Andyrasika/mistral-viggo-finetune

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig

base_model_id = "mistralai/Mistral-7B-v0.1"
bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_use_double_quant=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.bfloat16
)

base_model = AutoModelForCausalLM.from_pretrained(
    base_model_id,  # Mistral, same as before
    quantization_config=bnb_config,  # Same quantization config as before
    device_map="auto",
    trust_remote_code=True,
    use_auth_token=True
)

eval_tokenizer = AutoTokenizer.from_pretrained(
    base_model_id,
    add_bos_token=True,
    trust_remote_code=True,
)

Now load the QLoRA adapter from the appropriate checkpoint directory

from peft import PeftModel

ft_model = PeftModel.from_pretrained(base_model, "mistral-viggo-finetune/checkpoint-950")

Let's try the same eval_prompt and thus model_input as above, and see if the new finetuned model performs better.

eval_prompt = """Given a target sentence construct the underlying meaning representation of the input sentence as a single function with attributes and attribute values.
This function should describe the target string accurately and the function must be one of the following ['inform', 'request', 'give_opinion', 'confirm', 'verify_attribute', 'suggest', 'request_explanation', 'recommend', 'request_attribute'].
The attributes must be one of the following: ['name', 'exp_release_date', 'release_year', 'developer', 'esrb', 'rating', 'genres', 'player_perspective', 'has_multiplayer', 'platforms', 'available_on_steam', 'has_linux_release', 'has_mac_release', 'specifier']

### Target sentence:
Earlier, you stated that you didn't have strong feelings about PlayStation's Little Big Adventure. Is your opinion true for all games which don't have multiplayer?

### Meaning representation:
"""

model_input = tokenizer(eval_prompt, return_tensors="pt").to("cuda")

ft_model.eval()
with torch.no_grad():
    print(eval_tokenizer.decode(ft_model.generate(**model_input, max_new_tokens=100)[0], skip_special_tokens=True))