Intelligence with a human temperature

import torch
from transformers import AutoModel, AutoTokenizer

repo = "cheonai/cheon-reranker-0.6b-v1"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModel.from_pretrained(repo, trust_remote_code=True, torch_dtype=torch.float32)
model.eval()

# Query + candidates go into one sequence. Track each candidate's token span
# as you build it instead of hardcoding positions. Candidates don't need to
# share a language - the tokenizer and span logic don't care.
query = "query: 이 사건의 처리 기한은 언제까지인가요?\n"
candidates = [
    "candidate (en): The appeal must be filed within 30 days of the decision.",
    "candidate (ko): 이의신청은 처분을 안 날부터 30일 이내에 제기해야 합니다.",
    "candidate (zh): 上诉必须在裁定后30天内提出。",
    "candidate (ja): 不服申立ては、決定を知った日から30日以内に行う必要があります。",
]

ids = tok(query, add_special_tokens=False)["input_ids"]
doc_spans = []
for text in candidates:
    piece = tok(text, add_special_tokens=False)["input_ids"]
    start = len(ids)
    ids += piece
    doc_spans.append((start, len(ids)))

input_ids = torch.tensor([ids])
attention_mask = torch.ones_like(input_ids)
corpus_ids = [0] * len(candidates)  # optional per-candidate corpus/collection tag

with torch.no_grad():
    scores = model(
        input_ids=input_ids,
        attention_mask=attention_mask,
        doc_spans=doc_spans,
        corpus_ids=corpus_ids,
    )
print(scores)  # higher = more relevant