Update app.py

app.py

@@ -15,23 +15,7 @@ model = AutoModelForCausalLM.from_pretrained(
     checkpoint, device_map="auto", offload_folder="offload", trust_remote_code=True)
 
 # tokenizer = AutoTokenizer.from_pretrained(checkpoint, trust_remote_code=True, torch_dtype="auto")
-tokenizer = AutoTokenizer.from_pretrained(checkpoint, trust_remote_code=True)
-
-# model = AutoModelForCausalLM.from_pretrained(
-#     checkpoint, device_map="auto", 
-#     # offload_folder="off_load", 
-#     trust_remote_code=True,
-#     # torch_dtype="auto",
-# )
-# tokenizer = AutoTokenizer.from_pretrained(checkpoint, 
-#                                           trust_remote_code=True,
-#                                           torch_dtype="auto",
-#                                          )
-
-# model = "tiiuae/FalconLite2"
-# tokenizer = AutoTokenizer.from_pretrained(model, 
-#                                           torch_dtype="auto"
-#                                          )
+tokenizer = AutoTokenizer.from_pretrained(checkpoint, trust_remote_code=True)                                       )
 
 pipeline = transformers.pipeline(
     "text-generation",
@@ -42,58 +26,6 @@ pipeline = transformers.pipeline(
     device_map="auto",
 )
 
-# pipeline = transformers.pipeline(
-#     "text-generation",
-#     model=model,
-#     tokenizer=tokenizer,
-#     # use_safetensors=True, 
-#     # torch_dtype=torch.bfloat16,
-#     trust_remote_code=True,
-#     device_map="auto",
-#     offload_folder="off_load",
-#     # offload_state_dict = True,
-# )
-
-# def format_chat_prompt(message, chat_history):
-#     prompt = ""
-#     for turn in chat_history:
-#         user_message, bot_message = turn
-#         prompt = f"{prompt}\nUser: {user_message}\nAssistant: {bot_message}"
-#     prompt = f"{prompt}\nUser: {message}\nAssistant:"
-#     return prompt
-
-# def respond(message, chat_history):
-#         formatted_prompt = format_chat_prompt(message, chat_history)
-#         # print(formatted_prompt)
-#         bot_message = generate_seqs(prompt = formatted_prompt,
-#                                      max_new_tokens=1024,
-#                                      stop_sequence=["\nUser:", "<|endoftext|>"]).split('Assistant: ')[-1]
-
-#         chat_history.append((message, bot_message))
-#         return "", chat_history
-
-# def generate_seqs(prompt, max_new_tokens=None, stop_sequence=None):
-#     output = pipeline(prompt,
-#       max_length=200,
-#       max_new_tokens = max_new_tokens,
-#       stop_sequence = stop_sequence,
-#       do_sample=True,
-#       top_k=10,
-#       num_return_sequences=1,
-#       eos_token_id=tokenizer.eos_token_id)
-#     return output[0]['generated_text']
-
-# with gr.Blocks() as demo:
-#     chatbot = gr.Chatbot(height=240) #just to fit the notebook
-#     msg = gr.Textbox(label="Prompt")
-#     btn = gr.Button("Submit")
-#     clear = gr.ClearButton(components=[msg, chatbot], value="Clear console")
-
-#     btn.click(respond, inputs=[msg, chatbot], outputs=[msg, chatbot])
-#     msg.submit(respond, inputs=[msg, chatbot], outputs=[msg, chatbot]) #Press enter to submit
-# demo.launch()
-
-
 def format_chat_prompt(message, chat_history, instruction):
     prompt = f"System:{instruction}"
     for turn in chat_history: