Sunday's repositories
transformers2TensorRT
本项目介绍了使用Transformers模块微调文本分类模型,以及模型转pth格式,进而转为onnx格式和TensorRT的engine格式,最后通过TensorRT进行推理的完整流程
quick-mixtral
A repo for learning code and debug of mixtral, Mixtral-8x7B-v0.1, Mixtral-8x7B-Instruct-v0.1 and new mixtral future
Codes-storm
Mind mapping for codes.
machine-learning
A machine learning repo.
awesome-chatgpt-prompts
This repo includes ChatGPT prompt curation to use ChatGPT better.
benchmark
A microbenchmark support library
cub
THIS REPOSITORY HAS MOVED TO github.com/nvidia/cub, WHICH IS AUTOMATICALLY MIRRORED HERE.
QASystemOnMedicalGraph
该项目是基于医疗领域知识图谱的问答系统。实现比较简单。
GeminiProChat
Minimal web UI for GeminiPro.
googletest
GoogleTest - Google Testing and Mocking Framework
GPT2-Chinese
Chinese version of GPT2 training code, using BERT tokenizer.
GPT2-chitchat
GPT2 for Chinese chitchat/用于中文闲聊的GPT2模型(实现了DialoGPT的MMI**)
onnx
Open standard for machine learning interoperability
onnx-tensorrt
ONNX-TensorRT: TensorRT backend for ONNX
protobuf
Protocol Buffers - Google's data interchange format
TensorRT
NVIDIA® TensorRT™, an SDK for high-performance deep learning inference, includes a deep learning inference optimizer and runtime that delivers low latency and high throughput for inference applications.