初始化项目，由ModelHub XC社区提供模型

Model: TanitAI/Tanit-Med-8B-DPO Source: Original Platform
2026-07-20 21:51:09 +08:00
commit 5dc6e8b53f
8 changed files with 534 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,36 @@
+*.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,305 @@
+---
+license: apache-2.0
+language:
+- en
+base_model:
+- Qwen/Qwen3-8B
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- medical
+- clinical-reasoning
+- chain-of-thought
+- qwen3
+- sft
+- dpo
+- tanit
+datasets:
+- FreedomIntelligence/medical-o1-reasoning-SFT
+- FreedomIntelligence/Medical-R1-Distill-Data
+- UCSC-VLAA/MedReason
+- UCSC-VLAA/m23k-tokenized
+- Intelligent-Internet/II-Medical-RL
+- hongzhouyu/FineMed-DPO
+- super-dainiu/medagents-benchmark
+model-index:
+- name: Tanit-Med-8B
+  results:
+  - task: {type: question-answering, name: Medical QA}
+    dataset: {name: 'MedAgentsBench: MedQA', type: super-dainiu/medagents-benchmark, config: MedQA, split: test}
+    metrics: [{type: accuracy, value: 65.0, name: Accuracy}]
+  - task: {type: question-answering, name: Medical QA}
+    dataset: {name: 'MedAgentsBench: PubMedQA', type: super-dainiu/medagents-benchmark, config: PubMedQA, split: test}
+    metrics: [{type: accuracy, value: 68.0, name: Accuracy}]
+  - task: {type: question-answering, name: Medical QA}
+    dataset: {name: 'MedAgentsBench: MedMCQA', type: super-dainiu/medagents-benchmark, config: MedMCQA, split: test}
+    metrics: [{type: accuracy, value: 57.8, name: Accuracy}]
+  - task: {type: question-answering, name: Medical QA}
+    dataset: {name: 'MedAgentsBench: MedBullets', type: super-dainiu/medagents-benchmark, config: MedBullets, split: test}
+    metrics: [{type: accuracy, value: 42.9, name: Accuracy}]
+  - task: {type: question-answering, name: Medical QA}
+    dataset: {name: 'MedAgentsBench: MMLU (medical)', type: super-dainiu/medagents-benchmark, config: MMLU, split: test}
+    metrics: [{type: accuracy, value: 77.5, name: Accuracy}]
+  - task: {type: question-answering, name: Medical QA}
+    dataset: {name: 'MedAgentsBench: MMLU-Pro (medical)', type: super-dainiu/medagents-benchmark, config: MMLU-Pro, split: test}
+    metrics: [{type: accuracy, value: 47.3, name: Accuracy}]
+  - task: {type: question-answering, name: Medical QA}
+    dataset: {name: 'MedAgentsBench: MedExQA', type: super-dainiu/medagents-benchmark, config: MedExQA, split: test}
+    metrics: [{type: accuracy, value: 73.3, name: Accuracy}]
+  - task: {type: question-answering, name: Medical QA}
+    dataset: {name: 'MedAgentsBench: MedXpertQA-R', type: super-dainiu/medagents-benchmark, config: MedXpertQA-R, split: test}
+    metrics: [{type: accuracy, value: 12.1, name: Accuracy}]
+  - task: {type: question-answering, name: Medical QA}
+    dataset: {name: 'MedAgentsBench: MedXpertQA-U', type: super-dainiu/medagents-benchmark, config: MedXpertQA-U, split: test}
+    metrics: [{type: accuracy, value: 14.6, name: Accuracy}]
+  - task: {type: question-answering, name: Medical QA}
+    dataset: {name: 'MedAgentsBench: AfriMedQA', type: super-dainiu/medagents-benchmark, config: AfrimedQA, split: test}
+    metrics: [{type: accuracy, value: 48.9, name: Accuracy}]
+---
+
+# Tanit-Med-8B
+
+*An 8B medical reasoning model that thinks before it answers — and a model card that tells you where it doesn't.*
+
+Tanit-Med-8B is a full fine-tune of [Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) for clinical multiple-choice reasoning and medical question answering. It was trained in four stages — broad medical SFT, reasoning SFT, DPO, and a short chain-of-thought polish — and evaluated across the ten benchmarks in [MedAgentsBench](https://huggingface.co/datasets/super-dainiu/medagents-benchmark), on both the standard and the hard splits.
