Add files using upload-large-folder tool

.gitattributes

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

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 2026 Alibaba Cloud
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -0,0 +1,92 @@
+---
+license: apache-2.0
+language:
+- en
+base_model:
+- Qwen/Qwen-AgentWorld-35B-A3B
+- Qwen/Qwen3.6-35B-A3B
+pipeline_tag: image-text-to-text
+library_name: transformers
+tags:
+- multimodal
+- vision
+- image-text-to-text
+- merge
+- vision-graft
+- qwen3_5_moe
+- agent
+---
+
+# Qwen-AgentWorld-35B-A3B-VL36 (vision-grafted, Qwen3.6 ViT)
+
+**TL;DR —** a *weight-grafted* multimodal variant of
+[Qwen/Qwen-AgentWorld-35B-A3B](https://huggingface.co/Qwen/Qwen-AgentWorld-35B-A3B):
+its agentic text backbone, with the vision tower (ViT + projector) transplanted in
+from [Qwen/Qwen3.6-35B-A3B](https://huggingface.co/Qwen/Qwen3.6-35B-A3B).
+**No training was performed — this is pure weight surgery.** Full precision **BF16**
+(not a quantized model).
+
+> ⚠️ **Experimental, cross-generation graft.** The vision tower comes from Qwen**3.6**
+> while the AgentWorld backbone is a Qwen**3.5**-generation derivative. The projector
+> (`merger.linear_fc2`) lands dimensionally exactly on the text hidden size (2048) and the
+> vision config matches bit-for-bit, so it loads and runs. In smoke tests the 3.6 ViT gives
+> clean, accurate grounding (correctly named shapes, colors and OCR'd a number with precise
+> spatial relations). But this is **not** a natively co-trained VLM and has **not** been
+> benchmarked. Use at your own risk.
+>
+> A same-generation variant using the **Qwen3.5** ViT also exists
+> (`Qwen-AgentWorld-35B-A3B-VL`); 3.6's vision tower is the stronger encoder, hence this build.
+
+## What we changed vs. Qwen-AgentWorld-35B-A3B
+
+AgentWorld ships **text-only weights** (693 tensors, all `model.language_model.*` + `lm_head`)
+even though its config already declares a `vision_config`, image/video token ids, and a
+vision+tool-capable chat template — it is effectively a Qwen3.5-VL *waiting for a vision encoder*.
+We:
+
+1. Extracted the **333 `model.visual.*` tensors** (27-layer ViT + patch/position embeds +
+   merger/projector) from **Qwen3.6-35B-A3B** (BF16).
+2. Added them to the AgentWorld checkpoint **without touching a single text tensor** — so the
+   agent / tool-calling skills are byte-for-byte preserved.
+3. Removed the `language_model_only` flag from the config so the runner instantiates the tower.
+
+Result: **1026 tensors** (693 text + 333 vision), architecture
+`Qwen3_5MoeForConditionalGeneration`, projector maps vision hidden 1152 → text hidden 2048.
+
+## Serving (vLLM ≥ 0.23)
+
+```bash
+vllm serve havok2/Qwen-AgentWorld-35B-A3B-VL36 \
+  --tensor-parallel-size 4 \
+  --reasoning-parser qwen3 \
+  --limit-mm-per-prompt '{"image": 4, "video": 1}'
+# IMPORTANT: do NOT pass --language-model-only — that disables the vision tower.
+```
+
+Loads as a standard Qwen3.5-MoE VLM. ~70 GB BF16; fits on 4×24 GB with `--tensor-parallel-size 4`.
+
+## Capabilities & limitations
+
+- ✅ **Agentic text + tool-calling** — identical to AgentWorld (weights untouched).
+- ✅ **Image / video input** — works; smoke-tested on synthetic images (shapes, colors, OCR).
+- ⚠️ **Vision quality is not benchmarked**; cross-generation graft, may differ from a natively co-trained VLM.
+- ⚠️ No additional safety tuning or evaluation beyond basic smoke tests.
+
+## Reproduce it yourself (no 70 GB download needed)
+
+Rebuild locally from the two source models with the included
+[`build_merged_vl36.py`](build_merged_vl36.py). It downloads the AgentWorld backbone and
+**only the Qwen3.6 shards that contain the vision tensors**, then performs the graft:
+
+```bash
+pip install huggingface_hub safetensors torch
+python build_merged_vl36.py        # -> ./Qwen-AgentWorld-35B-A3B-VL36
+```
+
+## Attribution & license
+
+- **Text backbone & agent post-training:** [Qwen/Qwen-AgentWorld-35B-A3B](https://huggingface.co/Qwen/Qwen-AgentWorld-35B-A3B) (Apache-2.0), itself based on `Qwen3.5-35B-A3B-Base`.
+- **Vision tower (ViT + projector):** [Qwen/Qwen3.6-35B-A3B](https://huggingface.co/Qwen/Qwen3.6-35B-A3B) (Apache-2.0).
+
+This derivative is released under **Apache-2.0**. Modification: vision-tower graft as described
+above (no training). See `LICENSE`. Not affiliated with or endorsed by Alibaba / the Qwen team.

build_merged_vl36.py

@@ -0,0 +1,80 @@
+#!/usr/bin/env python
+"""Rebuild Qwen-AgentWorld-35B-A3B-VL36 locally from the two source models.
+
+Grafts the Qwen3.6 vision tower (`model.visual.*` = ViT + projector) onto the
+text-only AgentWorld backbone. No training — pure weight surgery. Output is a
+self-contained BF16 checkpoint dir ./Qwen-AgentWorld-35B-A3B-VL36.
+
+Requires: pip install huggingface_hub safetensors torch
+Downloads: the full AgentWorld backbone (~70 GB) + only the Qwen3.6 shards that
+hold the 333 vision tensors. No full 72 GB Qwen3.6 download.
+"""
+import os, json, shutil
+import torch
+from huggingface_hub import snapshot_download, hf_hub_download
+from safetensors import safe_open
+from safetensors.torch import save_file
+
+AGENT_REPO  = "Qwen/Qwen-AgentWorld-35B-A3B"   # text backbone + config/tokenizer/template/processor
+VISION_REPO = "Qwen/Qwen3.6-35B-A3B"           # donor of model.visual.* (stronger 3.6 vision tower)
+OUT = os.path.abspath("Qwen-AgentWorld-35B-A3B-VL36")
+VISION_SHARD = "model-vision.safetensors"
+
+# 1) AgentWorld backbone (text weights + all small companion files)
+print("[1/5] downloading AgentWorld backbone ...")
+aw = snapshot_download(AGENT_REPO)
+
+# 2) Qwen3.6 vision shards only — find which shards hold model.visual.* via the index
+print("[2/5] downloading only the Qwen3.6 shards that contain model.visual.* ...")
+vidx = json.load(open(hf_hub_download(VISION_REPO, "model.safetensors.index.json")))
+vision_shards = sorted({v for k, v in vidx["weight_map"].items() if k.startswith("model.visual.")})
+vfiles = [hf_hub_download(VISION_REPO, sh) for sh in vision_shards]
+print(f"        vision lives in: {vision_shards}")
+
+os.makedirs(OUT, exist_ok=True)
+
+# 3) link AgentWorld text shards into OUT (no copy of the 65 GB)
+aw_idx = json.load(open(os.path.join(aw, "model.safetensors.index.json")))
+text_map = dict(aw_idx["weight_map"])
+assert not any(k.startswith("model.visual") for k in text_map), "AgentWorld already has vision keys?!"
+for sh in sorted(set(text_map.values())):
+    dst = os.path.join(OUT, sh)
+    if os.path.lexists(dst):
+        os.remove(dst)
+    os.symlink(os.path.realpath(os.path.join(aw, sh)), dst)
+print(f"[3/5] linked {len(set(text_map.values()))} text shards ({len(text_map)} tensors)")
+
+# 4) extract the 333 vision tensors -> new shard
+print("[4/5] extracting model.visual.* ...")
+vision = {}
+for f in vfiles:
+    with safe_open(f, framework="pt", device="cpu") as h:
+        for k in h.keys():
+            if k.startswith("model.visual."):
+                vision[k] = h.get_tensor(k)
+assert len(vision) == 333, f"expected 333 vision tensors, got {len(vision)}"
+assert tuple(vision["model.visual.merger.linear_fc2.weight"].shape) == (2048, 4608)
+save_file(vision, os.path.join(OUT, VISION_SHARD), metadata={"format": "pt"})
+vbytes = sum(t.numel() * t.element_size() for t in vision.values())
+print(f"        wrote {VISION_SHARD} ({vbytes/1e9:.2f} GB)")
+
+# merged index
+merged = dict(text_map)
+merged.update({k: VISION_SHARD for k in vision})
+total = int(aw_idx.get("metadata", {}).get("total_size", 0)) + vbytes
+json.dump({"metadata": {"total_size": total}, "weight_map": merged},
+          open(os.path.join(OUT, "model.safetensors.index.json"), "w"), indent=2)
+
+# 5) config (drop the language_model_only flag so the ViT is built) + small companions
+cfg = json.load(open(os.path.join(aw, "config.json")))
+cfg.pop("language_model_only", None)
+json.dump(cfg, open(os.path.join(OUT, "config.json"), "w"), indent=2)
+for fn in ["tokenizer_config.json", "tokenizer.json", "vocab.json", "merges.txt",
+           "generation_config.json", "chat_template.jinja",
+           "preprocessor_config.json", "video_preprocessor_config.json"]:
+    src = os.path.join(aw, fn)
+    if os.path.exists(src):
+        shutil.copy(os.path.realpath(src), os.path.join(OUT, fn))
+
+print(f"[5/5] DONE -> {OUT}  ({len(merged)} tensors, {total/1e9:.1f} GB)")
+print("Serve with vLLM WITHOUT --language-model-only.")

