Update app.py

app.py

@@ -9,10 +9,10 @@ from transformers import AutoTokenizer, AutoConfig, LlamaForCausalLM, LlamaToken
 
 auth_token = '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' #= os.environ.get("TOKEN_FROM_SECRET")
 
-tokenizer = LlamaTokenizer.from_pretrained("Claimed/capybara", use_auth_token=auth_token)
+# tokenizer = LlamaTokenizer.from_pretrained("Claimed/capybara", use_auth_token=auth_token)
 
-model = LlamaForCausalLM.from_pretrained(
-    "Claimed/capybara", use_auth_token=auth_token)
+# model = LlamaForCausalLM.from_pretrained(
+#     "Claimed/capybara", use_auth_token=auth_token)
 #model = model.to('cuda')
 
 
@@ -76,53 +76,53 @@ def classifier(userin):
     return broad_scope_predictions[1]
     
 
-def generateresponse(history):
-    """
-    Model definition here:
-    """
-    '''
-    global model
-    global tokenizer
-
-    PROMPT = f"""Below is an instruction that describes a task. Write a response that appropriately completes the request.
-    ### Instruction:
-    {user}
-    ### Response:"""
-
-    inputs = tokenizer(
-        PROMPT,
-        return_tensors="pt",
-    )
-    input_ids = inputs["input_ids"].cuda()
-
-    generation_config = GenerationConfig(
-        temperature=0.6,
-        top_p=0.95,
-        repetition_penalty=1.15,
-    )
-    print("Generating...")
-    generation_output = model.generate(
-        input_ids=input_ids,
-        generation_config=generation_config,
-        return_dict_in_generate=True,
-        output_scores=True,
-        max_new_tokens=256,
-    )
-    output = []
-    for s in generation_output.sequences:
-        outputs.append(tokenizer.decode(s))
-        print(tokenizer.decode(s))
+# def generateresponse(history):
+#     """
+#     Model definition here:
+#     """
+#     '''
+#     global model
+#     global tokenizer
+
+#     PROMPT = f"""Below is an instruction that describes a task. Write a response that appropriately completes the request.
+#     ### Instruction:
+#     {user}
+#     ### Response:"""
+
+#     inputs = tokenizer(
+#         PROMPT,
+#         return_tensors="pt",
+#     )
+#     input_ids = inputs["input_ids"].cuda()
+
+#     generation_config = GenerationConfig(
+#         temperature=0.6,
+#         top_p=0.95,
+#         repetition_penalty=1.15,
+#     )
+#     print("Generating...")
+#     generation_output = model.generate(
+#         input_ids=input_ids,
+#         generation_config=generation_config,
+#         return_dict_in_generate=True,
+#         output_scores=True,
+#         max_new_tokens=256,
+#     )
+#     output = []
+#     for s in generation_output.sequences:
+#         outputs.append(tokenizer.decode(s))
+#         print(tokenizer.decode(s))
     
-    output = (outputs[0].split('### Response:'))[1]
+#     output = (outputs[0].split('### Response:'))[1]
 
-    '''
+#     '''
 
-    user = history[-1][0]
+    # user = history[-1][0]
     
-    response = f"You asked: {user}"
-    history[-1][1] = response
-    print(history)
-    return history
+    # response = f"You asked: {user}"
+    # history[-1][1] = response
+    # print(history)
+    # return history
 
 
 theme = gr.themes.Base(
@@ -206,7 +206,7 @@ with gr.Blocks(title='Claimed', theme=theme) as demo:
 
     with gr.Tab("CPC Classifier"):
         gr.Markdown("""
-        Use this tool to classify your invention according to Cooperative Patent Classification system. 
+        Use this tool to classify your invention according to the Cooperative Patent Classification system. 
         
         """)
         with gr.Row(scale=1, min_width=600):
@@ -240,9 +240,9 @@ with gr.Blocks(title='Claimed', theme=theme) as demo:
         with gr.Column(scale=0.15, min_width=0):
             btn = gr.Button("Submit")
 
-    txt.submit(add_text, [chatbot, txt], [chatbot, txt]).then(
-        generateresponse, chatbot, chatbot
-    )
+    # txt.submit(add_text, [chatbot, txt], [chatbot, txt]).then(
+    #     generateresponse, chatbot, chatbot
+    # )
 
     gr.Markdown("""
     # HAVE AN IDEA? GET IT CLAIMED