chore: remove st

app.py

@@ -2,8 +2,6 @@
 import os
 from dotenv import load_dotenv
 
-st.set_page_config(page_title="Chat", page_icon=":page_facing_up:")
-
 load_dotenv()
 
 from huggingface_hub import login
@@ -13,58 +11,14 @@ login(token=os.getenv("HUGGINGFACEHUB_API_KEY"))
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import gradio as gr
 
+# # HuggingFaceTB/SmolLM2-135M-Instruct
 # model_name="deepseek-ai/DeepSeek-R1-Distill-Qwen-7B" # 15G
 model_name="meta-llama/Llama-3.2-3B-Instruct"   # 6.5G
 
-# # 
-# # HuggingFaceTB/SmolLM2-135M-Instruct
-# # deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
-# checkpoint = "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"
-# checkpoint = "meta-llama/Llama-3.2-3B-Instruct"   # 6.5G
 device = "mps"  # "cuda" or "cpu"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name).to(device)
 
-# def predict(message, history):
-#     history.append({"role": "user", "content": message})
-#     input_text = tokenizer.apply_chat_template(history, tokenize=False)
-#     inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)  
-#     outputs = model.generate(inputs, max_new_tokens=100, temperature=0.2, top_p=0.9, do_sample=True)
-#     decoded = tokenizer.decode(outputs[0])
-#     response = decoded.split("<|im_start|>assistant\n")[-1].split("<|im_end|>")[0]
-#     return response
-
-# demo = gr.ChatInterface(predict, type="messages")
-
-# demo.launch()
-
-# import os
-# from dotenv import load_dotenv
-
-# load_dotenv()
-
-# from huggingface_hub import login
-# login(token=os.getenv("HUGGINGFACEHUB_API_KEY"))
-
-# pipe = pipeline(model=model_name, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True)
-# prompt = """Let's go through this step-by-step:
-# 1. You start with 15 muffins.
-# 2. You eat 2 muffins, leaving you with 13 muffins.
-# 3. You give 5 muffins to your neighbor, leaving you with 8 muffins.
-# 4. Your partner buys 6 more muffins, bringing the total number of muffins to 14.
-# 5. Your partner eats 2 muffins, leaving you with 12 muffins.
-# If you eat 6 muffins, how many are left?"""
-
-# torch.device("mps")
-
-# pipeline = pipeline.to("mps")
-
-# outputs = pipe(prompt, max_new_tokens=20, do_sample=True, top_k=10)
-# print(f"processing")
-
-# for output in outputs:
-#     print(f"Result: {output['generated_text']}")
-
 system_prompt = (
     "You are a customer officer that helps extract transaction id from the USER INPUT and determine the transaction type based on the transaction id. "
     "To find transaction id, follow all the steps below: "