Super-squash branch 'main' using huggingface_hub

Co-authored-by: BoZhang <BoZhang@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,38 @@
+*.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
+figures/Sage-A1.5-benchmark.png filter=lfs diff=lfs merge=lfs -text
+figures/Sage-A1p5-benchmark.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,655 @@
+---
+library_name: transformers
+license: apache-2.0
+pipeline_tag: text-generation
+tags:
+  - moe
+  - vlm
+  - vision
+  - agentic
+  - code
+  - tool-use
+---
+
+# Sage-A1.5
+
+<div style="display: flex; flex-direction: column; align-items: center; line-height: 1.2;">
+  <div style="display: flex; justify-content: center; align-items: center; gap: 10px; height: 30px;">
+    <span style="font-size: 16px;" role="img" aria-label="Homepage">🏠</span>
+    <a href="https://alpha-innovator.github.io/Sage-A1.5/"><b>Homepage</b></a>
+    <span style="color: #ccc;">|</span>
+    <img src="./figures/24px.svg" width="16" height="16" alt="Technical Report" style="filter: invert(0.5);">
+    <a href="https://arxiv.org/abs/2610.28578"><b>Technical Report</b></a>
+  </div>
+
+  <div style="display: flex; justify-content: center; align-items: center; gap: 10px; height: 30px; margin-top: 2px;">
+    <img src="./figures/hf-logo.svg" width="16" height="16" alt="Hugging Face">
+    <a href="https://huggingface.co/InternScience/Sage-A1.5"><b>Hugging Face</b></a>
+    <span style="color: #ccc;">|</span>
+    <img src="./figures/github-logo.svg" width="16" height="16" alt="GitHub">
+    <a href="https://github.com/InternScience/Agents-A1"><b>Github</b></a>
+    <span style="color: #ccc;">|</span>
+    <img src="./figures/modelscope-logo.svg" width="16" height="16" alt="Model Scope">
+    <a href="https://modelscope.cn/models/InternScience/Sage-A1.5"><b>ModelScope</b></a>
+  </div>
+</div>
+
+> [!Note]
+> This repository contains model weights and configuration files for Sage-A1.5 in the Hugging Face Transformers format.
+>
+> These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, etc.
+
+---
+
+**Sage‑A1.5** is a 35B Mixture‑of‑Experts agentic model from Shanghai AI Laboratory, built to advance long-horizon scientific problem solving through adaptive capability composition. Building upon **A1**, **Sage‑A1.5** learns not only to solve individual tasks, but also to organize work and revise its approach during execution, highlighting three key capabilities: **Agentic Orchestration, Verification, and Open Scientific Discovery**.
+
+First, agentic orchestration extends single-agent execution through task delegation and parallel collaboration among subagents with isolated contexts, 
+enabling complex tasks to be decomposed and addressed concurrently while reducing interference across concurrent subagents. 
+Second, agentic verification strengthens long-horizon reliability through progress checking, evidence validation, and reflective strategy revision, 
+allowing **Sage‑A1.5** to recognize unproductive search paths and pursue alternative approaches. 
+Third, open scientific discovery extends agentic capabilities beyond answering predefined questions to conducting exploratory research, 
+connecting scientific inquiry with interactive analysis and inspectable research artifacts. 
+We hope **Sage‑A1.5** provides the community with an accessible foundation for open scientific discovery, 
+offering a practical path from long-horizon task execution to collaborative, verifiable, and inspectable scientific exploration.
+
+![Sage-A1 Benchmark Overview](./figures/Sage-A1p5-benchmark.png)
+
+## Highlights
+- **Agentic Orchestration**: Orchestrates parallel investigations across subagents with independent contexts, enabling them to challenge assumptions, refine conclusions through evidence, and synthesize their findings into comprehensive results.
+- **Verification Mode**: An opt-in self-review capability that lives inside the model's own chain of thought — the model pauses mid-trajectory to review what it has established and what has failed, then acts on a revised direction in the same turn, with no external critic.
+- **Agentic Reasoning**: Sage-A1.5 excels at decomposing complex tasks into executable sub-steps, planning ahead, and adapting its strategy based on intermediate results.
+- **Tool Use**: Natively supports function calling and tool integration, enabling seamless interaction with APIs, code interpreters, search engines, and other external tools.
+- **Scientific and Professional Reasoning**: Handles tool-integrated scientific reasoning and professional knowledge question answering.
+- **Instruction Following**: Precisely follows detailed, multi-constraint instructions across diverse domains.
+
+We welcome developers and enterprises to integrate and try Sage-A1.5 and share their feedback.
+
+## Performance
+
