ScottWang96

InternLM-Math

State-of-the-art bilingual open-sourced Math reasoning LLMs.

summarize_from_feedback_details

lm-human-preferences

Code for the paper Fine-Tuning Language Models from Human Preferences

awesome-instruction-datasets

A collection of awesome-prompt-datasets, awesome-instruction-dataset, to train ChatLLM such as chatgpt 收录各种各样的指令数据集, 用于训练 ChatLLM 模型。

instruction-datasets

All available datasets for Instruction Tuning of Large Language Models

dlrover

DLRover: An Automatic Distributed Deep Learning System

ToRA

ToRA is a series of Tool-integrated Reasoning LLM Agents designed to solve challenging mathematical reasoning problems by interacting with tools [ICLR'24].

AgentBench

A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

LLaMA-Factory

Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)

OpenRLHF

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & Mixtral)

airllm

AirLLM 70B inference with single 4GB GPU

MOSS-RLHF

MOSS-RLHF

BIG-Bench-Hard

Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them

direct-preference-optimization

Reference implementation for DPO (Direct Preference Optimization)

Awesome-Chinese-LLM

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

ceval

Official github repo for C-Eval, a Chinese evaluation suite for foundation models [NeurIPS 2023]

Dict-of-Sensitive-Words

chain-of-thought-hub

Benchmarking large language models' complex reasoning ability with chain-of-thought prompting

Safety-Prompts

Chinese safety prompts for evaluating and improving the safety of LLMs. 中文安全prompts，用于评估和提升大模型的安全性。

safe-rlhf

Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

alpaca-lora

Instruct-tune LLaMA on consumer hardware

OpenDelta

A plug-and-play library for parameter-efficient-tuning (Delta Tuning)

LMFlow

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

DeepSpeedExamples

Example models using DeepSpeed

FastChat

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

GPT-4-LLM

Instruction Tuning with GPT-4

InstructionWild

gpt4all

GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.

ChatGLM-6B

ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

stanford_alpaca

Code and documentation to train Stanford's Alpaca models, and generate the data.