chiennv2000

mlc-llm

Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.

dspy

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

flash-attention

Fast and memory-efficient exact attention

readme-md-generator

📄 CLI that generates beautiful README.md files

NeMo

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

unsloth

Finetune Llama 3, Mistral & Gemma LLMs 2-5x faster with 80% less memory

shell_gpt

A command-line productivity tool powered by AI large language models like GPT-4, will help you accomplish your tasks faster and more efficiently.

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.

OLMo

Modeling, training, eval, and inference code for OLMo

AutoGPTQ

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

llmware

Providing enterprise-grade LLM-based development framework, tools, and fine-tuned models.

lmdeploy

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

Olive

Olive is an easy-to-use hardware-aware model optimization tool that composes industry-leading techniques across model compression, optimization, and compilation.

fsdp_qlora

Training LLMs with QLoRA + FSDP

fastRAG

Efficient Retrieval Augmentation and Generation Framework

pyreft

ReFT: Representation Finetuning for Language Models

mamba.py

A simple and efficient Mamba implementation in PyTorch and MLX.

flash-linear-attention

Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton

gritlm

Generative Representational Instruction Tuning

veScale

A PyTorch Native LLM Training Framework

open_lm

A repository for research on medium sized language models.

TransformerCompression

For releasing code related to compression methods for transformers, accompanying our publications

cosmopedia

st-moe-pytorch

Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch

mend

MEND: Fast Model Editing at Scale

KnowledgeEditor

Code for Editing Factual Knowledge in Language Models

Everything-of-Thoughts-XoT

An implemtation of Everyting of Thoughts (XoT).

DiffusionNER

Code for the paper "DiffusionNER: Boundary Diffusion for Named Entity Recognition", accepted at ACL 2023.

ST-LLM

Official implementation of the paper "ST-LLM: Large Language Models Are Effective Temporal Learners"

Rainbow-Table

Group Project for UO CS631 (Advanced Parallel Computing)