+We evaluate Sage-A1.5 in real-world agentic and research-oriented workflows across six
+directions — long-horizon search, engineering tasks, instruction following, scientific research,
+general agentic tasks, and scientific agentic tasks. Despite operating in the ~35B model class,
+Sage-A1.5 delivers highly competitive performance against frontier-scale systems such as
+Kimi-K3, GLM-5.3, and GPT-5.6-sol. It achieves overall SOTA on XBench-DS-2510 (92.0),
+IFBench (81.6), PinchBench (90.0), FrontierScience-Olympiad (81.0), FrontierScience-Research (48.3),
+CMT (80.0), and OmniDocBench (91.5), and reaches 95.1 on GAIA — higher than every
+larger-scale model we compare against. Among comparable ~35B models it ranks first on a broad
+range of tasks, including BrowseComp (81.7), SWE-bench Pro (61.2), MLE-Lite (65.2),
+SciCode (44.3, tied with Agents-A1), AA-LCR (81.0), HLE w/ tools (55.1),
+VitaBench (45.4), and ChemCOTBench (66.5).
+Compared with A1, it improves substantially on engineering and agentic workloads
+(SWE-bench Pro +17.6, SWE-bench Multilingual +14.0, PinchBench +13.1, MLE-Lite +21.3).
+These results show that Sage-A1.5 combines strong long-horizon search ability, robust
+scientific reasoning, and reliable instruction following, establishing it as a highly capable and
+efficient agentic model that narrows the gap with much larger frontier models.
+
+
+<p>
+🥇 Overall SOTA &nbsp;&nbsp;
+🟢 Best Among Comparable Models (~35B)
+</p>
+
+<table>
+<thead>
+<tr>
+<th rowspan="2" align="left">Benchmark</th>
+<th colspan="3" align="center" style="text-align:center;">
+    📏 Comparable Models (~35B)
+</th>
+
+<th colspan="3" align="center" style="text-align:center;">
+    🚀 Larger-scale Models
+</th>
+</tr>
+
+<tr>
+<th align="center">Sage-A1.5</th>
+<th align="center">Agents-A1</th>
+<th align="center">Ornith-1.5</th>
+  
+<th align="center">Kimi-K3</th>
+<th align="center">GLM-5.3</th>
+<th align="center">GPT-5.6-sol</th>
+
+</tr>
+</thead>
+
+<tbody>
+
+<tr>
+    <td colspan="8" align="left"><b>🔍 Long-horizon Search</b></td>
+</tr>
+
+<tr>
+<td align="left">GAIA</td>
+<td align="center">95.1</td>
+<td align="center">96.0 🥇</td>
+<td align="center">77.6</td>
+<td align="center">92.2</td>
+<td align="center">92.2</td>
+<td align="center">88.3</td>
+</tr>
+
+<tr>
+<td align="left">BrowseComp</td>
+<td align="center">81.7 w/o Agentic Orchestration<br>82.8 🟢 w/ Agentic Orchestration</td>
+<td align="center">75.5</td>
+<td align="center">67.6</td>
+<td align="center">91.2 🥇</td>
+<td align="center">76.2</td>
+<td align="center">90.4</td>
+</tr>
+
+<tr>
+<td align="left">DeepResearch-Bench2</td>
+<td align="center">43.7 w/o Agentic Orchestration<br>47.5 w/ Agentic Orchestration</td>
+<td align="center">37.5</td>
+<td align="center">48.6 🟢</td>
+<td align="center">52.4</td>
+<td align="center">55.7</td>
+<td align="center">57.9 🥇</td>
+</tr>
+
+<tr>
+<td align="left">XBench-DS-2510</td>
+<td align="center">92.0 🥇</td>
+<td align="center">86.0</td>
+<td align="center">80.0</td>
+<td align="center">85.0</td>
+<td align="center">84.0</td>
+<td align="center">90.0</td>
+</tr>
+
+
+
+<tr>
+    <td colspan="8" align="left"><b>⚙️ Engineering Tasks</b></td>
+</tr>
+
+<tr>
+<td align="left">MLE-Lite</td>
+<td align="center">65.2 🟢</td>
+<td align="center">43.9</td>
+<td align="center">39.4</td>
+<td align="center">72.7</td>
+<td align="center">72.7</td>
+<td align="center">77.3 🥇</td>
+</tr>
+
+<tr>
+<td align="left">SciCode</td>
+<td align="center">44.3 🟢</td>
+<td align="center">44.3</td>
+<td align="center">39.5</td>
+<td align="center">58.7</td>
+<td align="center">59.0 🥇</td>
+<td align="center">56.1</td>
+</tr>
+
+<tr>
+<td align="left">SWE-bench Pro</td>
+<td align="center">61.2 🟢</td>
+<td align="center">43.6</td>
+<td align="center">59.6</td>
+<td align="center">63.3</td>
+<td align="center">64.6</td>
+<td align="center">64.6 🥇</td>
+</tr>
+
+<tr>
+<td align="left">SWE-bench Multilingual</td>
+<td align="center">72.7 🟢</td>
+<td align="center">58.7</td>
+<td align="center">71.4</td>
+<td align="center">80.8</td>
+<td align="center">81.3 🥇</td>
+<td align="center">74.1</td>
+</tr>
+
+<tr>
+    <td colspan="8" align="left"><b>📋 Instruction Following</b></td>
+</tr>
+
+<tr>
+<td align="left">IFBench</td>
+<td align="center">81.6 🥇</td>
+<td align="center">80.6</td>
+<td align="center">44.6</td>
+<td align="center">72.1</td>
+<td align="center">53.4</td>
+<td align="center">72.7</td>
+</tr>
+
+<tr>
+<td align="left">AA-LCR</td>
+<td align="center">81.0 🟢</td>
+<td align="center">74.2</td>
+<td align="center">73.2</td>
+<td align="center">88.7 🥇</td>
+<td align="center">79.7</td>
+<td align="center">84.0</td>
+</tr>
+
+
+<tr>
+    <td colspan="8" align="left"><b>🧪 Scientific Research</b></td>
+</tr>
+
+<tr>
+<td align="left">FrontierScience-Olympiad</td>
