Community maintained hardware plugin for vLLM on Ascend

OpenAgents: An Open Platform for Language Agents in the Wild

Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.

A generative agent implementation for LLaMA based models, derived from langchain's implementation.

AgentSims is an easy-to-use infrastructure for researchers from all disciplines to test the specific capacities they are interested in.

A 13B large language model developed by Baichuan Intelligent Technology

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

chatglm多gpu用deepspeed和

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

Port of Facebook's LLaMA model in C/C++

中文nlp解决方案(大模型、数据、模型、训练、推理)

纯c++的全平台llm加速库，支持python调用，chatglm-6B级模型单卡可达10000+token / s，支持glm, llama, moss基座，手机端流畅运行

Python bindings for llama.cpp

A gradio web UI for running Large Language Models like LLaMA, llama.cpp, GPT-J, Pythia, OPT, and GALACTICA.

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Family of instruction-following LLMs powered by Evol-Instruct: WizardLM, WizardCoder

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

JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

An open-source tool-augmented conversational language model from Fudan University

一种平价的chatgpt实现方案, 基于ChatGLM-6B + LoRA

Making large AI models cheaper, faster and more accessible

WebGLM: An Efficient Web-enhanced Question Answering System (KDD 2023)

This repo contains the data preparation, tokenization, training and inference code for BLOOMChat. BLOOMChat is a 176 billion parameter multilingual chat model based on BLOOM.

ModelScope: bring the notion of Model-as-a-Service to life.

本地知识库 + chatGLM6B + CustomAgent

Ongoing research training transformer language models at scale, including: BERT & GPT-2