update inference with transformers

README.md

@@ -51,9 +51,8 @@ print(result)
 ```py
 from transformers import AutoModelForCausalLM
  
-model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2")
-model.to("cuda")
- 
+model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2", device_map="auto")
+tokens = torch.tensor(tokens).view(1, -1) 
 generated_ids = model.generate(tokens, max_new_tokens=1000, do_sample=True)
 
 # decode with mistral tokenizer