+<td align="center">81.0 🥇</td>
+<td align="center">79.0</td>
+<td align="center">70.0</td>
+<td align="center">69.0</td>
+<td align="center">67.0</td>
+<td align="center">73.0</td>
+</tr>
+
+<tr>
+<td align="left">FrontierScience-Research</td>
+<td align="center">48.3 🥇</td>
+<td align="center">40.0</td>
+<td align="center">6.7</td>
+<td align="center">21.7</td>
+<td align="center">16.7</td>
+<td align="center">26.7</td>
+</tr>
+
+<tr>
+<td align="left">HiPhO</td>
+<td align="center">45.3</td>
+<td align="center">46.4 🥇</td>
+<td align="center">39.5</td>
+<td align="center">42.4</td>
+<td align="center">39.7</td>
+<td align="center">46.2</td>
+</tr>
+
+<tr>
+<td align="left">HLE w/ tools</td>
+<td align="center">55.1 🟢</td>
+<td align="center">47.6</td>
+<td align="center">33.4</td>
+<td align="center">56.0</td>
+<td align="center">62.5</td>
+<td align="center">64.5 🥇</td>
+</tr>
+
+<tr>
+<td align="left">CMT</td>
+<td align="center">80.0 🥇</td>
+<td align="center">72.0</td>
+<td align="center">26.0</td>
+<td align="center">34.0</td>
+<td align="center">40.0</td>
+<td align="center">50.0</td>
+</tr>
+
+<tr>
+<td align="left">CritPt</td>
+<td align="center">20.0 🟢</td>
+<td align="center">4.3</td>
+<td align="center">2.9</td>
+<td align="center">23.4</td>
+<td align="center">19.1</td>
+<td align="center">32.3 🥇</td>
+</tr>
+
+
+<tr>
+    <td colspan="8" align="left"><b>🤖 General Agentic Tasks</b></td>
+</tr>
+
+<tr>
+<td align="left">Agents' Last Exam (ALE-CLI)</td>
+<td align="center">19.1 🟢</td>
+<td align="center">10.2</td>
+<td align="center">14.3</td>
+<td align="center">27.6</td>
+<td align="center">28.5</td>
+<td align="center">28.6 🥇</td>
+</tr>
+
+<tr>
+<td align="left">VitaBench</td>
+<td align="center">45.4 🟢</td>
+<td align="center">38.7</td>
+<td align="center">44.6</td>
+<td align="center">59.0 🥇</td>
+<td align="center">58.7</td>
+<td align="center">46.8</td>
+</tr>
+
+<tr>
+<td align="left">PinchBench</td>
+<td align="center">90.0 🥇</td>
+<td align="center">76.9</td>
+<td align="center">88.6</td>
+<td align="center">88.2</td>
+<td align="center">86.6</td>
+<td align="center">87.3</td>
+</tr>
+
+<tr>
+    <td colspan="8" align="left"><b>🔬 Scientific Agentic Tasks</b></td>
+</tr>
+
+<tr>
+<td align="left">ChemCOTBench</td>
+<td align="center">66.5 🟢</td>
+<td align="center">64.0</td>
+<td align="center">53.8</td>
+<td align="center">82.5 🥇</td>
+<td align="center">78.3</td>
+<td align="center">77.9</td>
+</tr>
+
+
+<tr>
+<td align="left">MatTools</td>
+<td align="center">42.6</td>
+<td align="center">47.1 🟢</td>
+<td align="center">38.6</td>
+<td align="center">24.3</td>
+<td align="center">53.2 🥇</td>
+<td align="center">45.6</td>
+</tr>
+
+<tr>
+<td align="left">OmniDocBench</td>
+<td align="center">91.5 🥇</td>
+<td align="center">89.5</td>
+<td align="center">89.6</td>
+<td align="center">91.1</td>
+<td align="center">-</td>
+<td align="center">85.8</td>
+</tr>
+
+</tbody>
+</table>
+
+> [!Note]
+> SWE-Bench Series: We use the mini-SWE-agent harness with a temperature of 1.0, top-p of 0.95, a 200K-token context window, and automatic context compaction enabled. All evaluations are conducted in a fully offline environment without internet access.
+>
+> GLM-5.3 on OmniDocBench: GLM-5.3 is a text-only (unimodal) model without multimodal input support, so its results on OmniDocBench, a multimodal benchmark, are not reported.
+
+
+## Usage
+
+### SGLang
+
+[SGLang](https://github.com/sgl-project/sglang) is a fast serving framework for large language models and vision language models.
+
+Install SGLang with uv:
+
+```shell
+uv venv --python 3.12 --seed --managed-python
+source .venv/bin/activate
+
+uv pip install sglang
+```
+
+See [its documentation](https://docs.sglang.ai/get_started/install.html) for more details.
+
+The following commands create API endpoints at `http://localhost:8000/v1`:
+
+- **Standard Version**:
+
+  ```shell
+  python -m sglang.launch_server \
+    --model-path InternScience/Sage-A1.5 \
+    --port 8000 \
+    --mem-fraction-static 0.8 \
+    --context-length 262144 \
+    --reasoning-parser qwen3 \
+    --tool-call-parser qwen3_coder
+  ```
+
+- **Multi-Token Prediction (MTP)**:
+
+  ```shell
+  python -m sglang.launch_server \
+    --model-path InternScience/Sage-A1.5 \
+    --port 8000 \
+    --mem-fraction-static 0.8 \
+    --context-length 262144 \
+    --reasoning-parser qwen3 \
+    --tool-call-parser qwen3_coder \
+    --speculative-algorithm EAGLE \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4
+  ```
+
+### vLLM
+
+[vLLM](https://github.com/vllm-project/vllm) is a high-throughput and memory-efficient inference and serving engine for LLMs.
+
+Install vLLM from the main branch via uv:
+
+```shell
+uv venv --python 3.12 --seed --managed-python
+source .venv/bin/activate
+
+uv pip install vllm --torch-backend=auto
