Upload handler.py with huggingface_hub

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 vocab.txt filter=lfs diff=lfs merge=lfs -text
+handler.py filter=lfs diff=lfs merge=lfs -text

handler.py

@@ -1,40 +1,3 @@
-from typing import Dict, List, Any
-from transformers import AutoModel, AutoTokenizer
-
-
-class EndpointHandler:
-    def __init__(self, path="."):
-        self.tokenizer = AutoTokenizer.from_pretrained(path)
-        self.model = AutoModel.from_pretrained(
-            path,
-            trust_remote_code=True,
-            do_syntax=True, do_prefix=False, do_morph=False, do_ner=True, do_lex=True
-        )
-        self.model.eval()
-
-    def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
-        """
-        data args:
-            inputs (:obj: `str` | `PIL.Image` | `np.array`)
-            kwargs
-        Return:
-            A :obj:`list` | `dict`: will be serialized and returned
-        """
-        # return self.pipeline(data['inputs'])
-        outputs = self.model.predict(data['inputs'], self.tokenizer, output_style='json')
-        for i, output in enumerate(outputs):
-            lem = ' '.join([x['lex'] for x in output['tokens']])
-            ner = [
-                {
-                    'word': ' '.join([x['lex'] for x in output['tokens'][x['token_start']:x['token_end'] + 1]]),
-                    'entity_group': x['label'],
-                    'token_start': x['token_start'],
-                    'token_end': x['token_end']
-                }
-                for x in output['ner_entities']
-            ]
-            outputs[i] = {
-                'lex': lem,
-                'ner': ner
-            }
-        return outputs
+version https://git-lfs.github.com/spec/v1
+oid sha256:26ce128baa792901b22cecfdd6a7dc783307e60d4b766dcd3aa4d1eaeb3a36d2
+size 744148153