Rocke Dong's repositories
graphrag
A modular graph-based Retrieval-Augmented Generation (RAG) system
sqlglot
Python SQL Parser and Transpiler
MAC-SQL
MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL
sql-practice
My SQL practice arena, as a living cheatsheat / knowledge repo for my SQL adventures.
buffer-of-thought-llm
Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models
test-suite-sql-eval
Semantic Evaluation for Text-to-SQL with Distilled Test Suites
DBCopilot
Code and data for the paper "DBCᴏᴘɪʟᴏᴛ: Scaling Natural Language Querying to Massive Databases"
opencompass
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
InternLM
Official release of InternLM2 7B and 20B base and chat models. 200K context support
PrimeKG
Precision Medicine Knowledge Graph (PrimeKG)
trl
Train transformer language models with reinforcement learning.
alignment-handbook
Robust recipes to align language models with human and AI preferences
llama3
The official Meta Llama 3 GitHub site
ProteinMPNN
Code for the ProteinMPNN paper
RFdiffusion
Code for running RFdiffusion
buildme
buildme
DeepSpeedExamples
Example models using DeepSpeed
Qwen1.5
Qwen1.5 is the improved version of Qwen, the large language model series developed by Qwen team, Alibaba Cloud.
Qwen
The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
ChatGLM3
ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型
weblangchain_chatglm
Retrieval Augmented Generation (RAG) implementation through libraries like Tavily, LangChain, ChatGLM3
ColabDesign
Making Protein Design accessible to all via Google Colab!
Hand-on-RAG
顾名思义:手搓的RAG
ColabFold
Making Protein folding accessible to all!