songhuan541 Goto Github PK

adapter-transformers

Huggingface Transformers + Adapters = ❤️

auto-gpt

An experimental open-source attempt to make GPT-4 fully autonomous.

awesome-chatgpt-zh

ChatGPT 中文指南，ChatGPT 中文调教指南，指令指南，精选资源清单，更好的使用 chatGPT 让你的生产力 up up up!

cformers

SoTA Transformers with C-backend for fast inference on your CPU.

chatglm-mnn

Pure C++, Easy Deploy ChatGLM-6B.

codegen

CodeGen is an open-source model for program synthesis. Trained on TPU-v4. Competitive with OpenAI Codex.

codegen-fine-tuning

cuml

cuML - RAPIDS Machine Learning Library

dolly

fauxpilot

FauxPilot - an open-source GitHub Copilot server

fengshenbang-lm

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，成为中文认知智能的基础设施。

flash-attention

Fast and memory-efficient exact attention

flexgen

Running large language models like OPT-175B/GPT-3 on a single GPU. Focusing on large-batch high-throughput generation.

google-research

Google Research

gpt-4-llm

kernl

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.

papilot

Papilot - an open-source GitHub Copilot server based PaddleNLP

py-tree-sitter-languages

Binary Python wheels for all tree sitter languages.

reacc

Source codes for paper ”ReACC: A Retrieval-Augmented Code Completion Framework“

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。

self-instruct

Aligning pretrained language models with instruction data generated by themselves.

tpu-mlir

Machine learning compiler based on MLIR for Sophgo TPU.

transformers-bloom-inference

Fast Inference Solutions for BLOOM

tree-sitter-parsers

triton

Development repository for the Triton language and compiler

wenda

闻达：一个LLM调用平台。为小模型外挂知识库查找和设计自动执行动作，实现不亚于于大模型的生成能力