ghkl98

api调用后，不输出预期的结果

1

 

为什么部署到dify上会这样提示啊

2

Failed to generate chat completion, detail: [address=0.0.0.0:35103, pid=3767] Model model_format='pytorch' model_size_in_billions=13 quantizations=['4-bit', '8-bit', 'none'] model_id='' model_hub='huggingface' model_uri='/root/Chinese-llama' model_revision=None is not for chat.

QUESTIONAttributeError: [address=0.0.0.0:33767, pid=5848] Model model_format='pytorch' model_size_in_billions=13 quantizations=['4-bit', '8-bit', 'none'] model_id='FlagAlpha/Llama2-Chinese-13b-Chat' model_hub='huggingface' model_uri='file:///root/chinese-llama2' model_revision=None is not for chat.

16

我想部署自己的本地模型，写的model.json如下 { "version": 1, "context_length": 2048, "model_name": "customer-llama-2", "model_lang": [ "en", "zh" ], "model_ability": [ "chat" ], "model_specs": [ { "model_format": "pytorch", "model_size_in_billions": 13, "quantizations": [ "4-bit", "8-bit", "none" ],...