"ModelScope中,llm 和 vllm 的输入格式还不一样么? history1 = resp_list[1]['history']
request_list = [{'query': '这有什么好吃的', 'history': history1}]
resp_list = inference_vllm(llm_engine, template, request_list) query = '浙江的省会在哪里?'
gen = inference_stream(model, template, query)
print(f'query: {query}')
for response, history in gen:
print(f'response: {response}')
query = '这有什么好吃的?'
gen = inference_stream(model, template, query, history)"
ModelScope旨在打造下一代开源的模型即服务共享平台,为泛AI开发者提供灵活、易用、低成本的一站式模型服务产品,让模型应用更简单!欢迎加入技术交流群:微信公众号:魔搭ModelScope社区,钉钉群号:44837352