chat_template.jinja

@@ -0,0 +1,159 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'audio' in item or item.type == 'audio' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain audio.') }}
+                {%- endif %}
+                {{- '<|audio_start|><|audio_pad|><|audio_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,115 @@
+{
+  "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,
+    "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_gate_type": "swish",
+    "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,
+    "use_cache": true,
+    "vocab_size": 248320
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.0.dev0",
+  "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
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+    "bos_token_id": 248044,
+    "do_sample": true,
+    "eos_token_id": [
+        248046,
+        248044
+    ],
+    "pad_token_id": 248044,
+    "temperature": 0.6,
+    "top_k": 20,
+    "top_p": 0.95
+}

model-00001-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87e3b0dd296f3d0e723b72e58474bc61d613a4428dce91025234a68770c7308b
+size 3221427536

model-00002-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3d857f4d5ce2df35b7f1db4d0376aed7d08e0ca0c66e74f9a59fe94a4ec43c7
+size 3258975384

model-00003-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:094da1e16b80fc3a3ea69272a399f5ce8f589fa133cf8eb7da07be7e9ebe96e9
+size 3221226048

model-00004-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4b35aa2a06f25d1999584554c93939b7153f5e3bd742020a8c8577f292bf3f5
+size 3263173992

model-00005-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e404f494eed7dba0cc17275c2a78f6bebac892fea9e36b3ca4bf0ef6f6bacaa5
+size 3271755384

model-00006-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df8e50cc4b39e20b6a9230f74dccd5983a5ea122ec034ea64681781f010b5058
+size 3221226048

model-00007-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea1106a42dc1ad5ef8eca0368b8554b9baa2f80382ffdbe3bcb2b37c76e251ce
+size 3222340416

model-00008-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a55da43e6b0a7b4e6cb694a99e5771f41bd7ccfe2ab17fdbb4ce61ac720f78b0
+size 3221230464

model-00009-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40d11673e7439f6bb40323daf220b2bca0d5234ed1b61f796e0ab3ffd1193bfe
+size 3256877912

model-00010-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fef1c12dfed720dc8e7842a872a678393e3289cc68a49183766bd22ae70acb0
+size 3363838800

model-00011-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3eb8dc24da411913a950a4191d513f9ae8a70a26b1c0488b887cc8a59b2f603
+size 3784847976

model-00012-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b60240c4d2f5a3cc489b4c4f197bff4cbb56b1b38bc139b57f78cdaa20e62ba5
+size 3221230280

model-00013-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ee5d6246bb4996157944090ee0b940e29769998cda46d86d3b7c70cb664228c
+size 3259172088

model-00014-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3132403084227cf9b40aa1fc238d4cb8e820bb1516524683a87fe14f6ffa2b88
+size 3222278984

model-00015-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02a8a1c0978a4ad942bb9b08d373b87818a051d725c5f3986376a15c48bda681
+size 3254780624

model-00016-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fc007b8c939ff8a5d1a17fefa80f8ec093889f22ab08484311cc87391557631
+size 3223389016

model-00017-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:633b3eefe26ddb3d7b65d4e07883da8cb11e8579e4602e21a8ca6b5e8dc0926c
+size 3254784856

model-00018-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:732b4f76adf16c1bfc47b16b8df39c81bb241d0ccd214e6a5bd14f7ea42570c8
+size 3242394864

model-00019-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf1c8f06059a0dc4c4cd60f737afeb21a3227414f9dfd23862bf3ad5f883a23c
+size 3221226048

model-00020-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ae74e2261e1e6589cc1f9e82aa4cb02c7cda3d60a7a76816bd27098a5de51da
+size 3225424872

model-00021-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6379e7108900493e234856276c32250c113e4fc461511f72d6b1015441e6057
+size 3889712984

model-vision.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f730cecc09c40191e62eacf706743b1ce80a4170a761ba6bd157b102bd9f3edf
+size 893179528

