Gary Fan (garyfanhku)

garyfanhku

Geek Repo

Location:HK

Github PK Tool:Github PK Tool

Gary Fan's starred repositories

ChatGPT-Next-Web

A cross-platform ChatGPT/Gemini UI (Web / PWA / Linux / Win / MacOS). 一键拥有你自己的跨平台 ChatGPT/Gemini 应用。

Language:TypeScriptLicense:MITStargazers:70420Issues:400Issues:2671

lobe-chat

🤯 Lobe Chat - an open-source, modern-design LLMs/AI chat framework. Supports Multi AI Providers( OpenAI / Claude 3 / Gemini / Ollama / Bedrock / Azure / Mistral / Perplexity ), Multi-Modals (Vision/TTS) and plugin system. One-click FREE deployment of your private ChatGPT chat application.

Language:TypeScriptLicense:MITStargazers:31552Issues:157Issues:1357

Langchain-Chatchat

Langchain-Chatchat(原Langchain-ChatGLM)基于 Langchain 与 ChatGLM 等语言模型的本地知识库问答 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM) QA app with langchain

Language:PythonLicense:Apache-2.0Stargazers:28315Issues:266Issues:3223

guidance

A guidance language for controlling large language models.

Language:Jupyter NotebookLicense:MITStargazers:17701Issues:115Issues:455

ml-engineering

Machine Learning Engineering Open Book

Language:PythonLicense:CC-BY-SA-4.0Stargazers:9978Issues:100Issues:18

llama-recipes

Scripts for fine-tuning Llama2 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization & question answering. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment.Demo apps to showcase Llama2 for WhatsApp & Messenger

Language:Jupyter NotebookLicense:NOASSERTIONStargazers:7850Issues:68Issues:227

TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

Language:C++License:Apache-2.0Stargazers:6880Issues:83Issues:1355

resume

Software developer resume in Latex

Language:TeXLicense:MITStargazers:4761Issues:49Issues:32

alignment-handbook

Robust recipes to align language models with human and AI preferences

Language:PythonLicense:Apache-2.0Stargazers:3960Issues:110Issues:115

lmql

A language for constraint-guided and efficient LLM programming.

Language:PythonLicense:Apache-2.0Stargazers:3386Issues:22Issues:242

Awesome-LLMOps

An awesome & curated list of best LLMOps tools for developers

Language:ShellLicense:CC0-1.0Stargazers:3160Issues:57Issues:9

S-LoRA

S-LoRA: Serving Thousands of Concurrent LoRA Adapters

Language:PythonLicense:Apache-2.0Stargazers:1529Issues:24Issues:37

Awesome-LLM-Reasoning

Reasoning in Large Language Models: Papers and Resources, including Chain-of-Thought, Instruction-Tuning and Multimodality.

Language:PythonLicense:Apache-2.0Stargazers:998Issues:10Issues:53

flashinfer

FlashInfer: Kernel Library for LLM Serving

Language:CudaLicense:Apache-2.0Stargazers:686Issues:13Issues:50

vec2text

utilities for decoding deep representations (like sentence embeddings) back to text

Language:PythonLicense:NOASSERTIONStargazers:604Issues:13Issues:38

Awesome-Out-Of-Distribution-Detection

A professionally curated list of papers, tutorials, books, videos, articles and open-source libraries etc for Out-of-distribution detection, robustness, and generalization

gritlm

Generative Representational Instruction Tuning

Language:Jupyter NotebookLicense:MITStargazers:414Issues:8Issues:29

adept-inference

Inference code for Persimmon-8B

Language:PythonLicense:Apache-2.0Stargazers:411Issues:16Issues:7

honest_llama

Inference-Time Intervention: Eliciting Truthful Answers from a Language Model

Language:PythonLicense:MITStargazers:365Issues:9Issues:31

DoLa

Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"

Awesome-Information-Bottleneck

This is a curated list for Information Bottleneck Principle, in memory of Professor Naftali Tishby.

License:MITStargazers:285Issues:13Issues:0

BMPrinciples

A collection of phenomenons observed during the scaling of big foundation models, which may be developed into consensus, principles, or laws in the future

OpenASCE

OpenASCE (Open All-Scale Casual Engine) is a Python package for end-to-end large-scale causal learning. It provides causal discovery, causal effect estimation and attribution algorithms all in one package.

Language:PythonLicense:Apache-2.0Stargazers:55Issues:8Issues:0

FactorCL

[NeurIPS 2023] Factorized Contrastive Learning: Going Beyond Multi-view Redundancy

Language:Jupyter NotebookLicense:MITStargazers:47Issues:3Issues:4
Language:Jupyter NotebookLicense:Apache-2.0Stargazers:17Issues:4Issues:0
Language:Jupyter NotebookStargazers:14Issues:2Issues:0