revert back changes

app.py

@@ -4,35 +4,9 @@ import requests
 import pytz
 import yaml
 from tools.final_answer import FinalAnswerTool
-from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 
 from Gradio_UI import GradioUI
 
-# Load the model locally
-model_id = "Qwen/Qwen2-7B"  # Replace with any local model
-
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id)
-
-# Create a local pipeline
-llm_pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer)
-
-class LocalModel:
-    def __init__(self, pipeline, max_tokens=2096, temperature=0.5):
-        self.pipeline = pipeline
-        self.max_tokens = max_tokens
-        self.temperature = temperature
-
-    def chat(self, prompt: str):
-        response = self.pipeline(
-            prompt,
-            max_new_tokens=self.max_tokens,
-            temperature=self.temperature,
-            do_sample=True
-        )
-        return response[0]["generated_text"]
-
-
 # Below is an example of a tool that does nothing. Amaze us with your creativity !
 @tool
 def my_custom_tool(arg1:str, arg2:int)-> str: #it's import to specify the return type
@@ -65,14 +39,12 @@ final_answer = FinalAnswerTool()
 # If the agent does not answer, the model is overloaded, please use another model or the following Hugging Face Endpoint that also contains qwen2.5 coder:
 # model_id='https://pflgm2locj2t89co.us-east-1.aws.endpoints.huggingface.cloud' 
 
-# model = HfApiModel(
-# max_tokens=2096,
-# temperature=0.5,
-# model_id='Qwen/Qwen2.5-Coder-32B-Instruct',# it is possible that this model may be overloaded
-# custom_role_conversions=None,
-# )
-
-model = LocalModel(llm_pipeline)
+model = HfApiModel(
+max_tokens=2096,
+temperature=0.5,
+model_id='Qwen/Qwen2.5-Coder-32B-Instruct',# it is possible that this model may be overloaded
+custom_role_conversions=None,
+)
 
 
 # Import tool from Hub