Duplicate from PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-MLX-4bit

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

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,129 @@
+---
+library_name: mlx
+license: mit
+base_model: ornith-ai/Ornith-1.5-35B-A3B
+pipeline_tag: image-text-to-text
+tags:
+- mlx
+- mlx-vlm
+- ornith
+- qwen3.5-moe
+- multimodal
+- abliterated
+- 4-bit
+---
+
+# Ornith 1.5 35B-A3B Abliterated MLX — 4-bit compact
+
+An unofficial experimental MLX derivative of
+[`ornith-ai/Ornith-1.5-35B-A3B`](https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B), pinned to
+revision `e4dfb35a93d4b6822a811a7676f3488514abe7e2`. The original model is by Ornith AI; the MLX
+conversion, refusal-direction experiment, and validation were performed by
+PocketAI Model Lab. `PocketAiHub` identifies the publisher of this derivative.
+
+
+
+## Important safety notice
+
+This checkpoint was deliberately modified to suppress learned refusal behavior.
+It may produce harmful, illegal, offensive, deceptive, or dangerously incorrect
+content more readily than the upstream instruction model. Abliteration is not
+truthfulness training, a capability improvement, or a guarantee of universal
+compliance. Independently evaluate and constrain outputs for your use case.
+
+## Format
+
+- MLX affine 4-bit/group 64; router and shared-expert gates 8-bit
+- Stored model payload: 20,429,166,953 bytes (19.03 GiB)
+- Vision tower retained; the 4-bit build passed a basic image-input smoke test
+- Native MTP speculative-decoding head is not included because `mlx-vlm==0.6.8`
+  drops `mtp.*` tensors during conversion
+- Validated with `mlx==0.32.0` and `mlx-vlm==0.6.8`
+
+Other releases:
+
+- [BF16 reference](https://huggingface.co/PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-MLX-BF16)
+- [8-bit recommended](https://huggingface.co/PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-MLX-8bit)
+- [4-bit compact](https://huggingface.co/PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-MLX-4bit)
+
+## Abliteration recipe
+
+A projected harmful-minus-harmless direction was measured from 256
+length-matched prompts per class at the assistant-generation boundary.
+
+- Direction source layer: 27
+- Destination layers: 15–39
+- Scale: 1.0
+- Per-input-column norm preservation: enabled
+- Modified physical tensors: 75
+- Modified logical expert/projection paths: 6,450
+- Direction SHA-256: `b4bef4649c209aae888c7b313feb89005f897938c0a01540a6852f0e3bf4b407`
+
+See [`abliteration-manifest.json`](./abliteration-manifest.json) for the
+machine-readable recipe.
+
+## Behavioral screen
+
+The regular BF16 parent produced explicit-refusal phrases on 12/12 harmful gate
+prompts. The selected abliterated BF16 candidate produced 0/12 on the same gate
+and retained 12/12 deterministic capability checks.
+
+| Batch-1 screen | Explicit-refusal phrase flags | Final-answer text present |
+| --- | ---: | ---: |
+| Harmful prompts | 0/100 | 100/100 |
+| Benign controls | 0/100 | 100/100 |
+
+The scorer is phrase based. The 128-token ceiling makes this an early-refusal
+screen rather than a complete answer-quality evaluation, and manual inspection
+found semantic refusals that it did not flag. “Abliterated” describes the
+weight-editing method; it does not mean “fully uncensored.”
+
+## Matched-teacher drift
+
+The drift suite used 36 prompts—12 capability, 12 harmful, and 12 benign—with
+481 shared teacher positions and exact KL over all 248,320 logits. It also
+captured all 40 residual layers, K/V state for 10 full-attention layers, and
+convolution/recurrent state for 30 linear-attention layers.
+
+| Pure BF16 ablation split | Mean forward KL | Top-1 agreement | Residual cosine |
+| --- | ---: | ---: | ---: |
+| Capability | 0.018342 | 97.94% | 0.995895 |
+| Benign | 0.307388 | 85.42% | 0.969620 |
+| Harmful | 1.049146 | 60.94% | 0.890754 |
+
+Across all 481 positions, the pure BF16 ablation measured mean KL
+`0.545185`, top-1 agreement
+`78.17%`, and residual cosine
+`0.952090` versus regular BF16.
+
+Against the abliterated BF16 master, this quantization measured mean KL `0.143691`, top-1 agreement `87.32%`, and residual cosine `0.958471`.
+
+The total 4-bit compact path versus regular BF16 measured mean KL
+`0.664004`, top-1 agreement
+`75.26%`, and residual cosine
+`0.920719`.
+
+Machine-readable behavioral, residual, and cache metrics are in
+[`validation-summary.json`](./validation-summary.json).
+
+## Load with MLX-VLM
+
+```bash
+python -m pip install "mlx==0.32.0" "mlx-vlm==0.6.8"
+mlx_vlm.generate --model PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-MLX-4bit --prompt "Explain why seasons occur." --max-tokens 256
+```
+
+For an image prompt:
+
+```bash
+mlx_vlm.generate --model PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-MLX-4bit --prompt "Describe this image." --image photo.jpg --max-tokens 256
+```
+
+The vision tower is present in every release, but only the 4-bit model received
+an end-to-end image smoke test. Broader vision, video, coding, tool-use, and
+long-context evaluations remain future work.
+
+## License and attribution
+
+The upstream model card declares MIT. This derivative preserves the upstream
+attribution and links to the exact pinned source revision above.

