LewisVille-flow

DeepFaceLab

DeepFaceLab is the leading software for creating deepfakes.

ColossalAI

Making large AI models cheaper, faster and more accessible

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

LLaMA-Factory

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

LLMs-from-scratch

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

llamafile

Distribute and run LLMs with a single file.

llama3-from-scratch

llama3 implementation one matrix multiplication at a time

MemGPT

Create LLM agents with long-term memory and custom tools 📚🦙

Megatron-LM

Ongoing research training transformer models at scale

lit-llama

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

alignment-handbook

Robust recipes to align language models with human and AI preferences

LMOps

General technology for enabling AI capabilities w/ LLMs and MLLMs

exllama

A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.

Awesome-LLM-Inference

📖A curated list of Awesome LLM Inference Paper with codes, TensorRT-LLM, vLLM, streaming-llm, AWQ, SmoothQuant, WINT8/4, Continuous Batching, FlashAttention, PagedAttention etc.

CrypTen

A framework for Privacy Preserving Machine Learning

fastRAG

Efficient Retrieval Augmentation and Generation Framework

grade-school-math

Awesome-LLM-RAG

Awesome-LLM-RAG: a curated list of advanced retrieval augmented generation (RAG) in Large Language Models

RisuAI

Make your own story. User-friendly software for LLM roleplaying

slowllama

Finetune llama2-70b and codellama on MacBook Air without quantization

CharacterEval

openroleplay.ai

openroleplay.ai is an open source character.ai alternative.

LogicKor

한국어 언어모델 다분야 사고력 벤치마크

42dot_LLM

42dot LLM consists of a pre-trained language model, 42dot LLM-PLM, and a fine-tuned model, 42dot LLM-SFT, which is trained to respond to user prompts and supports both languages simultaneously by training a large amount of Korean and English text.

Adaptive-MT-LLM-Fine-tuning

Fine-tuning Mistral LLM for Adaptive Machine Translation

liner-pdf-chat-tutorial

LINER PDF Chat Tutorial with ChatGPT & Pinecone

LLM-PaperReview

Review papers of NLP, mainly LLM.

KoNEFTune

Random Noisy Embeddings with fine-tuning 방법론을 한국어 LLM에 간단히 적용할 수 있는 Kosy🍵llama