+```
+
+See [its documentation](https://docs.vllm.ai/en/stable/getting_started/installation/index.html) for more details.
+
+The following commands create API endpoints at `http://localhost:8000/v1`:
+
+- **Standard Version** (1 GPUs, 262K context):
+
+  ```shell
+  vllm serve InternScience/Sage-A1.5 \
+    --port 8000 \
+    --max-model-len 262144 \
+    --reasoning-parser qwen3 \
+    --enable-auto-tool-choice \
+    --tool-call-parser qwen3_coder
+
+  ```
+- **Text-Only** (skips vision encoder to free KV cache memory):
+
+  ```shell
+  vllm serve InternScience/Sage-A1.5 \
+    --port 8000 \
+    --tensor-parallel-size 1 \
+    --max-model-len 262144 \
+    --reasoning-parser qwen3 \
+    --language-model-only
+  ```
+
+- **Multi-Token Prediction (MTP)**:
+  ```shell
+  vllm serve InternScience/Sage-A1.5 \
+    --port 8000 \
+    --max-model-len 262144 \
+    --reasoning-parser qwen3 \
+    --enable-auto-tool-choice \
+    --tool-call-parser qwen3_coder \
+    --speculative-config '{"method":"mtp","num_speculative_tokens":3,"moe_backend":"triton"}'
+  ```  
+
+### Advanced Modes
+
+Sage-A1.5 ships two opt-in modes that build on the standard serving setup above. Both are off by
+default: Agentic Orchestration Mode is turned on by registering a tool, Verification Mode by a chat-template flag.
+
+#### Agentic Orchestration
+
+Agentic Orchestration Mode (see [Highlights](#highlights)) lets the model fan out independent sub-questions to
+sub-agents that run **in parallel**, each with its own context window and its own tool access. It is
+enabled by exposing a `spawn_subagent` tool to the model: the model calls it whenever a task
+decomposes into independent investigations, and your harness runs each sub-task and returns the
+structured results.
+
+Sub-agents are not restricted to any fixed tool set — they can be given whatever tools your
+deployment registers (search, page reading, code execution, retrieval, internal APIs, …). By default
+they inherit the main agent's tools; set `subagent_tools` if you want them to have a different, for
+instance narrower, set.
+
+Register the following tool schema alongside your other tools:
+
+```python
+SPAWN_SUBAGENT_SCHEMA = {
+    "type": "function",
+    "function": {
+        "name": "spawn_subagent",
+        "description": (
+            "Dispatch one or more sub-agents IN PARALLEL to investigate independent "
+            "sub-questions. Each sub-agent has access to google_search and read_page "
+            "but CANNOT see your conversation. You MUST give each sub-agent everything "
+            "it needs via the `task`, `context`, and `expected_output` fields. Sub-agents "
+            "return structured JSON: {answer, status, evidence, unresolved_issues}."
+        ),
+        "parameters": {
+            "type": "object",
+            "properties": {
+                "tasks": {
+                    "type": "array",
+                    "minItems": 1,
+                    "description": "List of independent sub-tasks to dispatch in parallel.",
+                    "items": {
+                        "type": "object",
+                        "properties": {
+                            "task": {
+                                "type": "string",
+                                "description": "Self-contained sub-question. The sub-agent has no other context.",
+                            },
+                            "context": {
+                                "type": "string",
+                                "description": "Background facts and constraints the sub-agent needs.",
+                            },
+                            "expected_output": {
+                                "type": "string",
+                                "description": "Form of the desired answer (e.g. 'a year YYYY', 'a person name').",
+                            },
+                        },
+                        "required": ["task", "context", "expected_output"],
+                    },
+                },
+            },
+            "required": ["tasks"],
+        },
+    },
+}
+```
+
+Because a sub-agent cannot see the main conversation, every task must be self-contained — `task`,
+`context`, and `expected_output` are all required. Each sub-agent returns one compact JSON object
+`{answer, status, evidence, unresolved_issues}`, and the batch is handed back to the main model in
+input order.
+
+**Notes:**
+
+- Keep each sub-task **independent**. Tasks in one batch run concurrently and cannot see each
+  other's results, so anything sequential belongs in separate `spawn_subagent` calls.
+- `expected_output` acts as a format constraint on the sub-agent's `answer` (e.g. `'a year YYYY'`,
+  `'a person name'`), which keeps results short and easy to merge.
