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

BUILD_RECIPE.json

@@ -0,0 +1,102 @@
+{
+  "adapter_id": "qwen35-moe-ornith15-quant-matrix-v1",
+  "architecture_signature": {
+    "full_attention_layers": 10,
+    "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"
+    ],
+    "layers": 40,
+    "linear_attention_layers": 30,
+    "model_type": "qwen3_5_moe",
+    "num_experts": 256,
+    "num_experts_per_tok": 8,
+    "text_model_type": "qwen3_5_moe_text"
+  },
+  "body_bits": 4,
+  "body_group_size": 32,
+  "body_mode": "affine",
+  "expected_float_exclusions": 60,
+  "expected_q4_modules": 372,
+  "expected_q8_modules": 80,
+  "expected_quantizable_modules": 512,
+  "module_overrides": [
+    {
+      "precision": "bf16",
+      "quantize": false,
+      "suffix": "linear_attn.in_proj_a"
+    },
+    {
+      "precision": "bf16",
+      "quantize": false,
+      "suffix": "linear_attn.in_proj_b"
+    },
+    {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine",
+      "suffix": "mlp.gate"
+    },
+    {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine",
+      "suffix": "mlp.shared_expert_gate"
+    }
+  ],
+  "mtp_depth": "runtime-qualified",
+  "mtp_policy": "same-parent-bf16-sidecar",
+  "profile": "control-candidate",
+  "recipe_id": "affine4-router8-bf16-recurrence",
+  "recipe_version": 1,
+  "source_signature": {
+    "indexed_tensors": 1811,
+    "mtp_tensors": 785,
+    "recurrent_a_weights": 30,
+    "recurrent_b_weights": 30,
+    "vision_tensors": 333
+  },
+  "vision_policy": "same-parent-bf16-preserve",
+  "artifact_name": "ornith-1.5-35b-a3b-affine4-router8-bf16recurrence-vision-mtplx",
+  "source_model": "ornith-ai/Ornith-1.5-35B-A3B",
+  "source_revision": "fbb995a79eedd569a5edc5f2af9644c0fa1124fc",
+  "release_repo": "Shiftedx/ornith-1.5-35b-a3b-affine4-router8-bf16recurrence-vision-mtplx"
+}

README.md

@@ -0,0 +1,63 @@
+---
+license: mit
+license_link: https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B/blob/fbb995a79eedd569a5edc5f2af9644c0fa1124fc/LICENSE
+base_model:
+- ornith-ai/Ornith-1.5-35B-A3B
+base_model_relation: quantized
+library_name: mlx
+pipeline_tag: image-text-to-text
+tags:
+- mlx
+- mlx-vlm
+- mtplx
+- qwen3.5
+- moe
+- vision
+- speculative-decoding
+- apple-silicon
+---
+
+# ornith-1.5-35b-a3b-affine4-router8-bf16recurrence-vision-mtplx
+
+Affine 4-bit language body with 8-bit MoE router gates and recurrent-state inputs retained in BF16, plus BF16 vision and native BF16 MTP. Built from [ornith-ai/Ornith-1.5-35B-A3B](https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B) revision [`fbb995a`](https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B/tree/fbb995a79eedd569a5edc5f2af9644c0fa1124fc) for Apple Silicon.
+
+## Format
+
+- Logical size: 24.29 GB
+- Qwen3.5 MoE multimodal: 35B total parameters, 3B active
+- Language body: affine 4-bit/group-32 with 80 MoE router gates at affine 8-bit/group-64; 60 recurrent input modules retained in BF16
+- Vision: 333 same-parent BF16 tensors
+- MTP: 785 same-parent BF16 tensors in `mtp/weights.safetensors`
+- Context metadata: 262,144 tokens
+- Tokenizer, chat template, and image/video processor metadata preserved
+
+The fail-closed precision recipe and conversion assertions are included in `BUILD_RECIPE.json` and `conversion_receipt.json`.
+
+The matched AR/D1/D2/D3 sweep selected **D1** at 118.50 decode tok/s on the qualification host.
+
+## Usage
+
+```bash
+mtplx serve \
+  --model Shiftedx/ornith-1.5-35b-a3b-affine4-router8-bf16recurrence-vision-mtplx \
+  --profile turbo \
+  --generation-mode mtp \
+  --load-mtp \
+  --depth 1
+```
+
+```bash
+python -m mlx_vlm.generate \
+  --model Shiftedx/ornith-1.5-35b-a3b-affine4-router8-bf16recurrence-vision-mtplx \
+  --image image.jpg \
+  --prompt "Describe this image." \
+  --max-tokens 256
+```
+
+## Qualification and limitations
+
+- Structural loading, deterministic text, vision, and MTPLX tensor gates passed locally.
+- This control quant is experimental; behavior may differ from the BF16 parent and the higher-precision hybrid.
+- Full BF16 parent parity was not run on the 64 GiB qualification host.
+- Post-publication Shiftedx Bench results will be attached to the immutable evaluated weight revision.
+- Review the [upstream model card](https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B) for intended use, training details, license, and safety considerations.

