Visual Question Answering
Transformers
Safetensors
English
videollama2_mistral
text-generation
multimodal large language model
large video-language model
ccclemenfff commited on
Commit
614cc6d
·
1 Parent(s): b80570e

fix data form support

Browse files
Files changed (1) hide show
  1. handler.py +3 -0
handler.py CHANGED
@@ -34,6 +34,9 @@ class EndpointHandler:
34
  "prompt": "描述图片内容的自然语言指令"
35
  }
36
  """
 
 
 
37
  # 判断输入模态
38
  if "video" in data:
39
  modal = "video"
 
34
  "prompt": "描述图片内容的自然语言指令"
35
  }
36
  """
37
+ # Hugging Face接口会把真正的输入放在inputs字段里
38
+ data = data.get("inputs", data)
39
+
40
  # 判断输入模态
41
  if "video" in data:
42
  modal = "video"