+- A sub-agent that cannot resolve its task returns `"UNKNOWN"` with a `status` of `unknown` or
+  `insufficient_evidence` rather than guessing — check `status` before using an answer.
+- Batch size and per-sub-agent turn budget are harness-side settings
+  (`max_tasks_per_spawn`, default 5; `subagent_max_turns`, default 20). Oversized batches are
+  rejected with an error message instead of being truncated.
+- The schema's `description` above names `google_search` and `read_page` because that is the
+  reference setup. If you give sub-agents a different tool set, update that sentence to match —
+  it is what tells the main model what its sub-agents can actually do.
+
+#### Verification Mode
+
+Verification Mode (see [Highlights](#highlights)) is **opt-in** and off by default. Enable it per request by
+passing `verification` through `chat_template_kwargs`; the chat template then appends the verification
+protocol trigger to the end of your system message.
+
+- **OpenAI Python client** (via `extra_body`):
+
+  ```python
+  from openai import OpenAI
+
+  client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY")
+
+  response = client.chat.completions.create(
+      model="InternScience/Sage-A1.5",
+      messages=[
+          {"role": "system", "content": "You are a helpful assistant."},
+          {"role": "user", "content": "Find the population of Beijing and cross-check it."},
+      ],
+      tools=TOOLS,
+      extra_body={"chat_template_kwargs": {"verification": True}},
+  )
+
+  message = response.choices[0].message
+  print(message.reasoning_content)  # self-review happens inside the chain of thought
+  print(message.content)
+  ```
+
+- **curl**:
+
+  ```shell
+  curl http://localhost:8000/v1/chat/completions \
+    -H 'Content-Type: application/json' \
+    -d '{
+      "model": "InternScience/Sage-A1.5",
+      "messages": [
+        {"role": "system", "content": "You are a helpful assistant."},
+        {"role": "user", "content": "Find the population of Shanghai and cross-check it."}
+      ],
+      "chat_template_kwargs": {"verification": true}
+    }'
+  ```
+
+**Notes:**
+
+- A **non-empty system message is required**. Because the trigger is appended to the end of the system
+  content, a request with `verification: true` and no system message (or a whitespace-only one) is
+  rejected with HTTP 400.
+- Pass a **JSON boolean**, not a string: `{"verification": true}`, not `{"verification": "true"}`.
+- Omitting `chat_template_kwargs` is equivalent to `{"verification": false}`, which renders the prompt
+  unchanged.
+- Verification Mode is independent of tool use — it works with or without `tools`.
+- The self-review is emitted as reasoning content, so read `reasoning_content` in addition to `content`.
+
+### Recommended Sampling Parameters
+
+For the best generation quality, we recommend the following sampling parameters:
+
+- `temperature`: 1.0
+- `top_p`: 0.95
+- `top_k`: 20
+- `min_p`: 0.0
+- `presence_penalty`: 1.5
+- `repetition_penalty`: 1.0
+  
+
+## Agent Capability Evaluation
+
+To provide the community with a unified agent evaluation codebase for fair comparison, 
+we have also open-sourced an evaluation framework for assessing agentic models across core capabilities, including tool use and multi-step reasoning. 
+The evaluation code is included in the [Sage-A1/evaluation](https://github.com/InternScience/Agents-A1/tree/main/evaluation) of this repository.
+
+We use this framework to evaluate the released model under a standardized and reproducible setting. 
+Specifically, the model is tested on a set of agent-oriented tasks that require it to understand user goals, decompose complex instructions, 
+interact with tools or environments when necessary, and produce final results. 
+The evaluation results reported in [Model Card](https://huggingface.co/InternScience/Sage-A1.5) are generated using the open-source framework above, 
+so that users can reproduce the experiments, compare other models under the same protocol, and further extend the benchmark for new agent scenarios. 
+(**Note that:** To ensure a fair comparison, we report the benchmark results from their original technical reports. 
+If a model does not report the corresponding benchmark results, we evaluate it using the same evaluation protocol as our model.)
+
+For detailed evaluation scripts, task definitions, metrics, and reproduction instructions, please refer to the evaluation codebase.
+
+## Citation
+
+If you find our work helpful, feel free to give us a cite.
+
+```
+@misc{lou2026sagea15longhorizonexecutionscientific,
+      title={Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition}, 
+      author={Sage-A1.5 Team},
+      year={2026},
+      eprint={2610.28578},
+      archivePrefix={arXiv},
+      primaryClass={cs.AI},
+      url={https://arxiv.org/abs/2610.28578}, 
+}
+```