model.safetensors.index.json

@@ -0,0 +1,1033 @@
+{
+  "metadata": {
+    "total_size": 70214363872
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.embed_tokens.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.0.input_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.0.linear_attn.A_log": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.0.linear_attn.conv1d.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.0.linear_attn.dt_bias": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00010-of-00021.safetensors",
+    "model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.0.linear_attn.norm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.0.linear_attn.out_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.0.mlp.experts.down_proj": "model-00001-of-00021.safetensors",
+    "model.language_model.layers.0.mlp.experts.gate_up_proj": "model-00001-of-00021.safetensors",
+    "model.language_model.layers.0.mlp.gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.0.mlp.shared_expert.down_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.0.mlp.shared_expert.gate_proj.weight": "model-00010-of-00021.safetensors",
+    "model.language_model.layers.0.mlp.shared_expert.up_proj.weight": "model-00010-of-00021.safetensors",
+    "model.language_model.layers.0.mlp.shared_expert_gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.0.post_attention_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.1.input_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.1.linear_attn.A_log": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.1.linear_attn.conv1d.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.1.linear_attn.dt_bias": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.1.linear_attn.norm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.1.linear_attn.out_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.1.mlp.experts.down_proj": "model-00001-of-00021.safetensors",
+    "model.language_model.layers.1.mlp.experts.gate_up_proj": "model-00001-of-00021.safetensors",
+    "model.language_model.layers.1.mlp.gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.1.mlp.shared_expert.down_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.1.mlp.shared_expert.gate_proj.weight": "model-00010-of-00021.safetensors",
+    "model.language_model.layers.1.mlp.shared_expert.up_proj.weight": "model-00010-of-00021.safetensors",
+    "model.language_model.layers.1.mlp.shared_expert_gate.weight": "model-00001-of-00021.safetensors",
+    "model.language_model.layers.1.post_attention_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.10.input_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.10.linear_attn.A_log": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.10.linear_attn.conv1d.weight": "model-00005-of-00021.safetensors",
+    "model.language_model.layers.10.linear_attn.dt_bias": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00005-of-00021.safetensors",
+    "model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.10.linear_attn.norm.weight": "model-00005-of-00021.safetensors",
+    "model.language_model.layers.10.linear_attn.out_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.10.mlp.experts.down_proj": "model-00006-of-00021.safetensors",
+    "model.language_model.layers.10.mlp.experts.gate_up_proj": "model-00006-of-00021.safetensors",
+    "model.language_model.layers.10.mlp.gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.10.mlp.shared_expert.down_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.10.mlp.shared_expert.gate_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.10.mlp.shared_expert.up_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.10.mlp.shared_expert_gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.10.post_attention_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.11.input_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.11.mlp.experts.down_proj": "model-00006-of-00021.safetensors",
+    "model.language_model.layers.11.mlp.experts.gate_up_proj": "model-00006-of-00021.safetensors",
+    "model.language_model.layers.11.mlp.gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.11.mlp.shared_expert.down_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.11.mlp.shared_expert.gate_proj.weight": "model-00010-of-00021.safetensors",
+    "model.language_model.layers.11.mlp.shared_expert.up_proj.weight": "model-00010-of-00021.safetensors",
+    "model.language_model.layers.11.mlp.shared_expert_gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.11.post_attention_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.11.self_attn.k_norm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.11.self_attn.k_proj.weight": "model-00010-of-00021.safetensors",
+    "model.language_model.layers.11.self_attn.o_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.11.self_attn.q_norm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.11.self_attn.q_proj.weight": "model-00010-of-00021.safetensors",
+    "model.language_model.layers.11.self_attn.v_proj.weight": "model-00010-of-00021.safetensors",
+    "model.language_model.layers.12.input_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.12.linear_attn.A_log": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.12.linear_attn.conv1d.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.12.linear_attn.dt_bias": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.12.linear_attn.norm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.12.linear_attn.out_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.12.mlp.experts.down_proj": "model-00007-of-00021.safetensors",
+    "model.language_model.layers.12.mlp.experts.gate_up_proj": "model-00007-of-00021.safetensors",
+    "model.language_model.layers.12.mlp.gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.12.mlp.shared_expert.down_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.12.mlp.shared_expert.gate_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.12.mlp.shared_expert.up_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.12.mlp.shared_expert_gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.12.post_attention_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.13.input_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.13.linear_attn.A_log": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.13.linear_attn.conv1d.weight": "model-00007-of-00021.safetensors",
+    "model.language_model.layers.13.linear_attn.dt_bias": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.13.linear_attn.norm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.13.linear_attn.out_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.13.mlp.experts.down_proj": "model-00007-of-00021.safetensors",
+    "model.language_model.layers.13.mlp.experts.gate_up_proj": "model-00007-of-00021.safetensors",
+    "model.language_model.layers.13.mlp.gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.13.mlp.shared_expert.down_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.13.mlp.shared_expert.gate_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.13.mlp.shared_expert.up_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.13.mlp.shared_expert_gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.13.post_attention_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.14.input_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.14.linear_attn.A_log": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.14.linear_attn.conv1d.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.14.linear_attn.dt_bias": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.14.linear_attn.norm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.14.linear_attn.out_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.14.mlp.experts.down_proj": "model-00008-of-00021.safetensors",
+    "model.language_model.layers.14.mlp.experts.gate_up_proj": "model-00008-of-00021.safetensors",
+    "model.language_model.layers.14.mlp.gate.weight": "model-00007-of-00021.safetensors",
+    "model.language_model.layers.14.mlp.shared_expert.down_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.14.mlp.shared_expert.gate_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.14.mlp.shared_expert.up_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.14.mlp.shared_expert_gate.weight": "model-00008-of-00021.safetensors",
+    "model.language_model.layers.14.post_attention_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.15.input_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.15.mlp.experts.down_proj": "model-00008-of-00021.safetensors",
+    "model.language_model.layers.15.mlp.experts.gate_up_proj": "model-00008-of-00021.safetensors",
+    "model.language_model.layers.15.mlp.gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.15.mlp.shared_expert.down_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.15.mlp.shared_expert.gate_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.15.mlp.shared_expert.up_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.15.mlp.shared_expert_gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.15.post_attention_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.15.self_attn.k_norm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.15.self_attn.k_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.15.self_attn.o_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.15.self_attn.q_norm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.15.self_attn.q_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.15.self_attn.v_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.16.input_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.16.linear_attn.A_log": "model-00008-of-00021.safetensors",
+    "model.language_model.layers.16.linear_attn.conv1d.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.16.linear_attn.dt_bias": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00010-of-00021.safetensors",
+    "model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.16.linear_attn.norm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.16.linear_attn.out_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.16.mlp.experts.down_proj": "model-00009-of-00021.safetensors",
+    "model.language_model.layers.16.mlp.experts.gate_up_proj": "model-00009-of-00021.safetensors",
+    "model.language_model.layers.16.mlp.gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.16.mlp.shared_expert.down_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.16.mlp.shared_expert.gate_proj.weight": "model-00010-of-00021.safetensors",
+    "model.language_model.layers.16.mlp.shared_expert.up_proj.weight": "model-00010-of-00021.safetensors",
+    "model.language_model.layers.16.mlp.shared_expert_gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.16.post_attention_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.17.input_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.17.linear_attn.A_log": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.17.linear_attn.conv1d.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.17.linear_attn.dt_bias": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00009-of-00021.safetensors",
+    "model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.17.linear_attn.norm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.17.linear_attn.out_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.17.mlp.experts.down_proj": "model-00009-of-00021.safetensors",
+    "model.language_model.layers.17.mlp.experts.gate_up_proj": "model-00009-of-00021.safetensors",
+    "model.language_model.layers.17.mlp.gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.17.mlp.shared_expert.down_proj.weight": "model-00009-of-00021.safetensors",
+    "model.language_model.layers.17.mlp.shared_expert.gate_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.17.mlp.shared_expert.up_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.17.mlp.shared_expert_gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.17.post_attention_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.18.input_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.18.linear_attn.A_log": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.18.linear_attn.conv1d.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.18.linear_attn.dt_bias": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.18.linear_attn.norm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.18.linear_attn.out_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.18.mlp.experts.down_proj": "model-00010-of-00021.safetensors",
+    "model.language_model.layers.18.mlp.experts.gate_up_proj": "model-00010-of-00021.safetensors",
+    "model.language_model.layers.18.mlp.gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.18.mlp.shared_expert.down_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.18.mlp.shared_expert.gate_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.18.mlp.shared_expert.up_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.18.mlp.shared_expert_gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.18.post_attention_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.19.input_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.19.mlp.experts.down_proj": "model-00010-of-00021.safetensors",
+    "model.language_model.layers.19.mlp.experts.gate_up_proj": "model-00010-of-00021.safetensors",
+    "model.language_model.layers.19.mlp.gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.19.mlp.shared_expert.down_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.19.mlp.shared_expert.gate_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.19.mlp.shared_expert.up_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.19.mlp.shared_expert_gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.19.post_attention_layernorm.weight": "model-00010-of-00021.safetensors",
+    "model.language_model.layers.19.self_attn.k_norm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.19.self_attn.k_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.19.self_attn.o_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.19.self_attn.q_norm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.19.self_attn.q_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.19.self_attn.v_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.2.input_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.2.linear_attn.A_log": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00021.safetensors",
