jibowang

open_llama: ValueError: head_size (100) is not supported. Supported head sizes: [64, 80, 96, 128]

1

I start vllm with “openlm-research/open_llama_3b” model: ``` from vllm import LLM, SamplingParams import os prompts = [ "The president of the United States is" ] sampling_params = SamplingParams(temperature=0.8, top_p=0.95) llm...