EADST

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

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.
相关标签
About Me
XD
Goals determine what you are going to be.
Category
标签云
Pillow Jupyter Michelin hf HaggingFace CV 递归学习法 LoRA FP32 YOLO Zip uwsgi Diagram PyTorch LaTeX Miniforge Jetson Firewall AI tar PIP Web BTC Password CEIR Magnet CC ONNX Git API GPT4 UI Baidu VGG-16 v0.dev UNIX Random 第一性原理 llama.cpp Django 飞书 域名 图标 搞笑 VSCode Plate 报税 Mixtral 财报 Knowledge 关于博主 scipy TensorRT Crawler CUDA Website Video 云服务器 RAR Hotel Excel 顶会 GPTQ GIT Nginx FP64 CAM Bert Ubuntu XGBoost GoogLeNet Template Vim Base64 Cloudreve DeepStream Proxy Markdown SQLite News FastAPI Sklearn 版权 Vmess Windows Shortcut OCR 音频 SPIE 多线程 ModelScope CTC Tracking git FP16 Clash TensorFlow VPN ChatGPT COCO CSV Data 算法题 TTS Llama Card Color LLAMA Land Translation BF16 transformers tqdm Permission Interview Bipartite Quantize Algorithm TSV BeautifulSoup Animate Plotly SAM Pandas 净利润 Bin NLP Linux Docker PDB Use git-lfs 阿里云 Tiktoken Claude IndexTTS2 强化学习 InvalidArgumentError JSON Rebuttal printf Qwen2 Numpy Quantization logger Python Image2Text Paper ResNet-50 继承 Gemma Attention Breakpoint Hilton 公式 Augmentation Anaconda Agent Paddle Conda Hungarian WAN EXCEL QWEN WebCrawler Heatmap Qwen uWSGI icon 签证 Search HuggingFace FP8 腾讯云 Dataset Food GGML v2ray Pytorch CLAP Statistics LLM Streamlit MD5 mmap Tensor Google NLTK LeetCode RGB Domain OpenAI Datetime Review Bitcoin OpenCV PDF Pickle Distillation Safetensors Transformers PyCharm Math diffusers FlashAttention XML 图形思考法 SQL 证件照 DeepSeek Input Qwen2.5 Disk Freesound NameSilo 多进程 Ptyhon Github Logo C++ torchinfo SVR
站点统计

本站现有博文324篇,共被浏览819386

本站已经建立2523天!

热门文章
文章归档
回到顶部