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

LLaMA2 SFT/RLHF training framework

🐚 OpenDevin: Code Less, Make More

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

A toolkit for inference and evaluation of 'mixtral-8x7b-32kseqlen' from Mistral AI

Train transformer language models with reinforcement learning.

Openai style api for open large language models, using LLMs just as chatgpt! Support for LLaMA, LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, Xverse, SqlCoder, CodeLLaMA, ChatGLM, ChatGLM2, ChatGLM3 etc.…

Enable Next-Gen Large Language Model Applications. Join our Discord: https://discord.gg/pAbnFJrkgZ

OpenAI's Code Interpreter in your terminal, running locally

A GPT-4 AI Tutor Prompt for customizable personalized learning experiences.

BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

Firefly(流萤): 中文对话式大语言模型(全量微调+QLoRA)，支持微调Llma2、Llama、Baichuan、InternLM、Ziya、Bloom等大模型

中文LLaMA&Alpaca大语言模型+本地CPU/GPU部署 (Chinese LLaMA & Alpaca LLMs)

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

A high-throughput and memory-efficient inference and serving engine for LLMs

FlagAI (Fast LArge-scale General AI models) is a fast, easy-to-use and extensible toolkit for large-scale model.

Unsupervised text tokenizer for Neural Network-based text generation.

Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。

LLM training code for MosaicML foundation models

decentralising the Ai Industry, just some language model api's...

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

Official repo for the paper: Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models

Plug and play modules to optimize the performances of your AI systems 🚀

Inference code for LLaMA models

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

Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.

该仓库主要记录 NLP 算法工程师相关的面试题