Publish verified v8 diagnostic distractor adapter

Verified recovery artifact with pinned Qwen3-8B base revision, truthful model card, and aggregate frozen benchmark summary. No raw Eedi data, predictions, checkpoints, optimizer state, or credentials.

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,268 @@
+---
+base_model: unsloth/Qwen3-8B-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+license: apache-2.0
+language:
+- en
+tags:
+- qwen3
+- peft
+- lora
+- qlora
+- education
+- mathematics
+- middle-school
+- diagnostic-assessment
+---
+
+# Qwen3-8B Diagnostic Distractor LoRA v8
+
+This is a PEFT LoRA adapter trained to propose diagnostic wrong answers for
+sixth-grade and middle-school **Number** mathematics questions. Given a trusted
+question, correct answer, and topic, it is trained to return exactly three
+different distractors. Each distractor names a distinct student misconception,
+shows the question-specific arithmetic that misconception would produce, and
+reports the resulting answer.
+
+The outputs are hypotheses for assessment authors, not diagnoses of learners.
+Generated content must be parsed and independently checked before it reaches a
+student.
+
+## Model and artifact identity
+
+- Base model: [`unsloth/Qwen3-8B-bnb-4bit`](https://huggingface.co/unsloth/Qwen3-8B-bnb-4bit)
+- Immutable base revision: `1deaf68f694c40dbce295da300851729d759b21a`
+- Adapter type: causal-LM LoRA, rank 32, alpha 32, dropout 0
+- Target modules: `q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`,
+  `up_proj`, and `down_proj`
+- PEFT version recorded by the artifact: 0.19.1
+- Recovered ZIP: 325,882,649 bytes; SHA-256
+  `e00dcb7653e9baa19fb103bbe0712b419fccb281724b487847de7f03a960c7fb`
+- `adapter_model.safetensors`: 349,243,752 bytes; SHA-256
+  `e949ee36800f429ba5dc02b761aa54bf8037af6d406fac9e5a04c7b68cce4a12`
+
+The recovered ZIP named the correct base model but stored `revision: null` in
+`adapter_config.json`. For this publication, that metadata field was set to the
+immutable revision in the training receipt. Adapter weights and tokenizer files
+were not changed.
+
+## Output contract
+
+The model was supervised to emit only one JSON object with this shape:
+
+```json
+{
+  "distractors": [
+    {
+      "misconception": "<short misconception>",
+      "computation": "<arithmetic> = <value>",
+      "answer": "<value>"
+    },
+    {
+      "misconception": "...",
+      "computation": "...",
+      "answer": "..."
+    },
+    {
+      "misconception": "...",
+      "computation": "...",
+      "answer": "..."
+    }
+  ]
+}
+```
+
+The intended constraints are:
+
+1. exactly three distractors;
+2. three distinct, specific misconceptions;
+3. three distinct wrong answers, none equal to the key; and
+4. each `computation` evaluates to its paired `answer` for the supplied
+   question.
+
+These are generation targets, not guarantees. Enforce them in trusted code.
+
+## Usage
+
+Qwen3 support requires a current Transformers release. The base is a
+bitsandbytes 4-bit checkpoint, so use a compatible CUDA environment.
+
+```python
+import json
+import torch
+from peft import PeftModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+ADAPTER = "j2ampn/qwen3-8b-distractor-lora-v8"
+BASE = "unsloth/Qwen3-8B-bnb-4bit"
+BASE_REVISION = "1deaf68f694c40dbce295da300851729d759b21a"
+
+SYSTEM_PROMPT = """You are an expert middle-school mathematics assessment writer. Given a "Number" strand math question and its correct answer, produce exactly three diagnostic distractors (wrong answers) for a multiple-choice version.
+
+For each distractor provide, in this order:
+- misconception: the specific student misconception or procedural error.
+- computation: the exact arithmetic a student with THAT misconception performs on THIS question, written as a plain expression that ends in '= <answer>' (e.g. "0.4 ÷ 0.2 = 2"). Use only digits, + - × ÷, parentheses, decimals, and fractions a/b.
