Qwen3.6-35B-A3B-Escha-W2 — 2-bit eschamoe model card (verified per-GPU configs, 5-GPU benchmarks)

.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

LICENSE

@@ -0,0 +1,202 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2024-2026 Alibaba Cloud (Qwen Team) — base model Qwen3.6-35B-A3B.
+   2-bit quantized derivative Copyright 2026 EschaLabs.
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -0,0 +1,549 @@
+---
+license: apache-2.0
+base_model:
+- Qwen/Qwen3.6-35B-A3B
+base_model_relation: quantized
+pipeline_tag: text-generation
+language:
+- en
+tags:
+- mixture-of-experts
+- moe
+- qwen3
+- 2-bit
+- quantization
+- eschamoe
+- sglang
+- zml
+- code
+- reasoning
+- conversational
+metrics:
+- accuracy
+- code_eval
+model-index:
+- name: Qwen3.6-35B-A3B-Escha-W2
+  results:
+  - task: {type: text-generation, name: Code Generation}
+    dataset: {type: evalplus/humanevalplus, name: HumanEval+}
+    metrics:
+    - {type: pass@1, value: 92.07, name: pass@1 (greedy, thinking-off)}
+  - task: {type: text-generation, name: Code Reasoning}
+    dataset: {type: cruxeval, name: CRUXEval-O}
+    metrics:
+    - {type: accuracy, value: 61.75, name: acc (n=800)}
+  - task: {type: text-generation, name: Code Generation}
+    dataset: {type: livecodebench, name: LiveCodeBench v6 (release_v6, N=182 subset)}
+    metrics:
+    - {type: pass@1, value: 62.64, name: pass@1 (subset — retention vs FP8)}
+  - task: {type: text-generation, name: Commonsense Reasoning}
+    dataset: {type: commonsense, name: Commonsense-6 (avg)}
+    metrics:
+    - {type: accuracy, value: 76.06, name: avg acc (thinking-off)}
+  - task: {type: text-generation, name: Knowledge & Reasoning}
+    dataset: {type: TIGER-Lab/MMLU-Pro, name: MMLU-Pro}
+    metrics:
+    - {type: accuracy, value: 80.9, name: acc (5-shot CoT, thinking-on)}
+  - task: {type: text-generation, name: Math Reasoning}
+    dataset: {type: math-500, name: MATH-500}
+    metrics:
+    - {type: accuracy, value: 93.8, name: acc (thinking-on, budget-capped)}
+  - task: {type: text-generation, name: Graduate-level Science}
+    dataset: {type: gpqa, name: GPQA-Diamond}
+    metrics:
+    - {type: accuracy, value: 77.8, name: acc (thinking-on)}
+---
+
+# Qwen3.6-35B-A3B-Escha-W2 — 2-bit quantized (`eschamoe`)
+
+By **[Escha Labs Inc.](https://eschalabs.com/)**
+
+**Escha-W2** is a 2-bit quantized build of **Qwen3.6-35B-A3B**, a Mixture-of-Experts model with
+256 experts, packaged with everything needed to serve it locally through an **OpenAI-compatible
+HTTP API**. (The runtime and served model id keep the `escha` name — see *Connecting a client*.)
+
+The whole thing is **12.3 GB on disk** and runs on a **single 24 GB consumer GPU** — or on a
+**16 GB card** (e.g. RTX 5060 Ti) with a reduced context window.
+
+| | |
+|---|---|
+| Base model | Qwen3.6-35B-A3B (MoE, 256 experts) |
+| Quantization | 2-bit experts (`eschamoe`; mixed 2/3-bit per projection), int8 dense layers |
+| Size on disk | 12.3 GB |
+| Minimum GPU | **16 GB** VRAM (reduced context), **24 GB** recommended; NVIDIA Ampere (sm_80) → Blackwell (sm_120) |
+| Platform | Linux x86-64, **glibc ≥ 2.28** (Ubuntu 20.04+, RHEL/Rocky/Alma 8+) — the wheel is `manylinux_2_28` |
+| CUDA | an NVIDIA **driver** — no CUDA toolkit needed (`ptxas` ships inside `triton`, a PyTorch dependency) |
+| Python | **3.12**, for the SGLang engine — the ZML engine needs no Python at all |
+| Interface | OpenAI-compatible `/v1` on port 30000 |
+
+---
+
+## Contents
+
+| Path | What it is |
+|---|---|
+| `*.safetensors`, `config.json`, `tokenizer*`, `vocab.json`, `merges.txt`, `*.jinja` | the quantized weights, tokenizer and config (at the repo root) |
+| `opencode.json` | example client config (see *Connecting a client*) |
+| `LICENSE`, `THIRD_PARTY_LICENSES/` | Apache-2.0 plus the upstream license texts |
+
+This repo holds **only the model**. The **runtimes** live in a separate repo,
+**[EschaLabs/escha-runtime-qwen3moe](https://huggingface.co/EschaLabs/escha-runtime-qwen3moe)**,
+one directory per engine: **`sglang/`** (the `escha` wheel + `serve.sh` — servers, concurrency,
+tools, structured output) and **`zml/`** (a single-binary runtime — no Python, no dependencies,
+and the stronger single-user decode on most cards).
+
+### Which engine?
+
+**Use `sglang/` unless you have a specific reason not to.** It is the engine every number on this
+page was measured with, and the only one that supports concurrency, tool calling, structured
+output and a reasoning parser.
+
+Choose `zml/` when you want a single-user box with **no Python at all** — one binary, no venv, no
+CUDA toolkit, 14-second install — and you generate long answers. It is the only way to run this
+model without a Python environment.
+
+Two things decide whether that trade is worth it on **your** box:
+
+- **The decode lead is card-dependent.** On answers ≥1k tokens, measured 2026-07-27: **+15–26%**
+  on an RTX 5090 or 3090, **+8–11%** on a 5080, **+2–5%** on a 4090 (against a fully tuned SGLang),
+  and a **tie** on a 5060 Ti. ZML loses short replies on every card, and its first start compiles
+  graphs — 75–145 s on a 4090, minutes on a 16 GB card, versus ~33 s for SGLang.
+- **The lead is greedy-only.** ZML's fast path fuses 16 decode steps per GPU dispatch with
+  on-device argmax; any `temperature > 0` falls back to a per-token loop that is **~2.15× slower**
+  (RTX 4090, 512-token answer: 218 tok/s at `temperature: 0` vs 102 at `0.6`). Send
+  `"temperature": 0` for the quoted numbers — including with `opencode.json` below, which sets
+  `0.6`. The SGLang engine samples at full speed.
+
+> **ZML needs the 24 GB it asks for.** On 16 GB cards long prompts fail with an opaque
+> `HTTP 500` — measured from ≥2,048 tokens on a 5080 and from ~700 on a 5060 Ti. Use the
+> SGLang engine on 16 GB.
+
+---
+
+## Quickstart
+
+Install the **[Escha runtime](https://huggingface.co/EschaLabs/escha-runtime-qwen3moe)** first (wheel +
+`serve.sh` + full detail, including two requirements that fail **quietly**) — then download this
+model and serve it:
+
+```bash
+python3.12 -m venv .venv && source .venv/bin/activate
+pip install -U pip wheel "huggingface_hub[cli]"
+
+# torch MUST be pinned to 2.9.x. `escha._C` is ABI-linked to libtorch and the wheel does
+# NOT declare a torch dependency, so a bare ">=2.9.0" resolves to 2.11 and `import escha`
+# then fails with `undefined symbol: _ZN3c10...` — after two multi-GB downloads.
+pip install "torch==2.9.*" --index-url https://download.pytorch.org/whl/cu128
+
+# 1. runtime: fetch the sglang/ engine dir (wheel + serve.sh), install the wheel.
+#    Use the glob — a pinned wheel filename goes stale on every rebuild.
+hf download EschaLabs/escha-runtime-qwen3moe --include "sglang/*" --local-dir .
+pip install ./sglang/escha-*.whl     # pulls transformers>=5.8 + the full dep closure
+
+# 2. this model:
+hf download EschaLabs/Qwen3.6-35B-A3B-Escha-W2 --local-dir ./escha-w2
+
+MODEL=./escha-w2 bash sglang/serve.sh
+```
+
+Sanity-check the stack before serving — the first line must print three `True`s:
+
+```bash
+python -c "import torch, escha, sglang; print(torch.cuda.is_available(), hasattr(torch.ops.escha, 'escham_moe_linear'), bool(sglang.__version__))"
+python -c "import escha; print(escha.__version__)"     # paste this into bug reports
+```
+
+Then:
+
+```bash
+curl -s http://127.0.0.1:30000/v1/models | python3 -m json.tool
+```
+
+> **If generation looks like fluent nonsense, check your `transformers` version first.**