+    "model.language_model.layers.2.linear_attn.dt_bias": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00021.safetensors",
+    "model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.2.linear_attn.norm.weight": "model-00001-of-00021.safetensors",
+    "model.language_model.layers.2.linear_attn.out_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.2.mlp.experts.down_proj": "model-00002-of-00021.safetensors",
+    "model.language_model.layers.2.mlp.experts.gate_up_proj": "model-00002-of-00021.safetensors",
+    "model.language_model.layers.2.mlp.gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.2.mlp.shared_expert.down_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.2.mlp.shared_expert.gate_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.2.mlp.shared_expert.up_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.2.mlp.shared_expert_gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.2.post_attention_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.20.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.20.linear_attn.A_log": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.20.linear_attn.conv1d.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.20.linear_attn.dt_bias": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.20.linear_attn.norm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.20.linear_attn.out_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.20.mlp.experts.down_proj": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.20.mlp.experts.gate_up_proj": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.20.mlp.gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.20.mlp.shared_expert.down_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.20.mlp.shared_expert.gate_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.20.mlp.shared_expert.up_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.20.mlp.shared_expert_gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.20.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.21.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.21.linear_attn.A_log": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.21.linear_attn.conv1d.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.21.linear_attn.dt_bias": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.21.linear_attn.norm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.21.linear_attn.out_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.21.mlp.experts.down_proj": "model-00012-of-00021.safetensors",
+    "model.language_model.layers.21.mlp.experts.gate_up_proj": "model-00012-of-00021.safetensors",
+    "model.language_model.layers.21.mlp.gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.21.mlp.shared_expert.down_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.21.mlp.shared_expert.gate_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.21.mlp.shared_expert.up_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.21.mlp.shared_expert_gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.21.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.22.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.22.linear_attn.A_log": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.22.linear_attn.conv1d.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.22.linear_attn.dt_bias": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.22.linear_attn.norm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.22.linear_attn.out_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.22.mlp.experts.down_proj": "model-00012-of-00021.safetensors",
+    "model.language_model.layers.22.mlp.experts.gate_up_proj": "model-00012-of-00021.safetensors",
+    "model.language_model.layers.22.mlp.gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.22.mlp.shared_expert.down_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.22.mlp.shared_expert.gate_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.22.mlp.shared_expert.up_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.22.mlp.shared_expert_gate.weight": "model-00012-of-00021.safetensors",
+    "model.language_model.layers.22.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.23.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.23.mlp.experts.down_proj": "model-00013-of-00021.safetensors",
+    "model.language_model.layers.23.mlp.experts.gate_up_proj": "model-00013-of-00021.safetensors",
+    "model.language_model.layers.23.mlp.gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.23.mlp.shared_expert.down_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.23.mlp.shared_expert.gate_proj.weight": "model-00013-of-00021.safetensors",
+    "model.language_model.layers.23.mlp.shared_expert.up_proj.weight": "model-00013-of-00021.safetensors",
+    "model.language_model.layers.23.mlp.shared_expert_gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.23.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.23.self_attn.k_norm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.23.self_attn.k_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.23.self_attn.o_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.23.self_attn.q_norm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.23.self_attn.q_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.23.self_attn.v_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.24.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.24.linear_attn.A_log": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.24.linear_attn.conv1d.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.24.linear_attn.dt_bias": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.24.linear_attn.norm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.24.linear_attn.out_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.24.mlp.experts.down_proj": "model-00013-of-00021.safetensors",
+    "model.language_model.layers.24.mlp.experts.gate_up_proj": "model-00013-of-00021.safetensors",
+    "model.language_model.layers.24.mlp.gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.24.mlp.shared_expert.down_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.24.mlp.shared_expert.gate_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.24.mlp.shared_expert.up_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.24.mlp.shared_expert_gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.24.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.25.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.25.linear_attn.A_log": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.25.linear_attn.conv1d.weight": "model-00013-of-00021.safetensors",
+    "model.language_model.layers.25.linear_attn.dt_bias": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00013-of-00021.safetensors",
+    "model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00013-of-00021.safetensors",
+    "model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.25.linear_attn.norm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.25.linear_attn.out_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.25.mlp.experts.down_proj": "model-00014-of-00021.safetensors",
+    "model.language_model.layers.25.mlp.experts.gate_up_proj": "model-00014-of-00021.safetensors",
+    "model.language_model.layers.25.mlp.gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.25.mlp.shared_expert.down_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.25.mlp.shared_expert.gate_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.25.mlp.shared_expert.up_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.25.mlp.shared_expert_gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.25.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.26.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.26.linear_attn.A_log": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.26.linear_attn.conv1d.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.26.linear_attn.dt_bias": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.26.linear_attn.norm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.26.linear_attn.out_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.26.mlp.experts.down_proj": "model-00014-of-00021.safetensors",
+    "model.language_model.layers.26.mlp.experts.gate_up_proj": "model-00014-of-00021.safetensors",
+    "model.language_model.layers.26.mlp.gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.26.mlp.shared_expert.down_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.26.mlp.shared_expert.gate_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.26.mlp.shared_expert.up_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.26.mlp.shared_expert_gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.26.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.27.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.27.mlp.experts.down_proj": "model-00015-of-00021.safetensors",
+    "model.language_model.layers.27.mlp.experts.gate_up_proj": "model-00015-of-00021.safetensors",
+    "model.language_model.layers.27.mlp.gate.weight": "model-00014-of-00021.safetensors",
+    "model.language_model.layers.27.mlp.shared_expert.down_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.27.mlp.shared_expert.gate_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.27.mlp.shared_expert.up_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.27.mlp.shared_expert_gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.27.post_attention_layernorm.weight": "model-00014-of-00021.safetensors",
+    "model.language_model.layers.27.self_attn.k_norm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.27.self_attn.k_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.27.self_attn.o_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.27.self_attn.q_norm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.27.self_attn.q_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.27.self_attn.v_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.28.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.28.linear_attn.A_log": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.28.linear_attn.conv1d.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.28.linear_attn.dt_bias": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.28.linear_attn.norm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.28.linear_attn.out_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.28.mlp.experts.down_proj": "model-00015-of-00021.safetensors",
+    "model.language_model.layers.28.mlp.experts.gate_up_proj": "model-00015-of-00021.safetensors",
+    "model.language_model.layers.28.mlp.gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.28.mlp.shared_expert.down_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.28.mlp.shared_expert.gate_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.28.mlp.shared_expert.up_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.28.mlp.shared_expert_gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.28.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.29.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.29.linear_attn.A_log": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.29.linear_attn.conv1d.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.29.linear_attn.dt_bias": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00015-of-00021.safetensors",
+    "model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.29.linear_attn.norm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.29.linear_attn.out_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.29.mlp.experts.down_proj": "model-00016-of-00021.safetensors",
+    "model.language_model.layers.29.mlp.experts.gate_up_proj": "model-00016-of-00021.safetensors",
+    "model.language_model.layers.29.mlp.gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.29.mlp.shared_expert.down_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.29.mlp.shared_expert.gate_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.29.mlp.shared_expert.up_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.29.mlp.shared_expert_gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.29.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.3.input_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.3.mlp.experts.down_proj": "model-00002-of-00021.safetensors",
+    "model.language_model.layers.3.mlp.experts.gate_up_proj": "model-00002-of-00021.safetensors",
+    "model.language_model.layers.3.mlp.gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.3.mlp.shared_expert.down_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.3.mlp.shared_expert.gate_proj.weight": "model-00002-of-00021.safetensors",
+    "model.language_model.layers.3.mlp.shared_expert.up_proj.weight": "model-00002-of-00021.safetensors",
+    "model.language_model.layers.3.mlp.shared_expert_gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.3.post_attention_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.3.self_attn.k_norm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.3.self_attn.k_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.3.self_attn.o_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.3.self_attn.q_norm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.3.self_attn.q_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.3.self_attn.v_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.30.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.30.linear_attn.A_log": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.30.linear_attn.conv1d.weight": "model-00016-of-00021.safetensors",
+    "model.language_model.layers.30.linear_attn.dt_bias": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.30.linear_attn.norm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.30.linear_attn.out_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.30.mlp.experts.down_proj": "model-00016-of-00021.safetensors",
+    "model.language_model.layers.30.mlp.experts.gate_up_proj": "model-00016-of-00021.safetensors",
+    "model.language_model.layers.30.mlp.gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.30.mlp.shared_expert.down_proj.weight": "model-00016-of-00021.safetensors",
+    "model.language_model.layers.30.mlp.shared_expert.gate_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.30.mlp.shared_expert.up_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.30.mlp.shared_expert_gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.30.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.31.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.31.mlp.experts.down_proj": "model-00017-of-00021.safetensors",
