tmp: use `trust_remote_code=True` flag

README.md

@@ -34,6 +34,7 @@ tokenizer = AutoTokenizer.from_pretrained("stabilityai/stablelm-2-12b")
 model = AutoModelForCausalLM.from_pretrained(
   "stabilityai/stablelm-2-12b",
   torch_dtype="auto",
+  trust_remote_code=True
 )
 model.cuda()
 inputs = tokenizer("The weather is always wonderful", return_tensors="pt").to(model.device)
@@ -59,6 +60,7 @@ model = AutoModelForCausalLM.from_pretrained(
   "stabilityai/stablelm-2-12b",
   torch_dtype="auto",
   attn_implementation="flash_attention_2",
+  trust_remote_code=True
 )
 model.cuda()
 inputs = tokenizer("The weather is always wonderful", return_tensors="pt").to(model.device)