+> Below 5.8 the server does not fail — it logs one warning and then serves with the wrong
+> architecture parameters. This is the single most likely cause of bad output.
+
+---
+
+## Connecting a client
+
+The server speaks the standard OpenAI API, so anything that can point at a custom base URL works —
+LM Studio, opencode, Open WebUI, the `openai` Python package, plain `curl`.
+
+```
+Base URL : http://127.0.0.1:30000/v1
+Model    : escha-qwen36-35b-a3b-w2      (override with SERVED_NAME=...)
+API key  : not required for localhost
+```
+
+`opencode.json` in this folder is a ready-made config for [opencode](https://opencode.ai) — copy it
+to `~/.config/opencode/opencode.json`. It sets `temperature: 0.6` (Qwen's recommended sampling for
+answer quality); on the **ZML** engine that halves decode speed — set `0` there if you want the
+headline throughput instead.
+
+If you expose the server beyond your own machine, set `HOST=0.0.0.0` **and** `API_KEY=...`, and put
+it behind a VPN or tunnel rather than opening the port directly to the internet.
+
+---
+
+## Thinking mode
+
+The model can reason before answering. Toggle it **per request** via `chat_template_kwargs` — a
+top-level `enable_thinking` field is ignored:
+
+```json
+{
+  "model": "escha-qwen36-35b-a3b-w2",
+  "messages": [{"role": "user", "content": "..."}],
+  "chat_template_kwargs": {"enable_thinking": true}
+}
+```
+
+With thinking **on**, the reasoning arrives in `reasoning_content` and the answer in `content` —
+read both. To turn thinking off for the whole server instead, start it with `THINK=0`.
+
+`usage.reasoning_tokens` reports how much of the answer went to reasoning — use it to size a
+[thinking budget](https://huggingface.co/EschaLabs/escha-runtime-qwen3moe/blob/main/sglang/INSTALL.md).
+
+---
+
+## Tuning
+
+`serve.sh` documents every knob at the top of the file. The ones that matter most on a 24 GB card:
+
+| Variable | Default | Notes |
+|---|---|---|
+| `MEM` | `0.78` | Fraction of VRAM reserved for the weight + KV pool. **Too low fails**, with "Not enough memory … increase --mem-fraction-static". Lower it only together with `CTXLEN`. |
+| `CTXLEN` | `32768` | Context length. Raise once the defaults work. |
+| `GRAPHS` | `1` | CUDA graphs — **mandatory for performance** on this launch-bound hybrid MoE (eager is ~4.4× slower). Set `0` only to debug a capture failure. |
+| `RADIX` | `1` | Prefix caching. **`RADIX=0` is worth ~20% single-stream decode** here — the default is `1` for multi-turn agent reuse, so set it explicitly. See below. |
+| `THINK` | `1` | `0` serves with thinking disabled by default. |
+| `SERVED_NAME` | `escha-qwen36-35b-a3b-w2` | The model id clients must use. |
+
+For per-architecture (incl. the RTX 50-series `ATTN_BACKEND=triton` knob) and per-VRAM
+(16 / 24 / 40 GB+) launch recipes, see the **[runtime's "Running on your GPU" cookbook](https://huggingface.co/EschaLabs/escha-runtime-qwen3moe/blob/main/sglang/INSTALL.md)**.
+
+---
+
+## Verified configurations
+
+Each command below was run on 2026-07-27 on the **first** card named in its heading, and produced
+the numbers in [Performance across GPUs](#performance-across-gpus); a second name is a same-arch,
+same-VRAM sibling the recipe should carry to, not a separately measured card. Copy the line for
+your card. `MODEL=` and `VENV=` are omitted for brevity — set `MODEL` to your download directory.
+
+**RTX 4090 / L40S — 24 GB, sm_89**
+
+```bash
+RADIX=0 MAXMAMBA=32 MAXREQ=32 CUDA_GRAPH_BS="1 2 4 8 16 32" \
+  MEM=0.78 CTXLEN=32768 bash sglang/serve.sh          # 225 tok/s bs1 · 1,321 tok/s @ bs32
+```
+
+**RTX 3090 / A6000 — 24 GB, sm_86 (Ampere)**
+
+```bash
+RADIX=0 MAXMAMBA=16 MAXREQ=16 CUDA_GRAPH_BS="1 2 4 8 16" \
+  MEM=0.78 CTXLEN=32768 bash sglang/serve.sh          # 154 tok/s bs1 · 390 tok/s @ bs16
+# serving ≥8 concurrent streams? add INT8=off  (+12–20% aggregate, costs 2.2 GB of KV pool)
+```
+
+**RTX 5090 — 32 GB, sm_120**
+
+```bash
+# single user (best latency)
+INT8=on ATTN_BACKEND=triton MEM=0.82 CTXLEN=32768 bash sglang/serve.sh    # 283 tok/s bs1
+# batched (best throughput)
+ATTN_BACKEND=triton MEM=0.82 CTXLEN=32768 MAXREQ=32 MAXMAMBA=48 RADIX=0 \
+  CUDA_GRAPH_BS="1 2 4 8 16 32" bash sglang/serve.sh                      # ~2,670 tok/s @ bs32
+```
+
+**RTX 5080 / 5060 Ti — 16 GB, sm_120**
+
+```bash
+ATTN_BACKEND=triton MEM=0.92 CTXLEN=8192 CHUNK=2048 MAXREQ=16 MAXMAMBA=16 \
+  RADIX=0 GRAPHS=1 CUDA_GRAPH_BS="1 2 4 8 16" bash sglang/serve.sh
+# 5080: 212 tok/s bs1 · 914 tok/s @ bs16   |   5060 Ti: 128 tok/s bs1 · 387 tok/s @ bs16
+```
+
+### Three settings that are worth getting right
+
+- **`CUDA_GRAPH_BS` must list your maximum batch size.** If `MAXREQ=16` but the capture list
+  stops at 8, batch 16 silently runs **eager** — measured **−8.8%** aggregate on a 5060 Ti, and it
+  makes batch 16 look like a throughput ceiling when it is not. Costs ~2.5 s of startup and no
+  VRAM.
+- **`MEM=0.92`, not higher, on a 16 GB card.** At `0.94` a 16 GB card has ~0.43 GB of headroom and
+  a `1024/1024` batch-16 request can OOM inside the fused MoE op and take the **whole server** down.
+  `0.92` survives it and costs nothing in throughput.
+- **`RADIX=0` unless you specifically need prefix caching.** On this hybrid model the radix cache
+  is incompatible with the overlap scheduler, so `RADIX=1` silently disables it — worth **~20%
+  single-stream decode** (measured 187 → 225 tok/s on a 4090) and it also clamps concurrency via
+  the mamba state pool. Keep `RADIX=1` only for multi-turn agent workloads that genuinely reuse
+  long prefixes.
+
+This checkpoint is **text-only** (the `qwen3_5_moe` config declares a vision tower, but the quantized
+weights contain none — vision is in the quant `ignore` list); `serve.sh` sets `SGLANG_VLM_TEXT_ONLY=1`
+by default so the tower is never instantiated. Do not send image inputs.
+
+---
+
+## Requirements in detail
+
+- **GPU** — **16 GB VRAM minimum** (reduced context; e.g. RTX 5060 Ti), **24 GB recommended**;
+  NVIDIA Ampere (sm_80) through Blackwell (sm_120). The runtime ships a fat binary with native
+  kernels for Ampere (sm_80/86), Ada (sm_89), Hopper (sm_90), and Blackwell (sm_100/sm_120), plus
+  PTX for forward-compat on newer GPUs. The kernel launch route is auto-selected per GPU at runtime.
+  Cards older than sm_80 (e.g. Turing) are not supported.
+- **An NVIDIA driver — but no CUDA toolkit.** `ptxas` ships inside `triton`, which PyTorch already
+  installs, and `serve.sh` probes that copy first; you do not need to install CUDA to serve this
+  model. If discovery ever fails, point `TRITON_PTXAS_PATH` at a ptxas **binary** (not its
+  directory — a directory is silently rejected).
+- **Linux x86-64 with glibc ≥ 2.28** — the wheel is tagged `manylinux_2_28`, so Ubuntu 20.04+ and
+  RHEL/Rocky/Alma 8+ are fine. WSL2 is untested.
+- **`vm.overcommit_memory=1`** — on a fresh machine the first Triton compile forks a large process
+  and fails under the default setting. `serve.sh` prints the one-line fix if it detects this.
+- **`transformers >= 5.8` — ignore this file's `transformers_version` for pinning.** The runtime
+  wheel installs a compatible transformers for you. Do **not** pin transformers to "match" any
+  version field you find in the repo's `config.json` — versions below 5.8 lack this architecture's
+  config class and serve fluent-looking nonsense with only a single warning.
+
+### Format notes
+
+- `escha_s_in` / `escha_s_out` ship as **all-ones**: the trained scales are already folded into
