XGLM-564M

from openmind import AutoTokenizer, AutoModelForCausalLM, is_torch_npu_available
from openmind_hub import snapshot_download
import torch.nn.functional as F
from torch import Tensor
import openmind
import torch
import argparse

def get_logprobs(prompt):
        inputs = tokenizer(prompt, return_tensors="pt")
        input_ids, output_ids = inputs["input_ids"], inputs["input_ids"][:, 1:]
        outputs = model(**inputs, labels=input_ids)
        logits = outputs.logits
        logprobs = torch.gather(F.log_softmax(logits, dim=2), 2, output_ids.unsqueeze(2))
        return logprobs

# Zero-shot evaluation for the Choice of Plausible Alternatives (COPA) task.
# A return value of 0 indicates that the first alternative is more plausible,
# while 1 indicates that the second alternative is more plausible.
def COPA_eval(prompt, alternative1, alternative2):
    lprob1 = get_logprobs(prompt + "\n" + alternative1).sum()
    lprob2 = get_logprobs(prompt + "\n" + alternative2).sum()
    return 0 if lprob1 > lprob2 else 1

def parse_args():
    parser = argparse.ArgumentParser()
    parser.add_argument(
        "--model_name_or_path",
        type=str,
        help="Path to model",
        default="jeffding/xglm-564M-openmind",
    )
    args = parser.parse_args()
    return args


args = parse_args()
model_path = args.model_name_or_path

if is_torch_npu_available():
    device = "npu:0"
else:
    device = "cpu"
        
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path)

data_samples = {
    'en': [
        {
            "premise": "I wanted to conserve energy.",
            "choice1": "I swept the floor in the unoccupied room.",
            "choice2": "I shut off the light in the unoccupied room.",
            "question": "effect",
            "label": "1"
        },
        {
            "premise": "The flame on the candle went out.",
            "choice1": "I blew on the wick.",
            "choice2": "I put a match to the wick.",
            "question": "cause",
            "label": "0"
        }
    ],
    'zh': [
        {
            "premise": "我想节约能源。",
            "choice1": "我在空着的房间里扫了地板。",
            "choice2": "我把空房间里的灯关了。",
            "question": "effect",
            "label": "1"
        },
        {
            "premise": "蜡烛上的火焰熄灭了。",
            "choice1": "我吹灭了灯芯。",
            "choice2": "我把一根火柴放在灯芯上。",
            "question": "cause",
            "label": "0"
        }
    ],
    'hi': [
        {
            "premise": "M te vle konsève enèji.",
            "choice1": "Mwen te fin baleye chanm lib la.",
            "choice2": "Mwen te femen limyè nan chanm lib la.",
            "question": "effect",
            "label": "1"
        },
        {
            "premise": "Flam bouji a te etenn.",
            "choice1": "Mwen te soufle bouji a.",
            "choice2": "Mwen te limen mèch bouji a.",
            "question": "cause",
            "label": "0"
        }
    ]
}



for lang in data_samples:
    for idx, example in enumerate(data_samples[lang]):
        predict = COPA_eval(example["premise"], example["choice1"], example["choice2"])
        print(f'{lang}-{idx}', predict, example['label'])