Fan (koalazf99)

koalazf99

Geek Repo

Company:Shanghai Jiao Tong University

Location:Shanghai

Home Page:koalazf99.github.io

Twitter:@FaZhou_998

Github PK Tool:Github PK Tool


Organizations
OpenLemur

Fan's starred repositories

OpenDevin

🐚 OpenDevin: Code Less, Make More

Language:PythonLicense:MITStargazers:28477Issues:281Issues:1100

LLaMA-Factory

A WebUI for Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

Language:PythonLicense:Apache-2.0Stargazers:25758Issues:174Issues:4164

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Language:PythonLicense:Apache-2.0Stargazers:17981Issues:157Issues:1382

devika

Devika is an Agentic AI Software Engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective. Devika aims to be a competitive open-source alternative to Devin by Cognition AI.

Language:PythonLicense:MITStargazers:17861Issues:204Issues:367

litgpt

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

Language:PythonLicense:Apache-2.0Stargazers:8163Issues:82Issues:680

DiT

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

Language:PythonLicense:NOASSERTIONStargazers:5632Issues:46Issues:73

promptbase

All things prompt engineering

Language:PythonLicense:MITStargazers:5238Issues:60Issues:13

LLMLingua

To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

Language:PythonLicense:MITStargazers:4170Issues:31Issues:103

MiniGemini

Official implementation for Mini-Gemini

Language:PythonLicense:Apache-2.0Stargazers:2711Issues:23Issues:75

open-parse

Improved file parsing for LLM’s

Language:PythonLicense:MITStargazers:2083Issues:12Issues:26

DeepSeek-VL

DeepSeek-VL: Towards Real-World Vision-Language Understanding

Language:PythonLicense:MITStargazers:1859Issues:18Issues:41

starcoder2

Home of StarCoder2!

Language:PythonLicense:Apache-2.0Stargazers:1597Issues:17Issues:17

lmms-eval

Accelerating the development of large multimodal models (LMMs) with lmms-eval

Language:PythonLicense:NOASSERTIONStargazers:1039Issues:4Issues:84

llm-colosseum

Benchmark LLMs by fighting in Street Fighter 3! The new way to evaluate the quality of an LLM

Language:Jupyter NotebookLicense:MITStargazers:1022Issues:17Issues:25

Triton-Puzzles

Puzzles for learning Triton

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:845Issues:6Issues:7

flashinfer

FlashInfer: Kernel Library for LLM Serving

Language:CudaLicense:Apache-2.0Stargazers:764Issues:13Issues:70

text-dedup

All-in-one text de-duplication

Language:PythonLicense:Apache-2.0Stargazers:539Issues:4Issues:57

Megatron-LLM

distributed trainer for LLMs

Language:PythonLicense:NOASSERTIONStargazers:499Issues:18Issues:57
Language:PythonLicense:MITStargazers:130Issues:4Issues:0

QuRating

[ICML 2024] Selecting High-Quality Data for Training Language Models

scaling

Language models scale reliably with over-training and on downstream tasks

Language:Jupyter NotebookLicense:MITStargazers:87Issues:8Issues:3

sailor-llm

Sailor: Open Language Models for South-East Asia

Language:PythonLicense:MITStargazers:83Issues:7Issues:1

the-stack-v2

Code for the curation of The Stack v2 and StarCoder2 training data

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:75Issues:5Issues:5

math-evaluation-harness

A simple toolkit for benchmarking LLMs on mathematical reasoning tasks. 🧮✨

Language:PythonLicense:MITStargazers:47Issues:2Issues:2

bitnet

Modeling code for a BitNet b1.58 Llama-style model.

Language:PythonLicense:MITStargazers:22Issues:5Issues:2

turking-bench

Web-grounded natural language instructions

Language:HTMLLicense:Apache-2.0Stargazers:11Issues:4Issues:38
Language:PythonStargazers:4Issues:1Issues:0

option_trading_resources

Comprehensive options trading resource including books, papers, tools, etc. (Work In Progress)