+  `escha_rin` / `escha_rout` at export. Do not edit or "re-apply" them — non-ones values would be
+  applied *on top of* the folded scales.
+- `escha_config` (int32[9]) and `quantization_config.layer_meta` are **informational** (written by
+  the exporter for offline tools). The runtime derives each projection's code rate from the code
+  tensor's shape; `layer_meta` records it as `K` (2 for `gate_up_proj`, 3 for `down_proj`) with
+  `bits` mirroring `K`.
+- The `mtp.*` tensors (next-token-prediction head) are present in the checkpoint but **not
+  served**; speculative decoding additionally needs a separate draft export that is not part of
+  this release.
+
+---
+
+## Benchmarks
+
+Two questions matter for a 2-bit build: **how much quality did it cost**, and **how does it serve**.
+Quality is measured against an **FP8 baseline**[^fp8]; serving is measured on a **single RTX 4090**.
+
+> **Which runtime produced these numbers.** Every figure on this page — quality and serving —
+> was measured through the **SGLang engine** of the
+> [escha-runtime-qwen3moe](https://huggingface.co/EschaLabs/escha-runtime-qwen3moe/tree/main/sglang)
+> repo, using its shipped `serve.sh` and the launch recipes in
+> [`sglang/INSTALL.md`](https://huggingface.co/EschaLabs/escha-runtime-qwen3moe/blob/main/sglang/INSTALL.md).
+> The same repo also ships a **[ZML engine](https://huggingface.co/EschaLabs/escha-runtime-qwen3moe/tree/main/zml)**
+> (single-binary, no Python) whose serving profile differs: higher sustained single-stream
+> decode on long answers, but **one request at a time** — so none of the batched
+> throughput or concurrency figures below apply to it. Pick the engine from the
+> [runtime README](https://huggingface.co/EschaLabs/escha-runtime-qwen3moe) comparison.
+
+### Quality vs FP8
+
+**Commonsense-6**[^cs6] — thinking-off, same box, paired:
+
+| | GB | boolq | piqa | arc-e | arc-c | hellaswag | winogrande | **avg** |
+|---|---|---|---|---|---|---|---|---|
+| FP8 baseline | 35.0 | 84.46 | 82.59 | 71.93 | 54.86 | 83.38 | 73.40 | 75.10 |
+| **this build** | **12.3** | **88.38** | **82.10** | **73.82** | **55.38** | **82.44** | **74.27** | **76.06** |
+
+**Capabilities** — one representative benchmark per axis, this build vs the FP8 baseline. Retention is
+this-build ÷ FP8.
+
+| Capability | Benchmark | FP8 | **this build** | Δ | retention |
+|---|---|---|---|---|---|
+| Broad knowledge | MMLU-Pro (n=12,032) | 82.3 | **80.9** | −1.4 | 98.3% |
+| Math reasoning | MATH-500 (n=500)[^math] | 91.2 | **93.8** | +2.6 | 102.9% |
+| Graduate science | GPQA-Diamond (n=198)[^gpqa] | 74.7 | **77.8** | +3.1 | 104.2% |
+| Coding | LiveCodeBench v6 (n=182)[^lcb] | 67.0 | **62.6** | −4.4 | 93.4% |
+| Tool use | BFCL-AST, weighted (n=1000)[^bfcl] | 88.2 | **88.9** | +0.7 | 100.8% |
+| Long context | RULER, 8k–128k avg[^ruler] | 89.4 | **89.9** | +0.5 | 100.5% |
+| **mean**[^avg] | unweighted, 6 axes | **82.1** | **82.3** | **+0.2** | **100.2%** |
+
+Across the six axes this 2-bit build stays within noise of the ~3× larger FP8 baseline everywhere except
+long-horizon code generation (LiveCodeBench), the one capacity-bound gap. Coding parity is corroborated by
+two better-powered paired-McNemar ties with FP8: HumanEval+ 92.07 vs 93.9 and CRUXEval-O 61.75 vs 63.0.[^code]
+
+#### Evaluation protocol (reproduce these numbers)
+
+Thinking mode and the token budget change reasoning scores materially, so both are stated per
+benchmark. **Both arms (this build and FP8) always ran the identical protocol**, so every Δ above is
+apples-to-apples.
+
+| Benchmark | Thinking | Token budget | Notes |
+|---|---|---|---|
+| MMLU-Pro | **on**, 5-shot CoT chat | `max_tokens` **4,096** | **13.9% of answers hit the cap** (FP8: 13.0% — symmetric). See the caveat below. |
+| MATH-500 | **on** + **thinking-budget cap** | budget 28,672 / `max_tokens` 32,768 | Cap forces `</think>` → **0 non-terminations**. |
+| GPQA-Diamond | **on**, uncapped thinking | 16,384 | |
+| LiveCodeBench v6 | **on** + thinking-budget cap | budget 16,384 / `max_tokens` 32,768 | |
+| HumanEval+, MBPP+, CRUXEval-O | **off** | 4,096 | Thinking-on derails code extraction. |
+| BFCL-AST, Commonsense-6 | **off** | 4,096 / loglikelihood | |
+| RULER 8k–128k | **off** | retrieval | |
+
+Sampling for the thinking-on runs is Qwen's recommended thinking config: `temperature=1.0,
+top_p=0.95, top_k=20, min_p=0, presence_penalty=1.5`, n=1.
+
+> **Caveat on the MMLU-Pro number (read if you are comparing to published leaderboards).** At a
+> 4,096-token cap with thinking on, **13.9%** of questions run out of budget mid-reasoning; those are
+> scored from the truncated trace and land at **49.5%** correct versus **86.0%** for answers that
+> finish. FP8 truncates at the same rate (13.0%), so the **−1.4 gap is unaffected** — but both
+> absolute numbers are **conservative by roughly 2–3 pp** against harnesses that allow a larger
+> budget (this is the main reason our FP8 baseline reads 82.3 where Qwen publishes 85.2 for the
+> unquantized model). If you re-run with a bigger budget — or better, with the
+> [thinking-budget cap](https://huggingface.co/EschaLabs/escha-runtime-qwen3moe/blob/main/sglang/INSTALL.md#bounded-thinking-thinking_budget)
+> that forces an answer — expect **both** arms to rise by a similar margin.
+
+### Performance across GPUs
+
+Measured end-to-end on five consumer cards with the **SGLang engine**
+([`sglang/`](https://huggingface.co/EschaLabs/escha-runtime-qwen3moe/tree/main/sglang); launch
+recipes per card in the
+[runtime cookbook](https://huggingface.co/EschaLabs/escha-runtime-qwen3moe/blob/main/sglang/INSTALL.md)).
+*Decode = what one user sees streaming; peak throughput = total server output at the best batch size.*
+
+| GPU | VRAM | arch | 1-user decode | TTFT (2k prompt) | peak server throughput | context |
+|---|---|---|---|---|---|---|
+| RTX 5090 | 32 GB | sm_120 | **283 tok/s**[^int8on] | 0.22 s | **~2,670 tok/s** @ bs 32 | 32k |
+| RTX 4090 | 24 GB | sm_89 | **225 tok/s** | 0.26 s | **1,321 tok/s** @ bs 32 | 32k |
+| RTX 5080 | 16 GB | sm_120 | **212 tok/s** | 0.18 s @1k | 914 tok/s @ bs 16 | 8k |
+| RTX 3090 | 24 GB | sm_86 | **154 tok/s** | 0.63 s | 390 tok/s @ bs 16 | 32k |
+| RTX 5060 Ti | 16 GB | sm_120 | **128 tok/s** | 0.52 s @1k | 387 tok/s @ bs 16 | 8k |
+
+Every row was measured on that physical card with the launch command in
+[Verified configurations](#verified-configurations) above — 2026-07-27, five independent
+fresh-machine evaluations, one harness.
+
+For scale: fast reading is ~5 words/s (≈7 tok/s) — even the slowest card here decodes ~18× faster
+than you can read, and a 5090 serves a 32-user pool at interactive speed. Three levers matter on
+every card: **CUDA graphs** (`GRAPHS=1`, the default — this hybrid MoE is launch-bound eager, graphs
+are worth **4.4×**), **`RADIX=0`** for throughput/latency work (worth ~20% single-stream — see
+Verified configurations), and the **`INT8` knob** (single-user vs batched).
+
+Two things the spread above is *not*: it is not a VRAM ranking (the 16 GB 5080 beats the 24 GB
+3090 by 38%), and it is not a generation ranking. It tracks **memory bandwidth and SM count** —
+this is a 2-bit model, so decode is bandwidth-bound at batch 1 and compute-bound at batch.
+Ampere (3090) is the slowest per stream and also the only card here where the kernel route
+auto-selects `lovelace` rather than `blackwell`.
+
+[^int8on]: 5090 and 3090 single-user numbers use `INT8=on` (int8-as-stored; measured +21–24% at
