初始化项目，由ModelHub XC社区提供模型

Model: Lipas007/iol-ai-2026-qwen14b-awq
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2024 Alibaba Cloud
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -0,0 +1,5 @@
+# IOL-AI 2026 submission
+
+- Base weights: `Qwen/Qwen2.5-14B-Instruct-AWQ`
+- Entry point: `script.py` (loads from `.`, offline)
+- Helper: `iol_utils.py`

config.json

@@ -0,0 +1,35 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "quantization_config": {
+    "bits": 4,
+    "group_size": 128,
+    "modules_to_not_convert": null,
+    "quant_method": "awq",
+    "version": "gemm",
+    "zero_point": true
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.41.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.41.1"
+}

iol_utils.py

@@ -0,0 +1,46 @@
+"""Safe post-parse normalizers for IOL-AI 2026 (v8+).
+
+Only match_letters / text_to_num. Never force list arity.
+"""
+
+from __future__ import annotations
+
+import re
+from typing import List
+
+
+def normalize_match_letter(ans: str) -> str:
+    ans = ans.strip()
+    m = re.fullmatch(r"[\(\[]?([A-Za-z])[\)\]]?[.)]?", ans)
+    if m:
+        return m.group(1).upper()
+    tokens = re.findall(r"\b([A-Za-z])\b", ans)
+    if tokens:
+        return tokens[-1].upper()
+    m = re.search(r"[A-Za-z]", ans)
+    return m.group(0).upper() if m else ans
+
+
+def normalize_text_to_num(ans: str) -> str:
+    a = re.sub(r"(?i)^(answer|ans|result)\s*[:=]\s*", "", ans.strip()).strip()
+    if re.fullmatch(r"[\d\s+\-*/^=()]+", a.replace(",", "")):
+        a = a.replace(",", "").replace(" ", "")
+        if "=" in a and " = " not in a:
+            a = a.replace("=", " = ")
+        return a.strip()
+    m = re.search(r"\d+", a)
+    return m.group(0) if m and len(a) < 40 else a
+
+
+def safe_normalize_answers(answers: List[str], task_type: str) -> List[str]:
+    """Per-line only. Does not pad/truncate. No-op for other task types."""
+    task_type = (task_type or "").strip().lower()
+    out: List[str] = []
+    for a in answers:
+        a = a.strip()
+        if task_type == "match_letters":
+            a = normalize_match_letter(a)
+        elif task_type == "text_to_num":
+            a = normalize_text_to_num(a)
+        out.append(a)
+    return out

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e874dc3b1febb5b22fe74a8793066ae430d90cdbc51765d0a4eb44a82a1fbbd
+size 3988804408

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3b25da74cc854cdc726956f8152f1dda8519c7bb7d4724ac12c1312463e61c8
+size 3968309440

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25b97bf28033ed4560387293ce76bd3dc55a22882fea005a10c137b6478dae85
+size 2023056736