RELEASE_MANIFEST.json

@@ -0,0 +1,192 @@
+{
+  "artifact_name": "ornith-1.5-35b-a3b-affine4-router8-bf16recurrence-vision-mtplx",
+  "repo_id": "Shiftedx/ornith-1.5-35b-a3b-affine4-router8-bf16recurrence-vision-mtplx",
+  "source_model": "ornith-ai/Ornith-1.5-35B-A3B",
+  "source_revision": "fbb995a79eedd569a5edc5f2af9644c0fa1124fc",
+  "recipe": "Affine 4-bit + router 8-bit + BF16 recurrence control",
+  "qualification": "locally-qualified-experimental",
+  "structure": {
+    "quantized_modules": 452,
+    "affine8_modules": 80,
+    "affine4_modules": 372,
+    "bf16_recurrent_inputs": 60,
+    "vision_tensors": 333,
+    "mtp_tensors": 785,
+    "indexed_shards": 17
+  },
+  "staged_at": "2026-08-19T19:39:53+00:00",
+  "file_count": 34,
+  "total_bytes": 24285012018,
+  "files": [
+    {
+      "path": "BUILD_RECIPE.json",
+      "size": 2716,
+      "sha256": "7fac1b87818cda5dc3e399b46f3bc1f1b089c65ea2628c06434ecc64ed610f8e"
+    },
+    {
+      "path": "README.md",
+      "size": 2432,
+      "sha256": "7d40810e2f9c588a9606c4a5388d35a58fe08cf7b14177db5eae4bd9edeb6f2c"
+    },
+    {
+      "path": "chat_template.jinja",
+      "size": 7536,
+      "sha256": "182e77dd83bd8e9ca818b240b82e28f243762cd5dda32e6eef327df7b1cd107e"
+    },
+    {
+      "path": "config.json",
+      "size": 24863,
+      "sha256": "9068fb8e783b971df25bba6e372379f7b0a65f275c0dc5d0d5c54bd04c60d782"
+    },
+    {
+      "path": "configuration.json",
+      "size": 58,
+      "sha256": "c1b09db419119513247e9b8b912c4b9897106c9b20c6cada7e107d993c5435eb"
+    },
+    {
+      "path": "conversion_receipt.json",
+      "size": 2864,
+      "sha256": "c3fd7724c0e85aa48dd3e77bbb546ab5a7b815499ba6e737b8ae2ced483b4669"
+    },
+    {
+      "path": "generation_config.json",
+      "size": 202,
+      "sha256": "e70c136c1b78ddc1fb0905bac8e733a4dc448d4f852a5dd75143fffc70be550e"
+    },
+    {
+      "path": "merges.txt",
+      "size": 3353259,
+      "sha256": "a9d356d7bdf1ef4949e3e748e95b8e10ad9d4e2e838eddc38a0a7b6b94d1db8d"
+    },
+    {
+      "path": "model-00001-of-00016.safetensors",
+      "size": 1204383247,
+      "sha256": "9972f4d4b3af487ce73524077e20b0c42fb5583eb580fb58ae217e4ed4d0e7c2"
+    },
+    {
+      "path": "model-00002-of-00016.safetensors",
+      "size": 1241660582,
+      "sha256": "0dc685ed5e81521ea572fff851b5c740f7c4929050efb3a30448fa211c0d1a48"
+    },
+    {
+      "path": "model-00003-of-00016.safetensors",
+      "size": 1557632078,
+      "sha256": "efafa965f93e5600f908b3c0758f5df74643f634372bc130f104aac1998c35b4"
+    },
+    {
+      "path": "model-00004-of-00016.safetensors",
+      "size": 1409428926,
+      "sha256": "0de9b36da58514a63e17cf0586875373f2de4477e1636b3831486f538c3ab1d9"
+    },
+    {
+      "path": "model-00005-of-00016.safetensors",
+      "size": 1241660684,
+      "sha256": "83a7d46f34709417c3c983cd009dfd04c3e62d48f94935091030828a3a490f31"
+    },
+    {
+      "path": "model-00006-of-00016.safetensors",
+      "size": 1557632128,
+      "sha256": "0cfb554dc2e8adef4ba75291fd19c3ea4d361bbb5532399acd8390f889905340"
+    },
+    {
+      "path": "model-00007-of-00016.safetensors",
+      "size": 1409429086,
+      "sha256": "0b2579f6eadb4454df2a114f1879a69bed3805dd5276b5b72732fd96647a75f4"