+    bs 1 on the 5090, +35–42% on the 3090). Peak-throughput numbers use `INT8` off above 24 GB —
+    int8 *costs* 11–52% at high batch, and the crossover is around **concurrency 8** (measured on
+    the 3090). Cards ≤ 24 GB auto-enable int8; if you serve ≥ 8 concurrent streams on a 24 GB card,
+    set `INT8=off` explicitly.
+
+### Serving — NVIDIA ISL/OSL grid, RTX 4090
+
+Aggregate decode tok/s. Input/output shapes are the standard NVIDIA grid; 2 reps, median[^grid].
+This grid was **reproduced from scratch on a separate 4090** following only the public docs:
+all bs 1 shapes matched within 0.1–1.8% (measured on the same decode window), including the
+20,000-token-prompt cell to 0.1%.
+
+| ISL / OSL | bs 1 | bs 8 | bs 16 |
+|---|---|---|---|
+| 128 / 128 | 225.2 | 956.8 | **1139.3** |
+| 128 / 2048 | 225.2 | 883.3 | 1035.6 |
+| 128 / 4096 | 224.0 | 872.4 | 1022.6 |
+| 500 / 2000 | 224.7 | 867.1 | 1023.9 |
+| 1000 / 1000 | 224.6 | 869.8 | 1006.8 |
+| 1000 / 2000 | 223.9 | 858.7 | 1005.3 |
+| 1024 / 2048 | 223.9 | 857.3 | 1005.7 |
+| 2048 / 128 | 221.2 | 667.4[^ramp] | 671.3[^ramp] |
+| 2048 / 2048 | 222.5 | 832.8 | 966.3 |
+| 5000 / 500 | 219.4 | 614.1[^ramp] | 665.2[^ramp] |
+| 20000 / 2000 | 202.7 | 480.8 | 759.2[^pool] |
+
+### Latency SLA — MLPerf-style Poisson arrivals, RTX 4090
+
+Poisson arrivals[^sla] — 1000-in / 400-out, 100 requests per point, nearest-rank p99:
+
+| arrival rate | TTFT p50 | TTFT p99 | TPOT p99 | out tok/s | Interactive | Conversational |
+|---|---|---|---|---|---|---|
+| **1.0 req/s** | 168 ms | **433 ms** | 16.3 ms | 445 | **PASS** | **PASS** |
+| 1.25 req/s | 197 ms | 1,073 ms | 20.6 ms | 550 | fail | **PASS** |
+| 1.5 req/s | 304 ms | 3,281 ms | 20.6 ms | 640 | fail | fail |
+| 2.0 req/s | 5,947 ms | 8,001 ms | 20.5 ms | 717 | fail | fail |
+| 12.0 req/s | 21,454 ms | 41,964 ms | 19.8 ms | 772 | fail | fail |
+
+Saturation is **~1.9 req/s** (772 tok/s ÷ 400 output tokens). Past that, waits grow by ordinary
+queueing, not by any defect. **Decode is never the limiter** — TPOT keeps 2.4–45× headroom at every
+rate tested; the binding constraint is always TTFT/prefill[^tpot].
+
+[^fp8]: FP8 is the baseline because it is the closest widely-available reference to full precision
+    (it tracks BF16 on these tasks), and because BF16 for this model does not fit on a 24 GB card at
+    all. FP8 itself needs ~35 GB, so the comparison is against a build that requires substantially
+    more hardware than this one.
+
+[^cs6]: Same box, same in-process harness for both arms, so backend differences cancel. The
+    dense (non-expert) layers here are int8; that is **lossless** against an fp16-dense build of the
+    same weights (boolq 88.38 vs 88.04), so the size saving costs nothing measurable.
+
+[^math]: MATH-500 is served with a thinking-budget cap — the correct protocol for a reasoning model
+    (0 non-terminations; uncapped, the model over-thinks and truncates, which the cap fixes without
+    changing answer quality). Read the result as **parity** with FP8; the small margin is capping
+    protocol, not a real quality gain.
+
+[^gpqa]: GPQA-Diamond is run-to-run unstable by ±~5 pp at this sample size, so treat +3.1 as an
+    **effective tie** with FP8, not a genuine lead.
+
+[^lcb]: LiveCodeBench v6, `release_v6` slice (contest dates 2025-01 onward, N=182) — a
+    post-training-cutoff subset chosen to limit contamination. Both builds are scored on the same
+    182 problems, so read −4.4 as **retention vs FP8**, not a leaderboard score. Long-horizon code
+    generation is the most capacity-sensitive task measured, and the one clear 2-bit gap.
+
+[^bfcl]: BFCL-AST, matched same-driver run (thinking-off, n=1000, AST-weighted across the four
+    non-live categories). Tool-call form is preserved at 2-bit — a tie with FP8.
+
+[^ruler]: RULER (synthetic long-context retrieval), 4-task average across 8k / 32k / 64k / 128k.
+    Near-lossless through 128k.
+
+[^avg]: **Unweighted** mean of the six rows — a reading convenience, not a statistic to lean
+    on. The axes have wildly different sample sizes (MMLU-Pro n=12,032 vs LiveCodeBench
+    n=182) and different score scales, so the mean hides the one real gap (coding) behind
+    gains elsewhere. Read the per-axis rows for anything that matters.
+
+[^code]: Paired McNemar (exact two-sided) on identical prompts — per-item comparisons on full native
+    sample sets. Both land on a statistical tie: HumanEval+ turns on just 7 disagreements (2 win /
+    5 loss of 164 — underpowered), CRUXEval-O is far better powered (64 disagreements) and still ties.
+
+[^grid]: Measured with CUDA graphs on and a 16-request cap (`GRAPHS=1 MAXREQ=16`), prefix caching
+    **off** (`RADIX=0`), and output length pinned so every cell decodes the full OSL. `GRAPHS=1`
+    and `RADIX=0` are both required to reproduce these numbers; `GRAPHS=1` is already the
+    `serve.sh` default, `RADIX=0` is not. Single-stream (bs 1) is flat at ~220 tok/s across shapes
+    because decode is memory-bound, not compute-bound, at batch 1.
+
+[^ramp]: Short-output cells at batch are dominated by request turnaround rather than by decode: with
+    only 128–500 output tokens the ramp in and out of the batch is a large fraction of the wall time.
+    These cells understate steady-state decode throughput.
+
+[^pool]: At 20k input the KV pool cannot hold 16 concurrent requests, so some queue and this number
+    is **pessimistic** — the achievable figure is higher than shown. Raising the memory fraction to
+    de-queue it failed on a 24 GB card; it is an envelope limit, not a tuning miss.
+
+[^sla]: MLPerf Server-style: Poisson arrivals (not synchronized bursts) and p99 rather than median —
+    burst harnesses systematically misreport this workload. Thresholds are the MLPerf interactive
+    categories: **Interactive** = TTFT p99 ≤ 450 ms and TPOT ≤ 40 ms; **Conversational** = ≤ 2000 ms
+    and ≤ 200 ms.
+
+[^tpot]: One caveat worth knowing before you turn thinking on: TTFT measures the first token
+    *generated*, but with thinking enabled the first token a **user sees** comes after the reasoning
+    block. On real problems that gap is large — first generated token in ~75 ms, first answer token
+    at a median of ~15 s, and a long tail. Capping the thinking budget removes the runaway tail. If
+    latency to a visible answer matters more than reasoning depth, serve with `THINK=0`.
+
+## Licenses and attribution
+
+This repository contains **model weights only**, released under the **Apache License, Version 2.0**
+(see [`LICENSE`](LICENSE)).
+
+- **Model weights** — a 2-bit quantized derivative of Qwen3.6-35B-A3B (Apache-2.0, Qwen); base
+  license text at [`THIRD_PARTY_LICENSES/Qwen-LICENSE.txt`](THIRD_PARTY_LICENSES/Qwen-LICENSE.txt).
+- **Tokenizer** — Qwen (`Qwen2Tokenizer`), Apache-2.0.
+- **Chat template** — from
+  [froggeric/Qwen-Fixed-Chat-Templates](https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates)
+  (Apache-2.0, inherited from Qwen), which fixes tool-calling and thinking-mode handling for
+  this model family.
+
+The **runtime** (the `escha` wheel: the SGLang serving fork + CUDA kernels, and their third-party
+licenses — SGLang, exllamav3, AQLM, and the BSD-3/MIT upstreams vendored in SGLang) is distributed
+separately and carries its own `LICENSE` + `THIRD_PARTY_LICENSES/`:
+**[EschaLabs/escha-runtime-qwen3moe](https://huggingface.co/EschaLabs/escha-runtime-qwen3moe)**. All bundled code there is permissive
+(Apache-2.0 / MIT / BSD-3-Clause) — no copyleft.