chat_template.jinja

@@ -0,0 +1,168 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{#- Verification protocol switch, turned on with chat_template_kwargs={"verification": true}.
+    At training time this exact suffix is appended to the end of the system content
+    (script/build_verify_trigger.py); it must stay byte-for-byte identical here. #}
+{%- set verify_tail = 'Verification protocol: enabled' %}
+{%- set verify_trigger = '\n\n' + verify_tail %}
+{%- set verify_on = verification is defined and verification %}
+{%- if verify_on and verification is string and verification|lower not in ['true', '1', 'yes', 'on'] %}
+    {{- raise_exception('verification must be a boolean, not the string ' ~ verification|tojson ~ '. Send a JSON boolean: {"chat_template_kwargs": {"verification": true}}.') }}
+{%- endif %}
+{%- if verify_on and (messages[0].role != 'system' or not render_content(messages[0].content, false, true)|trim) %}
+    {{- raise_exception('verification=true requires a non-empty system message: the verification protocol trigger is appended to the end of the system content.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- set content = content + verify_trigger if (verify_on and not content.endswith(verify_tail)) else content %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- set content = content + verify_trigger if (verify_on and not content.endswith(verify_tail)) else content %}
+        {{- '<|im_start|>system\n' + 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" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|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 %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- 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' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,119 @@
+{
+    "architectures": [
+        "Qwen3_5MoeForConditionalGeneration"
+    ],
+    "image_token_id": 248056,
+    "model_type": "qwen3_5_moe",
+    "text_config": {
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "attn_output_gate": true,
+        "bos_token_id": 248044,
+        "dtype": "bfloat16",
+        "eos_token_id": 248044,
+        "full_attention_interval": 4,
+        "head_dim": 256,
+        "hidden_act": "silu",
+        "hidden_size": 2048,
+        "initializer_range": 0.02,
+        "layer_types": [
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention"
+        ],
+        "linear_conv_kernel_dim": 4,
+        "linear_key_head_dim": 128,
+        "linear_num_key_heads": 16,
+        "linear_num_value_heads": 32,
+        "linear_value_head_dim": 128,
+        "mamba_ssm_dtype": "float32",
+        "max_position_embeddings": 262144,
+        "model_type": "qwen3_5_moe_text",
+        "moe_intermediate_size": 512,
+        "mtp_num_hidden_layers": 1,
+        "mtp_use_dedicated_embeddings": false,
+        "num_attention_heads": 16,
+        "num_experts": 256,
+        "num_experts_per_tok": 8,
+        "num_hidden_layers": 40,
+        "num_key_value_heads": 2,
+        "output_router_logits": false,
+        "pad_token_id": null,
+        "partial_rotary_factor": 0.25,
+        "rms_norm_eps": 1e-06,
+        "rope_parameters": {
+            "mrope_interleaved": true,
+            "mrope_section": [
+                11,
+                11,
+                10
+            ],
+            "partial_rotary_factor": 0.25,
+            "rope_theta": 10000000,
+            "rope_type": "default"
+        },
+        "router_aux_loss_coef": 0.001,
+        "shared_expert_intermediate_size": 512,
+        "tie_word_embeddings": false,
+        "use_cache": true,
+        "vocab_size": 248320
+    },
+    "tie_word_embeddings": false,
+    "transformers_version": "4.57.1",
+    "video_token_id": 248057,
+    "vision_config": {
+        "deepstack_visual_indexes": [],
+        "depth": 27,
+        "hidden_act": "gelu_pytorch_tanh",
+        "hidden_size": 1152,
+        "in_channels": 3,
+        "initializer_range": 0.02,
+        "intermediate_size": 4304,
+        "model_type": "qwen3_5_moe",
+        "num_heads": 16,
+        "num_position_embeddings": 2304,
+        "out_hidden_size": 2048,
+        "patch_size": 16,
+        "spatial_merge_size": 2,
+        "temporal_patch_size": 2
+    },
+    "vision_end_token_id": 248054,
+    "vision_start_token_id": 248053
+}