+
+It is named for Tanit, the Carthaginian goddess who watched over the western Mediterranean. The name is a commitment as much as a nod: this model is built by a North African team, and AfriMedQA is a first-class benchmark here, not a footnote.
+
+**The short version:** on the standard splits, Tanit-Med-8B is, to our knowledge, the strongest open 8B medical model on MedAgentsBench — a 50.7% macro average, against 34.6% for the next-best 8B peer. On the *hard* splits it is not meaningfully better than any other 8B model, and neither is anyone else. We think both halves of that sentence matter, so both are in this card.
+
+---
+
+## At a glance
+
+| | |
+|---|---|
+| **Base model** | Qwen/Qwen3-8B (dense, 8.2B params) |
+| **Precision** | BF16 |
+| **Context** | 32K native (trained at 8,192-token packed sequences) |
+| **Reasoning** | `<think>` blocks, always on by default (≈99% of responses) |
+| **Language** | English (only language evaluated) |
+| **License** | Apache-2.0 |
+| **Best at** | Multiple-choice clinical QA, USMLE-style vignettes, medical exam reasoning |
+| **Not for** | Diagnosis, treatment, dosing, triage, or anything touching a real patient |
+
+---
+
+## Results
+
+All numbers below are **zero-shot, greedy decoding**, using the MedAgentsBench prompt and answer-index extraction. `FULL` is the standard test split; `HARD` is the MedAgentsBench hard subset. Baseline numbers for the other 8B models were produced by us under the same harness.
+
+### Against open 8B medical models
+
+| Benchmark | **Tanit-Med-8B** | DeepSeek-R1-0528-Qwen3-8B | Falcon-H1R-7B | HuatuoGPT-o1-8B | MedReason-8B | Ministral-3-8B-Reasoning |
+|---|---|---|---|---|---|---|
+| MedQA | **65.0** | 44.0 | 28.9 | 29.5 | 28.0 | 27.8 |
+| PubMedQA | **68.0** | 60.2 | 60.0 | 55.2 | 55.2 | 57.2 |
+| MedMCQA | **57.8** | 42.9 | 33.6 | 35.8 | 35.0 | 34.3 |
+| MedBullets | **42.9** | 26.0 | 20.1 | 20.5 | 19.2 | 17.2 |
+| MMLU (med) | **77.5** | 50.5 | 30.3 | 26.6 | 22.8 | 22.2 |
+| MMLU-Pro (med) | **47.3** | 20.7 | 13.6 | 13.6 | 14.4 | 9.4 |
+| MedExQA | **73.3** | 49.3 | 35.1 | 28.7 | 21.7 | 21.7 |
+| MedXpertQA-R | 12.1 | 10.5 | 9.6 | 11.4 | **18.1** | 11.0 |
+| MedXpertQA-U | 14.6 | 9.7 | 10.4 | 11.5 | **16.5** | 9.7 |
+| AfriMedQA | **48.9** | 32.2 | 25.3 | 12.6 | 12.6 | 10.9 |
+| **Macro avg** | **50.7** | 34.6 | 26.7 | 24.5 | 24.4 | 22.1 |
+
+Tanit-Med-8B wins eight of ten. The two it loses are the two where nobody is really winning (see below).
+
+The AfriMedQA gap is the one we're proudest of: **48.9 vs 32.2** for the strongest baseline, and 4× the score of HuatuoGPT-o1 and MedReason. Medical models trained on US-exam corpora tend to fall over on questions grounded in African clinical practice. This one falls over less.
+
+### Against frontier models, for scale
+
+These are the published MedAgentsBench reference numbers ([arXiv:2503.07459](https://arxiv.org/abs/2503.07459)), **not re-run by us**. Cross-harness comparison, so read them as a ruler rather than a leaderboard. Averaged over the nine benchmarks the paper reports.
+
+| Model | FULL (9-bench avg) | HARD (9-bench avg) |
+|---|---|---|
+| DeepSeek-R1 | 73.9 | 32.5 |
+| o3-mini | 71.8 | 28.0 |
+| GPT-4o | 68.2 | 18.0 |
+| o1-mini | 67.8 | 25.3 |
+| DeepSeek-V3 | 63.1 | 12.2 |
+| Claude-3.5-Sonnet | 61.8 | 12.3 |
+| Llama-3.3-70B | 61.8 | 12.4 |
+| QwQ-32B | 61.0 | 17.1 |
+| GPT-4o-mini | 57.8 | 10.8 |
+| Claude-3.5-Haiku | 55.0 | 12.0 |
+| **Tanit-Med-8B** | **50.9** | **20.4** |
+
+An 8B model running on a single consumer GPU lands about 5 points behind GPT-4o-mini and 4 behind Claude-3.5-Haiku on the standard splits. That is the honest position: competitive with last-generation *small* frontier models, not with frontier models.