THIRD_PARTY_LICENSES/Qwen-LICENSE.txt

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2024-2025 Alibaba Cloud (Qwen Team)
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

chat_template.jinja

@@ -0,0 +1,329 @@
+{%- set template_version = "qwen3.6-froggeric-v21.3" %}
+{%- set _tool_format = tool_call_format if tool_call_format is defined else 'xml' %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- set add_vision_id = add_vision_id if add_vision_id is defined else false %}
+{%- set enable_thinking = enable_thinking if enable_thinking is defined else true %}
+{%- set auto_disable_thinking_with_tools = auto_disable_thinking_with_tools if auto_disable_thinking_with_tools is defined else false %}
+{%- set _preserve_thinking = preserve_thinking if preserve_thinking is defined else true %}
+{%- set max_tool_arg_chars = max_tool_arg_chars if max_tool_arg_chars is defined else 0 %}
+{%- set max_tool_response_chars = max_tool_response_chars if max_tool_response_chars is defined else 0 %}
+{%- set _has_tools = (tools is defined and tools and tools is iterable and tools is not mapping) %}
+{%- set ns_state = namespace(thinking=enable_thinking) %}
+{%- if auto_disable_thinking_with_tools and _has_tools %}
+    {%- set ns_state.thinking = false %}
+{%- endif %}
+{%- 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 item is mapping %}
+                {%- if item.type == 'image' or 'image' in item or 'image_url' in item %}
+                    {%- 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 item.type == 'video' or 'video' in item %}
+                    {%- 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 %}
+            {%- else %}
+                {{- item | string }}
+            {%- 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 %}
+{%- set _first_role = messages[0].role %}
+{%- if _first_role == 'system' or _first_role == 'developer' %}
+    {%- set _sys_msg = messages[0] %}
+    {%- set _msgs = messages[1:] %}
+{%- else %}
+    {%- set _sys_msg = none %}
+    {%- set _msgs = messages %}
+{%- endif %}
+{%- set _sc = '' %}
+{%- if _sys_msg is not none %}
+    {%- set _sc = render_content(_sys_msg.content, false, true) | trim %}
+    {%- if '<|think_off|>' in _sc %}
+        {%- set ns_state.thinking = false %}
+        {%- set _sc = _sc.split('<|think_off|>') | join('') | trim %}
+    {%- elif '<|think_on|>' in _sc %}
+        {%- set ns_state.thinking = true %}
+        {%- set _sc = _sc.split('<|think_on|>') | join('') | trim %}
+    {%- endif %}
+{%- endif %}
+{%- if _has_tools %}
+    {{- '<|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>' }}
+    {%- set tool_instructions %}
+If you choose to call a function ONLY reply in the following format with NO suffix:
+
+{%- if _tool_format == 'json' %}
+<think>
+Brief explanation of tool call
+</think>
+<tool_call>
+{"name": "example_function_name", "arguments": {"example_parameter_1": "value_1", "example_parameter_2": "This is the value for the second parameter"}}
+</tool_call>
+{%- else %}
+<think>
+Brief explanation of tool call
+</think>
+<tool_call>
+<function=example_function_name>
+<parameter=example_parameter_1>
+value_1
+</parameter>
+<parameter=example_parameter_2>
+This is the value for the second parameter
+that can span
+multiple lines
+</parameter>
+</function>
+</tool_call>
+{%- endif %}
+
+<IMPORTANT>
+Reminder:
+- You can use the <think></think> block to plan your next tool call OR to synthesize data and formulate your final response to the user.
+- ALL explanation and reasoning MUST be placed strictly inside the <think></think> block.
+{%- if _tool_format == 'json' %}
+- Function calls MUST follow the specified format: a single JSON object with "name" and "arguments" keys inside <tool_call></tool_call> XML tags.
+{%- else %}
+- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags.
+{%- endif %}
+- If you choose to call a tool, you MUST output the <tool_call> block IMMEDIATELY after thinking, with NO conversational text before it.
+{%- if _tool_format == 'json' %}
+- The <tool_call> tag MUST be at the very beginning of a new line, with NO spaces or indentation before it.
+{%- else %}
+- The <tool_call> and <function> tags MUST be at the very beginning of a new line, with NO spaces or indentation before them.
+{%- endif %}
+- To call multiple functions, output a separate, completely closed <tool_call></tool_call> block for EACH function. Do NOT nest <tool_call> blocks.
+- If you have all necessary data, provide your final answer directly to the user without any tool call.
+</IMPORTANT>
+    {%- endset %}
+    {{- '\n\n' ~ tool_instructions | trim }}
+    {%- if _sc %}
+        {{- '\n\n' + _sc }}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if _sc %}
+        {{- '<|im_start|>system\n' + _sc + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set _last_idx = _msgs | length - 1 %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=_last_idx) %}
+{%- for message in _msgs[::-1] %}
+    {%- set index = (_msgs | length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == 'user' %}
+        {%- set _rc = render_content(message.content, false) | trim %}
+        {%- if not (_rc.startswith('<tool_response>') and _rc.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {%- if _last_idx > 50 %}
+        {%- set ns.last_query_index = _last_idx %}
+    {%- else %}
+        {%- set ns.last_query_index = 0 %}
+    {%- endif %}
+{%- endif %}
+{%- set ns2 = namespace(prev_role='', consecutive_failures=0) %}
+{%- for message in _msgs %}
+    {%- set is_system = (message.role == "system" or message.role == "developer") %}
+    {%- set content = render_content(message.content, true, is_system) | trim %}
+    {%- if is_system or message.role == 'user' %}
+        {%- if '<|think_off|>' in content %}
+            {%- set ns_state.thinking = false %}
+            {%- set content = content.split('<|think_off|>') | join('') | trim %}
+        {%- elif '<|think_on|>' in content %}
+            {%- set ns_state.thinking = true %}
+            {%- set content = content.split('<|think_on|>') | join('') | trim %}
+        {%- endif %}
+    {%- endif %}
+    {%- if is_system %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- elif message.role == 'user' %}
+        {%- set ns2.consecutive_failures = 0 %}
+        {{- '<|im_start|>user\n' + content + '<|im_end|>\n' }}
+    {%- elif message.role == 'assistant' %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- if message.reasoning_content is string %}
+                {%- set reasoning_content = message.reasoning_content %}
+            {%- else %}
+                {%- set reasoning_content = message.reasoning_content | string %}
+            {%- endif %}
+        {%- elif message.thinking is defined and message.thinking is not none %}
+            {%- if message.thinking is string %}
+                {%- set reasoning_content = message.thinking %}
+            {%- else %}
+                {%- set reasoning_content = message.thinking | string %}
+            {%- endif %}
+        {%- else %}
+            {%- set _think_end = '' %}
+            {%- if content.startswith('</think>') %}
+                {%- set _think_end = '</think>' %}
+            {%- elif content.startswith('</thinking>') %}
+                {%- set _think_end = '</thinking>' %}
+            {%- elif '\n</think>' in content %}
+                {%- set _think_end = '\n</think>' %}
+            {%- elif '\n</thinking>' in content %}
+                {%- set _think_end = '\n</thinking>' %}
+            {%- elif '\n</ think>' in content %}
+                {%- set _think_end = '\n</ think>' %}
+            {%- elif '\n</think >' in content %}
+                {%- set _think_end = '\n</think >' %}
+            {%- endif %}
+            {%- if _think_end %}
+                {%- if 'thinking' in _think_end %}
+                    {%- set _think_start = '<thinking>' %}
+                {%- else %}
+                    {%- set _think_start = '<think>' %}
+                {%- endif %}
+                {%- set reasoning_content = content.split(_think_end)[0].rstrip('\n') %}
+                {%- if _think_start in reasoning_content %}
+                    {%- set reasoning_content = reasoning_content.split(_think_start)[-1].lstrip('\n') %}
+                {%- endif %}
+                {%- set content = content.split(_think_end)[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content | trim %}
+        {%- if (_preserve_thinking or loop.index0 > ns.last_query_index) and reasoning_content %}
+            {{- '<|im_start|>assistant\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>assistant\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls is defined and 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 and tool_call.function is not none %}
+                    {%- set tc = tool_call.function %}
+                {%- else %}
+                    {%- set tc = tool_call %}
+                {%- endif %}
+                {%- if _tool_format == 'json' %}
+                    {%- if not loop.first or content | trim %}
+                        {{- '\n\n' }}
+                    {%- endif %}
+                    {%- set _args = '{}' %}
+                    {%- if tc.arguments is defined and tc.arguments is not none %}
+                        {%- if tc.arguments is mapping %}
+                            {%- set _args = tc.arguments | tojson %}
+                        {%- elif tc.arguments is string and tc.arguments %}
+                            {%- set _args = tc.arguments %}
+                        {%- endif %}
+                    {%- endif %}
+                    {{- '<tool_call>\n{"name": ' }}{{- tc.name | tojson }}{{- ', "arguments": ' }}{{- _args }}{{- '}\n</tool_call>' }}
+                {%- else %}
+                    {%- if loop.first %}
+                        {%- if content | trim %}
+                            {{- '\n\n<tool_call>\n<function=' + tc.name + '>\n' }}
+                        {%- else %}
+                            {{- '<tool_call>\n<function=' + tc.name + '>\n' }}