+- answer: the value the computation evaluates to. It MUST equal the computation's result.
+
+Rules:
+- Exactly 3 distractors, each tagged to a distinct misconception.
+- Each answer is exactly what a student making that misconception would compute (numerically consistent with the misconception and its shown computation).
+- The three answers must all be different, and none may equal the correct answer.
+
+Respond with ONLY a JSON object, no prose, in this exact schema:
+{"distractors": [{"misconception": "<short misconception>", "computation": "<arithmetic> = <value>", "answer": "<value>"}, {"misconception": "...", "computation": "...", "answer": "..."}, {"misconception": "...", "computation": "...", "answer": "..."}]}"""
+
+tokenizer = AutoTokenizer.from_pretrained(ADAPTER)
+base = AutoModelForCausalLM.from_pretrained(
+    BASE,
+    revision=BASE_REVISION,
+    torch_dtype="auto",
+    device_map="auto",
+)
+model = PeftModel.from_pretrained(base, ADAPTER)
+model.eval()
+
+messages = [
+    {"role": "system", "content": SYSTEM_PROMPT},
+    {
+        "role": "user",
+        "content": (
+            "Question: What is 3/4 of 20?\n"
+            "Correct answer: 15\n"
+            "Topic: Fractions"
+        ),
+    },
+]
+input_ids = tokenizer.apply_chat_template(
+    messages,
+    tokenize=True,
+    add_generation_prompt=True,
+    enable_thinking=False,
+    return_tensors="pt",
+).to(model.device)
+
+with torch.inference_mode():
+    output_ids = model.generate(
+        input_ids=input_ids,
+        max_new_tokens=512,
+        do_sample=False,
+    )
+
+text = tokenizer.decode(
+    output_ids[0, input_ids.shape[1]:],
+    skip_special_tokens=True,
+)
+payload = json.loads(text)
+print(payload)
+```
+
+The registered **model-only** track uses greedy generation as shown above. The
+separate best-of-N result below does not come from this single call.
+
+## Training
+
+“One-shot” means one planned training invocation, not one training example. The
+run used QLoRA SFT against the pinned 4-bit base for three planned epochs with:
+
+- 3,572 verified training rows and a deterministic prompt-grouped train/validation
+  split;
+- response-only loss, maximum sequence length 2,048;
+- batch size 1, gradient accumulation 8;
+- learning rate `1.5e-4`, cosine schedule, 5% warmup;
+- 8-bit AdamW, weight decay 0.01, seed 42; and
+- automatic restoration of the checkpoint with lowest validation loss.
+
+The selected checkpoint was `outputs_v8/checkpoint-403`, with validation loss
+`0.051324423402547836`. The frozen 140-item benchmark was not used for training,
+validation, checkpoint selection, or tuning.
+
+Training combined programmatically generated misconception procedures with
+filtered real-question targets. No raw training dataset is included in this
+model repository.
+
+## Evaluation
+
+The following are the final deterministic hard-gate results from
+[`TABLE_V8_RESULTS.md`](https://github.com/jsonjj/diagnostic-distractor-slm/blob/5aa7146b0fa7fc71efbd10feac4e57c2839e05a4/TABLE_V8_RESULTS.md).
+Brackets are 95% intervals.
+
+| Metric | Opus generator baseline | v8 model-only | v8 verifier-guided best-of-4 |
+|---|---:|---:|---:|
+| Valid exactly-3 output | 97.1% (136/140) [92.9, 98.9] | 100.0% (140/140) [97.3, 100.0] | 100.0% (140/140) [97.3, 100.0] |
+| No answer equals key | 94.3% (132/140) [89.1, 97.1] | 94.3% (132/140) [89.1, 97.1] | 96.4% (135/140) [91.9, 98.5] |
+| Three distinct answers | 85.0% (119/140) [78.2, 90.0] | 80.7% (113/140) [73.4, 86.4] | 96.4% (135/140) [91.9, 98.5] |
+| Three distinct misconceptions | 97.1% (136/140) [92.9, 98.9] | 100.0% (140/140) [97.3, 100.0] | 100.0% (140/140) [97.3, 100.0] |
+| Hardened computation validity | 40.3% (170/422) [34.2, 47.4] | 79.3% (333/420) [73.3, 84.5] | 84.8% (356/420) [79.0, 89.3] |
+
+**Model-only** is deterministic greedy output from the adapter. **Best-of-4** is
+a system track: it adds three seeded sampled candidates to the greedy candidate,
