YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

Eagle v2 model for qvikhr 1.5b model. Got following speedup while inferencing using sglang:

Batch Size Speedup
1 1.72
2 1.49
4 1.47
8 1.38
16 0.95
32 0.56

guide for running it using sglang is here: https://gitlab.com/qklent/eagle_train/-/blob/main/run_inference_instruction.md?ref_type=heads

For training, you can use this commit from the same repo 2f5a5c5bc457034f671a14cf6ff1da4644b4c4f2. (training scripts adaptation to eagle 3 is still in progress, so main branch is broken)

Downloads last month
8
Safetensors
Model size
0.3B params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support