adamlin120

FastChat

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

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.

llm-eval

LLM-Eval: Unified Multi-Dimensional Automatic Evaluation for Open-Domain Conversations with Large Language Models

lm

lm-evaluation-harness

A framework for few-shot evaluation of language models.

adamlin120.github.io

AutoAWQ

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

awesome-synthetic-datasets

awesome synthetic (text) datasets

BTX

chat-ui

Open source codebase powering the HuggingChat app

cohere-toolkit

Cohere Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.

cosmopedia

gooaye-gpt

ievals

Official github repo for TMMLU+, Large scale traditional chinese massive multitask language understanding

llm.c

LLM training in simple, raw C/CUDA

LongChat

Official repository for LongChat and LongEval

mergekit

Tools for merging pretrained large language models.

mixture-of-experts-reading-list

ml-engineering

Machine Learning Engineering Open Book

MR-Models

聯發創新基地（MediaTek Research) 致力於研究基礎模型。我們將研究體現在適合繁體中文使用者的模型上，並在使用權許可的情況下，提供模型給學術界研究或產業界使用。

nanotron

Minimalistic large language model 3D-parallelism training

needle-haystack

NeMo

NeMo: a framework for generative AI

open-instruct

open_asr_leaderboard

taipei-1-runbook

TCEval

tmlu

Traditional Mandarin Language Understanding Benchmark

tmux-config

Tmux configuration, that supercharges your tmux to build cozy and cool terminal environment

YALT

A Full Stack LLM Framework