Update app.py

app.py

@@ -1,10 +1,13 @@
+import os
 import spaces
 import torch
 import transformers
 import gradio as gr
 
-# from airllm import HuggingFaceModelLoader, AutoModelForCausalLM
+from dotenv import load_dotenv
 
+load_dotenv()
+access_token = os.("HF_ACCESS_TOKEN")
 model_id = "meta-llama/Meta-Llama-3.1-8B-Instruct"
 
 pipeline = transformers.pipeline(
@@ -12,6 +15,7 @@ pipeline = transformers.pipeline(
     model=model_id,
     model_kwargs={"torch_dtype": torch.bfloat16},
     device_map="auto",
+    token=HF_ACCESS_TOKEN
 )
 
 @spaces.GPU
@@ -21,19 +25,6 @@ def generate_text(input_text):
     output = pipeline(prompt, 
                       max_new_tokens=256,
                      )
-    # input_tokens = model.tokenizer(input_text,
-    #                                return_tensors="np", 
-    #                                return_attention_mask=False, 
-    #                                truncation=True, 
-    #                                max_length=MAX_LENGTH, 
-    #                                padding=False)
-
-               
-    # output = model.generate(mx.array(input_tokens['input_ids']),
-    #                                    max_new_tokens=20,
-    #                                    use_cache=True,
-    #                                    return_dict_in_generate=True)
-
     return output