Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • 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

migtissera
/
Tess-4-27B-EAGLE3

Transformers
Safetensors
llama
tess
eagle3
speculative-decoding
draft-model
qwen3
text-generation-inference
Model card Files Files and versions
xet
Community
1

Instructions to use migtissera/Tess-4-27B-EAGLE3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use migtissera/Tess-4-27B-EAGLE3 with Transformers:

    # Load model directly
    from transformers import AutoTokenizer, LlamaForCausalLMEagle3
    
    tokenizer = AutoTokenizer.from_pretrained("migtissera/Tess-4-27B-EAGLE3")
    model = LlamaForCausalLMEagle3.from_pretrained("migtissera/Tess-4-27B-EAGLE3", device_map="auto")
  • Notebooks
  • Google Colab
  • Kaggle
Tess-4-27B-EAGLE3
1.22 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 2 commits
migtissera's picture
migtissera
EAGLE-3 draft β€” 1.76x avg decode speedup, measured
221aeaa verified 2 months ago
  • .gitattributes
    1.52 kB
    initial commit 2 months ago
  • README.md
    3.22 kB
    EAGLE-3 draft β€” 1.76x avg decode speedup, measured 2 months ago
  • config.json
    868 Bytes
    EAGLE-3 draft β€” 1.76x avg decode speedup, measured 2 months ago
  • model.safetensors
    1.22 GB
    xet
    EAGLE-3 draft β€” 1.76x avg decode speedup, measured 2 months ago