import torch
from transformers import (AutoModelForCausalLM,
                         AutoTokenizer,
                         BitsAndBytesConfig,
                         TrainingArguments,
                         pipeline,
                         logging,
                         TrainerCallback)
device = "cuda" # the device to load the model onto
bnb_config = BitsAndBytesConfig(
    load_in_4bit = True,
    bnb_4bit_use_double_quant = False,
    bnb_4bit_quant_type = 'nf4',
    bnb_4bit_compute_dtype = getattr(torch, "float16")
)
model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2",quantization_config=bnb_config,)
tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2")

messages = [
    {"role": "user", "content": "What is your favourite condiment?"},
    {"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
    {"role": "user", "content": "Do you have mayonnaise recipes?"}
]

encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")

model_inputs = encodeds.to(device)
# model.to(device)

generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])