Ren Hang (superfan89)

superfan89

Geek Repo

Location:Beijing, China

Github PK Tool:Github PK Tool

Ren Hang's starred repositories

rustlings

:crab: Small exercises to get you used to reading and writing Rust code!

Language:RustLicense:MITStargazers:53217Issues:326Issues:663

llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:37816Issues:397Issues:67

dspy

DSPy: The framework for programming—not prompting—foundation models

Language:PythonLicense:MITStargazers:17526Issues:142Issues:745

ML-YouTube-Courses

📺 Discover the latest machine learning / AI courses on YouTube.

TypeChat

TypeChat is a library that makes it easy to build natural language interfaces using types.

Language:TypeScriptLicense:MITStargazers:8159Issues:68Issues:82

DeepSeek-Coder

DeepSeek Coder: Let the Code Write Itself

Language:PythonLicense:MITStargazers:6624Issues:69Issues:158

TaskWeaver

A code-first agent framework for seamlessly planning and executing data analytics tasks.

Language:PythonLicense:MITStargazers:5249Issues:66Issues:202
Language:PythonLicense:Apache-2.0Stargazers:4103Issues:52Issues:119

rust-bert

Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...)

Language:RustLicense:Apache-2.0Stargazers:2595Issues:39Issues:215

datatrove

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

Language:PythonLicense:Apache-2.0Stargazers:1971Issues:45Issues:125

eclipse.jdt.ls

Java language server

HuixiangDou

HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance

Language:PythonLicense:BSD-3-ClauseStargazers:1452Issues:23Issues:35

Open-Assistant

YORG Open Source Version

Language:PythonLicense:Apache-2.0Stargazers:1449Issues:159Issues:0

debug-adapter-protocol

Defines a common protocol for debug adapters.

Language:HTMLLicense:NOASSERTIONStargazers:1407Issues:64Issues:288

functionary

Chat language model that can use tools and interpret the results

Language:PythonLicense:MITStargazers:1376Issues:20Issues:120

self-rewarding-lm-pytorch

Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI

Language:PythonLicense:MITStargazers:1317Issues:23Issues:17

nanotron

Minimalistic large language model 3D-parallelism training

Language:PythonLicense:Apache-2.0Stargazers:1155Issues:40Issues:76

DeepSeek-MoE

DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models

Language:PythonLicense:MITStargazers:977Issues:15Issues:38

cc_net

Tools to download and cleanup Common Crawl data

Language:PythonLicense:MITStargazers:964Issues:23Issues:44

GPU-Benchmarks-on-LLM-Inference

Multiple NVIDIA GPUs or Apple Silicon for Large Language Model Inference?

Language:Jupyter NotebookStargazers:862Issues:17Issues:14

stable-diffusion-webui-dataset-tag-editor

Extension to edit dataset captions for SD web UI by AUTOMATIC1111

Language:PythonLicense:MITStargazers:681Issues:7Issues:83

Chinese-Mixtral-8x7B

中文Mixtral-8x7B(Chinese-Mixtral-8x7B)

Language:PythonLicense:Apache-2.0Stargazers:640Issues:15Issues:29

LLMSpeculativeSampling

Fast inference from large lauguage models via speculative decoding

Language:PythonLicense:Apache-2.0Stargazers:530Issues:2Issues:14

vscode-java-debug

Java Debugger for Visual Studio Code.

Language:TypeScriptLicense:NOASSERTIONStargazers:528Issues:48Issues:1019

java-debug

The debug server implementation for Java. It conforms to the debug protocol of Visual Studio Code (DAP, Debugger Adapter Protocol).

Language:JavaLicense:NOASSERTIONStargazers:334Issues:30Issues:140

local-llm-function-calling

A tool for generating function arguments and choosing what function to call with local LLMs

Language:PythonLicense:MITStargazers:331Issues:4Issues:14

FuseLLM

FuseLLM & FuseChat Project

Language:PythonLicense:Apache-2.0Stargazers:314Issues:0Issues:0

bagel

A bagel, with everything.

DHS-LLM-Workshop

DHS 2023 LLM Workshop by Sourab Mangrulkar

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:263Issues:6Issues:12

c4-dataset-script

Inspired by google c4, here is a series of colossal clean data cleaning scripts focused on CommonCrawl data processing. Including Chinese data processing and cleaning methods in MassiveText.

Language:PythonLicense:MITStargazers:119Issues:5Issues:0