Update app.py

app.py

@@ -1,16 +1,16 @@
-#import os
+import os
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import gradio as gr
-#hf_token = os.getenv("hftoken")
+hf_token = os.getenv("hftoken")
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") 
 
 
 b_tokenizer = AutoTokenizer.from_pretrained("bigscience/bloom-560m")#using small parameter version of model for faster inference on hf
 b_model = AutoModelForCausalLM.from_pretrained("bigscience/bloom-560m")
 
-g_tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-2b")#using small paramerter version of model for faster inference on hf
-g_model = AutoModelForCausalLM.from_pretrained("google/gemma-2-2b")
+g_tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-2b",token = hf_token)#using small paramerter version of model for faster inference on hf
+g_model = AutoModelForCausalLM.from_pretrained("google/gemma-2-2b",token = hf_token)
 
 def Sentence_Commpletion(model_name, input):