import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = "GRMenon/mental-mistral-7b-instruct-autotrain"

tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
    model_path,
    device_map="auto",
    torch_dtype='auto'
).eval()

device = "cuda" if torch.cuda.is_available() else "cpu"

# Prompt content:
messages = [
    {"role": "user", "content": "Hey Connor! I have been feeling a bit down lately. I could really use some advice on how to feel better?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages,
                                          tokenize=True,
                                          add_generation_prompt=True,
                                          return_tensors='pt').to(device)
output_ids = model.generate(input_ids=input_ids,
                            max_new_tokens=512,
                            do_sample=True,
                            pad_token_id=2)
response = tokenizer.batch_decode(output_ids.detach().cpu().numpy(),
                                  skip_special_tokens = True)

# Model response: 
print(response[0])