Update app.py

app.py

@@ -2,30 +2,16 @@
 import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 import torch
-from huggingface_hub import HfApi, HfFolder
-
-# Replace '<your_api_token>' with your actual API token
-api_token = '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'
-
-# Initialize the HfApi with the API token
-api = HfApi(token=api_token)
-print('loggedin')
-# Verify that you're logged in
-user = api.whoami()
-print(user)
 # Load model and tokenizer
 model_name = "meta-llama/Llama-2-7b-chat-hf"
 print("started loading model")
 
-api_token = "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"  # Replace with your actual API token
-
 model = AutoModelForCausalLM.from_pretrained(
     model_name,
     low_cpu_mem_usage=True,
     return_dict=True,
 
-    revision="main",  # Or the desired revision
-    token=api_token
+    revision="main", 
 )
     # return_dict=True,
     # torch_dtype=torch.float16,
@@ -33,8 +19,6 @@ print("loaded model")
 
 tokenizer = AutoTokenizer.from_pretrained(
     model_name,
-    revision="main", 
-    token=api_token
     # Or the desired revision
 )