+    "model.language_model.layers.31.mlp.experts.gate_up_proj": "model-00017-of-00021.safetensors",
+    "model.language_model.layers.31.mlp.gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.31.mlp.shared_expert.down_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.31.mlp.shared_expert.gate_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.31.mlp.shared_expert.up_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.31.mlp.shared_expert_gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.31.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.31.self_attn.k_norm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.31.self_attn.k_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.31.self_attn.o_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.31.self_attn.q_norm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.31.self_attn.q_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.31.self_attn.v_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.32.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.32.linear_attn.A_log": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.32.linear_attn.conv1d.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.32.linear_attn.dt_bias": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.32.linear_attn.in_proj_a.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.32.linear_attn.in_proj_b.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.32.linear_attn.in_proj_qkv.weight": "model-00017-of-00021.safetensors",
+    "model.language_model.layers.32.linear_attn.in_proj_z.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.32.linear_attn.norm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.32.linear_attn.out_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.32.mlp.experts.down_proj": "model-00017-of-00021.safetensors",
+    "model.language_model.layers.32.mlp.experts.gate_up_proj": "model-00017-of-00021.safetensors",
+    "model.language_model.layers.32.mlp.gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.32.mlp.shared_expert.down_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.32.mlp.shared_expert.gate_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.32.mlp.shared_expert.up_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.32.mlp.shared_expert_gate.weight": "model-00017-of-00021.safetensors",
+    "model.language_model.layers.32.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.33.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.33.linear_attn.A_log": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.33.linear_attn.conv1d.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.33.linear_attn.dt_bias": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.33.linear_attn.in_proj_a.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.33.linear_attn.in_proj_b.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.33.linear_attn.in_proj_qkv.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.33.linear_attn.in_proj_z.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.33.linear_attn.norm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.33.linear_attn.out_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.33.mlp.experts.down_proj": "model-00018-of-00021.safetensors",
+    "model.language_model.layers.33.mlp.experts.gate_up_proj": "model-00018-of-00021.safetensors",
+    "model.language_model.layers.33.mlp.gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.33.mlp.shared_expert.down_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.33.mlp.shared_expert.gate_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.33.mlp.shared_expert.up_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.33.mlp.shared_expert_gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.33.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.34.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.34.linear_attn.A_log": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.34.linear_attn.conv1d.weight": "model-00018-of-00021.safetensors",
+    "model.language_model.layers.34.linear_attn.dt_bias": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.34.linear_attn.in_proj_a.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.34.linear_attn.in_proj_b.weight": "model-00018-of-00021.safetensors",
+    "model.language_model.layers.34.linear_attn.in_proj_qkv.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.34.linear_attn.in_proj_z.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.34.linear_attn.norm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.34.linear_attn.out_proj.weight": "model-00018-of-00021.safetensors",
+    "model.language_model.layers.34.mlp.experts.down_proj": "model-00018-of-00021.safetensors",
+    "model.language_model.layers.34.mlp.experts.gate_up_proj": "model-00018-of-00021.safetensors",
+    "model.language_model.layers.34.mlp.gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.34.mlp.shared_expert.down_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.34.mlp.shared_expert.gate_proj.weight": "model-00018-of-00021.safetensors",
+    "model.language_model.layers.34.mlp.shared_expert.up_proj.weight": "model-00018-of-00021.safetensors",
+    "model.language_model.layers.34.mlp.shared_expert_gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.34.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.35.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.35.mlp.experts.down_proj": "model-00019-of-00021.safetensors",
+    "model.language_model.layers.35.mlp.experts.gate_up_proj": "model-00019-of-00021.safetensors",
+    "model.language_model.layers.35.mlp.gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.35.mlp.shared_expert.down_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.35.mlp.shared_expert.gate_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.35.mlp.shared_expert.up_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.35.mlp.shared_expert_gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.35.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.35.self_attn.k_norm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.35.self_attn.k_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.35.self_attn.o_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.35.self_attn.q_norm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.35.self_attn.q_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.35.self_attn.v_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.36.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.36.linear_attn.A_log": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.36.linear_attn.conv1d.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.36.linear_attn.dt_bias": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.36.linear_attn.in_proj_a.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.36.linear_attn.in_proj_b.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.36.linear_attn.in_proj_qkv.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.36.linear_attn.in_proj_z.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.36.linear_attn.norm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.36.linear_attn.out_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.36.mlp.experts.down_proj": "model-00019-of-00021.safetensors",
+    "model.language_model.layers.36.mlp.experts.gate_up_proj": "model-00019-of-00021.safetensors",
+    "model.language_model.layers.36.mlp.gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.36.mlp.shared_expert.down_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.36.mlp.shared_expert.gate_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.36.mlp.shared_expert.up_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.36.mlp.shared_expert_gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.36.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.37.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.37.linear_attn.A_log": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.37.linear_attn.conv1d.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.37.linear_attn.dt_bias": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.37.linear_attn.in_proj_a.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.37.linear_attn.in_proj_b.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.37.linear_attn.in_proj_qkv.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.37.linear_attn.in_proj_z.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.37.linear_attn.norm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.37.linear_attn.out_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.37.mlp.experts.down_proj": "model-00020-of-00021.safetensors",
+    "model.language_model.layers.37.mlp.experts.gate_up_proj": "model-00020-of-00021.safetensors",
+    "model.language_model.layers.37.mlp.gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.37.mlp.shared_expert.down_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.37.mlp.shared_expert.gate_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.37.mlp.shared_expert.up_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.37.mlp.shared_expert_gate.weight": "model-00020-of-00021.safetensors",
+    "model.language_model.layers.37.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.38.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.38.linear_attn.A_log": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.38.linear_attn.conv1d.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.38.linear_attn.dt_bias": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.38.linear_attn.in_proj_a.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.38.linear_attn.in_proj_b.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.38.linear_attn.in_proj_qkv.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.38.linear_attn.in_proj_z.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.38.linear_attn.norm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.38.linear_attn.out_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.38.mlp.experts.down_proj": "model-00020-of-00021.safetensors",
+    "model.language_model.layers.38.mlp.experts.gate_up_proj": "model-00020-of-00021.safetensors",
+    "model.language_model.layers.38.mlp.gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.38.mlp.shared_expert.down_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.38.mlp.shared_expert.gate_proj.weight": "model-00020-of-00021.safetensors",
+    "model.language_model.layers.38.mlp.shared_expert.up_proj.weight": "model-00020-of-00021.safetensors",
+    "model.language_model.layers.38.mlp.shared_expert_gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.38.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.39.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.39.mlp.experts.down_proj": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.39.mlp.experts.gate_up_proj": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.39.mlp.gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.39.mlp.shared_expert.down_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.39.mlp.shared_expert.gate_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.39.mlp.shared_expert.up_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.39.mlp.shared_expert_gate.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.39.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.39.self_attn.k_norm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.39.self_attn.k_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.39.self_attn.o_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.39.self_attn.q_norm.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.39.self_attn.q_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.39.self_attn.v_proj.weight": "model-00021-of-00021.safetensors",
+    "model.language_model.layers.4.input_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.4.linear_attn.A_log": "model-00002-of-00021.safetensors",
+    "model.language_model.layers.4.linear_attn.conv1d.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.4.linear_attn.dt_bias": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00002-of-00021.safetensors",
+    "model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00010-of-00021.safetensors",
+    "model.language_model.layers.4.linear_attn.norm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.4.linear_attn.out_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.4.mlp.experts.down_proj": "model-00003-of-00021.safetensors",
+    "model.language_model.layers.4.mlp.experts.gate_up_proj": "model-00003-of-00021.safetensors",
+    "model.language_model.layers.4.mlp.gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.4.mlp.shared_expert.down_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.4.mlp.shared_expert.gate_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.4.mlp.shared_expert.up_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.4.mlp.shared_expert_gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.4.post_attention_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.5.input_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.5.linear_attn.A_log": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.5.linear_attn.conv1d.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.5.linear_attn.dt_bias": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.5.linear_attn.norm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.5.linear_attn.out_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.5.mlp.experts.down_proj": "model-00003-of-00021.safetensors",
+    "model.language_model.layers.5.mlp.experts.gate_up_proj": "model-00003-of-00021.safetensors",
+    "model.language_model.layers.5.mlp.gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.5.mlp.shared_expert.down_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.5.mlp.shared_expert.gate_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.5.mlp.shared_expert.up_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.5.mlp.shared_expert_gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.5.post_attention_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.6.input_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.6.linear_attn.A_log": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.6.linear_attn.conv1d.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.6.linear_attn.dt_bias": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.6.linear_attn.norm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.6.linear_attn.out_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.6.mlp.experts.down_proj": "model-00004-of-00021.safetensors",
