import numpy as np

results = []
inputs_with_offsets = tokenizer(example, return_offsets_mapping=True)
tokens = inputs_with_offsets.tokens()
offsets = inputs_with_offsets["offset_mapping"]

idx = 0
while idx < len(predictions):
    pred = predictions[idx]
    label = model.config.id2label[pred]
    if label != "O":
        # Remove the B- or I-
        label = label[2:]
        start, _ = offsets[idx]

        # Grab all the tokens labeled with I-label
        all_scores = []
        while (
            idx < len(predictions)
            and model.config.id2label[predictions[idx]] == f"I-{label}"
        ):
-           all_scores.append(probabilities[idx][pred])
+           all_scores.append(probs[idx][predictions[idx]])
            _, end = offsets[idx]
            idx += 1

        # The score is the mean of all the scores of the tokens in that grouped entity
        score = np.mean(all_scores).item()
        word = example[start:end]
        results.append(
            {
                "entity_group": label,
                "score": score,
                "word": word,
                "start": start,
                "end": end,
            }
        )
    idx += 1

print(results)

candidates = []
for start_probs, end_probs in zip(start_probabilities, end_probabilities):
    scores = start_probs[:, None] * end_probs[None, :]
    idx = torch.triu(scores).argmax().item()

-   start_idx = idx // scores.shape[0]
-   end_idx = idx % scores.shape[0]
+   start_idx = idx // scores.shape[1]
+   end_idx = idx % scores.shape[1]
    score = scores[start_idx, end_idx].item()
    candidates.append((start_idx, end_idx, score))

print(candidates)