+
+Please do **not** read the HARD column as "an 8B model beats GPT-4o." See the next section for why that number is a mirage.
+
+---
+
+## How to read the hard splits (please read this)
+
+The MedAgentsBench hard subsets were built by keeping only questions that **fewer than half of a panel of baseline LLMs answered correctly** — a panel that included GPT-4o. Those models are therefore *adversarially selected against* on this split. GPT-4o's 18.0 is not a measurement of GPT-4o being worse at medicine than an 8B model; it is a measurement of the filter having done its job.
+
+Three things follow, and we'd rather say them ourselves than have someone say them in the community tab:
+
+**1. At 8B, the hard splits do not separate models.** Here is every 8B-class model we tested, macro-averaged over the ten hard subsets:
+
+| Model | HARD macro avg |
+|---|---|
+| Falcon-H1R-7B | 21.5 |
+| MedReason-8B | 21.2 |
+| HuatuoGPT-o1-8B | 20.7 |
+| **Tanit-Med-8B** | **20.3** |
+| Ministral-3-8B-Reasoning | 19.6 |
+| DeepSeek-R1-0528-Qwen3-8B | 17.4 |
+
+A 4-point spread across six models with wildly different training. Our +16-point advantage on the standard splits evaporates entirely. We do not claim a hard-split win, because there isn't one.
+
+**2. The samples are tiny.** AfriMedQA-hard is *32 questions* — one item is worth 3.1 points. Seven of the ten hard subsets are n=100. Treat any difference under ~8 points on these splits as noise, ours included.
+
+**3. Bigger doesn't fix it, and self-consistency can make it worse.** In our own baseline sweep, Qwen3-30B-A3B with sampling + self-consistency (k=3) reached **60.2%** micro-average on the standard splits and **14.9%** on the hard ones — *below* Qwen3-0.6B's 20.2%. On adversarially-filtered items, majority voting appears to converge confidently on the attractive distractor. This was the most useful negative result of the project and it is why we ship a greedy, single-sample model.
+
+---
+
+## Where this model fails
+
+- **MedXpertQA is unsolved at this scale.** Its items carry up to ten answer options, which puts chance around 10%. We score 12.1 (R) and 14.6 (U) — barely off the floor. So does every other 8B model here. DeepSeek-R1 gets 37.3. This is not a benchmark we are competitive on; it's a benchmark that shows where 8B runs out of road.
+- **MedReason-8B beats us on both MedXpertQA subsets** (18.1 / 16.5). Knowledge-graph-grounded training seems to buy something on deep-reasoning items that our curriculum doesn't.
+- **Hard splits: no better than the field.** See above.
+- **Long-form clinical advice is untested.** Every number in this card comes from multiple-choice benchmarks. We have not evaluated free-text safety, hedging, refusal behaviour, hallucinated citations, or drug dosing.
+- **English only.** AfriMedQA is English-language. We have run no non-English evaluation.
+- **Answer-format brittleness.** The phase-4 checkpoint is tuned to emit a strict final-answer line. Prompt it off-format and extraction gets flaky (see *Evaluation protocol*).
+
+### A note we owe you
+
+We have not yet published a like-for-like **Qwen3-8B baseline** under this exact frozen harness. Our internal sweep of Qwen3-8B in thinking mode lands in a similar range to Tanit-Med-8B on several standard splits, and we are not going to make a claim of the form *"medical fine-tuning beats the base model"* until that number is measured under the same conditions as everything else in this card. Until it is up, read the peer table as a comparison against **other medical fine-tunes**, not as proof that medical SFT was worth it. That number is coming, and it will go here whatever it says.
+
+---
+
+## Training
+
+Four stages, full fine-tune (no LoRA), ZeRO-3 / FSDP, bf16.
