from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

device = 'cpu'

model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.1")
model.to('cpu')
tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.1")

vegeterian_recipe_prompt = """### Instruction: Act as a gourmet chef. 
I have a friend coming over who is a vegetarian.
I want to impress my friend with a special vegetarian dish. 
What do you recommend?

Give me two options, along with the whole recipe for each.

 ### Answer:
 """

encoded_instruction = tokenizer(vegeterian_recipe_prompt,  return_tensors="pt", add_special_tokens=True)

model_inputs = encoded_instruction.to(device)

generated_ids = model.generate(**model_inputs, max_new_tokens=500, do_sample=True, pad_token_id=tokenizer.eos_token_id)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])