+    },
+    {
+      "path": "model-00008-of-00016.safetensors",
+      "size": 1241660794,
+      "sha256": "40e1fe64a7765565ec3b95e43d9f73fb4afea163b878445505b762fc6cf187fb"
+    },
+    {
+      "path": "model-00009-of-00016.safetensors",
+      "size": 1557632192,
+      "sha256": "240ab5195cf227f0698431cba0cb48cf9a8dd6a6256be56caa3887c0b91907e4"
+    },
+    {
+      "path": "model-00010-of-00016.safetensors",
+      "size": 1409428994,
+      "sha256": "b857d803e9feb576bb636548bbf633887c910521bb06d5d1361b8df9b3df9a8b"
+    },
+    {
+      "path": "model-00011-of-00016.safetensors",
+      "size": 1241660694,
+      "sha256": "c48512b3df7a9cbbf0a513485692ccbda9607222ef4c08ac3ba813dff4f2f226"
+    },
+    {
+      "path": "model-00012-of-00016.safetensors",
+      "size": 1557632126,
+      "sha256": "13c7856bdd76b220e219523d83f12cdcb4db1620c27d0d146e99fb2ee62a444a"
+    },
+    {
+      "path": "model-00013-of-00016.safetensors",
+      "size": 1409429118,
+      "sha256": "c32facde86e275a624dcec1e26bb98143d81378673add5435ce6ea0597ce322d"
+    },
+    {
+      "path": "model-00014-of-00016.safetensors",
+      "size": 1241660734,
+      "sha256": "492d46520ccb004a7e77e9fb49072a625aeca775f97c1af131bcdd13ccf5cb61"
+    },
+    {
+      "path": "model-00015-of-00016.safetensors",
+      "size": 1557632166,
+      "sha256": "52cd8aeddbca3c25ff0511495ee46e151ad787c427ef4735b8336cab02b0b00a"
+    },
+    {
+      "path": "model-00016-of-00016.safetensors",
+      "size": 840749811,
+      "sha256": "ddbda98a53ec88f9ae3da2d1141edd0dcda4a237130b15e86625f5d25e2be0f5"
+    },
+    {
+      "path": "model-vision-00001-of-00001.safetensors",
+      "size": 893179493,
+      "sha256": "ce387e11510de90772c482840c6d2bb8df1fe0f2d280b02cfea8484d04007f6b"
+    },
+    {
+      "path": "model.safetensors.index.json",
+      "size": 197539,
+      "sha256": "f02ea76b6d5e2c53d78bc0371b4ec8b4ae1db08481938ed1496e45ec05ba87c0"
+    },
+    {
+      "path": "mtp/weights.safetensors",
+      "size": 1689375998,
+      "sha256": "33a4a0693757980c1c18cbbeba4d5f68922e084727d6e21dec33593b99f8733c"
+    },
+    {
+      "path": "mtplx_runtime.json",
+      "size": 2273,
+      "sha256": "d39694d5bc3c8cf5427dd2e5107a021f0fb959240f132603e4231a6d7602dc3d"
+    },
+    {
+      "path": "preprocessor_config.json",
+      "size": 390,
+      "sha256": "27225450ac9c6529872ee1924fcb0962ff5634834f817040f444118116f4e516"
+    },
+    {
+      "path": "processor_config.json",
+      "size": 1191,
+      "sha256": "d89ef49ce9cd37fbf510158e13c1ef063d9286411c1ec9049932dbe0487143b1"
+    },
+    {
+      "path": "tokenizer.json",
+      "size": 12807982,
+      "sha256": "5f9e4d4901a92b997e463c1f46055088b6cca5ca61a6522d1b9f64c4bb81cb42"
+    },
+    {
+      "path": "tokenizer_config.json",
+      "size": 16718,
+      "sha256": "5186f0defcd7f232382c7f0aebcd2252d073bb921ab240e407b7ae8745d2b29b"
+    },
+    {
+      "path": "video_preprocessor_config.json",
+      "size": 385,
+      "sha256": "7768af27c1fafa9cc9011c1dc20067e03f8915e03b63504550e11d5066986d13"
+    },
+    {
+      "path": "vocab.json",
+      "size": 6722759,
+      "sha256": "ce99b4cb2983d118806ce0a8b777a35b093e2000a503ebde25853284c9dfa003"
+    }
+  ]
+}

