Framework for building, orchestrating and deploying multi-agent systems. Managed by OpenAI Solutions team. Experimental framework.

Apify API client for Python

Extend existing LLMs way beyond the original training length with constant memory usage, and without retraining

The official repo of Qwen-7B (通义千问-7B) chat & pretrained large language model proposed by Alibaba Cloud.

This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.

A guidance language for controlling large language models.

All the code examples I use in my videos

Efficient Streaming Language Models with Attention Sinks

Firefly(流萤): 中文对话式大语言模型(全量微调+QLoRA)，支持微调Baichuan2、CodeLlama、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya、Bloom等大模型

XTuner is a toolkit for efficiently fine-tuning LLM

ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

ChatGLM2-6B 全参数微调，支持多轮对话的高效微调。

Fine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调

Powerful and flexible Instagram scraping library for Python, providing easy-to-use and expressive tools for accessing data programmatically

Instruct-tune LLaMA on consumer hardware

A gradio web UI for running Large Language Models like GPT-J 6B, OPT, GALACTICA, LLaMA, and Pygmalion.

Making big AI models cheaper, easier, and more scalable

Fast Inference Solutions for BLOOM

GPT2 for Chinese chitchat/用于中文闲聊的GPT2模型(实现了DialoGPT的MMI思想)

Easy-to-use and powerful NLP library with Awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications, including Neural Search, Question Answering, Information Ex…