xiaoToby
xiaoToby
@richardliaw hi, I saw that the part of code about def step(self, action_dict) is written by you. I met some error here, main about the attribute action_dict, there is nothing...
@samvelyan please help
> I found this problem mainly from enabling `self.double.q`, if you set `self.double.q=False` in the default config, then qmix can run. Hi, where to set self.double.q=False And when I run...
> 部署llama3-8b-instruct模型，基于vllm的openai兼容接口。服务拉起来之后，每次请求访问都必须达到最长上下文的输出才会停止。是需要在tokenizer_config.json文件哪里配置停止词吗？ 请求访问如下： { "model": "Meta-Llama-3-8B-Instruct", "messages": [ {"role": "user", "content": "Please tell me a 100 words children's story. Please reply in Chinese."} ], "temperature": 0.1 } 接口返回内容如下： { "id":...
You can check and infer to this post #76 , maybe it will help you @xinzaifeixiang1992
the same problem. The better way is to apply the install request on official Meta website.  It's quick !
> @xiaoToby looking at that repo, it looks like it's just using fastapi. I think you may have some luck if you give it a shot, but my biggest concern...
Actually, I do not know what serverless platform. I use it on web page
> Hi @xiaoToby - are you using our serverless platform? Yes, I use the serverless platform @SirOibaf