Yuanfu Wang's repositories

cgdt

[AAAI'2024] Critic-Guided Decision Transformer for Offline Reinforcement Learning

Language:PythonLicense:MITStargazers:10Issues:2Issues:0

RepoAgent

An LLM-powered repository agent designed to assist developers and teams in generating documentation and understanding repositories quickly.

Language:PythonLicense:Apache-2.0Stargazers:1Issues:0Issues:0

safe-rlhf

Safe-RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

Language:PythonLicense:Apache-2.0Stargazers:1Issues:0Issues:0

agenta

The LLMOps platform to build robust LLM apps. Easily experiment and evaluate different prompts, models, and workflows.

Language:TypeScriptLicense:MITStargazers:0Issues:0Issues:0
Language:PythonLicense:MITStargazers:0Issues:0Issues:0

DeepSpeedExamples

Example models using DeepSpeed

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

dify

An Open-Source Assistants API and GPTs alternative. Dify.AI is an LLM application development platform. It integrates the concepts of Backend as a Service and LLMOps, covering the core tech stack required for building generative AI-native applications, including a built-in RAG engine.

Language:TypeScriptLicense:NOASSERTIONStargazers:0Issues:0Issues:0

gpt-researcher

LLM based autonomous agent that conducts deep local and web research on any topic and generates a long report with citations.

License:Apache-2.0Stargazers:0Issues:0Issues:0

graphrag

A modular graph-based Retrieval-Augmented Generation (RAG) system

Language:PythonLicense:MITStargazers:0Issues:0Issues:0

HarmBench

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Language:Jupyter NotebookLicense:MITStargazers:0Issues:0Issues:0

IVR

Author's implementation of SQL and EQL in "Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization"

Language:PythonLicense:MITStargazers:0Issues:0Issues:0

langflow

⛓️ Langflow is a dynamic graph where each node is an executable unit. Its modular and interactive design fosters rapid experimentation and prototyping, pushing hard on the limits of creativity.

Language:PythonLicense:MITStargazers:0Issues:0Issues:0
License:MITStargazers:0Issues:0Issues:0

lighteval

Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

License:MITStargazers:0Issues:0Issues:0

LLaMA-Factory

Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM)

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

lm-evaluation-harness

A framework for few-shot evaluation of language models.

Language:PythonLicense:MITStargazers:0Issues:0Issues:0

lmm-r1

Extend OpenRLHF to support LMM RL training for reproduction of DeepSeek-R1 on multimodal tasks.

License:Apache-2.0Stargazers:0Issues:0Issues:0

lmms-eval

Accelerating the development of large multimodal models (LMMs) with one-click evaluation module - lmms-eval.

Language:PythonLicense:NOASSERTIONStargazers:0Issues:0Issues:0

ms-swift

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, ...).

License:Apache-2.0Stargazers:0Issues:0Issues:0

neuralmmo

Baselines for Neural MMO -- new users should treat this repo as a starter project

Language:PythonLicense:MITStargazers:0Issues:0Issues:0

notion-feeder

🕸 A Node app for creating a Feed Reader in Notion.

Language:JavaScriptLicense:MITStargazers:0Issues:0Issues:0

R1-V

Witness the aha moment of VLM with less than $3.

Stargazers:0Issues:0Issues:0

ragflow

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

SimPO

SimPO: Simple Preference Optimization with a Reference-Free Reward

Language:PythonStargazers:0Issues:0Issues:0

Stable-Alignment

Efficient, Effective, and Stable alternative of RLHF. Code for the paper "Training Socially Aligned Language Models in Simulated Human Society".

Language:PythonLicense:NOASSERTIONStargazers:0Issues:0Issues:0

trl

Train transformer language models with reinforcement learning.

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

verl

verl: Volcano Engine Reinforcement Learning for LLMs

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

VITA

✨✨VITA: Towards Open-Source Interactive Omni Multimodal LLM

Language:PythonLicense:NOASSERTIONStargazers:0Issues:0Issues:0

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

VLMEvalKit

Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks

License:Apache-2.0Stargazers:0Issues:0Issues:0