Update README.md

README.md

@@ -59,14 +59,11 @@ To run inference with the model in full `bfloat16` precision you need approximat
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import transformers
 import torch
-from peft import PeftModel
 
-model = "tiiuae/falcon-40B"
-adapters_name = 'vilm/vulture-40B'
+model = "vilm/vulture-40B"
 
 tokenizer = AutoTokenizer.from_pretrained(model)
 m = AutoModelForCausalLM.from_pretrained(model, torch_dtype=torch.bfloat16, device_map="auto" )
-m = PeftModel.from_pretrained(m, adapters_name)
 
 prompt = "A chat between a curious user and an artificial intelligence assistant.\n\nUSER:Thành phố Hồ Chí Minh nằm ở đâu?<|endoftext|>ASSISTANT:"