+    "model.language_model.layers.6.mlp.experts.gate_up_proj": "model-00004-of-00021.safetensors",
+    "model.language_model.layers.6.mlp.gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.6.mlp.shared_expert.down_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.6.mlp.shared_expert.gate_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.6.mlp.shared_expert.up_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.6.mlp.shared_expert_gate.weight": "model-00004-of-00021.safetensors",
+    "model.language_model.layers.6.post_attention_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.7.input_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.7.mlp.experts.down_proj": "model-00004-of-00021.safetensors",
+    "model.language_model.layers.7.mlp.experts.gate_up_proj": "model-00004-of-00021.safetensors",
+    "model.language_model.layers.7.mlp.gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.7.mlp.shared_expert.down_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.7.mlp.shared_expert.gate_proj.weight": "model-00004-of-00021.safetensors",
+    "model.language_model.layers.7.mlp.shared_expert.up_proj.weight": "model-00004-of-00021.safetensors",
+    "model.language_model.layers.7.mlp.shared_expert_gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.7.post_attention_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.7.self_attn.k_norm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.7.self_attn.k_proj.weight": "model-00004-of-00021.safetensors",
+    "model.language_model.layers.7.self_attn.o_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.7.self_attn.q_norm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.7.self_attn.q_proj.weight": "model-00004-of-00021.safetensors",
+    "model.language_model.layers.7.self_attn.v_proj.weight": "model-00004-of-00021.safetensors",
+    "model.language_model.layers.8.input_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.8.linear_attn.A_log": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.8.linear_attn.conv1d.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.8.linear_attn.dt_bias": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.8.linear_attn.norm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.8.linear_attn.out_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.8.mlp.experts.down_proj": "model-00005-of-00021.safetensors",
+    "model.language_model.layers.8.mlp.experts.gate_up_proj": "model-00005-of-00021.safetensors",
+    "model.language_model.layers.8.mlp.gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.8.mlp.shared_expert.down_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.8.mlp.shared_expert.gate_proj.weight": "model-00010-of-00021.safetensors",
+    "model.language_model.layers.8.mlp.shared_expert.up_proj.weight": "model-00010-of-00021.safetensors",
+    "model.language_model.layers.8.mlp.shared_expert_gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.8.post_attention_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.9.input_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.9.linear_attn.A_log": "model-00005-of-00021.safetensors",
+    "model.language_model.layers.9.linear_attn.conv1d.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.9.linear_attn.dt_bias": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00005-of-00021.safetensors",
+    "model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.9.linear_attn.norm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.9.linear_attn.out_proj.weight": "model-00005-of-00021.safetensors",
+    "model.language_model.layers.9.mlp.experts.down_proj": "model-00005-of-00021.safetensors",
+    "model.language_model.layers.9.mlp.experts.gate_up_proj": "model-00005-of-00021.safetensors",
+    "model.language_model.layers.9.mlp.gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.9.mlp.shared_expert.down_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.9.mlp.shared_expert.gate_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.9.mlp.shared_expert.up_proj.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.9.mlp.shared_expert_gate.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.layers.9.post_attention_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.language_model.norm.weight": "model-00021-of-00021.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.weight": "model-vision.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.weight": "model-vision.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.weight": "model-vision.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.weight": "model-vision.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.weight": "model-vision.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.weight": "model-vision.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.weight": "model-vision.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.weight": "model-vision.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.weight": "model-vision.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.weight": "model-vision.safetensors",
+    "model.visual.merger.linear_fc1.weight": "model-vision.safetensors",
+    "model.visual.merger.linear_fc2.weight": "model-vision.safetensors",
+    "model.visual.blocks.0.attn.proj.bias": "model-vision.safetensors",
+    "model.visual.blocks.0.attn.proj.weight": "model-vision.safetensors",
+    "model.visual.blocks.0.attn.qkv.bias": "model-vision.safetensors",
+    "model.visual.blocks.0.attn.qkv.weight": "model-vision.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.bias": "model-vision.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.bias": "model-vision.safetensors",
+    "model.visual.blocks.0.norm1.bias": "model-vision.safetensors",
+    "model.visual.blocks.0.norm1.weight": "model-vision.safetensors",
+    "model.visual.blocks.0.norm2.bias": "model-vision.safetensors",
+    "model.visual.blocks.0.norm2.weight": "model-vision.safetensors",
+    "model.visual.blocks.1.attn.proj.bias": "model-vision.safetensors",
+    "model.visual.blocks.1.attn.proj.weight": "model-vision.safetensors",
+    "model.visual.blocks.1.attn.qkv.bias": "model-vision.safetensors",
+    "model.visual.blocks.1.attn.qkv.weight": "model-vision.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.bias": "model-vision.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.bias": "model-vision.safetensors",
+    "model.visual.blocks.1.norm1.bias": "model-vision.safetensors",
+    "model.visual.blocks.1.norm1.weight": "model-vision.safetensors",
+    "model.visual.blocks.1.norm2.bias": "model-vision.safetensors",
+    "model.visual.blocks.1.norm2.weight": "model-vision.safetensors",
+    "model.visual.blocks.10.attn.proj.bias": "model-vision.safetensors",
+    "model.visual.blocks.10.attn.proj.weight": "model-vision.safetensors",
+    "model.visual.blocks.10.attn.qkv.bias": "model-vision.safetensors",
+    "model.visual.blocks.10.attn.qkv.weight": "model-vision.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.bias": "model-vision.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.bias": "model-vision.safetensors",
+    "model.visual.blocks.10.norm1.bias": "model-vision.safetensors",
+    "model.visual.blocks.10.norm1.weight": "model-vision.safetensors",
+    "model.visual.blocks.10.norm2.bias": "model-vision.safetensors",
+    "model.visual.blocks.10.norm2.weight": "model-vision.safetensors",
+    "model.visual.blocks.11.attn.proj.bias": "model-vision.safetensors",
+    "model.visual.blocks.11.attn.proj.weight": "model-vision.safetensors",
+    "model.visual.blocks.11.attn.qkv.bias": "model-vision.safetensors",
+    "model.visual.blocks.11.attn.qkv.weight": "model-vision.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.bias": "model-vision.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.bias": "model-vision.safetensors",
+    "model.visual.blocks.11.norm1.bias": "model-vision.safetensors",
+    "model.visual.blocks.11.norm1.weight": "model-vision.safetensors",
+    "model.visual.blocks.11.norm2.bias": "model-vision.safetensors",
+    "model.visual.blocks.11.norm2.weight": "model-vision.safetensors",
+    "model.visual.blocks.12.attn.proj.bias": "model-vision.safetensors",
+    "model.visual.blocks.12.attn.proj.weight": "model-vision.safetensors",
+    "model.visual.blocks.12.attn.qkv.bias": "model-vision.safetensors",
+    "model.visual.blocks.12.attn.qkv.weight": "model-vision.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.bias": "model-vision.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.bias": "model-vision.safetensors",
+    "model.visual.blocks.12.norm1.bias": "model-vision.safetensors",
+    "model.visual.blocks.12.norm1.weight": "model-vision.safetensors",
+    "model.visual.blocks.12.norm2.bias": "model-vision.safetensors",
+    "model.visual.blocks.12.norm2.weight": "model-vision.safetensors",
+    "model.visual.blocks.13.attn.proj.bias": "model-vision.safetensors",
+    "model.visual.blocks.13.attn.proj.weight": "model-vision.safetensors",
+    "model.visual.blocks.13.attn.qkv.bias": "model-vision.safetensors",
+    "model.visual.blocks.13.attn.qkv.weight": "model-vision.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.bias": "model-vision.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.weight": "model-vision.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.bias": "model-vision.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.weight": "model-vision.safetensors",
+    "model.visual.blocks.13.norm1.bias": "model-vision.safetensors",
+    "model.visual.blocks.13.norm1.weight": "model-vision.safetensors",
+    "model.visual.blocks.13.norm2.bias": "model-vision.safetensors",
+    "model.visual.blocks.13.norm2.weight": "model-vision.safetensors",
+    "model.visual.blocks.14.attn.proj.bias": "model-vision.safetensors",
+    "model.visual.blocks.14.attn.proj.weight": "model-vision.safetensors",
+    "model.visual.blocks.14.attn.qkv.bias": "model-vision.safetensors",
+    "model.visual.blocks.14.attn.qkv.weight": "model-vision.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.bias": "model-vision.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.weight": "model-vision.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.bias": "model-vision.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.weight": "model-vision.safetensors",
+    "model.visual.blocks.14.norm1.bias": "model-vision.safetensors",
+    "model.visual.blocks.14.norm1.weight": "model-vision.safetensors",
+    "model.visual.blocks.14.norm2.bias": "model-vision.safetensors",
+    "model.visual.blocks.14.norm2.weight": "model-vision.safetensors",
+    "model.visual.blocks.15.attn.proj.bias": "model-vision.safetensors",
+    "model.visual.blocks.15.attn.proj.weight": "model-vision.safetensors",
+    "model.visual.blocks.15.attn.qkv.bias": "model-vision.safetensors",
+    "model.visual.blocks.15.attn.qkv.weight": "model-vision.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.bias": "model-vision.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.weight": "model-vision.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.bias": "model-vision.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.weight": "model-vision.safetensors",
+    "model.visual.blocks.15.norm1.bias": "model-vision.safetensors",
+    "model.visual.blocks.15.norm1.weight": "model-vision.safetensors",
+    "model.visual.blocks.15.norm2.bias": "model-vision.safetensors",
+    "model.visual.blocks.15.norm2.weight": "model-vision.safetensors",
+    "model.visual.blocks.16.attn.proj.bias": "model-vision.safetensors",
+    "model.visual.blocks.16.attn.proj.weight": "model-vision.safetensors",
+    "model.visual.blocks.16.attn.qkv.bias": "model-vision.safetensors",
+    "model.visual.blocks.16.attn.qkv.weight": "model-vision.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.bias": "model-vision.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.weight": "model-vision.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.bias": "model-vision.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.weight": "model-vision.safetensors",
+    "model.visual.blocks.16.norm1.bias": "model-vision.safetensors",
+    "model.visual.blocks.16.norm1.weight": "model-vision.safetensors",
+    "model.visual.blocks.16.norm2.bias": "model-vision.safetensors",
+    "model.visual.blocks.16.norm2.weight": "model-vision.safetensors",
+    "model.visual.blocks.17.attn.proj.bias": "model-vision.safetensors",
+    "model.visual.blocks.17.attn.proj.weight": "model-vision.safetensors",
+    "model.visual.blocks.17.attn.qkv.bias": "model-vision.safetensors",
+    "model.visual.blocks.17.attn.qkv.weight": "model-vision.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.bias": "model-vision.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.weight": "model-vision.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.bias": "model-vision.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.weight": "model-vision.safetensors",
+    "model.visual.blocks.17.norm1.bias": "model-vision.safetensors",
+    "model.visual.blocks.17.norm1.weight": "model-vision.safetensors",
+    "model.visual.blocks.17.norm2.bias": "model-vision.safetensors",
+    "model.visual.blocks.17.norm2.weight": "model-vision.safetensors",
+    "model.visual.blocks.18.attn.proj.bias": "model-vision.safetensors",
+    "model.visual.blocks.18.attn.proj.weight": "model-vision.safetensors",
+    "model.visual.blocks.18.attn.qkv.bias": "model-vision.safetensors",
+    "model.visual.blocks.18.attn.qkv.weight": "model-vision.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.bias": "model-vision.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.weight": "model-vision.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.bias": "model-vision.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.weight": "model-vision.safetensors",
+    "model.visual.blocks.18.norm1.bias": "model-vision.safetensors",
+    "model.visual.blocks.18.norm1.weight": "model-vision.safetensors",
+    "model.visual.blocks.18.norm2.bias": "model-vision.safetensors",
+    "model.visual.blocks.18.norm2.weight": "model-vision.safetensors",
+    "model.visual.blocks.19.attn.proj.bias": "model-vision.safetensors",
+    "model.visual.blocks.19.attn.proj.weight": "model-vision.safetensors",