+                        {%- endif %}
+                    {%- else %}
+                        {{- '\n\n<tool_call>\n<function=' + tc.name + '>\n' }}
+                    {%- endif %}
+                    {%- if tc.arguments is defined and tc.arguments is not none %}
+                        {%- if tc.arguments is mapping %}
+                            {%- for args_name, args_value in tc.arguments.items() %}
+                                {{- '<parameter=' + args_name + '>\n' }}
+                                {%- if args_value is mapping or (args_value is sequence and args_value is not string) %}
+                                    {%- set _av = args_value | tojson %}
+                                {%- else %}
+                                    {%- set _av = args_value | string %}
+                                {%- endif %}
+                                {%- if max_tool_arg_chars > 0 and _av | length > max_tool_arg_chars %}
+                                    {{- _av[:max_tool_arg_chars] + '\n[TRUNCATED — original length ' ~ (_av | length | string) ~ ' chars]' }}
+                                {%- else %}
+                                    {{- _av }}
+                                {%- endif %}
+                                {{- '\n</parameter>\n' }}
+                            {%- endfor %}
+                        {%- elif tc.arguments is string and tc.arguments %}
+                            {{- tc.arguments }}
+                        {%- endif %}
+                    {%- endif %}
+                    {{- '</function>\n</tool_call>' }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == 'tool' %}
+        {%- set _content_lower = content | lower %}
+        {%- set _content_head = _content_lower[:80] %}
+        {%- if content | length < 500 and '$ ' not in content and 'took ' not in _content_lower and ('"error":' in _content_head or 'error:' in _content_head or 'err!' in _content_head or 'fatal:' in _content_head or 'exception:' in _content_head or 'traceback' in _content_head or 'command not found' in _content_head or 'invalid syntax' in _content_head or 'failed to' in _content_head) %}
+            {%- set ns2.consecutive_failures = ns2.consecutive_failures + 1 %}
+        {%- else %}
+            {%- set ns2.consecutive_failures = 0 %}
+        {%- endif %}
+        {%- if ns2.prev_role != 'tool' %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {%- if max_tool_response_chars > 0 and content | length > max_tool_response_chars %}
+            {%- set content = content[:max_tool_response_chars] + '\n[TRUNCATED — original length ' ~ (content | length | string) ~ ' chars]' %}
+        {%- endif %}
+        {{- '\n<tool_response>\n' + content }}
+        {%- if ns2.consecutive_failures >= 2 %}
+            {{- '\n\n⚠️ SYSTEM WARNING: ' ~ ns2.consecutive_failures ~ ' consecutive tool errors detected. Your previous approach is incorrect. You MUST use a fundamentally different approach or corrected arguments.' }}
+        {%- elif ns2.consecutive_failures == 1 %}
+            {{- '\n\n⚠️ SYSTEM WARNING: The previous tool call returned an error. Diagnose the failure and retry with completely corrected arguments.' }}
+        {%- endif %}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- else %}
+            {%- set _next_role = _msgs[loop.index0 + 1].role %}
+            {%- if _next_role != 'tool' %}
+                {{- '<|im_end|>\n' }}
+            {%- endif %}
+        {%- endif %}
+    {%- else %}
+        {{- '<|im_start|>user\n[' + message.role + ']: ' + content + '<|im_end|>\n' }}
+    {%- endif %}
+    {%- set ns2.prev_role = message.role %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if not ns_state.thinking %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- elif ns2.consecutive_failures >= 2 %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,871 @@
+{
+  "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": "5.8.0",
+  "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,
+  "quantization_config": {
+    "quant_method": "eschamoe",
+    "format_version": "2.0",
+    "global_config": {
+      "bits": 2.0,
+      "num_experts": 256,
+      "experts_kind": "qwen35moe"
+    },
+    "layer_meta": {
+      "model.language_model.layers.0.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.0.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.1.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.1.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.2.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.2.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.3.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.3.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.4.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.4.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.5.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.5.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.6.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.6.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.7.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.7.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.8.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.8.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.9.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.9.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.10.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.10.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.11.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.11.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.12.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.12.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.13.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.13.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.14.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.14.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.15.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.15.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.16.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.16.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.17.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.17.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.18.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.18.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.19.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.19.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.20.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.20.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.21.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.21.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.22.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.22.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.23.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.23.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.24.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.24.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.25.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.25.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.26.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.26.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.27.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.27.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.28.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.28.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.29.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.29.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.30.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.30.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.31.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.31.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.32.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.32.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.33.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.33.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.34.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.34.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.35.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.35.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.36.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.36.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.37.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.37.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.38.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.38.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      },
+      "model.language_model.layers.39.mlp.experts.gate_up_proj": {
+        "bits": 2.0,
+        "K": 2,
+        "num_experts": 256,
+        "in_features": 2048,
+        "out_features": 1024,
+        "in_p": 2048,
+        "out_p": 1024
+      },
+      "model.language_model.layers.39.mlp.experts.down_proj": {
+        "bits": 3.0,
+        "K": 3,
+        "num_experts": 256,
+        "in_features": 512,
+        "out_features": 2048,
+        "in_p": 512,
+        "out_p": 2048
+      }
+    },
+    "ignore": [
+      "A_log",
+      "conv1d",
+      "dt_bias",
+      "embed_tokens",
+      "in_proj_a",
+      "in_proj_b",
+      "input_layernorm",
+      "k_norm",
+      "lm_head",
+      "mlp.gate",
+      "norm",
+      "post_attention_layernorm",
+      "q_norm",
+      "shared_expert_gate",
+      "visual"
+    ],
+    "fold_scales": true,
+    "int8_embedding": true,
+    "non_expert_int8": true,
+    "key_prefix": "model.language_model"
+  }
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+    "bos_token_id": 248044,
+    "do_sample": true,
+    "eos_token_id": [
+        248046,
+        248044
+    ],
+    "pad_token_id": 248044,
+    "temperature": 1.0,
+    "top_k": 20,
+    "top_p": 0.95
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7e39d727094a68e0ceed6beccd3fbab028570dd1e0ff97f6e182639e18ef466
+size 5366375728