+then uses trusted local code to select by structure, key safety, distinctness,
+and hardened computation checks. It must not be described as model-only
+performance.
+
+Good Distractor Rate (GDR), Good@3, holistic diagnostic-quality/plausibility,
+and the registered overall win rule are **unavailable / not demonstrated**.
+There is no accepted independent judge or completed human review for those
+holistic measures. There are also no observed student option-pick frequencies;
+the evaluation cannot establish that any distractor is frequently selected by
+students.
+
+Aggregate machine-readable results are in
+[`benchmark_summary.json`](benchmark_summary.json). No protected benchmark
+questions, raw Eedi records, or prediction rows are distributed here.
+
+## Limitations
+
+- The model can emit malformed JSON, a correct answer as a distractor, duplicate
+  answers, invalid arithmetic, or a misconception label that does not explain
+  its answer.
+- Deterministic arithmetic checks do not establish student plausibility,
+  diagnostic usefulness, or misconception-to-answer validity in every case.
+- The benchmark covers English middle-school Number content and should not be
+  generalized to other subjects, languages, ages, or high-stakes decisions.
+- A generated misconception is a content-design hypothesis. It must not be used
+  as an automated diagnosis of a learner.
+- Results do not measure observed student choice frequency.
+- The best-of-4 figures require the repository verifier and additional
+  generation; loading this adapter alone reproduces only the model-only track.
+
+## Safety, privacy, and local game use
+
+The intended Wayline game path runs inference locally. Trusted code supplies
+only the question, correct answer, topic, and fixed prompt. It does not send a
+learner's name, profile/session ID, answer selection, confidence, or progress to
+the model. No Hugging Face or provider credential is embedded in these files or
+required after local download.
+
+Treat raw model text as untrusted. Parse exact JSON, reject key collisions and
+duplicates, evaluate arithmetic, apply curriculum constraints, and use human
+review for released content. The model should not directly grade students,
+change progression, or present unverified material to children.
+
+For a local `llama.cpp` game runtime, the base and adapter must first be merged
+and exported to a separately validated GGUF. This repository does not claim that
+the adapter by itself is a production-ready game package.
+
+## License and data terms
+
+The adapter is released under Apache-2.0, matching the pinned base model's
+declared license and the owner's prior adapter release. The source repository
+describes raw Eedi Kaggle inputs under separate CC BY-NC 4.0 terms. No raw Eedi
+data is included here, and the model license does not replace any source-data
+terms that apply when reproducing the training pipeline.
+
+## Source and frozen evidence
+
+- Source repository:
+  <https://github.com/jsonjj/diagnostic-distractor-slm>
+- Frozen source revision:
+  [`5aa7146b0fa7fc71efbd10feac4e57c2839e05a4`](https://github.com/jsonjj/diagnostic-distractor-slm/tree/5aa7146b0fa7fc71efbd10feac4e57c2839e05a4)
+- Final results:
+  [`TABLE_V8_RESULTS.md`](https://github.com/jsonjj/diagnostic-distractor-slm/blob/5aa7146b0fa7fc71efbd10feac4e57c2839e05a4/TABLE_V8_RESULTS.md)
+- Artifact validation:
+  [`v8_artifact_validation.json`](https://github.com/jsonjj/diagnostic-distractor-slm/blob/5aa7146b0fa7fc71efbd10feac4e57c2839e05a4/data/eval_out/v8_artifact_validation.json)
+- Final benchmark record:
+  [`benchmark_v8_final.json`](https://github.com/jsonjj/diagnostic-distractor-slm/blob/5aa7146b0fa7fc71efbd10feac4e57c2839e05a4/data/eval_out/benchmark_v8_final.json)
+- Training receipt:
+  [`v8_training_receipt.json`](https://github.com/jsonjj/diagnostic-distractor-slm/blob/5aa7146b0fa7fc71efbd10feac4e57c2839e05a4/v8_training_receipt.json)

