 UpdatedNov 14, 2024 -
LLM-Dojo Public
Forked from mst272/LLM-Dojo欢迎来到 LLM-Dojo，这里是一个开源大模型学习场所，使用简洁且易阅读的代码构建模型训练框架(支持各种主流模型如Qwen、Llama、GLM等等)、RLHF框架(DPO/CPO/KTO/PPO)等各种功能。👩🎓👨🎓
Python UpdatedNov 8, 2024 -
-
LLaVA-MoD Public
Forked from shufangxun/LLaVA-MoDMaking LLaVA Tiny via MoE-Knowledge Distillation
Python Apache License 2.0 UpdatedOct 24, 2024 -
Self-Correcting-LLM--Reinforcement-Learning- Public
Forked from sanowl/Self-Correcting-LLM--Reinforcement-Learning-This my attempt to create Self-Correcting-LLM based on the paper Training Language Models to Self-Correct via Reinforcement Learning by google
Python UpdatedOct 16, 2024 -
TinyLLaVA_Factory Public
Forked from TinyLLaVA/TinyLLaVA_FactoryA Framework of Small-scale Large Multimodal Models
Python Apache License 2.0 UpdatedOct 16, 2024 -
-
SuperCorrect-llm Public
Forked from YangLing0818/SuperCorrect-llmSuperCorrect: Supervising and Correcting Language Models with Error-Driven Insights
Python UpdatedOct 14, 2024 -
g1 Public
Forked from bklieger-groq/g1g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains
Python MIT License UpdatedOct 7, 2024 -
Google_SCoRe Public
Forked from daje0601/Google_SCoRePaper Reproduction Google SCoRE(Training Language Models to Self-Correct via Reinforcement Learning)
Jupyter Notebook Apache License 2.0 UpdatedSep 21, 2024 -
GOT-OCR2.0 Public
Forked from Ucas-HaoranWei/GOT-OCR2.0Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
Python UpdatedSep 19, 2024 -
-
DynamicPose Public
Forked from dynamic-X-LAB/DynamicPoseDynamicPose, a simple and robust framework for animating human images.
Python UpdatedAug 29, 2024 -
PhotoPoster Public
Forked from dynamic-X-LAB/PhotoPosterTo support and further the research in the field of portrait animation , we are excited to launch PhotoPoster, an open project for pose-driven image generation.
Python UpdatedAug 26, 2024 -
facefusion Public
Forked from facefusion/facefusionNext generation face swapper and enhancer
Python Other UpdatedAug 12, 2024 -
florence2-finetuning Public
Forked from andimarafioti/florence2-finetuningQuick exploration into fine tuning florence 2
Jupyter Notebook MIT License UpdatedJul 31, 2024 -
Moore-AnimateAnyone Public
Forked from MooreThreads/Moore-AnimateAnyonePython Apache License 2.0 UpdatedJul 31, 2024 -
AniTalker Public
Forked from X-LANCE/AniTalker[ACM MM 2024] This is the official code for "AniTalker: Animate Vivid and Diverse Talking Faces through Identity-Decoupled Facial Motion Encoding"
Python Apache License 2.0 UpdatedJul 30, 2024 -
-
UniAnimate Public
Forked from ali-vilab/UniAnimateCode for Paper "UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation".
Python UpdatedJul 23, 2024 -
EchoMimic Public
Forked from antgroup/echomimicLifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning
Python Apache License 2.0 UpdatedJul 9, 2024 -
Math-LLaVA Public
Forked from HZQ950419/Math-LLaVACode for Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models
Python Apache License 2.0 UpdatedJun 28, 2024
{{ message }}