trannhatquy

graphrag

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

DeepSeek-V2

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

snowflake-arctic

llama3

The official Meta Llama 3 GitHub site

OpenChatML

MiniCPM-V

MiniCPM-Llama3-V 2.5: A GPT-4V Level Multimodal LLM on Your Phone

mergoo

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

llm2vec

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

pyreft

ReFT: Representation Finetuning for Language Models

JetMoE

Reaching LLaMA2 Performance with 0.1M Dollars

generative-ai-for-beginners

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

gpt-llm-trainer

reward-bench

RewardBench: the first evaluation tool for reward models.

evolutionary-model-merge

Official repository of Evolutionary Optimization of Model Merging Recipes

ragas

Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines

HPT

HPT - Open Multimodal LLMs from HyperGAI

optimum-quanto

A pytorch quantization backend for optimum

FlexGen

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

hqq

Official implementation of Half-Quadratic Quantization (HQQ)

GaLore

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

minbpe

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

dspy

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

sglang

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

DeepSeek-MoE

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

unsloth

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

LLMDataHub

A quick guide (especially) for trending instruction finetuning datasets

LLM-Benchmark-Logs

Just a bunch of benchmark logs for different LLMs

stripedhyena

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

promptbase

All things prompt engineering

gpt-fast

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