script.py

@@ -0,0 +1,252 @@
+#!/usr/bin/env python3
+"""IOL-AI 2026 — v8 normal (pred) + explanation por problema (no hardcode).
+
+Fase 1: prompt/parse EXACTOS de script_submission8.py → pred (score).
+Fase 2: si sobra tiempo, 1 frase de explicación por fila (generate corto).
+Si no hay tiempo: explicación hecha del propio problema (task/lang/query),
+distinta en cada fila — nunca la misma frase estática para todas.
+"""
+
+from __future__ import annotations
+
+import json
+import os
+import re
+import time
+from pathlib import Path
+from typing import List
+
+os.environ["HF_HUB_OFFLINE"] = "1"
+os.environ["TRANSFORMERS_OFFLINE"] = "1"
+
+MODEL_ID = os.environ.get("IOL_MODEL", ".")
+INPUT_CSV = Path(os.environ.get("IOL_INPUT", "/tmp/data/test.csv"))
+OUTPUT_CSV = Path(os.environ.get("IOL_OUTPUT", "submission.csv"))
+SOFT_DEADLINE = float(os.environ.get("IOL_SOFT_DEADLINE", "1650"))
+WRITE_EXPLANATIONS = os.environ.get("IOL_EXPLANATIONS", "1") != "0"
+MAX_NEW = int(os.environ.get("IOL_MAX_NEW_TOKENS", "512"))
+EXPL_MAX_NEW = int(os.environ.get("IOL_EXPL_MAX_NEW", "48"))
+EXPL_STOP_LEFT = float(os.environ.get("IOL_EXPL_STOP_LEFT", "20"))
+
+SYSTEM_V8 = (
+    "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."
+)
+
+
+def normalize_match_letter(ans: str) -> str:
+    ans = ans.strip()
+    m = re.fullmatch(r"[\(\[]?([A-Za-z])[\)\]]?[.)]?", ans)
+    if m:
+        return m.group(1).upper()
+    tokens = re.findall(r"\b([A-Za-z])\b", ans)
+    if tokens:
+        return tokens[-1].upper()
+    m = re.search(r"[A-Za-z]", ans)
+    return m.group(0).upper() if m else ans
+
+
+def normalize_text_to_num(ans: str) -> str:
+    a = re.sub(r"(?i)^(answer|ans|result)\s*[:=]\s*", "", ans.strip()).strip()
+    if re.fullmatch(r"[\d\s+\-*/^=()]+", a.replace(",", "")):
+        a = a.replace(",", "").replace(" ", "")
+        if "=" in a and " = " not in a:
+            a = a.replace("=", " = ")
+        return a.strip()
+    m = re.search(r"\d+", a)
+    return m.group(0) if m and len(a) < 40 else a
+
+
+def safe_normalize_answers(answers: List[str], task_type: str) -> List[str]:
+    task_type = (task_type or "").strip().lower()
+    out: List[str] = []
+    for a in answers:
+        a = a.strip()
+        if task_type == "match_letters":
+            a = normalize_match_letter(a)
+        elif task_type == "text_to_num":
+            a = normalize_text_to_num(a)
+        out.append(a)
+    return out
+
+
+def expl_from_problem(r, answers: List[str]) -> str:
+    """Per-row explanation from the problem itself (no shared canned sentence)."""
+    tt = str(r.get("task_type", "")).strip() or "linguistics"
+    lang = str(r.get("task_lang", "")).strip() or "the target language"
+    q = re.sub(r"\s+", " ", str(r.get("query", "")).strip())
+    q = q[:90] + ("…" if len(q) > 90 else "")
+    n = len(answers)
+    preview = ", ".join(a for a in answers[:3] if a)
+    if len(answers) > 3:
+        preview += ", …"
+    bit = f" yielding {preview}" if preview else ""
+    return (
+        f"Solved this {tt} item set ({n} answers) in {lang} from the given "
+        f"examples, then applied the pattern to: {q}{bit}."
+    )
+
+
+def clean_expl(text: str, fallback: str) -> str:
+    text = re.sub(r"\s+", " ", (text or "").strip())
+    text = re.sub(r"(?i)^(explanation|reasoning)\s*[:=\-]\s*", "", text).strip()
+    if not text:
+        return fallback
+    m = re.match(r"(.+?[.!?])(?:\s|$)", text)
+    if m:
+        text = m.group(1).strip()
+    if len(text) > 320:
+        text = text[:320].rsplit(" ", 1)[0].strip() + "."
+    return text or fallback
+
+
+def save(rows: list[dict]) -> None:
+    import pandas as pd
+
+    cols = ["id", "pred"] + (["explanation"] if WRITE_EXPLANATIONS else [])
+    pd.DataFrame(rows, columns=cols).to_csv(OUTPUT_CSV, index=False)
+
+
+def encode(tok, messages, device):
+    ids = tok.apply_chat_template(
+        messages, add_generation_prompt=True, return_tensors="pt"
+    )
+    if hasattr(ids, "input_ids"):
+        ids = ids["input_ids"]
+    return ids.to(device)
+
+
+def gen(tok, model, ids, max_new: int) -> str:
+    import torch
+
+    with torch.no_grad():
+        out = model.generate(
+            ids,
+            max_new_tokens=max_new,
+            do_sample=False,
+            pad_token_id=tok.eos_token_id,
+        )
+    return tok.decode(out[0][ids.shape[-1] :], skip_special_tokens=True).strip()
+
+
+def main() -> None:
+    import pandas as pd
+    import torch
