cfl2005's Stars
XueFuzhao/awesome-mixture-of-experts
A collection of AWESOME things about mixture-of-experts
Tencent/PatrickStar
PatrickStar enables Larger, Faster, Greener Pretrained Models for NLP and democratizes AI for everyone.
mymusise/ChatGLM-Tuning
基于ChatGLM-6B + LoRA的Fintune方案
jianzhnie/LLamaTuner
Easy and Efficient Finetuning LLMs. (Supported LLama, LLama2, LLama3, Qwen, Baichuan, GLM , Falcon) 大模型高效量化训练+部署.
shuxueslpi/chatGLM-6B-QLoRA
使用peft库,对chatGLM-6B/chatGLM2-6B实现4bit的QLoRA高效微调,并做lora model和base model的merge及4bit的量化(quantize)。
bigscience-workshop/petals
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
netx-repo/PipeSwitch
PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications
microsoft/DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
FMInference/FlexGen
Running large language models on a single GPU for throughput-oriented scenarios.
tloen/alpaca-lora
Instruct-tune LLaMA on consumer hardware
deep-diver/LLM-As-Chatbot
LLM as a Chatbot Service
LC1332/Luotuo-Chinese-LLM
骆驼(Luotuo): Open Sourced Chinese Language Models. Developed by 陈启源 @ 华中师范大学 & 李鲁鲁 @ 商汤科技 & 冷子昂 @ 商汤科技
meta-llama/llama
Inference code for Llama models
tatsu-lab/stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
hpcaitech/ColossalAI
Making large AI models cheaper, faster and more accessible
cfl2005/FastPTM
CLUEbenchmark/CLUEDatasetSearch
搜索所有中文NLP数据集,附常用英文NLP数据集
NVlabs/DG-Net
:couple: Joint Discriminative and Generative Learning for Person Re-identification. CVPR'19 (Oral) :couple:
lartpang/PyTorchTricks
Some tricks of pytorch... :star:
PipelineAI/pipeline
PipelineAI
shakeel608/OpenNMT-py-with-BERT
OpenNMT Pytorch with BERT Embeddings
bert-nmt/bert-nmt
pytorch/examples
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
jemisjoky/TorchMPS
PyTorch toolbox for matrix product state models
ChineseGLUE/ChineseGLUE
Language Understanding Evaluation benchmark for Chinese: datasets, baselines, pre-trained models,corpus and leaderboard
DA-southampton/Read_Bert_Code
Bert源码阅读与讲解(Pytorch版本)-以BERT文本分类代码为例子
YouQixiaowu/CUDA-Programming-with-Python
关于书籍CUDA Programming使用了pycuda模块的Python版本的示例代码
Tencent/TurboTransformers
a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.
NVIDIA/FasterTransformer
Transformer related optimization, including BERT, GPT
jiangxiluning/chinese-ocr
运用tensorflow实现自然场景文字检测,keras/pytorch实现crnn+ctc实现不定长中文OCR识别