Update app.py

app.py

@@ -22,7 +22,7 @@ MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 HF_TOKEN = os.getenv("HF_TOKEN")
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 
-model_name = "Qwen/Qwen2.5-1.5B-Instruct"
+model_name = "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"
 '''
 model = AutoModelForCausalLM.from_pretrained(
     model_name,
@@ -34,10 +34,10 @@ tokenizer = AutoTokenizer.from_pretrained(model_name)
 
 peft_model = AutoPeftModelForCausalLM.from_pretrained("ehristoforu/fd-lora-64x128", torch_dtype=torch.float16, trust_remote_code=True)
 merged_model = peft_model.merge_and_unload()
-#merged_model.save_pretrained("./coolqwen")
+merged_model.save_pretrained("./coolqwen")
 #model.save_pretrained("./coolqwen")
-#tokenizer.save_pretrained("./coolqwen")
-'''
+tokenizer.save_pretrained("./coolqwen")
+
 from huggingface_hub import HfApi
 
 api = HfApi()
@@ -46,11 +46,11 @@ api = HfApi()
 
 api.upload_folder(
     folder_path="./coolqwen",
-    repo_id="ehristoforu/Falcon3-with-lora-think-7b-it",
+    repo_id="ehristoforu/ehristoforu/fd-lora-merged-64x128",
     repo_type="model",
     token=HF_TOKEN,
 )
-'''
+
 
 @spaces.GPU()
 def generate(