Yuanfu Wang's repositories
agenta
The LLMOps platform to build robust LLM apps. Easily experiment and evaluate different prompts, models, and workflows.
DeepSpeedExamples
Example models using DeepSpeed
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.
gpt-researcher
LLM based autonomous agent that conducts deep local and web research on any topic and generates a long report with citations.
graphrag
A modular graph-based Retrieval-Augmented Generation (RAG) system
HarmBench
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
IVR
Author's implementation of SQL and EQL in "Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization"
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.
lighteval
Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends
LLaMA-Factory
Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM)
lm-evaluation-harness
A framework for few-shot evaluation of language models.
lmm-r1
Extend OpenRLHF to support LMM RL training for reproduction of DeepSeek-R1 on multimodal tasks.
lmms-eval
Accelerating the development of large multimodal models (LMMs) with one-click evaluation module - lmms-eval.
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, ...).
neuralmmo
Baselines for Neural MMO -- new users should treat this repo as a starter project
notion-feeder
🕸 A Node app for creating a Feed Reader in Notion.
R1-V
Witness the aha moment of VLM with less than $3.
ragflow
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
SimPO
SimPO: Simple Preference Optimization with a Reference-Free Reward
Stable-Alignment
Efficient, Effective, and Stable alternative of RLHF. Code for the paper "Training Socially Aligned Language Models in Simulated Human Society".
trl
Train transformer language models with reinforcement learning.
verl
verl: Volcano Engine Reinforcement Learning for LLMs
VITA
✨✨VITA: Towards Open-Source Interactive Omni Multimodal LLM
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
VLMEvalKit
Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks