Daemon-ser

WildBench

Benchmarking LLMs with Challenging Tasks from Real Users

simple-evals

ComplexBench

llm_interview_note

主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

MAmmoTH

Code and data for "MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning" (ICLR 2024)

test

Measuring Massive Multitask Language Understanding | ICLR 2021

Awesome-LLMs-Datasets

Summarize existing representative LLMs text datasets.

math

The MATH Dataset (NeurIPS 2021)

DeepSeek-Coder-V2

DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence

LiveBench

LiveBench: A Challenging, Contamination-Free LLM Benchmark

LLaMA-Factory

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

Awesome-LLMs-Evaluation-Papers

The papers are organized according to our survey: Evaluating Large Language Models: A Comprehensive Survey.

Qwen2

Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.

helm

Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110). This framework is also used to evaluate text-to-image models in Holistic Evaluation of Text-to-Image Models (HEIM) (https://arxiv.org/abs/2311.04287).

awesome-auto-alignment

Collection of papers for scalable automated alignment.

LLM_Tree_Search

(ICML 2024) Alphazero-like Tree-Search can guide large language model decoding and training

DoLa

Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"

DeepSeek-LLM

DeepSeek LLM: Let there be answers

llms_tool

一个基于HuggingFace开发的大语言模型训练、测试工具。支持各模型的webui、终端预测，低参数量及全参数模型训练(预训练、SFT、RM、PPO、DPO)和融合、量化。

direct-preference-optimization

Reference implementation for DPO (Direct Preference Optimization)

data-juicer

A one-stop data processing system to make data higher-quality, juicier, and more digestible for (multimodal) LLMs! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷为大模型提供更高质量、更丰富、更易”消化“的数据！

Awesome-LLM-Long-Context-Modeling

📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥

AlignBench

大模型多维度中文对齐评测基准 (ACL 2024)

R-Drop

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

chatbot-ui

AI chat for every model.

trlx

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

speculative-decoding

Explorations into some recent techniques surrounding speculative decoding

sentencepiece

Unsupervised text tokenizer for Neural Network-based text generation.

sd-webui-EasyPhoto

📷 EasyPhoto | Your Smart AI Photo Generator.