+
+| Phase | Method | Data | Purpose |
+|---|---|---|---|
+| 1 | SFT | medical-o1-reasoning (Huatuo-o1) + Medical-R1-Distill + MedReason | Broad medical foundation, clinical language |
+| 2 | SFT | m23k + II-Medical-RL + ChatDoctor-RL + MedReason | MCQ robustness, multi-step reasoning structure |
+| 3 | DPO | FineMed-DPO (32.9K pairs) | Preference alignment; fewer confidently-wrong answers |
+| 4 | SFT | MedReason + Huatuo-o1, outputs rewritten to ≤6 reasoning bullets + final answer line | Concise, extractable chain-of-thought |
+
+### Hyperparameters
+
+| | |
+|---|---|
+| Optimizer | AdamW, β = (0.9, 0.95), ε = 1e-8, weight decay 0.1 |
+| Grad clip | 1.0 |
+| Max sequence length | 8,192, packing on |
+| Attention | FlashAttention |
+| Global batch | ~1,048,576 tokens/step (≈128 × 8,192 seqs), grad-accum to match |
+| Schedule | 2% warmup, cosine decay to 10% of peak |
+| Peak LR — phase 1 | 2.0e-5 |
+| Peak LR — phase 2 | 1.0e-5 |
+| Peak LR — phase 3 (DPO) | 5.0e-7 |
+| Peak LR — phase 4 | 5.0e-6 |
+
+### What each phase actually bought
+
+Measured on our internal eval harness, macro-averaged across all ten standard splits:
+
+- **Phase 1 → 2** was the single biggest jump. Reasoning SFT took MedBullets from 30.5 to 47.1 and MMLU-Pro from 25.7 to 43.8 — the compositional benchmarks, exactly where you'd hope forced multi-step reasoning would pay.
+- **Phase 3 (DPO)** *cost* raw accuracy. The DPO checkpoint sits several points below phase 4 on the standard splits and only reasons on 40–80% of prompts. What it bought was calibration: markedly fewer confident wrong answers. We ship it separately as [Tanit-Med-8B-DPO](https://huggingface.co/TanitAI/Tanit-Med-8B-DPO) because for some downstream uses that trade is the right one.
+- **Phase 4 (CoT polish)** recovered the accuracy *and* pushed the reasoning rate to ~99% of responses while shortening the traces. It also cut extraction failures by an order of magnitude, which — see below — turned out to matter more than we expected.
+
+We capped the reasoning budget at 4,096 tokens throughout. This follows [m1](https://arxiv.org/abs/2504.00869), which identifies an optimal medical-reasoning threshold around 4K tokens, past which accuracy *declines* — unlike in maths, forcing more reasoning on a medical question mostly gives a model with a shaky knowledge prior more rope to talk itself out of a correct answer. We saw the same thing and stopped fighting it.
+
+---
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "TanitAI/Tanit-Med-8B"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")
+
+messages = [
+    {"role": "system", "content": "You are Tanit, an expert medical AI assistant."},
+    {"role": "user", "content": (
+        "A 45-year-old presents with acute monoarthritis of the first MTP joint.\n"
+        "What is the most likely diagnosis?\n\n"
+        "A. Gout\nB. Pseudogout\nC. Septic arthritis\nD. Rheumatoid arthritis"
+    )},
+]
+
+prompt = tokenizer.apply_chat_template(
+    messages, tokenize=False, add_generation_prompt=True, enable_thinking=True
+)
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+out = model.generate(**inputs, max_new_tokens=4096, temperature=0.6, top_p=0.95, top_k=20)
+print(tokenizer.decode(out[0][inputs.input_ids.shape[-1]:], skip_special_tokens=True))
+```
+
+**Serving with vLLM:**
+
+```bash
+vllm serve TanitAI/Tanit-Med-8B --max-model-len 32768 --reasoning-parser qwen3
+```
+
+**Generation settings.** For open-ended use, follow Qwen3's thinking-mode defaults: `temperature=0.6`, `top_p=0.95`, `top_k=20`. For benchmark reproduction, use **greedy** (`temperature=0`) — every number in this card was produced that way. Do not use greedy decoding with `enable_thinking=True` for long open-ended generations; it degenerates into repetition, as it does for the base model.
+
+**Quantized:** [Tanit-Med-8B-NVFP4](https://huggingface.co/TanitAI/Tanit-Med-8B-NVFP4) runs on a single consumer GPU.
+
+---
+
+## Evaluation protocol
+
+Reproducing our numbers requires matching three things, in descending order of how much they'll bite you:
+
+1. **Answer extraction.** This is a bigger confound than most training decisions. Between two revisions of our own harness, the strict-format extraction-failure rate on this checkpoint moved from **31.3% → 4.8%** on MedQA (and 63% → 5% on MedQA-hard), while accuracy moved by about a point. If you benchmark against us and get a different number, check your extraction rate *first*. Ours is under 7% on every split.
