import os
os.environ["HF_HUB_OFFLINE"] = "1"
os.environ["TRANSFORMERS_OFFLINE"] = "1"
MODEL_ID = "."

import json
import pandas as pd
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

tok = AutoTokenizer.from_pretrained(MODEL_ID)
model = AutoModelForCausalLM.from_pretrained(
    MODEL_ID, torch_dtype=torch.float16, device_map="auto"
).eval()

df = pd.read_csv("/tmp/data/test.csv", dtype=str).fillna("")

rows = []
for _, r in df.iterrows():
    messages = [
        {"role": "system", "content":
            "You solve International Linguistics Olympiad problems. Answer every numbered "
            "item. Put each answer on its own line, in order, with no numbering and no extra text."},
        {"role": "user", "content": f"{r['context'].strip()}\n\n{r['query'].strip()}"},
    ]
    enc = tok.apply_chat_template(
        messages, add_generation_prompt=True, return_tensors="pt", return_dict=True,
    ).to(model.device)
    with torch.no_grad():
        out = model.generate(**enc, max_new_tokens=512, do_sample=False)
    text = tok.decode(out[0][enc["input_ids"].shape[-1]:], skip_special_tokens=True).strip()
    answers = [ln.strip() for ln in text.splitlines() if ln.strip()]
    rows.append({"id": r["id"], "pred": json.dumps(answers, ensure_ascii=False)})
    print(f"{len(rows)}/{len(df)} done", flush=True)

pd.DataFrame(rows).to_csv("submission.csv", index=False)
print("wrote submission.csv", flush=True)