Update app.py

app.py

@@ -6,7 +6,13 @@ from vllm import LLM, SamplingParams
 # 1) Load the Model
 # ------------------------
 # Download the model repository, specify revision if needed
-model_dir = snapshot_download(repo_id="BSC-LT/salamandraTA-7B-instruct-GGUF", revision="main")
+model_dir = snapshot_download(repo_id="BSC-LT/salamandraTA-7B-instruct-GGUF", revision="main",     allow_patterns=[
+                                                                                                                    "salamandrata_7b_inst_q4.gguf", 
+                                                                                                                    "*tokenizer*", 
+                                                                                                                    "tokenizer_config.json", 
+                                                                                                                    "tokenizer.model", 
+                                                                                                                    "config.json",
+                                                                                                                ])
 model_name = "salamandrata_7b_inst_q4.gguf"
 
 # Create an LLM instance from vLLM