Update run_inference.py

run_inference.py

@@ -1,11 +1,13 @@
 from peft import AutoPeftModelForCausalLM
 from transformers import AutoTokenizer
-import re
+
+from huggingface_hub import login
+login("YOUR TOKEN HERE")
 
 
 PROMPT = "[INST]YOUR PROMPT HERE[/INST]"
 MAX_LENGTH = 32768  # Do not change
-DEVICE = "cuda"
+DEVICE = "cpu"
 
 
 model_id = "agarkovv/CryptoTrader-LM"
@@ -27,5 +29,4 @@ res = model.generate(
     max_new_tokens=MAX_LENGTH,
 )
 output = tokenizer.decode(res[0], skip_special_tokens=True)
-answer = re.sub(r".*\[/INST\]\s*", "", output, flags=re.DOTALL)
-print(answer)
+print(output)