tuanio

evaluate

🤗 Evaluate: A library for easily evaluating machine learning models and datasets.

dsir

DSIR large-scale data selection framework for language model training

unsloth

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

nanotron

Minimalistic large language model 3D-parallelism training

llm-swarm

Manage scalable open LLM inference endpoints in Slurm clusters

lighteval

LightEval is a lightweight LLM evaluation suite that Hugging Face has been using internally with the recently released LLM data processing library datatrove and LLM training library nanotron.

datatrove

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

cosmopedia

NSCC_tutorial_for_ASPIRE2

NSCC is a high-performance computing center in Singapore.

LLaMA-Efficient-Tuning

Easy-to-use LLM fine-tuning framework (LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, ChatGLM2)

rectified-flow-pytorch

Implementation of rectified flow and some of its followup research / improvements in Pytorch

xtuner

An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)

data-is-better-together

Let's build better datasets, together!

MMML

Multi-Modality Multi-Loss Fusion Network

papers-we-love

Papers from the computer science community to read and discuss.

the-book-of-secret-knowledge

A collection of inspiring lists, manuals, cheatsheets, blogs, hacks, one-liners, cli/web tools and more.

fish-speech

Brand new TTS solution

mem0

The memory layer for Personalized AI

LLaMA-Factory

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

semantic-kernel

Integrate cutting-edge LLM technology quickly and easily into your apps

MoA-Ollama-Chat

This is the Mixture-of-Agents (MoA) concept, adapted from the original work by TogetherAI. My version is tailored for local model usage and features a user-friendly Gradio interface.

MoA

Together Mixture-Of-Agents (MoA) – 65.1% on AlpacaEval with OSS models

LaVy

Pioneering in Vietnamese Multimodal Large Language Model

envpool

C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.

tianshou

An elegant PyTorch deep reinforcement learning library.

sequence_align

Efficient implementations of Needleman-Wunsch and other sequence alignment algorithms written in Rust with Python bindings via PyO3.

mispronunciation-detection-diagnosis-wav2vec2-and-llm

Mispronunciation Detection using a pretrained and finetuned wav2vec2 model for phoneme recognition and diagnosis and feedback using large language model

VisionLLM-Vietnamese

MM-Vet

MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities (ICML 2024)

test

Measuring Massive Multitask Language Understanding | ICLR 2021