bmfire1 Goto Github PK

12306

12306智能刷票，订票

alpaca_chinese_dataset

人工精调的中文对话数据集和一段chatglm的微调代码

arcface_retinaface_mxnet2onnx

arcface and retinaface model convert mxnet to onnx.

belle

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

chatglm-6b

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

chinese-llama-alpaca

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

cognitive-services-speech-sdk

Sample code for the Microsoft Cognitive Services Speech SDK

cognitive-speech-tts

Microsoft Text-to-Speech API sample code in several languages, part of Cognitive Services.

cuda-programming

Sample codes for my CUDA programming book

cuda_freshman

darknet_fork

Convolutional Neural Networks

deepspeedexamples

Example models using DeepSpeed

deepstream-yolo

NVIDIA DeepStream SDK 6.1.1 / 6.1 / 6.0.1 / 6.0 implementation for YOLO models

deepstream_python_apps

DeepStream SDK Python bindings and sample applications

eet

Easy and Efficient Transformer : Scalable Inference Solution For Large NLP model

efficient-tuning-llms

大模型高效量化训练+部署 (Efficient Finetuning of QLoRA LLMs). QLoRA, LLama, bloom, baichuan-7B, GLM

facechain

FaceChain is a deep-learning toolchain for generating your Digital-Twin.

facegood-audio2face

http://www.facegood.cc

facemoji

😆 A voice chatbot that can imitate your expression. OpenCV+Dlib+Live2D+Moments Recorder+Turing Robot+Iflytek IAT+Iflytek TTS

fastllm

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

flexgen

Running large language models on a single GPU for throughput-oriented scenarios.

gpt-2

Code for the paper "Language Models are Unsupervised Multitask Learners"

gpu_hard_decode_rtsp

ffmpeg+cuvid硬解码rtsp

knead_proj

游戏中捏脸的实现

lamini

langchain-chatglm

langchain-ChatGLM, local knowledge based ChatGLM with langchain ｜ 基于本地知识库的 ChatGLM 问答

libai

LiBai(李白): A Toolbox for Large-Scale Distributed Parallel Training

libfacedetection

An open source library for face detection in images. The face detection speed can reach 1000FPS.

linux_code_test

CMake/Make/Shell/Multi-thread' usage

medusa

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads