Ma-Dan

Pinned Repositories

sherpa-ncnn
Real-time speech recognition using next-gen Kaldi with ncnn without Internet connection. Support iOS, Android, Raspberry Pi, VisionFive2, LicheePi4A etc.
Language:C++847 35 129133
asr-decode
从Kaldi中裁剪的轻量级语音识别解码推理框架，目前实现了MFCC+GMM+Viterbi，不依赖OpenFST、OpenBLAS等库
Language:C++18 2 14
keras-yolo4
A Keras implementation of YOLOv4 (Tensorflow backend)
Language:Python383 11 41176
llama2-infer
从零实现一个深度学习推理框架的练手实验
Language:Python0 1 00
rasa_bot
整理：基于Rasa-NLU和Rasa-Core的任务型ChatBot
Language:Python50 8 223
XLNet-ChineseNER
Tensorflow solution of NER task Using BiLSTM-CRF model with CMU/Google XLNet
Language:Python44 1 86
yolact
A simple, fully convolutional model for real-time instance segmentation.
Language:Python43 5 012
Yolact-CoreML
Yolact for iOS implemented using CoreML.
Language:Swift32 2 37
YOLOv3-CoreML
YOLOv3 for iOS implemented using CoreML.
Language:Swift171 10 2146
wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit
Language:Python3.8k 90 9761k

Ma-Dan's Repositories

Ma-Dan/CUDA-Learn-Note
🎉CUDA 笔记 / 大模型手撕CUDA / C++笔记，个人笔记，更新随缘: flash_attn、sgemm、sgemv、warp reduce、block reduce、dot product、elementwise、softmax、layernorm、rmsnorm、hist etc.
Language:Cuda2 0 0
Ma-Dan/llama.cpp
Port of Facebook's LLaMA model in C/C++
Language:C++2 0 0
Ma-Dan/llama2.c-to-ncnn
A converter for llama2.c legacy models to ncnn models.
Language:Python2 0 0
Ma-Dan/ChatLM-mini-Chinese
中文对话0.2B小模型（ChatLM-Chinese-0.2B），开源所有数据集来源、数据清洗、tokenizer训练、模型预训练、SFT指令微调、RLHF优化等流程的全部代码。支持下游任务sft微调。
Language:Python1
Ma-Dan/QAnything
Question and Answer based on Anything.
Language:Python1
Ma-Dan/llama2-infer
从零实现一个深度学习推理框架的练手实验
Language:Python0 1 00
Ma-Dan/alphageometry
Language:Python0 0
Ma-Dan/ChatGLM-MNN
Pure C++, Easy Deploy ChatGLM-6B.
Language:C++0 0
Ma-Dan/ColossalAI
Making large AI models cheaper, faster and more accessible
Language:Python0 0
Ma-Dan/DB-GPT
Revolutionizing Database Interactions with Private LLM Technology
Language:Python0 0
Ma-Dan/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
Language:C++0 0
Ma-Dan/Fooocus
Focus on prompting and generating
Language:Python0 0
Ma-Dan/hadoop-hive-spark-docker
Hadoop-Hive-Spark cluster + Jupyter on Docker
Language:Dockerfile
Ma-Dan/icefall
Language:Python0 0
Ma-Dan/k2
FSA/FST algorithms, differentiable, with PyTorch compatibility.
Language:Cuda0 0
Ma-Dan/libllm
Efficient inference of large language models.
Ma-Dan/llama2.c
Inference Llama 2 in one file of pure C
Language:C0 0
Ma-Dan/llm.c
LLM training in simple, raw C/CUDA
Language:Cuda
Ma-Dan/mamba-finetune
Language:Python1
Ma-Dan/ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
Language:C++0 0
Ma-Dan/Open-Sora-Plan
This project aim to reproducing Sora (Open AI T2V model), but we only have limited resource. We deeply wish the all open source community can contribute to this project.
Language:Jupyter Notebook0 0
Ma-Dan/PowerInfer
High-speed Large Language Model Serving on PCs with Consumer-grade GPUs
Language:C0 0
Ma-Dan/sherpa
Speech-to-text server framework with next-gen Kaldi
Language:C++0 0
Ma-Dan/sherpa-ncnn
Real-time speech recognition using next-gen Kaldi with ncnn
Language:C++0 0
Ma-Dan/tiny-gpu
A minimal GPU design in Verilog to learn how GPUs work from the ground up
Language:SystemVerilog
Ma-Dan/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
Language:Python0 0
Ma-Dan/vtensor
Language:C++0 0
Ma-Dan/wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit
Language:Python0 0
Ma-Dan/WeTextProcessing
Text Normalization & Inverse Text Normalization
Language:Python0 0
Ma-Dan/whisper
Robust Speech Recognition via Large-Scale Weak Supervision
Language:Python0 0