Update app.py

app.py

@@ -3,8 +3,8 @@ import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig,BitsAndBytesConfig
 
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-model = AutoModelForCausalLM.from_pretrained("models/TinyLlama/TinyLlama-1.1B-Chat-v1.0", trust_remote_code=True)
-tokenizer = AutoTokenizer.from_pretrained("models/TinyLlama/TinyLlama-1.1B-Chat-v1.0", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0", trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0", trust_remote_code=True)
 
 generation_config = GenerationConfig(
     penalty_alpha=0.6,