inference-optimization/Qwen3-8B-from-Qwen3-8B_regen-speculators.eagle31-llamaarch-ckpt1
010
Upload eagle31_per_position.png with huggingface_hub
Upload eagle31_acceptance_length.png with huggingface_hub
Upload eagle31_per_position.png with huggingface_hub
Upload eagle31_acceptance_length.png with huggingface_hub
Upload model.safetensors with huggingface_hub
Upload config.py with huggingface_hub
Upload config.json with huggingface_hub
initial commit