taoxunqiang
Results
3
comments of
taoxunqiang
> > "We tested the speculative inference using the first 100 inputs from alpaca test dataset as prompts. When model=gpt2-xl, draft_model=gpt2". > > I want to test speedup for my...
Where can I get the pretrained weights to help reproduce the result？
Is there a plan to release the code？ Thanks！