SHA256SUMS

@@ -0,0 +1,34 @@
+7fac1b87818cda5dc3e399b46f3bc1f1b089c65ea2628c06434ecc64ed610f8e  BUILD_RECIPE.json
+7d40810e2f9c588a9606c4a5388d35a58fe08cf7b14177db5eae4bd9edeb6f2c  README.md
+182e77dd83bd8e9ca818b240b82e28f243762cd5dda32e6eef327df7b1cd107e  chat_template.jinja
+9068fb8e783b971df25bba6e372379f7b0a65f275c0dc5d0d5c54bd04c60d782  config.json
+c1b09db419119513247e9b8b912c4b9897106c9b20c6cada7e107d993c5435eb  configuration.json
+c3fd7724c0e85aa48dd3e77bbb546ab5a7b815499ba6e737b8ae2ced483b4669  conversion_receipt.json
+e70c136c1b78ddc1fb0905bac8e733a4dc448d4f852a5dd75143fffc70be550e  generation_config.json
+a9d356d7bdf1ef4949e3e748e95b8e10ad9d4e2e838eddc38a0a7b6b94d1db8d  merges.txt
+9972f4d4b3af487ce73524077e20b0c42fb5583eb580fb58ae217e4ed4d0e7c2  model-00001-of-00016.safetensors
+0dc685ed5e81521ea572fff851b5c740f7c4929050efb3a30448fa211c0d1a48  model-00002-of-00016.safetensors
+efafa965f93e5600f908b3c0758f5df74643f634372bc130f104aac1998c35b4  model-00003-of-00016.safetensors
+0de9b36da58514a63e17cf0586875373f2de4477e1636b3831486f538c3ab1d9  model-00004-of-00016.safetensors
+83a7d46f34709417c3c983cd009dfd04c3e62d48f94935091030828a3a490f31  model-00005-of-00016.safetensors
+0cfb554dc2e8adef4ba75291fd19c3ea4d361bbb5532399acd8390f889905340  model-00006-of-00016.safetensors
+0b2579f6eadb4454df2a114f1879a69bed3805dd5276b5b72732fd96647a75f4  model-00007-of-00016.safetensors
+40e1fe64a7765565ec3b95e43d9f73fb4afea163b878445505b762fc6cf187fb  model-00008-of-00016.safetensors
+240ab5195cf227f0698431cba0cb48cf9a8dd6a6256be56caa3887c0b91907e4  model-00009-of-00016.safetensors
+b857d803e9feb576bb636548bbf633887c910521bb06d5d1361b8df9b3df9a8b  model-00010-of-00016.safetensors
+c48512b3df7a9cbbf0a513485692ccbda9607222ef4c08ac3ba813dff4f2f226  model-00011-of-00016.safetensors
+13c7856bdd76b220e219523d83f12cdcb4db1620c27d0d146e99fb2ee62a444a  model-00012-of-00016.safetensors
+c32facde86e275a624dcec1e26bb98143d81378673add5435ce6ea0597ce322d  model-00013-of-00016.safetensors
+492d46520ccb004a7e77e9fb49072a625aeca775f97c1af131bcdd13ccf5cb61  model-00014-of-00016.safetensors
+52cd8aeddbca3c25ff0511495ee46e151ad787c427ef4735b8336cab02b0b00a  model-00015-of-00016.safetensors
+ddbda98a53ec88f9ae3da2d1141edd0dcda4a237130b15e86625f5d25e2be0f5  model-00016-of-00016.safetensors
+ce387e11510de90772c482840c6d2bb8df1fe0f2d280b02cfea8484d04007f6b  model-vision-00001-of-00001.safetensors
+f02ea76b6d5e2c53d78bc0371b4ec8b4ae1db08481938ed1496e45ec05ba87c0  model.safetensors.index.json
+33a4a0693757980c1c18cbbeba4d5f68922e084727d6e21dec33593b99f8733c  mtp/weights.safetensors
+d39694d5bc3c8cf5427dd2e5107a021f0fb959240f132603e4231a6d7602dc3d  mtplx_runtime.json
+27225450ac9c6529872ee1924fcb0962ff5634834f817040f444118116f4e516  preprocessor_config.json
+d89ef49ce9cd37fbf510158e13c1ef063d9286411c1ec9049932dbe0487143b1  processor_config.json
+5f9e4d4901a92b997e463c1f46055088b6cca5ca61a6522d1b9f64c4bb81cb42  tokenizer.json
+5186f0defcd7f232382c7f0aebcd2252d073bb921ab240e407b7ae8745d2b29b  tokenizer_config.json
+7768af27c1fafa9cc9011c1dc20067e03f8915e03b63504550e11d5066986d13  video_preprocessor_config.json
+ce99b4cb2983d118806ce0a8b777a35b093e2000a503ebde25853284c9dfa003  vocab.json

