Update app.py

app.py

@@ -13,11 +13,11 @@ print("TORCH_CUDA", torch.cuda.is_available())
 
 print("loading model")
 # Load the tokenizer and model
-repo_name = "nvidia/Hymba-1.5B-Instruct"
+# repo_name = "nvidia/Hymba-1.5B-Instruct"
+repo_name = "HuggingFaceTB/SmolLM2-1.7B-Instruct"
 
 tokenizer = AutoTokenizer.from_pretrained(repo_name, trust_remote_code=True)
-#model = AutoModelForCausalLM.from_pretrained(repo_name, trust_remote_code=True)
-model = AutoModelForCausalLM.from_pretrained("HuggingFaceTB/SmolLM2-1.7B-Instruct", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(repo_name, trust_remote_code=True)
 
 model = model.cuda().to(torch.bfloat16)