Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

gitarist
/
Qwen3-8B-BPDQ-coded-2.5bit

Text Generation
Safetensors
qwen3
quantization
vllm
conversational
8-bit precision
bpdq
Model card Files Files and versions
xet
Community
Qwen3-8B-BPDQ-coded-2.5bit
3.14 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 4 commits
gitarist's picture
gitarist
faster coded kernel
47639c9 verified 19 days ago
  • .gitattributes
    1.57 kB
    Qwen3-8B BPDQ coded planes (8,7,3), 2.5 bits 20 days ago
  • README.md
    1.8 kB
    faster coded kernel 19 days ago
  • bpdq.py
    172 kB
    faster coded kernel 19 days ago
  • bpdq_config.json
    412 Bytes
    coded on-disk format (codeword indices), 3.1 GB 19 days ago
  • chat_template.jinja
    4.17 kB
    Qwen3-8B BPDQ coded planes (8,7,3), 2.5 bits 20 days ago
  • config.json
    2.43 kB
    coded on-disk format (codeword indices), 3.1 GB 19 days ago
  • generation_config.json
    239 Bytes
    Qwen3-8B BPDQ coded planes (8,7,3), 2.5 bits 20 days ago
  • merges.txt
    1.67 MB
    Qwen3-8B BPDQ coded planes (8,7,3), 2.5 bits 20 days ago
  • model.safetensors
    3.12 GB
    xet
    coded on-disk format (codeword indices), 3.1 GB 19 days ago
  • tokenizer.json
    11.4 MB
    xet
    Qwen3-8B BPDQ coded planes (8,7,3), 2.5 bits 20 days ago
  • tokenizer_config.json
    9.73 kB
    Qwen3-8B BPDQ coded planes (8,7,3), 2.5 bits 20 days ago
  • vocab.json
    2.78 MB
    Qwen3-8B BPDQ coded planes (8,7,3), 2.5 bits 20 days ago