update

main.py

@@ -27,18 +27,18 @@ def get_prompt(user_query: str, functions: list = []) -> str:
     return f"USER: <<question>> {user_query} <<function>> {functions_string}\nASSISTANT: "
 
 device : str = "cuda:0" if torch.cuda.is_available() else "cpu"
+log('Device: ' + device)
 torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
 
 result = subprocess.run('pwd && ls -lH && find /.cache/huggingface/hub && find /.cache/gorilla', shell=True, capture_output=True, text=True)
 log(result.stdout)
 
-model_id : str = "gorilla-llm/gorilla-openfunctions-v1"
+#model_id : str = "gorilla-llm/gorilla-openfunctions-v1"
+model_id : str = "M-FAC/bert-tiny-finetuned-mrpc"
 log('AutoTokenizer.from_pretrained ...')
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 log('AutoModelForCausalLM.from_pretrained ...')
 model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True)
-log('AutoModelForCausalLM.save_pretrained ...')
-model.save_pretrained('/.cache/gorilla')
 
 result = subprocess.run('pwd && ls -lH && find /.cache/huggingface/hub && find /.cache/gorilla', shell=True, capture_output=True, text=True)
 log(result.stdout)