Update app.py

app.py

@@ -6,21 +6,23 @@ import gradio as gr
 import spaces
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
+from huggingface_hub import login
+login(token="HUGGINGFACE_API_TOKEN")
 
 MAX_MAX_NEW_TOKENS = 2048
 DEFAULT_MAX_NEW_TOKENS = 1024
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 
-#if not torch.cuda.is_available():
-#    DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>"
+if not torch.cuda.is_available():
+    DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>"
 
 
-#if torch.cuda.is_available():
-#    model_id = "mistralai/Mistral-7B-Instruct-v0.2"
- #   model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", load_in_4bit=True)
-  #  tokenizer = AutoTokenizer.from_pretrained(model_id)
-   # tokenizer.use_default_system_prompt = False
+if torch.cuda.is_available():
+    model_id = "mistralai/Mistral-7B-Instruct-v0.2"
+    model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", load_in_4bit=True)
+    tokenizer = AutoTokenizer.from_pretrained(model_id)
+    tokenizer.use_default_system_prompt = False
 
 
 @spaces.GPU