EADST

Quick Review: SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression

作者：XD / 发表： 2023年12月6日 23:57 / 更新： 2023年12月6日 23:57 / 科研学习 / 阅读量：728

SpQR: A Sparse-Quantized Representation for Near-Lossless Large Language Model Weight Compression

Core Approach:

  • GPTQ without Outliers: Focuses on eliminating outliers during the GPTQ process, enabling more efficient and accurate weight compression for large language models.

本文作者：XD 转载请标明出处：http://www.eadst.com/blog/225

本站采用知识共享署名-非商业性使用-相同方式共享 4.0 国际许可协议进行许可。

上一篇
Quick Review: Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs
下一篇
Quick Review: QUIK: Towards End-to-end 4-Bit Inference on Generative Large Language Models
相关标签
LLM Quantization
About Me
XD
Goals determine what you are going to be.
Category
标签云
uWSGI 报税 git OpenCV SVR Docker FastAPI Tracking LeetCode LoRA Algorithm tar InvalidArgumentError TSV Food Git Pickle CV Vmess Knowledge BTC scipy CSV Pandas Magnet Pytorch GIT Numpy UNIX ONNX Plotly Shortcut Interview NLTK VGG-16 Bert Github git-lfs XGBoost SPIE Math Tensor 域名 Password CAM Safetensors Excel Web GoogLeNet NameSilo NLP Ptyhon Qwen2.5 DeepStream Attention XML COCO CEIR Nginx LLAMA C++ diffusers Website Use RGB VPN Distillation Hungarian Pillow FP16 LaTeX GGML QWEN Template Django Card Hilton llama.cpp YOLO 搞笑 Zip Streamlit FP32 Land Conda TensorFlow GPTQ GPT4 WebCrawler SQL Jetson Anaconda Gemma Augmentation 算法题 Transformers Ubuntu uwsgi Quantization Review FP64 OCR Crawler Diagram hf Bitcoin Windows torchinfo LLM Sklearn Michelin CTC Cloudreve Base64 ModelScope TensorRT Plate Quantize EXCEL OpenAI BF16 Input Data Qwen SQLite Python ChatGPT 签证 AI v2ray Dataset Hotel Translation 关于博主 Video Random Paper Baidu 腾讯云 Heatmap Clash Vim Datetime FlashAttention BeautifulSoup Disk logger Image2Text VSCode Statistics CUDA Markdown Tiktoken Permission Color HaggingFace JSON MD5 Bipartite HuggingFace transformers PyCharm PIP Domain ResNet-50 Linux Proxy Paddle PDF Google Bin 阿里云
站点统计

本站现有博文266篇,共被浏览440752次

本站已经建立2019天!

热门文章
文章归档
回到顶部