Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

fraQtl
/
Qwen-2.5-3B-optimized

Safetensors
qwen2
fraqtl
kv-cache-optimized
inference
Model card Files Files and versions
xet
Community
Qwen-2.5-3B-optimized
6.19 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 6 commits
Zenalyze's picture
Zenalyze
Add arXiv paper link
1ad9174 verified 1 day ago
  • .gitattributes
    1.57 kB
    fraQtl compressed: k=16 INT3, delta=+0.5128 5 days ago
  • README.md
    1.34 kB
    Add arXiv paper link 1 day ago
  • added_tokens.json
    605 Bytes
    fraQtl compressed: k=16 INT3, delta=+0.5128 5 days ago
  • config.json
    743 Bytes
    fraQtl compressed: k=16 INT3, delta=+0.5128 5 days ago
  • generation_config.json
    117 Bytes
    fraQtl compressed: k=16 INT3, delta=+0.5128 5 days ago
  • merges.txt
    1.67 MB
    fraQtl compressed: k=16 INT3, delta=+0.5128 5 days ago
  • model.safetensors
    6.17 GB
    xet
    fraQtl compressed: k=32 INT3, delta=+0.3080 5 days ago
  • model.safetensors.index.json
    24 kB
    fraQtl compressed: k=16 INT3, delta=+0.5128 5 days ago
  • special_tokens_map.json
    616 Bytes
    fraQtl compressed: k=16 INT3, delta=+0.5128 5 days ago
  • tokenizer.json
    11.4 MB
    xet
    fraQtl compressed: k=16 INT3, delta=+0.5128 5 days ago
  • tokenizer.model
    493 kB
    xet
    fraQtl compressed: k=16 INT3, delta=+0.5128 5 days ago
  • tokenizer_config.json
    7.23 kB
    fraQtl compressed: k=16 INT3, delta=+0.5128 5 days ago
  • vocab.json
    2.78 MB
    fraQtl compressed: k=16 INT3, delta=+0.5128 5 days ago