model-00000-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d3409417fa5f1e3edd85909392a2f0765a01f65827f1fface7453f1442bcec8
+size 5368997288

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:671387ecd4e1a09f94055c2f9a06cd4d132a711b52c9fee314bd1baeb8d198f8
+size 5369063800

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2d35969e7a8b428bad518f77bee6ef2dccf2e81bfa42e6be77b5540ade3286d
+size 5369063512

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c266d9026b8b722aab6d9a31d884605b0ead4447a88bd4a3c1ae29a6e3c66083
+size 5369065752

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93d865bb4125d9a7ed4b8cbcb3a736989f65d70ea107aa59775e074681bda507
+size 5369066360

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d76e6af642b41f241c10e369995b8bc6ffacde97c69c1ac5f1047e5dbdec925d
+size 5369066072

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b09f79a48f4fbadab908d3424e7263a2f115bdace0bdb151b341223e1c5e0afb
+size 5369066240

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2e8663737513dfbb6a92c3f616a5864db8e257d731aac4230360371597de991
+size 5369066360

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f737a41be7bdb4915eec15d02a5702166de4fb6a000c0b851520479a59d7722
+size 5369066072

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20b7acf194b67f8ec53dc64db9ad861f6788d6037f1ff52bb4ff1bc31e79b041
+size 5369066240

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2c8d703eea94c4fd06b49d044f23da05bdd4d1499fef481cad62dcb8d3cd781
+size 5369066360

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c5dac281c922d8eb0fd84b4079eae022db7008d3c063c4abc92d88f327d9ee5
+size 5369066072

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0a325bfd8b30aa7235103b1bf366e7c9088af9a7d884b624e6576a738fe4601
+size 5364702376

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d39a38b6b6968400db10786e06254b563c2034978de55fef0d6137a0a59c82a
+size 425339080

model-mtp.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6c8f36002c1db3906a771f613a7295486402f5c39e782df1607f01bce5f2e3f
+size 1689376064

preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 16777216,
+        "shortest_edge": 65536
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "image_processor_type": "Qwen2VLImageProcessorFast"
+}

processor_config.json

@@ -0,0 +1,63 @@
+{
+  "image_processor": {
+    "data_format": "channels_first",
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessorFast",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343

