Use FastChat to start the deepseek-coder-33b-instruct model, send a stream request and got an error response. If set stream=False, you can print a good response If change to other models, it also works with stream Start cmd: python3 -m f...
[INFO|configuration_utils.py:728] 2023-12-12 09:03:50,977 >> loading configuration file /media/models/models/deepseek-ai/deepseek-coder-33b-instruct/generation_config.json [INFO|configuration_utils.py:770] 2023-12-12 09:03:50,978 >> Generate config GenerationConfig { "bos_token_id": 32...