B. Shen's repositories
sbwww.github.io
personal homepage
LLM-Shearing
Preprint: Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning
bert-squeeze
🛠️ Tools for Transformers compression using PyTorch Lightning ⚡
ChineseNLPCorpus
中文自然语言处理数据集,平时做做实验的材料。欢迎补充提交合并。
cs-self-learning
计算机自学指南
Daxuexi
北京 青年大学习 使用Github Actions自动完成
DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Diffusion-BERT
Implementation of DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models
img2dataset
Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
IoT-For-Beginners
12 Weeks, 24 Lessons, IoT for All!
latexcv
:necktie: A collection of cv and resume templates written in LaTeX. Leave an issue if your language is not supported!
lighteval
LightEval is a lightweight LLM evaluation suite that Hugging Face has been using internally with the recently released LLM data processing library datatrove and LLM training library nanotron.
LLM-Pruner
[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support LLaMA, Llama-2, BLOOM, Vicuna, Baichuan, etc.
lm-evaluation-harness
A framework for few-shot evaluation of autoregressive language models.
mace
MACE is a deep learning inference framework optimized for mobile heterogeneous computing platforms.
Medusa
Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
mlc-llm
Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.
mlx
MLX: An array framework for Apple silicon
RWKV-Android
使用Android cpu 运行 RWKV V4 ONNX
smoothquant
SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
StableDiffusionOnDevice
本项目是一个通过文字生成图片的项目,基于开源模型Stable Diffusion V1.5生成可以在手机的CPU和NPU上运行的模型,包括其配套的模型运行框架。
tvm
Open deep learning compiler stack for cpu, gpu and specialized accelerators
wanda
A simple and effective LLM pruning approach.