trannhatquy

generative-ai-for-beginners

21 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/

llama3

The official Meta Llama 3 GitHub site

graphrag

A modular graph-based Retrieval-Augmented Generation (RAG) system

dspy

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

unsloth

Finetune Llama 3.2, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 80% less memory

MiniCPM-V

MiniCPM-V 2.6: A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone

minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

FlexiGen

Running large language models on a single GPU for throughput-oriented scenarios.

ragas

Supercharge Your LLM Application Evaluations 🚀

sglang

SGLang is a fast serving framework for large language models and vision language models.

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

promptbase

All things prompt engineering

gpt-llm-trainer

DeepSeek-V2

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

LLMDataHub

A quick guide (especially) for trending instruction finetuning datasets

GaLore

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

llm2vec

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

evolutionary-model-merge

Official repository of Evolutionary Optimization of Model Merging Recipes

pyreft

ReFT: Representation Finetuning for Language Models

DeepSeek-MoE

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

JetMoE

Reaching LLaMA2 Performance with 0.1M Dollars

optimum-quanto

A pytorch quantization backend for optimum

hqq

Official implementation of Half-Quadratic Quantization (HQQ)

snowflake-arctic

reward-bench

RewardBench: the first evaluation tool for reward models.

mergoo

A library for easily merging multiple LLM experts, and efficiently train the merged LLM.

HPT

HPT - Open Multimodal LLMs from HyperGAI

stripedhyena

Repository for StripedHyena, a state-of-the-art beyond Transformer architecture

OpenChatML

LLM-Benchmark-Logs

Just a bunch of benchmark logs for different LLMs