chat_template.jinja

@@ -0,0 +1,150 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- 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 %}
+        {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- 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 +1,959 @@
+{
+  "architectures": [
+    "Qwen3_5MoeForConditionalGeneration"
+  ],
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 248046,
+  "hidden_size": 2048,
+  "image_token_id": 248056,
+  "model_type": "qwen3_5_moe",
+  "pad_token_id": 248044,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_output_gate": true,
+    "bos_token_id": 248044,
+    "dtype": "bfloat16",
+    "eos_token_id": 248044,
+    "full_attention_interval": 4,
+    "head_dim": 256,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "initializer_range": 0.02,
+    "layer_types": [
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention"
+    ],
+    "linear_conv_kernel_dim": 4,
+    "linear_key_head_dim": 128,
+    "linear_num_key_heads": 16,
+    "linear_num_value_heads": 32,
+    "linear_value_head_dim": 128,
+    "mamba_ssm_dtype": "float32",
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_5_moe_text",
+    "moe_intermediate_size": 512,
+    "mtp_num_hidden_layers": 1,
+    "mtp_use_dedicated_embeddings": false,
+    "num_attention_heads": 16,
+    "num_experts": 256,
+    "num_experts_per_tok": 8,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 2,
+    "output_router_logits": false,
+    "pad_token_id": 248044,
+    "partial_rotary_factor": 0.25,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        11,
+        11,
+        10
+      ],
+      "partial_rotary_factor": 0.25,
+      "rope_theta": 10000000,
+      "type": "default"
+    },
+    "router_aux_loss_coef": 0.0,
+    "shared_expert_intermediate_size": 512,
+    "tie_word_embeddings": false,
+    "use_cache": false,
+    "vocab_size": 248320,
+    "num_nextn_predict_layers": 1
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.8.1",
+  "video_token_id": 248057,
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053,
+  "publisher": "ornith-ai",
+  "mtp_num_hidden_layers": 1,
+  "num_nextn_predict_layers": 1,
+  "quantization": {
+    "group_size": 32,
+    "bits": 4,
+    "mode": "affine",
+    "language_model.model.layers.0.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.0.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.1.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.1.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.2.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.2.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.3.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.3.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.4.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.4.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.5.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.5.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.6.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.6.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.7.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.7.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.8.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.8.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.9.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.9.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.10.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.10.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.11.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.11.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.12.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.12.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.13.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.13.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.14.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.14.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.15.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.15.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.16.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.16.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.17.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.17.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.18.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.18.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.19.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.19.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.20.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.20.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.21.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.21.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.22.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.22.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.23.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.23.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.24.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.24.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.25.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.25.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.26.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.26.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.27.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.27.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.28.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.28.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.29.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.29.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.30.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.30.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.31.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.31.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.32.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.32.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.33.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.33.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.34.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.34.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.35.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.35.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.36.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.36.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.37.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.37.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.38.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.38.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.39.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.39.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    }
