RelaxingSnorlax's picture
Upload Llama4 Eagle3 dummy drafter for vLLM testing
217d835 verified
|
raw
history blame
947 Bytes

Llama4 Eagle Drafter Model (Test)

This is a test Eagle drafter model for Llama4 with proper configuration and vocabulary mappings.

Model Details

  • Architecture: Llama4ForCausalLM (Eagle draft variant)
  • Hidden size: 2048
  • Layers: 1 (single decoder layer for Eagle draft)
  • Vocabulary: 128256 tokens (Llama4)
  • Includes: d2t and t2d vocabulary mappings

Configuration

  • Uses standard Llama4 architecture
  • Includes Eagle auxiliary state configuration
  • Has vocabulary mapping tensors (d2t/t2d) for draft-to-target conversion
  • Extended context support (262k max position embeddings)

Usage

This model is for testing Eagle speculative decoding with Llama4 in vLLM:

vllm serve <llama4-target-model> \
    --speculative-config '{"method": "eagle", "model": "nm-testing/llama4-eagle-drafter", ...}'

Testing Purpose

This model contains random weights and is only for vLLM Eagle implementation testing.