tokenizer_config.json

@@ -0,0 +1,305 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "248044": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248045": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248046": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248047": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248048": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248049": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248050": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248051": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248052": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248053": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248054": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248055": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248056": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248057": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248058": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "248059": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "248060": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "248061": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "248062": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "248063": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "248064": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "248065": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "248066": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "248067": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "248068": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "248069": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "248070": {
+      "content": "<|audio_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248071": {
+      "content": "<|audio_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248072": {
+      "content": "<tts_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248073": {
+      "content": "<tts_text_bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248074": {
+      "content": "<tts_text_eod>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248075": {
+      "content": "<tts_text_bos_single>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248076": {
+      "content": "<|audio_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n    {%- if content is string %}\n        {{- content }}\n    {%- elif content is iterable and content is not mapping %}\n        {%- for item in content %}\n            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n                {%- if is_system_content %}\n                    {{- raise_exception('System message cannot contain images.') }}\n                {%- endif %}\n                {%- if do_vision_count %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}\n                    {{- 'Picture ' ~ image_count.value ~ ': ' }}\n                {%- endif %}\n                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n            {%- elif 'video' in item or item.type == 'video' %}\n                {%- if is_system_content %}\n                    {{- raise_exception('System message cannot contain videos.') }}\n                {%- endif %}\n                {%- if do_vision_count %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}\n                    {{- 'Video ' ~ video_count.value ~ ': ' }}\n                {%- endif %}\n                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n            {%- elif 'text' in item %}\n                {{- item.text }}\n            {%- else %}\n                {{- raise_exception('Unexpected item type in content.') }}\n            {%- endif %}\n        {%- endfor %}\n    {%- elif content is none or content is undefined %}\n        {{- '' }}\n    {%- else %}\n        {{- raise_exception('Unexpected content type.') }}\n    {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n    {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{#- Verification protocol switch, turned on with chat_template_kwargs={\"verification\": true}.\n    At training time this exact suffix is appended to the end of the system content\n    (script/build_verify_trigger.py); it must stay byte-for-byte identical here. #}\n{%- set verify_tail = 'Verification protocol: enabled' %}\n{%- set verify_trigger = '\\n\\n' + verify_tail %}\n{%- set verify_on = verification is defined and verification %}\n{%- if verify_on and verification is string and verification|lower not in ['true', '1', 'yes', 'on'] %}\n    {{- raise_exception('verification must be a boolean, not the string ' ~ verification|tojson ~ '. Send a JSON boolean: {\"chat_template_kwargs\": {\"verification\": true}}.') }}\n{%- endif %}\n{%- if verify_on and (messages[0].role != 'system' or not render_content(messages[0].content, false, true)|trim) %}\n    {{- raise_exception('verification=true requires a non-empty system message: the verification protocol trigger is appended to the end of the system content.') }}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n    {{- '<|im_start|>system\\n' }}\n    {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\" }}\n    {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n<parameter=example_parameter_2>\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\nReminder:\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n</IMPORTANT>' }}\n    {%- if messages[0].role == 'system' %}\n        {%- set content = render_content(messages[0].content, false, true)|trim %}\n        {%- set content = content + verify_trigger if (verify_on and not content.endswith(verify_tail)) else content %}\n        {%- if content %}\n            {{- '\\n\\n' + content }}\n        {%- endif %}\n    {%- endif %}\n    {{- '<|im_end|>\\n' }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {%- set content = render_content(messages[0].content, false, true)|trim %}\n        {%- set content = content + verify_trigger if (verify_on and not content.endswith(verify_tail)) else content %}\n        {{- '<|im_start|>system\\n' + content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" %}\n        {%- set content = render_content(message.content, false)|trim %}\n        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n            {%- set ns.multi_step_tool = false %}\n            {%- set ns.last_query_index = index %}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n    {{- raise_exception('No user query found in messages.') }}\n{%- endif %}\n{%- for message in messages %}\n    {%- set content = render_content(message.content, true)|trim %}\n    {%- if message.role == \"system\" %}\n        {%- if not loop.first %}\n            {{- raise_exception('System message must be at the beginning.') }}\n        {%- endif %}\n    {%- elif message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- set reasoning_content = reasoning_content|trim %}\n        {%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}\n            {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\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                {%- if loop.first %}\n                    {%- if content|trim %}\n                        {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                    {%- else %}\n                        {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                    {%- endif %}\n                {%- else %}\n                    {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                {%- endif %}\n                {%- if tool_call.arguments is defined %}\n                    {%- for args_name, args_value in tool_call.arguments|items %}\n                        {{- '<parameter=' + args_name + '>\\n' }}\n                        {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}\n                        {{- args_value }}\n                        {{- '\\n</parameter>\\n' }}\n                    {%- endfor %}\n                {%- endif %}\n                {{- '</function>\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n            {{- '<|im_end|>\\n' }}\n        {%- elif loop.last %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- else %}\n        {{- raise_exception('Unexpected message role.') }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- else %}\n        {{- '<think>\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "add_bos_token": false,
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "extra_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  }
+}

video_preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 25165824,
+        "shortest_edge": 4096
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "video_processor_type": "Qwen3VLVideoProcessor"
+}