adapter_config.json

@@ -0,0 +1,52 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3-8B-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": "1deaf68f694c40dbce295da300851729d759b21a",
+  "target_modules": [
+    "q_proj",
+    "gate_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "down_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e949ee36800f429ba5dc02b761aa54bf8037af6d406fac9e5a04c7b68cce4a12
+size 349243752

benchmark_summary.json

@@ -0,0 +1,219 @@
+{
+  "adapter_artifact": {
+    "adapter_model": {
+      "bytes": 349243752,
+      "sha256": "e949ee36800f429ba5dc02b761aa54bf8037af6d406fac9e5a04c7b68cce4a12",
+      "tensor_count": 504
+    },
+    "published_adapter_config_sha256": "a1036d4a3bf1ded9718ad7a3c555ab989243bf8ce0aec8949d5ca2a79e2b06be",
+    "published_metadata_change": "Set adapter_config.json revision from null to the immutable base revision in the training receipt; weights and tokenizer artifacts are unchanged.",
+    "source_zip": {
+      "bytes": 325882649,
+      "crc_test_passed": true,
+      "duplicates_present": false,
+      "sha256": "e00dcb7653e9baa19fb103bbe0712b419fccb281724b487847de7f03a960c7fb",
+      "symlinks_present": false,
+      "unsafe_paths_present": false
+    }
+  },
+  "base_model": {
+    "repo_id": "unsloth/Qwen3-8B-bnb-4bit",
+    "revision": "1deaf68f694c40dbce295da300851729d759b21a"
+  },
+  "benchmark": {
+    "frozen_items": 140,
+    "frozen_sha256": "546c14f03707ce098146dac5e0c6e99c0a4619d6d4e32193a9fff4e3b9bfd1b1",
+    "measured_metrics": {
+      "opus_generator_baseline": {
+        "hardened_computation_validity": {
+          "ci95_percent": [
+            34.2,
+            47.4
+          ],
+          "denominator": 422,
+          "numerator": 170,
+          "score_percent": 40.3
+        },
+        "no_answer_equals_key": {
+          "ci95_percent": [
+            89.1,
+            97.1
+          ],
+          "denominator": 140,
+          "numerator": 132,
+          "score_percent": 94.3
+        },
+        "three_distinct_answers": {
+          "ci95_percent": [
+            78.2,
+            90.0
+          ],
+          "denominator": 140,
+          "numerator": 119,
+          "score_percent": 85.0
+        },
+        "three_distinct_misconceptions": {
+          "ci95_percent": [
+            92.9,
+            98.9
+          ],
+          "denominator": 140,
+          "numerator": 136,
+          "score_percent": 97.1
+        },
+        "valid_exactly_three": {
+          "ci95_percent": [
+            92.9,
+            98.9
+          ],
+          "denominator": 140,
+          "numerator": 136,
+          "score_percent": 97.1
+        }
+      },
+      "v8_model_only": {
+        "generation": "deterministic greedy",
+        "hardened_computation_validity": {
+          "ci95_percent": [
+            73.3,
+            84.5
+          ],
+          "denominator": 420,
+          "numerator": 333,
+          "score_percent": 79.3
+        },
+        "no_answer_equals_key": {
+          "ci95_percent": [
+            89.1,
+            97.1
+          ],
+          "denominator": 140,
+          "numerator": 132,
+          "score_percent": 94.3
+        },
+        "three_distinct_answers": {
+          "ci95_percent": [
+            73.4,
+            86.4
+          ],
+          "denominator": 140,
+          "numerator": 113,
+          "score_percent": 80.7
+        },
+        "three_distinct_misconceptions": {
+          "ci95_percent": [
+            97.3,
+            100.0
+          ],
+          "denominator": 140,
+          "numerator": 140,
+          "score_percent": 100.0
+        },
+        "track_type": "model_only",
+        "valid_exactly_three": {
+          "ci95_percent": [
+            97.3,
+            100.0
+          ],
+          "denominator": 140,
+          "numerator": 140,
+          "score_percent": 100.0
+        }
+      },
+      "v8_verifier_guided_best_of_4": {
+        "candidate_count": 4,
+        "generation": "one greedy candidate plus three seeded sampled candidates, selected by a deterministic local verifier",
+        "hardened_computation_validity": {
+          "ci95_percent": [
+            79.0,
+            89.3
+          ],
+          "denominator": 420,
+          "numerator": 356,
+          "score_percent": 84.8
+        },
+        "no_answer_equals_key": {
+          "ci95_percent": [
+            91.9,
+            98.5
+          ],