+  },
+  "quantization_config": {
+    "group_size": 32,
+    "bits": 4,
+    "mode": "affine",
+    "language_model.model.layers.0.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.0.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.1.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.1.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.2.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.2.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.3.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.3.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.4.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.4.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.5.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.5.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.6.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.6.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.7.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.7.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.8.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.8.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.9.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.9.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.10.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.10.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.11.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.11.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.12.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.12.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.13.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.13.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.14.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.14.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.15.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.15.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.16.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.16.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.17.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.17.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.18.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.18.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.19.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.19.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.20.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.20.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.21.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.21.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.22.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.22.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.23.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.23.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.24.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.24.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.25.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.25.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.26.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.26.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.27.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.27.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.28.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.28.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.29.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.29.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.30.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.30.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.31.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.31.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.32.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.32.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.33.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.33.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.34.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.34.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.35.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.35.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.36.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.36.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.37.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.37.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.38.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.38.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.39.mlp.gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.39.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    }
+  },
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 27,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_5_moe_vision",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2048,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "mlx_lm_extra_tensors": {
+    "mtp_file": "mtp/weights.safetensors",
+    "mtp_tensor_count": 785
+  },
+  "mtplx_wrapper": {
+    "artifact_name": "ornith-1.5-35b-a3b-affine4-router8-bf16recurrence-vision-mtplx",
+    "source_model": "ornith-ai/Ornith-1.5-35B-A3B",
+    "source_revision": "fbb995a79eedd569a5edc5f2af9644c0fa1124fc",
+    "body_source": "Shiftedx/ornith-1.5-35b-a3b-affine4-router8-bf16recurrence-vision-mtplx",
+    "mtp_source": "ornith-ai/Ornith-1.5-35B-A3B@fbb995a79eedd569a5edc5f2af9644c0fa1124fc",
+    "body_quantization": "affine4-router8-bf16-recurrence",
+    "runtime": "mtplx",
+    "mtplx_version": "2.7.1",
+    "native_mtp": true,
+    "validation_status": "locally-qualified-experimental"
+  },
+  "source_model": "ornith-ai/Ornith-1.5-35B-A3B",
+  "source_revision": "fbb995a79eedd569a5edc5f2af9644c0fa1124fc",
+  "release_repo": "Shiftedx/ornith-1.5-35b-a3b-affine4-router8-bf16recurrence-vision-mtplx",
+  "release_variant": "affine4-router8-bf16-recurrence-vision-mtplx"
+}