+    "model.visual.blocks.19.attn.qkv.bias": "model-vision.safetensors",
+    "model.visual.blocks.19.attn.qkv.weight": "model-vision.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.bias": "model-vision.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.weight": "model-vision.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.bias": "model-vision.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.weight": "model-vision.safetensors",
+    "model.visual.blocks.19.norm1.bias": "model-vision.safetensors",
+    "model.visual.blocks.19.norm1.weight": "model-vision.safetensors",
+    "model.visual.blocks.19.norm2.bias": "model-vision.safetensors",
+    "model.visual.blocks.19.norm2.weight": "model-vision.safetensors",
+    "model.visual.blocks.2.attn.proj.bias": "model-vision.safetensors",
+    "model.visual.blocks.2.attn.proj.weight": "model-vision.safetensors",
+    "model.visual.blocks.2.attn.qkv.bias": "model-vision.safetensors",
+    "model.visual.blocks.2.attn.qkv.weight": "model-vision.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.bias": "model-vision.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.weight": "model-vision.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.bias": "model-vision.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.weight": "model-vision.safetensors",
+    "model.visual.blocks.2.norm1.bias": "model-vision.safetensors",
+    "model.visual.blocks.2.norm1.weight": "model-vision.safetensors",
+    "model.visual.blocks.2.norm2.bias": "model-vision.safetensors",
+    "model.visual.blocks.2.norm2.weight": "model-vision.safetensors",
+    "model.visual.blocks.20.attn.proj.bias": "model-vision.safetensors",
+    "model.visual.blocks.20.attn.proj.weight": "model-vision.safetensors",
+    "model.visual.blocks.20.attn.qkv.bias": "model-vision.safetensors",
+    "model.visual.blocks.20.attn.qkv.weight": "model-vision.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.bias": "model-vision.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.weight": "model-vision.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.bias": "model-vision.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.weight": "model-vision.safetensors",
+    "model.visual.blocks.20.norm1.bias": "model-vision.safetensors",
+    "model.visual.blocks.20.norm1.weight": "model-vision.safetensors",
+    "model.visual.blocks.20.norm2.bias": "model-vision.safetensors",
+    "model.visual.blocks.20.norm2.weight": "model-vision.safetensors",
+    "model.visual.blocks.21.attn.proj.bias": "model-vision.safetensors",
+    "model.visual.blocks.21.attn.proj.weight": "model-vision.safetensors",
+    "model.visual.blocks.21.attn.qkv.bias": "model-vision.safetensors",
+    "model.visual.blocks.21.attn.qkv.weight": "model-vision.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.bias": "model-vision.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.weight": "model-vision.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.bias": "model-vision.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.weight": "model-vision.safetensors",
+    "model.visual.blocks.21.norm1.bias": "model-vision.safetensors",
+    "model.visual.blocks.21.norm1.weight": "model-vision.safetensors",
+    "model.visual.blocks.21.norm2.bias": "model-vision.safetensors",
+    "model.visual.blocks.21.norm2.weight": "model-vision.safetensors",
+    "model.visual.blocks.22.attn.proj.bias": "model-vision.safetensors",
+    "model.visual.blocks.22.attn.proj.weight": "model-vision.safetensors",
+    "model.visual.blocks.22.attn.qkv.bias": "model-vision.safetensors",
+    "model.visual.blocks.22.attn.qkv.weight": "model-vision.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.bias": "model-vision.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.weight": "model-vision.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.bias": "model-vision.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.weight": "model-vision.safetensors",
+    "model.visual.blocks.22.norm1.bias": "model-vision.safetensors",
+    "model.visual.blocks.22.norm1.weight": "model-vision.safetensors",
+    "model.visual.blocks.22.norm2.bias": "model-vision.safetensors",
+    "model.visual.blocks.22.norm2.weight": "model-vision.safetensors",
+    "model.visual.blocks.23.attn.proj.bias": "model-vision.safetensors",
+    "model.visual.blocks.23.attn.proj.weight": "model-vision.safetensors",
+    "model.visual.blocks.23.attn.qkv.bias": "model-vision.safetensors",
+    "model.visual.blocks.23.attn.qkv.weight": "model-vision.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.bias": "model-vision.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.weight": "model-vision.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.bias": "model-vision.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.weight": "model-vision.safetensors",
+    "model.visual.blocks.23.norm1.bias": "model-vision.safetensors",
+    "model.visual.blocks.23.norm1.weight": "model-vision.safetensors",
+    "model.visual.blocks.23.norm2.bias": "model-vision.safetensors",
+    "model.visual.blocks.23.norm2.weight": "model-vision.safetensors",
+    "model.visual.blocks.24.attn.proj.bias": "model-vision.safetensors",
+    "model.visual.blocks.24.attn.proj.weight": "model-vision.safetensors",
+    "model.visual.blocks.24.attn.qkv.bias": "model-vision.safetensors",
+    "model.visual.blocks.24.attn.qkv.weight": "model-vision.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc1.bias": "model-vision.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc1.weight": "model-vision.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc2.bias": "model-vision.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc2.weight": "model-vision.safetensors",
+    "model.visual.blocks.24.norm1.bias": "model-vision.safetensors",
+    "model.visual.blocks.24.norm1.weight": "model-vision.safetensors",
+    "model.visual.blocks.24.norm2.bias": "model-vision.safetensors",
+    "model.visual.blocks.24.norm2.weight": "model-vision.safetensors",
+    "model.visual.blocks.25.attn.proj.bias": "model-vision.safetensors",
+    "model.visual.blocks.25.attn.proj.weight": "model-vision.safetensors",
+    "model.visual.blocks.25.attn.qkv.bias": "model-vision.safetensors",
+    "model.visual.blocks.25.attn.qkv.weight": "model-vision.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc1.bias": "model-vision.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc1.weight": "model-vision.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc2.bias": "model-vision.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc2.weight": "model-vision.safetensors",
+    "model.visual.blocks.25.norm1.bias": "model-vision.safetensors",
+    "model.visual.blocks.25.norm1.weight": "model-vision.safetensors",
+    "model.visual.blocks.25.norm2.bias": "model-vision.safetensors",
+    "model.visual.blocks.25.norm2.weight": "model-vision.safetensors",
+    "model.visual.blocks.26.attn.proj.bias": "model-vision.safetensors",
+    "model.visual.blocks.26.attn.proj.weight": "model-vision.safetensors",
+    "model.visual.blocks.26.attn.qkv.bias": "model-vision.safetensors",
+    "model.visual.blocks.26.attn.qkv.weight": "model-vision.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc1.bias": "model-vision.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc1.weight": "model-vision.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc2.bias": "model-vision.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc2.weight": "model-vision.safetensors",
+    "model.visual.blocks.26.norm1.bias": "model-vision.safetensors",
+    "model.visual.blocks.26.norm1.weight": "model-vision.safetensors",
+    "model.visual.blocks.26.norm2.bias": "model-vision.safetensors",
+    "model.visual.blocks.26.norm2.weight": "model-vision.safetensors",
+    "model.visual.blocks.3.attn.proj.bias": "model-vision.safetensors",
+    "model.visual.blocks.3.attn.proj.weight": "model-vision.safetensors",
+    "model.visual.blocks.3.attn.qkv.bias": "model-vision.safetensors",
+    "model.visual.blocks.3.attn.qkv.weight": "model-vision.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.bias": "model-vision.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.weight": "model-vision.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.bias": "model-vision.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.weight": "model-vision.safetensors",
+    "model.visual.blocks.3.norm1.bias": "model-vision.safetensors",
+    "model.visual.blocks.3.norm1.weight": "model-vision.safetensors",
+    "model.visual.blocks.3.norm2.bias": "model-vision.safetensors",
+    "model.visual.blocks.3.norm2.weight": "model-vision.safetensors",
+    "model.visual.blocks.4.attn.proj.bias": "model-vision.safetensors",
+    "model.visual.blocks.4.attn.proj.weight": "model-vision.safetensors",
+    "model.visual.blocks.4.attn.qkv.bias": "model-vision.safetensors",
+    "model.visual.blocks.4.attn.qkv.weight": "model-vision.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.bias": "model-vision.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.weight": "model-vision.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.bias": "model-vision.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.weight": "model-vision.safetensors",
+    "model.visual.blocks.4.norm1.bias": "model-vision.safetensors",
+    "model.visual.blocks.4.norm1.weight": "model-vision.safetensors",
+    "model.visual.blocks.4.norm2.bias": "model-vision.safetensors",
+    "model.visual.blocks.4.norm2.weight": "model-vision.safetensors",
+    "model.visual.blocks.5.attn.proj.bias": "model-vision.safetensors",
+    "model.visual.blocks.5.attn.proj.weight": "model-vision.safetensors",
+    "model.visual.blocks.5.attn.qkv.bias": "model-vision.safetensors",
+    "model.visual.blocks.5.attn.qkv.weight": "model-vision.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.bias": "model-vision.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.weight": "model-vision.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.bias": "model-vision.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.weight": "model-vision.safetensors",
+    "model.visual.blocks.5.norm1.bias": "model-vision.safetensors",
+    "model.visual.blocks.5.norm1.weight": "model-vision.safetensors",
+    "model.visual.blocks.5.norm2.bias": "model-vision.safetensors",
+    "model.visual.blocks.5.norm2.weight": "model-vision.safetensors",
+    "model.visual.blocks.6.attn.proj.bias": "model-vision.safetensors",
+    "model.visual.blocks.6.attn.proj.weight": "model-vision.safetensors",
+    "model.visual.blocks.6.attn.qkv.bias": "model-vision.safetensors",
+    "model.visual.blocks.6.attn.qkv.weight": "model-vision.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.bias": "model-vision.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.weight": "model-vision.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.bias": "model-vision.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.weight": "model-vision.safetensors",
+    "model.visual.blocks.6.norm1.bias": "model-vision.safetensors",
+    "model.visual.blocks.6.norm1.weight": "model-vision.safetensors",
+    "model.visual.blocks.6.norm2.bias": "model-vision.safetensors",
+    "model.visual.blocks.6.norm2.weight": "model-vision.safetensors",
+    "model.visual.blocks.7.attn.proj.bias": "model-vision.safetensors",
+    "model.visual.blocks.7.attn.proj.weight": "model-vision.safetensors",
+    "model.visual.blocks.7.attn.qkv.bias": "model-vision.safetensors",
+    "model.visual.blocks.7.attn.qkv.weight": "model-vision.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.bias": "model-vision.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.weight": "model-vision.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.bias": "model-vision.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.weight": "model-vision.safetensors",
+    "model.visual.blocks.7.norm1.bias": "model-vision.safetensors",
+    "model.visual.blocks.7.norm1.weight": "model-vision.safetensors",
+    "model.visual.blocks.7.norm2.bias": "model-vision.safetensors",
+    "model.visual.blocks.7.norm2.weight": "model-vision.safetensors",
+    "model.visual.blocks.8.attn.proj.bias": "model-vision.safetensors",
+    "model.visual.blocks.8.attn.proj.weight": "model-vision.safetensors",
+    "model.visual.blocks.8.attn.qkv.bias": "model-vision.safetensors",
+    "model.visual.blocks.8.attn.qkv.weight": "model-vision.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.bias": "model-vision.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.weight": "model-vision.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.bias": "model-vision.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.weight": "model-vision.safetensors",
+    "model.visual.blocks.8.norm1.bias": "model-vision.safetensors",
+    "model.visual.blocks.8.norm1.weight": "model-vision.safetensors",
+    "model.visual.blocks.8.norm2.bias": "model-vision.safetensors",
+    "model.visual.blocks.8.norm2.weight": "model-vision.safetensors",
+    "model.visual.blocks.9.attn.proj.bias": "model-vision.safetensors",
+    "model.visual.blocks.9.attn.proj.weight": "model-vision.safetensors",
+    "model.visual.blocks.9.attn.qkv.bias": "model-vision.safetensors",
+    "model.visual.blocks.9.attn.qkv.weight": "model-vision.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.bias": "model-vision.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.weight": "model-vision.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.bias": "model-vision.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.weight": "model-vision.safetensors",
+    "model.visual.blocks.9.norm1.bias": "model-vision.safetensors",
+    "model.visual.blocks.9.norm1.weight": "model-vision.safetensors",
+    "model.visual.blocks.9.norm2.bias": "model-vision.safetensors",
+    "model.visual.blocks.9.norm2.weight": "model-vision.safetensors",
+    "model.visual.merger.linear_fc1.bias": "model-vision.safetensors",
+    "model.visual.merger.linear_fc2.bias": "model-vision.safetensors",
+    "model.visual.merger.norm.bias": "model-vision.safetensors",
+    "model.visual.merger.norm.weight": "model-vision.safetensors",
+    "model.visual.patch_embed.proj.bias": "model-vision.safetensors",
+    "model.visual.patch_embed.proj.weight": "model-vision.safetensors",
+    "model.visual.pos_embed.weight": "model-vision.safetensors"
+  }
+}