+          "denominator": 140,
+          "numerator": 135,
+          "score_percent": 96.4
+        },
+        "three_distinct_answers": {
+          "ci95_percent": [
+            91.9,
+            98.5
+          ],
+          "denominator": 140,
+          "numerator": 135,
+          "score_percent": 96.4
+        },
+        "three_distinct_misconceptions": {
+          "ci95_percent": [
+            97.3,
+            100.0
+          ],
+          "denominator": 140,
+          "numerator": 140,
+          "score_percent": 100.0
+        },
+        "track_type": "system",
+        "valid_exactly_three": {
+          "ci95_percent": [
+            97.3,
+            100.0
+          ],
+          "denominator": 140,
+          "numerator": 140,
+          "score_percent": 100.0
+        }
+      }
+    },
+    "method": "Deterministic local hard gates on the sealed v8 Number benchmark; intervals are 95%.",
+    "registered_verdict": {
+      "v8_model_only": "NOT DEMONSTRATED",
+      "v8_verifier_guided_best_of_4": "NOT DEMONSTRATED"
+    },
+    "unavailable_metrics": {
+      "diagnostic_quality_or_plausibility": "No accepted independent judge or completed human review.",
+      "good_at_3": "GDR is unavailable.",
+      "good_distractor_rate": "No accepted independent judge for holistic misconception mapping, specificity, plausibility, and diagnostic usefulness.",
+      "observed_student_pick_frequency": "No student option-selection frequency data exists for this benchmark."
+    }
+  },
+  "model_id": "j2ampn/qwen3-8b-distractor-lora-v8",
+  "schema_version": "diagnostic-distractor-v8-benchmark-summary-v1",
+  "source_evidence": {
+    "artifact_validation": {
+      "sha256": "6accd30757d0023eed252c45ba8f02a1e3499372782e6fbb7daeda53a13b7f7c",
+      "url": "https://github.com/jsonjj/diagnostic-distractor-slm/blob/5aa7146b0fa7fc71efbd10feac4e57c2839e05a4/data/eval_out/v8_artifact_validation.json"
+    },
+    "final_benchmark": {
+      "sha256": "419ec4a7f9b8c3e4baef1830582b0c54225be315d0cc740d517575aa208c1368",
+      "url": "https://github.com/jsonjj/diagnostic-distractor-slm/blob/5aa7146b0fa7fc71efbd10feac4e57c2839e05a4/data/eval_out/benchmark_v8_final.json"
+    },
+    "final_results": {
+      "sha256": "388b9d28267d9fc25aeef4bb885816b9764dfa94cba3c43c7475b0aa19b4ae9e",
+      "url": "https://github.com/jsonjj/diagnostic-distractor-slm/blob/5aa7146b0fa7fc71efbd10feac4e57c2839e05a4/TABLE_V8_RESULTS.md"
+    },
+    "repository": "https://github.com/jsonjj/diagnostic-distractor-slm",
+    "source_revision": "5aa7146b0fa7fc71efbd10feac4e57c2839e05a4",
+    "training_receipt": {
+      "sha256": "a88a1ca6dae5611ee64e34f7ecb236a17c82809f1a4f053c5daaa701c7e00571",
+      "url": "https://github.com/jsonjj/diagnostic-distractor-slm/blob/5aa7146b0fa7fc71efbd10feac4e57c2839e05a4/v8_training_receipt.json"
+    }
+  },
+  "training": {
+    "best_checkpoint": "outputs_v8/checkpoint-403",
+    "best_eval_loss": 0.051324423402547836,
+    "epochs_planned": 3,
+    "learning_rate": 0.00015,
+    "lora_alpha": 32,
+    "lora_rank": 32,
+    "seed": 42,
+    "train_rows": 3572,
+    "train_sha256": "babe071e310a389b8a0fb2d3a5b6414f1275129f3cad8c15be5ff175e098a5ad"
+  }
+}

chat_template.jinja

@@ -0,0 +1,97 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for forward_message in messages %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- set message = messages[index] %}
+    {%- set tool_start = '<tool_response>' %}
+    {%- set tool_start_length = tool_start|length %}
+    {%- set start_of_message = message.content[:tool_start_length] %}
+    {%- set tool_end = '</tool_response>' %}
+    {%- set tool_end_length = tool_end|length %}
+    {%- set start_pos = (message.content|length) - tool_end_length %}
+    {%- if start_pos < 0 %}
+        {%- set start_pos = 0 %}
+    {%- endif %}
+    {%- set end_of_message = message.content[start_pos:] %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = (message.content.split('</think>')|last).lstrip('\n') %}
+                {%- set reasoning_content = (message.content.split('</think>')|first).rstrip('\n') %}
+                {%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:476870a1f2fb6f6a2759a6ede2383bf9d5d738f17844563b65c91965b722ae09
+size 11422924

tokenizer_config.json

@@ -0,0 +1,225 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": false,
+  "model_max_length": 40960,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    }
+  }
+}