Upload code/ with huggingface_hub

code/inference.py

@@ -268,12 +268,6 @@ def pipelinex(
 
 
 
-logger = logging.getLogger(__name__)
-logger.setLevel(logging.DEBUG)
-
-JSON_CONTENT_TYPE = 'application/json'
-
-    
 
 # loads the model into memory from disk and returns it
 def model_fn(model_dir):
@@ -285,32 +279,16 @@ def model_fn(model_dir):
 
 
 # Perform prediction on the deserialized object, with the loaded model
-def predict_fn(input, model,tokenizer):
-    
+def predict_fn(data, model_tokenizer):
     
+    model,tokenizer = model_tokenizer 
     
-    logger.info("Calling model")
-    start_time = time.time()
-     #pipelines.py script in the cloned repo
     multimodel = pipelinex("multitask-qa-qg",tokenizer=tokenizer,model=model)
-    answers = multimodel(input)
-    print("--- Inference time: %s seconds ---" % (time.time() - start_time))
-
+    answers = multimodel(data)
+ 
     
     return answers
-# Deserialize the Invoke request body into an object we can perform prediction on
-def input_fn(request_body, content_type=JSON_CONTENT_TYPE):
-    logger.info('Deserializing the input data.')
-    # process an jsonlines uploaded to the endpoint
-    if content_type == JSON_CONTENT_TYPE: return request_body["text"]   
-    raise Exception('Requested unsupported ContentType in content_type: {}'.format(content_type))
-    
-# Serialize the prediction result into the desired response content type
-def output_fn(prediction, accept=JSON_CONTENT_TYPE):        
-    logger.info('Serializing the generated output.')
-    if accept == JSON_CONTENT_TYPE: return json.dumps(prediction), accept
-    raise Exception('Requested unsupported ContentType in Accept: {}'.format(accept))    
-    
+