Update app.py

app.py

@@ -1,70 +1,31 @@
 import gradio as gr
-# from huggingface_hub import InferenceClient
+# from unsloth import FastLanguageModel
+# import torch
+# from transformers import TextStreamer
+
+# # Define the model name and other parameters
+# model_name = "imsanjoykb/deepSQL-R1-distill-8B"
+# max_seq_length = 2048
+# dtype = None
+# load_in_4bit = True
+
+# # Initialize model and tokenizer to None
+# model = None
+# tokenizer = None
+
+# # Try to load the model and tokenizer from Hugging Face
+# try:
+#     model, tokenizer = FastLanguageModel.from_pretrained(
+#         model_name=model_name,
+#         max_seq_length=max_seq_length,
+#         dtype=dtype,
+#         load_in_4bit=load_in_4bit,
+#     )
+#     # Enable faster inference
+#     FastLanguageModel.for_inference(model)
+# except Exception as e:
+#     print(f"Failed to load model: {e}")
 
-# """
-# For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-# """
-# client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-# def respond(
-#     message,
-#     history: list[tuple[str, str]],
-#     system_message,
-#     max_tokens,
-#     temperature,
-#     top_p,
-# ):
-#     messages = [{"role": "system", "content": system_message}]
-
-#     for val in history:
-#         if val[0]:
-#             messages.append({"role": "user", "content": val[0]})
-#         if val[1]:
-#             messages.append({"role": "assistant", "content": val[1]})
-
-#     messages.append({"role": "user", "content": message})
-
-#     response = ""
-
-#     for message in client.chat_completion(
-#         messages,
-#         max_tokens=max_tokens,
-#         stream=True,
-#         temperature=temperature,
-#         top_p=top_p,
-#     ):
-#         token = message.choices[0].delta.content
-
-#         response += token
-#         yield response
-
-
-# """
-# For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-# """
-# demo = gr.ChatInterface(
-#     respond,
-#     additional_inputs=[
-#         gr.Textbox(value="You are a friendly SQL Chatbot.", label="System message"),
-#         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-#         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-#         gr.Slider(
-#             minimum=0.1,
-#             maximum=1.0,
-#             value=0.95,
-#             step=0.05,
-#             label="Top-p (nucleus sampling)",
-#         ),
-#     ],
-# )
-
-
-# if __name__ == "__main__":
-#     demo.launch()
-
-# Import necessary libraries
-import gradio as gr
 
 # Define the prompt template
 odoo_text2sql_prompt = """