changeto run on GPU

app.py

@@ -11,16 +11,19 @@ tokenizer = AutoTokenizer.from_pretrained(model_name,use_fast=True)
 #model = AutoModelForSeq2SeqLM.from_pretrained(model_name) 
 model = AutoModelForCausalLM.from_pretrained(model_name,device_map="auto",trust_remote_code=False,revision="main")
 
+#transfer model on GPU
+model.to("cuda")
+
 # Generate text using the model and tokenizer
 def generate_text(input_text):
-    input_ids = tokenizer.encode(input_text, return_tensors="pt")
+    input_ids = tokenizer.encode(input_text, return_tensors="pt").to("cuda")
     #attention_mask = input_ids.ne(tokenizer.pad_token_id).long()
     output = model.generate(input_ids, max_new_tokens=512, top_k=50, top_p=0.95, temperature=0.7, do_sample=True)# attention_mask=attention_mask, max_length=100, num_return_sequences=1, no_repeat_ngram_size=2, top_k=50, top_p=0.95, temperature=0.7, do_sample=True)
     return tokenizer.decode(output[0])
 
 # Example of disabling Exllama backend (if applicable in your configuration)
-config = {"disable_exllama": True}
-model.config.update(config)
+#config = {"disable_exllama": True}
+#model.config.update(config)
 
 # def generate_text(prompt):
 #     inputs = tokenizer(prompt, return_tensors="pt", truncation=True, max_length=512, padding="max_length")