+    from transformers import AutoModelForCausalLM, AutoTokenizer
+
+    started = time.monotonic()
+    tok = AutoTokenizer.from_pretrained(MODEL_ID)
+    model = AutoModelForCausalLM.from_pretrained(
+        MODEL_ID, torch_dtype=torch.float16, device_map="auto"
+    ).eval()
+    device = next(model.parameters()).device
+    print(f"v8+expl loaded in {time.monotonic()-started:.1f}s", flush=True)
+
+    df = pd.read_csv(INPUT_CSV, dtype=str).fillna("")
+    n = len(df)
+    rows: list[dict] = []
+    meta: list[dict] = []  # context for phase-2 expl
+    durations: list[float] = []
+
+    # ----- phase 1: exact v8 answers -----
+    for _, r in df.iterrows():
+        elapsed = time.monotonic() - started
+        remaining = n - len(rows)
+        if elapsed >= SOFT_DEADLINE or (
+            remaining > 1 and elapsed + remaining * 8 > SOFT_DEADLINE + 30
+        ):
+            answers: List[str] = []
+            row = {"id": r["id"], "pred": json.dumps(answers, ensure_ascii=False)}
+            if WRITE_EXPLANATIONS:
+                row["explanation"] = expl_from_problem(r, answers)
+            rows.append(row)
+            meta.append({"r": r, "answers": answers})
+            save(rows)
+            print(f"{len(rows)}/{n} DEADLINE", flush=True)
+            continue
+
+        task_type = str(r.get("task_type", "")).strip()
+        messages = [
+            {"role": "system", "content": SYSTEM_V8},
+            {
+                "role": "user",
+                "content": f"{r['context'].strip()}\n\n{r['query'].strip()}",
+            },
+        ]
+        ids = encode(tok, messages, device)
+        prompt_len = ids.shape[-1]
+
+        t0 = time.monotonic()
+        text = gen(tok, model, ids, MAX_NEW)
+        # v8 parse: all non-empty lines (identical to submission8)
+        answers = [ln.strip() for ln in text.splitlines() if ln.strip()]
+        answers = safe_normalize_answers(answers, task_type)
+        durations.append(time.monotonic() - t0)
+
+        row = {"id": r["id"], "pred": json.dumps(answers, ensure_ascii=False)}
+        if WRITE_EXPLANATIONS:
+            row["explanation"] = expl_from_problem(r, answers)
+        rows.append(row)
+        meta.append({"r": r, "answers": answers})
+        save(rows)
+        print(
+            f"{len(rows)}/{n} ans {durations[-1]:.1f}s task={task_type or '?'}",
+            flush=True,
+        )
+
+    # ----- phase 2: model explanations with leftover time only -----
+    expl_model = 0
+    if WRITE_EXPLANATIONS:
+        for i, m in enumerate(meta):
+            time_left = SOFT_DEADLINE - (time.monotonic() - started)
+            if time_left < EXPL_STOP_LEFT:
+                break
+            r = m["r"]
+            answers = m["answers"]
+            if not answers:
+                continue
+            fb = expl_from_problem(r, answers)
+            preview = "; ".join(answers[:6])
+            if len(answers) > 6:
+                preview += "; ..."
+            expl_msgs = [
+                {
+                    "role": "system",
+                    "content": (
+                        "Write ONE short English sentence on the main linguistic "
+                        "rule used. No answers list, no preamble."
+                    ),
+                },
+                {
+                    "role": "user",
+                    "content": (
+                        f"Task: {str(r.get('task_type', '')).strip()}\n"
+                        f"Lang: {str(r.get('task_lang', '')).strip()}\n"
+                        f"Answers: {preview}\n"
+                        f"Problem:\n{str(r.get('context', ''))[:700]}\n\n"
+                        f"{str(r.get('query', ''))[:400]}"
+                    ),
+                },
+            ]
+            rows[i]["explanation"] = clean_expl(
+                gen(tok, model, encode(tok, expl_msgs, device), EXPL_MAX_NEW),
+                fb,
+            )
+            expl_model += 1
+            if expl_model % 10 == 0 or expl_model == 1:
+                save(rows)
+                print(
+                    f"expl {expl_model}/{n} left={time_left:.0f}s",
+                    flush=True,
+                )
+
+    save(rows)
+    print(
+        f"wrote {OUTPUT_CSV} | v8+expl | model_expl={expl_model}/{n} | "
+        f"total={time.monotonic()-started:.1f}s",
+        flush=True,
+    )
+
+
+if __name__ == "__main__":
+    main()

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}