configuration.json

@@ -0,0 +1 @@
+{"framework":"Pytorch","task":"visual-question-answering"}

conversion_receipt.json

@@ -0,0 +1,96 @@
+{
+  "status": "pass",
+  "adapter_id": "qwen35-moe-ornith15-quant-matrix-v1",
+  "recipe_id": "affine4-router8-bf16-recurrence",
+  "source": "ornith-ai/Ornith-1.5-35B-A3B@fbb995a79eedd569a5edc5f2af9644c0fa1124fc",
+  "output": "Shiftedx/ornith-1.5-35b-a3b-affine4-router8-bf16recurrence-vision-mtplx",
+  "validated_source": {
+    "architecture": {
+      "model_type": "qwen3_5_moe",
+      "text_model_type": "qwen3_5_moe_text",
+      "layers": 40,
+      "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_attention_layers": 30,
+      "full_attention_layers": 10
+    },
+    "source": {
+      "indexed_tensors": 1811,
+      "vision_tensors": 333,
+      "mtp_tensors": 785,
+      "recurrent_a_weights": 30,
+      "recurrent_b_weights": 30
+    }
+  },
+  "expected": {
+    "quantized_modules": 452,
+    "float_exclusions": 60,
+    "q8_modules": 80,
+    "q4_modules": 372
+  },
+  "observed": {
+    "quantized_modules": 452,
+    "float_exclusions": 60,
+    "q8_modules": 80,
+    "q4_modules": 372,
+    "packed_precision_counts": {
+      "4": 372,
+      "8": 80
+    },
+    "packed_layout_mismatches": [],
+    "float_exclusions_with_scales": 0,
+    "float_exclusion_dtypes": {
+      "BF16": 60
+    },
+    "vision_tensors_in_text_body": 0,
+    "mtp_tensors_in_text_body": 0
+  },
+  "hashes": {
+    "source_config_sha256": "af198ccbe6c17dd973da98bbf6c92ce1c3ec7261c2e2fbc4c4f5150018418ea8",
+    "source_index_sha256": "0ad9fbfbb1a7514773ed881d3c9403019bd7ae9ff4c6af3cfc65ca7da784d78f",
+    "source_chat_template_sha256": "182e77dd83bd8e9ca818b240b82e28f243762cd5dda32e6eef327df7b1cd107e",
+    "recipe_sha256": "4052d1a3790e00026ef3ae4abd0edb642d2cc70e4b048b0fa93b40ff559777b1",
+    "converter_sha256": "3ec4d2c198ea22a7fcbb25569a3c6fe5e2bae03cda8d4e7ebf8db0a70dc5c145"
+  },
+  "failures": []
+}

generation_config.json

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

model-00001-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9972f4d4b3af487ce73524077e20b0c42fb5583eb580fb58ae217e4ed4d0e7c2
+size 1204383247

model-00002-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dc685ed5e81521ea572fff851b5c740f7c4929050efb3a30448fa211c0d1a48
+size 1241660582

model-00003-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efafa965f93e5600f908b3c0758f5df74643f634372bc130f104aac1998c35b4
+size 1557632078

model-00004-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0de9b36da58514a63e17cf0586875373f2de4477e1636b3831486f538c3ab1d9
+size 1409428926

model-00005-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83a7d46f34709417c3c983cd009dfd04c3e62d48f94935091030828a3a490f31
+size 1241660684

model-00006-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cfb554dc2e8adef4ba75291fd19c3ea4d361bbb5532399acd8390f889905340
+size 1557632128

model-00007-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b2579f6eadb4454df2a114f1879a69bed3805dd5276b5b72732fd96647a75f4
+size 1409429086

model-00008-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40e1fe64a7765565ec3b95e43d9f73fb4afea163b878445505b762fc6cf187fb
+size 1241660794

model-00009-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:240ab5195cf227f0698431cba0cb48cf9a8dd6a6256be56caa3887c0b91907e4
+size 1557632192

model-00010-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b857d803e9feb576bb636548bbf633887c910521bb06d5d1361b8df9b3df9a8b
+size 1409428994

model-00011-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c48512b3df7a9cbbf0a513485692ccbda9607222ef4c08ac3ba813dff4f2f226
+size 1241660694

model-00012-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13c7856bdd76b220e219523d83f12cdcb4db1620c27d0d146e99fb2ee62a444a
+size 1557632126

model-00013-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c32facde86e275a624dcec1e26bb98143d81378673add5435ce6ea0597ce322d
+size 1409429118

model-00014-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:492d46520ccb004a7e77e9fb49072a625aeca775f97c1af131bcdd13ccf5cb61
+size 1241660734

model-00015-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52cd8aeddbca3c25ff0511495ee46e151ad787c427ef4735b8336cab02b0b00a
+size 1557632166

model-00016-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddbda98a53ec88f9ae3da2d1141edd0dcda4a237130b15e86625f5d25e2be0f5
+size 840749811