+2. **Prompt.** We use the MedAgentsBench zero-shot prompt verbatim — knowledgeable-medical-assistant system message, question, options, "reply with the answer index only."
+3. **Decoding.** Greedy. Single sample. Reasoning budget 4,096 tokens, generation cap 16,384.
+
+Self-consistency (k=5) is worth roughly **+3–10% relative** on the standard splits if you can afford 5× the compute — but re-read the hard-split warning above before you assume it helps everywhere. It doesn't.
+
+---
+
+## The collection
+
+| Model | Stage | Use it if |
+|---|---|---|
+| [**Tanit-Med-8B**](https://huggingface.co/TanitAI/Tanit-Med-8B) | Phase 4 (CoT polish) | You want the best accuracy. **Start here.** |
+| [Tanit-Med-8B-DPO](https://huggingface.co/TanitAI/Tanit-Med-8B-DPO) | Phase 3 (DPO) | You'd trade a few points of accuracy for better-calibrated confidence |
+| [Tanit-MedReason-8B](https://huggingface.co/TanitAI/Tanit-MedReason-8B) | Phase 2 (reasoning SFT) | You want an un-DPO'd reasoning checkpoint to build on |
+| [Tanit-Med-8B-NVFP4](https://huggingface.co/TanitAI/Tanit-Med-8B-NVFP4) | Phase 4, FP4 | You're deploying on a consumer GPU |
+
+---
+
+## Intended use and limitations
+
+**Intended for:** medical NLP research, benchmark development, medical education tooling, retrieval-augmented clinical QA prototypes, and as a base for further fine-tuning.
+
+**Not intended for, and not safe for:** clinical decision support, diagnosis, treatment or dosing recommendations, triage, or any patient-facing deployment. Tanit-Med-8B is **not a medical device**. It has not been reviewed or cleared by any regulator, has not been evaluated for clinical safety, and has been measured only on multiple-choice exam questions — which correlate with medical knowledge but are not a proxy for clinical judgment. It answers with a `<think>` trace that *looks* like reasoning; a confident, fluent, well-structured trace can and does precede a wrong answer.
+
+**Known risks:** inherits the biases of its training corpora, which are overwhelmingly Western and exam-derived. Will hallucinate drug names, doses, and citations. Will not reliably refuse out-of-scope or unsafe requests — DPO here optimized for *correctness* under ambiguity, not for safety refusals.
+
+If you deploy anything downstream of this model in a setting where a person could be harmed, that safety work is yours to do, and it has not been done here.
+
+---
+
+## Licensing
+
+Model weights are released under **Apache-2.0**, inherited from Qwen3-8B. Note that the training corpora carry their own terms — several are research-oriented and some derive from sources with non-commercial restrictions. If you intend to use this model commercially, verify the licence of each dataset listed in the metadata; we are releasing weights, not indemnity.
+
+---
+
+## Citation
+
+```bibtex
+@misc{tanit-med-8b-2026,
+  title  = {Tanit-Med-8B: A Four-Stage Curriculum for Open Medical Reasoning at 8B},
+  author = {Tanit Healthcare Technologies},
+  year   = {2026},
+  url    = {https://huggingface.co/TanitAI/Tanit-Med-8B}
+}
+```
+
+Built on [Qwen3](https://huggingface.co/Qwen/Qwen3-8B) (Qwen Team). Evaluated with [MedAgentsBench](https://arxiv.org/abs/2503.07459) (Zhang et al., 2025). Trained on data from [FreedomIntelligence](https://huggingface.co/FreedomIntelligence), [UCSC-VLAA](https://huggingface.co/UCSC-VLAA), [Intelligent-Internet](https://huggingface.co/Intelligent-Internet), and [FineMed](https://huggingface.co/hongzhouyu). Our thanks to all of them — the open medical-AI stack is a shared one.
+
+**Found a problem with these numbers?** Open a discussion. We'd rather be corrected than cited wrongly.
--- a/chat_template.jinja
+++ b/chat_template.jinja
@@ -0,0 +1,89 @@
+{%- 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 message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].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' }}
+        {{- 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 %}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,71 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.2.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,12 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "5.2.0"
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8269042a54067af8cc9302b0b167d7ddea5947926cf17ecc6e13e6ff95c5387
+size 16381517208
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": true,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}