Open kkwhale7 opened 5 days ago
Why is VLLM's inference script use eos token as , TransFormers's inference script use tokenizer.eos(im_end), and why is it necessary to output tokens one by one.....
Why is VLLM's inference script use eos token as , TransFormers's inference script use tokenizer.eos(im_end), and why is it necessary to output tokens one by one.....