model-vision-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce387e11510de90772c482840c6d2bb8df1fe0f2d280b02cfea8484d04007f6b
+size 893179493

mtp/weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33a4a0693757980c1c18cbbeba4d5f68922e084727d6e21dec33593b99f8733c
+size 1689375998

mtplx_runtime.json

@@ -0,0 +1,55 @@
+{
+  "artifact_name": "ornith-1.5-35b-a3b-affine4-router8-bf16recurrence-vision-mtplx",
+  "model_id": "ornith-1.5-35b-a3b-affine4-router8-bf16recurrence-vision-mtplx",
+  "arch_id": "qwen3-next-mtp",
+  "mtplx_version": "2.7.1",
+  "base_model": "ornith-ai/Ornith-1.5-35B-A3B",
+  "base_revision": "fbb995a79eedd569a5edc5f2af9644c0fa1124fc",
+  "body_source": "Shiftedx/ornith-1.5-35b-a3b-affine4-router8-bf16recurrence-vision-mtplx",
+  "mtp_source": "ornith-ai/Ornith-1.5-35B-A3B@fbb995a79eedd569a5edc5f2af9644c0fa1124fc",
+  "body_quantization": "affine4-router8-bf16-recurrence",
+  "mtp_sidecar_file": "mtp/weights.safetensors",
+  "mtp_tensor_count": 785,
+  "mtp_sidecar_format": "bf16",
+  "mtp_depth_max": 3,
+  "mtp_depth_recommended": 1,
+  "recommended_profile": "sustained",
+  "recommended_settings": {
+    "generation_mode": "mtp",
+    "depth": 1,
+    "reasoning_mode": "off",
+    "enable_thinking": false,
+    "temperature": 0.6,
+    "top_p": 0.95,
+    "top_k": 20
+  },
+  "mtp_contract": {
+    "base_hidden_variant": "post_norm",
+    "hidden_variant": "post_norm",
+    "concat_order": "embedding_hidden",
+    "mtp_position_mode": "cache",
+    "mtp_prequantized": false,
+    "mtp_sidecar_format": "bf16",
+    "mtp_source": "native-embedded-bf16"
+  },
+  "exactness_baseline": {
+    "status": "pending-local-validation",
+    "source": "native BF16 MTP tensors extracted from the pinned source model",
+    "suite": "pending mtplx inspect/tune plus text and vision smokes",
+    "sampler": "temperature=0.6, top_p=0.95, top_k=20, thinking=false",
+    "depth": 1,
+    "body_quantization_current": "affine4-router8-bf16-recurrence",
+    "body_quantization_validated": "pending",
+    "public_release_blocker": true,
+    "transfer_note": "The body is a local quantized/abliterated MLX artifact and the MTP sidecar is the model's native embedded BF16 MTP block. Keep local until MTPLX tune and API smoke validation update this block."
+  },
+  "validation_status": "locally-qualified-experimental",
+  "verified_on": {
+    "system": "Darwin",
+    "machine": "arm64",
+    "host_class": "Apple M4 Max, 64 GiB unified memory",
+    "model": "ornith-1.5-35b-a3b-affine4-router8-bf16recurrence-vision-mtplx",
+    "mtplx_version": "2.7.1",
+    "status": "locally-qualified-experimental"
+  }
+}

preprocessor_config.json

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

processor_config.json

@@ -0,0 +1,60 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f9e4d4901a92b997e463c1f46055088b6cca5ca61a6522d1b9f64c4bb81cb42
+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 '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": 262144,
+    "pad_token": "<|endoftext|>",
+    "split_special_tokens": false,
+    "tokenizer_class": "Qwen2Tokenizer",
+    "unk_token": null,
+    "add_bos_token": false,
+    "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+    "extra_special_tokens": {
+        "audio_bos_token": "<|audio_start|>",
+        "audio_eos_token": "<|audio_end|>",
+        "audio_token": "<|audio_pad|>",
+        "image_token": "<|image_pad|>",
+        "video_token": "<|video_pad|>",
+        "vision_bos_token": "<|vision_start|>",
+        "vision_eos_token": "<|vision_end|>"
+    }
+}

video_preprocessor_config.json

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