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78af47edbb6fae23d352c630b1007ae5b77e1a04692d567290f469ada73419a6
+size 5311797632

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92f61ba609bd78437eb9a466dd15249007dcdf49facd808ec5b756d580df10f9
+size 1618779120

opencode.json

@@ -0,0 +1,28 @@
+{
+  "$schema": "https://opencode.ai/config.json",
+
+  "model": "escha/escha-qwen36-35b-a3b-w2",
+  "small_model": "escha/escha-qwen36-35b-a3b-w2",
+
+  "provider": {
+    "escha": {
+      "npm": "@ai-sdk/openai-compatible",
+      "name": "Escha (local)",
+      "options": {
+        "baseURL": "http://127.0.0.1:30000/v1",
+        "apiKey": "not-needed"
+      },
+      "models": {
+        "escha-qwen36-35b-a3b-w2": {
+          "name": "Qwen3.6-35B-A3B 2-bit",
+          "tools": true,
+          "reasoning": true,
+          "options": {
+            "temperature": 0.6,
+            "top_p": 0.95
+          }
+        }
+      }
+    }
+  }
+}

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"
+}

quantize_config.json

@@ -0,0 +1,4 @@
+{
+  "quant_method": "eschamoe",
+  "bits": 2.0
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f9e4d4901a92b997e463c1f46055088b6cca5ca61a6522d1b9f64c4bb81cb42
+size 12807982

