Eagle3 model for Qwen3-4B-Instruct-2507

  • Using SpecForge to train the model
  • Trained on Pro6000 * 1, used about 120 hours for 20 epochs
  • seq_length = 2048
  • Tested on vllm

Todo

  • Evaluate spec decoding result
Downloads last month
29
Safetensors
Model size
0.2B params
Tensor type
I64
BF16
BOOL
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support