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"
+}

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 image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n    {%- if content is string %}\n        {{- content }}\n    {%- elif content is iterable and content is not mapping %}\n        {%- for item in content %}\n            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n                {%- if is_system_content %}\n                    {{- raise_exception('System message cannot contain images.') }}\n                {%- endif %}\n                {%- if do_vision_count %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}\n                    {{- 'Picture ' ~ image_count.value ~ ': ' }}\n                {%- endif %}\n                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n            {%- elif 'video' in item or item.type == 'video' %}\n                {%- if is_system_content %}\n                    {{- raise_exception('System message cannot contain videos.') }}\n                {%- endif %}\n                {%- if do_vision_count %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}\n                    {{- 'Video ' ~ video_count.value ~ ': ' }}\n                {%- endif %}\n                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n            {%- elif 'audio' in item or item.type == 'audio' %}\n                {%- if is_system_content %}\n                    {{- raise_exception('System message cannot contain audio.') }}\n                {%- endif %}\n                {{- '<|audio_start|><|audio_pad|><|audio_end|>' }}\n            {%- elif 'text' in item %}\n                {{- item.text }}\n            {%- else %}\n                {{- raise_exception('Unexpected item type in content.') }}\n            {%- endif %}\n        {%- endfor %}\n    {%- elif content is none or content is undefined %}\n        {{- '' }}\n    {%- else %}\n        {{- raise_exception('Unexpected content type.') }}\n    {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n    {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n    {{- '<|im_start|>system\\n' }}\n    {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\" }}\n    {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n<parameter=example_parameter_2>\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\nReminder:\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n</IMPORTANT>' }}\n    {%- if messages[0].role == 'system' %}\n        {%- set content = render_content(messages[0].content, false, true)|trim %}\n        {%- if content %}\n            {{- '\\n\\n' + content }}\n        {%- endif %}\n    {%- endif %}\n    {{- '<|im_end|>\\n' }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {%- set content = render_content(messages[0].content, false, true)|trim %}\n        {{- '<|im_start|>system\\n' + content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" %}\n        {%- set content = render_content(message.content, false)|trim %}\n        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n            {%- set ns.multi_step_tool = false %}\n            {%- set ns.last_query_index = index %}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n    {{- raise_exception('No user query found in messages.') }}\n{%- endif %}\n{%- for message in messages %}\n    {%- set content = render_content(message.content, true)|trim %}\n    {%- if message.role == \"system\" %}\n        {%- if not loop.first %}\n            {{- raise_exception('System message must be at the beginning.') }}\n        {%- endif %}\n    {%- elif message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- set reasoning_content = reasoning_content|trim %}\n        {%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}\n            {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if tool_call.function is defined %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {%- if loop.first %}\n                    {%- if content|trim %}\n                        {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                    {%- else %}\n                        {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                    {%- endif %}\n                {%- else %}\n                    {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                {%- endif %}\n                {%- if tool_call.arguments is defined %}\n                    {%- for args_name, args_value in tool_call.arguments|items %}\n                        {{- '<parameter=' + args_name + '>\\n' }}\n                        {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}\n                        {{- args_value }}\n                        {{- '\\n</parameter>\\n' }}\n                    {%- endfor %}\n                {%- endif %}\n                {{- '</function>\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n            {{- '<|im_end|>\\n' }}\n        {%- elif loop.last %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- else %}\n        {{- raise_exception('Unexpected message role.') }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- else %}\n        {{- '<think>\\n' }}\n    {%- endif %}\n{%- endif %}",
+    "clean_up_tokenization_spaces": false,
+    "eos_token": "<|im_end|>",
+    "errors": "replace",
+    "model_max_length": 131072,
+    "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"
+}