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 template_version = \"qwen3.6-froggeric-v21.3\" %}\n{%- set _tool_format = tool_call_format if tool_call_format is defined else 'xml' %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- set add_vision_id = add_vision_id if add_vision_id is defined else false %}\n{%- set enable_thinking = enable_thinking if enable_thinking is defined else true %}\n{%- set auto_disable_thinking_with_tools = auto_disable_thinking_with_tools if auto_disable_thinking_with_tools is defined else false %}\n{%- set _preserve_thinking = preserve_thinking if preserve_thinking is defined else true %}\n{%- set max_tool_arg_chars = max_tool_arg_chars if max_tool_arg_chars is defined else 0 %}\n{%- set max_tool_response_chars = max_tool_response_chars if max_tool_response_chars is defined else 0 %}\n{%- set _has_tools = (tools is defined and tools and tools is iterable and tools is not mapping) %}\n{%- set ns_state = namespace(thinking=enable_thinking) %}\n{%- if auto_disable_thinking_with_tools and _has_tools %}\n    {%- set ns_state.thinking = false %}\n{%- endif %}\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 item is mapping %}\n                {%- if item.type == 'image' or 'image' in item or 'image_url' in item %}\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 item.type == 'video' or 'video' in item %}\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            {%- else %}\n                {{- item | string }}\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{%- set _first_role = messages[0].role %}\n{%- if _first_role == 'system' or _first_role == 'developer' %}\n    {%- set _sys_msg = messages[0] %}\n    {%- set _msgs = messages[1:] %}\n{%- else %}\n    {%- set _sys_msg = none %}\n    {%- set _msgs = messages %}\n{%- endif %}\n{%- set _sc = '' %}\n{%- if _sys_msg is not none %}\n    {%- set _sc = render_content(_sys_msg.content, false, true) | trim %}\n    {%- if '<|think_off|>' in _sc %}\n        {%- set ns_state.thinking = false %}\n        {%- set _sc = _sc.split('<|think_off|>') | join('') | trim %}\n    {%- elif '<|think_on|>' in _sc %}\n        {%- set ns_state.thinking = true %}\n        {%- set _sc = _sc.split('<|think_on|>') | join('') | trim %}\n    {%- endif %}\n{%- endif %}\n{%- if _has_tools %}\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    {%- set tool_instructions %}\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n{%- if _tool_format == 'json' %}\n<think>\nBrief explanation of tool call\n</think>\n<tool_call>\n{\"name\": \"example_function_name\", \"arguments\": {\"example_parameter_1\": \"value_1\", \"example_parameter_2\": \"This is the value for the second parameter\"}}\n</tool_call>\n{%- else %}\n<think>\nBrief explanation of tool call\n</think>\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{%- endif %}\n\n<IMPORTANT>\nReminder:\n- You can use the <think></think> block to plan your next tool call OR to synthesize data and formulate your final response to the user.\n- ALL explanation and reasoning MUST be placed strictly inside the <think></think> block.\n{%- if _tool_format == 'json' %}\n- Function calls MUST follow the specified format: a single JSON object with \"name\" and \"arguments\" keys inside <tool_call></tool_call> XML tags.\n{%- else %}\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags.\n{%- endif %}\n- If you choose to call a tool, you MUST output the <tool_call> block IMMEDIATELY after thinking, with NO conversational text before it.\n{%- if _tool_format == 'json' %}\n- The <tool_call> tag MUST be at the very beginning of a new line, with NO spaces or indentation before it.\n{%- else %}\n- The <tool_call> and <function> tags MUST be at the very beginning of a new line, with NO spaces or indentation before them.\n{%- endif %}\n- To call multiple functions, output a separate, completely closed <tool_call></tool_call> block for EACH function. Do NOT nest <tool_call> blocks.\n- If you have all necessary data, provide your final answer directly to the user without any tool call.\n</IMPORTANT>\n    {%- endset %}\n    {{- '\\n\\n' ~ tool_instructions | trim }}\n    {%- if _sc %}\n        {{- '\\n\\n' + _sc }}\n    {%- endif %}\n    {{- '<|im_end|>\\n' }}\n{%- else %}\n    {%- if _sc %}\n        {{- '<|im_start|>system\\n' + _sc + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set _last_idx = _msgs | length - 1 %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=_last_idx) %}\n{%- for message in _msgs[::-1] %}\n    {%- set index = (_msgs | length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == 'user' %}\n        {%- set _rc = render_content(message.content, false) | trim %}\n        {%- if not (_rc.startswith('<tool_response>') and _rc.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    {%- if _last_idx > 50 %}\n        {%- set ns.last_query_index = _last_idx %}\n    {%- else %}\n        {%- set ns.last_query_index = 0 %}\n    {%- endif %}\n{%- endif %}\n{%- set ns2 = namespace(prev_role='', consecutive_failures=0) %}\n{%- for message in _msgs %}\n    {%- set is_system = (message.role == \"system\" or message.role == \"developer\") %}\n    {%- set content = render_content(message.content, true, is_system) | trim %}\n    {%- if is_system or message.role == 'user' %}\n        {%- if '<|think_off|>' in content %}\n            {%- set ns_state.thinking = false %}\n            {%- set content = content.split('<|think_off|>') | join('') | trim %}\n        {%- elif '<|think_on|>' in content %}\n            {%- set ns_state.thinking = true %}\n            {%- set content = content.split('<|think_on|>') | join('') | trim %}\n        {%- endif %}\n    {%- endif %}\n    {%- if is_system %}\n        {{- '<|im_start|>system\\n' + content + '<|im_end|>\\n' }}\n    {%- elif message.role == 'user' %}\n        {%- set ns2.consecutive_failures = 0 %}\n        {{- '<|im_start|>user\\n' + content + '<|im_end|>\\n' }}\n    {%- elif message.role == 'assistant' %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- if message.reasoning_content is string %}\n                {%- set reasoning_content = message.reasoning_content %}\n            {%- else %}\n                {%- set reasoning_content = message.reasoning_content | string %}\n            {%- endif %}\n        {%- elif message.thinking is defined and message.thinking is not none %}\n            {%- if message.thinking is string %}\n                {%- set reasoning_content = message.thinking %}\n            {%- else %}\n                {%- set reasoning_content = message.thinking | string %}\n            {%- endif %}\n        {%- else %}\n            {%- set _think_end = '' %}\n            {%- if content.startswith('</think>') %}\n                {%- set _think_end = '</think>' %}\n            {%- elif content.startswith('</thinking>') %}\n                {%- set _think_end = '</thinking>' %}\n            {%- elif '\\n</think>' in content %}\n                {%- set _think_end = '\\n</think>' %}\n            {%- elif '\\n</thinking>' in content %}\n                {%- set _think_end = '\\n</thinking>' %}\n            {%- elif '\\n</ think>' in content %}\n                {%- set _think_end = '\\n</ think>' %}\n            {%- elif '\\n</think >' in content %}\n                {%- set _think_end = '\\n</think >' %}\n            {%- endif %}\n            {%- if _think_end %}\n                {%- if 'thinking' in _think_end %}\n                    {%- set _think_start = '<thinking>' %}\n                {%- else %}\n                    {%- set _think_start = '<think>' %}\n                {%- endif %}\n                {%- set reasoning_content = content.split(_think_end)[0].rstrip('\\n') %}\n                {%- if _think_start in reasoning_content %}\n                    {%- set reasoning_content = reasoning_content.split(_think_start)[-1].lstrip('\\n') %}\n                {%- endif %}\n                {%- set content = content.split(_think_end)[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- set reasoning_content = reasoning_content | trim %}\n        {%- if (_preserve_thinking or loop.index0 > ns.last_query_index) and reasoning_content %}\n            {{- '<|im_start|>assistant\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n        {%- else %}\n            {{- '<|im_start|>assistant\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls is defined and 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 and tool_call.function is not none %}\n                    {%- set tc = tool_call.function %}\n                {%- else %}\n                    {%- set tc = tool_call %}\n                {%- endif %}\n                {%- if _tool_format == 'json' %}\n                    {%- if not loop.first or content | trim %}\n                        {{- '\\n\\n' }}\n                    {%- endif %}\n                    {%- set _args = '{}' %}\n                    {%- if tc.arguments is defined and tc.arguments is not none %}\n                        {%- if tc.arguments is mapping %}\n                            {%- set _args = tc.arguments | tojson %}\n                        {%- elif tc.arguments is string and tc.arguments %}\n                            {%- set _args = tc.arguments %}\n                        {%- endif %}\n                    {%- endif %}\n                    {{- '<tool_call>\\n{\"name\": ' }}{{- tc.name | tojson }}{{- ', \"arguments\": ' }}{{- _args }}{{- '}\\n</tool_call>' }}\n                {%- else %}\n                    {%- if loop.first %}\n                        {%- if content | trim %}\n                            {{- '\\n\\n<tool_call>\\n<function=' + tc.name + '>\\n' }}\n                        {%- else %}\n                            {{- '<tool_call>\\n<function=' + tc.name + '>\\n' }}\n                        {%- endif %}\n                    {%- else %}\n                        {{- '\\n\\n<tool_call>\\n<function=' + tc.name + '>\\n' }}\n                    {%- endif %}\n                    {%- if tc.arguments is defined and tc.arguments is not none %}\n                        {%- if tc.arguments is mapping %}\n                            {%- for args_name, args_value in tc.arguments.items() %}\n                                {{- '<parameter=' + args_name + '>\\n' }}\n                                {%- if args_value is mapping or (args_value is sequence and args_value is not string) %}\n                                    {%- set _av = args_value | tojson %}\n                                {%- else %}\n                                    {%- set _av = args_value | string %}\n                                {%- endif %}\n                                {%- if max_tool_arg_chars > 0 and _av | length > max_tool_arg_chars %}\n                                    {{- _av[:max_tool_arg_chars] + '\\n[TRUNCATED — original length ' ~ (_av | length | string) ~ ' chars]' }}\n                                {%- else %}\n                                    {{- _av }}\n                                {%- endif %}\n                                {{- '\\n</parameter>\\n' }}\n                            {%- endfor %}\n                        {%- elif tc.arguments is string and tc.arguments %}\n                            {{- tc.arguments }}\n                        {%- endif %}\n                    {%- endif %}\n                    {{- '</function>\\n</tool_call>' }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == 'tool' %}\n        {%- set _content_lower = content | lower %}\n        {%- set _content_head = _content_lower[:80] %}\n        {%- if content | length < 500 and '$ ' not in content and 'took ' not in _content_lower and ('\"error\":' in _content_head or 'error:' in _content_head or 'err!' in _content_head or 'fatal:' in _content_head or 'exception:' in _content_head or 'traceback' in _content_head or 'command not found' in _content_head or 'invalid syntax' in _content_head or 'failed to' in _content_head) %}\n            {%- set ns2.consecutive_failures = ns2.consecutive_failures + 1 %}\n        {%- else %}\n            {%- set ns2.consecutive_failures = 0 %}\n        {%- endif %}\n        {%- if ns2.prev_role != 'tool' %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {%- if max_tool_response_chars > 0 and content | length > max_tool_response_chars %}\n            {%- set content = content[:max_tool_response_chars] + '\\n[TRUNCATED — original length ' ~ (content | length | string) ~ ' chars]' %}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' + content }}\n        {%- if ns2.consecutive_failures >= 2 %}\n            {{- '\\n\\n⚠️ SYSTEM WARNING: ' ~ ns2.consecutive_failures ~ ' consecutive tool errors detected. Your previous approach is incorrect. You MUST use a fundamentally different approach or corrected arguments.' }}\n        {%- elif ns2.consecutive_failures == 1 %}\n            {{- '\\n\\n⚠️ SYSTEM WARNING: The previous tool call returned an error. Diagnose the failure and retry with completely corrected arguments.' }}\n        {%- endif %}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last %}\n            {{- '<|im_end|>\\n' }}\n        {%- else %}\n            {%- set _next_role = _msgs[loop.index0 + 1].role %}\n            {%- if _next_role != 'tool' %}\n                {{- '<|im_end|>\\n' }}\n            {%- endif %}\n        {%- endif %}\n    {%- else %}\n        {{- '<|im_start|>user\\n[' + message.role + ']: ' + content + '<|im_end|>\\n' }}\n    {%- endif %}\n    {%- set ns2.prev_role = message.role %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if not ns_state.thinking %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- elif ns2.consecutive_failures >= 2 %}\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"
+}