test with dbert-base

handler.py

@@ -1,22 +1,29 @@
 from typing import  Dict, List, Any
+# import torch
+from transformers import DistilBertTokenizer, DistilBertForSequenceClassification
+
+
 # from optimum.onnxruntime import ORTModelForSequenceClassification
 from transformers import AutoModel
 # from transformers import AutoModelForSequenceClassification, AutoTokenizer
 
 from transformers import pipeline, AutoTokenizer
 
-checkpoint = "distilbert-base-uncased-finetuned-sst-2-english"
+# checkpoint = "distilbert-base-uncased-finetuned-sst-2-english"
+checkpoint = "distilbert-base-uncased"
 
 class EndpointHandler():
     
     def __init__(self, path=""):
         # load the optimized model
         # model = ORTModelForSequenceClassification.from_pretrained(path)
-        model = AutoModel.from_pretrained(checkpoint)
+        # model = AutoModel.from_pretrained(checkpoint)
         # model = AutoModelForSequenceClassification.from_pretrained(checkpoint)
 
         # tokenizer = AutoTokenizer.from_pretrained(path)
-        tokenizer = AutoTokenizer.from_pretrained(pretrained_model_name_or_path=checkpoint)
+        # tokenizer = AutoTokenizer.from_pretrained(pretrained_model_name_or_path=checkpoint)
+        model = DistilBertForSequenceClassification.from_pretrained(checkpoint)
+        tokenizer = DistilBertTokenizer.from_pretrained(checkpoint)
 
         # create inference pipeline
         self.pipeline = pipeline("text-classification", model=model, tokenizer=tokenizer)

model.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4ff21bc94e07b6a5b20db9d5ffc692adb220989684a59aee0a11b78607dc4560
-size 172529172

requirements.txt

@@ -5,4 +5,5 @@ mkl
 # spacy
 transformers
 datasets
-evaluate
+evaluate
+# torch