abliteration-manifest.json

@@ -0,0 +1,72 @@
+{
+  "schema_version": 1,
+  "method": "refusal-direction orthogonal weight projection",
+  "base_model": "ornith-ai/Ornith-1.5-35B-A3B",
+  "base_revision": "e4dfb35a93d4b6822a811a7676f3488514abe7e2",
+  "direction": {
+    "examples_per_class": 256,
+    "kind": "projected_unit_directions",
+    "sha256": "b4bef4649c209aae888c7b313feb89005f897938c0a01540a6852f0e3bf4b407",
+    "source_layer": 27,
+    "hidden_state": "residual_post at the assistant-generation boundary"
+  },
+  "projection": {
+    "destination_layers": [
+      15,
+      16,
+      17,
+      18,
+      19,
+      20,
+      21,
+      22,
+      23,
+      24,
+      25,
+      26,
+      27,
+      28,
+      29,
+      30,
+      31,
+      32,
+      33,
+      34,
+      35,
+      36,
+      37,
+      38,
+      39
+    ],
+    "target_kinds": [
+      "expert_down",
+      "full_attention_out",
+      "linear_attention_out",
+      "shared_expert_down"
+    ],
+    "scale": 1.0,
+    "norm_preserve": true,
+    "modified_physical_tensors": 75,
+    "modified_logical_paths": 6450,
+    "modified_by_kind": {
+      "expert_down": 25,
+      "full_attention_out": 7,
+      "linear_attention_out": 18,
+      "shared_expert_down": 25
+    },
+    "modified_logical_by_kind": {
+      "expert_down": 6400,
+      "full_attention_out": 7,
+      "linear_attention_out": 18,
+      "shared_expert_down": 25
+    }
+  },
+  "architecture": {
+    "modelType": "qwen3_5_moe",
+    "modelName": "Ornith-1.5-35B-A3B",
+    "hiddenSize": 2048,
+    "numHiddenLayers": 40,
+    "numExperts": 256,
+    "fullAttentionInterval": 4
+  }
+}

artifact-manifest.json

@@ -0,0 +1,102 @@
+{
+  "schema_version": 1,
+  "generated_at": "2026-08-21T04:03:46.399974+00:00",
+  "repository": "PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-MLX-4bit",
+  "base_model": "ornith-ai/Ornith-1.5-35B-A3B",
+  "base_revision": "e4dfb35a93d4b6822a811a7676f3488514abe7e2",
+  "variant": "4bit",
+  "model_payload_bytes": 20429166953,
+  "files": [
+    {
+      "path": "README.md",
+      "size_bytes": 4918,
+      "sha256": "fc3cc1cab7c09e6d3918400f071db6f85665722961f499fda64d52a490bda896"
+    },
+    {
+      "path": "abliteration-manifest.json",
+      "size_bytes": 1550,
+      "sha256": "82d49e30e1d0eca38c23e3b748f6e923562ee3ee7803ecfa5b07558c88caf224"
+    },
+    {
+      "path": "chat_template.jinja",
+      "size_bytes": 7536,
+      "sha256": "182e77dd83bd8e9ca818b240b82e28f243762cd5dda32e6eef327df7b1cd107e"
+    },
+    {
+      "path": "config.json",
+      "size_bytes": 24086,
+      "sha256": "a31b9165854d78fda080b4115d584af9924571458c8f89110f70fbf40cf1878f"
+    },
+    {
+      "path": "configuration.json",
+      "size_bytes": 58,
+      "sha256": "c1b09db419119513247e9b8b912c4b9897106c9b20c6cada7e107d993c5435eb"
+    },
+    {
+      "path": "generation_config.json",
+      "size_bytes": 202,
+      "sha256": "e70c136c1b78ddc1fb0905bac8e733a4dc448d4f852a5dd75143fffc70be550e"
+    },
+    {
+      "path": "model-00001-of-00004.safetensors",
+      "size_bytes": 5288196062,
+      "sha256": "ad2a4e532a2d4785f3f31c594ff39c99200a230a2889b20998d45c10ae66d169"
+    },
+    {
+      "path": "model-00002-of-00004.safetensors",
+      "size_bytes": 5368472657,
+      "sha256": "cea3387a2e2863c6d9444a14b7ab6d89f321edcf63f02e699de6dde4e866e160"
+    },
+    {
+      "path": "model-00003-of-00004.safetensors",
+      "size_bytes": 5368324255,
+      "sha256": "85a877f211adad37e9db68bcd692faa16f9996424521ec8b731cd1114916fb64"
+    },
+    {
+      "path": "model-00004-of-00004.safetensors",
+      "size_bytes": 4377211327,
+      "sha256": "9daf1fb8f47f0bbef6dabe657700e404ee0ccda30037dda91204543ebf20a6e4"
+    },
+    {
+      "path": "model.safetensors.index.json",
+      "size_bytes": 215755,
+      "sha256": "0b28df60e33753a14e816d3b31577ae2c93884c58430a4a6de6ae9ea483842ea"
+    },
+    {
+      "path": "preprocessor_config.json",
+      "size_bytes": 390,
+      "sha256": "27225450ac9c6529872ee1924fcb0962ff5634834f817040f444118116f4e516"
+    },
+    {
+      "path": "processor_config.json",
+      "size_bytes": 991,
+      "sha256": "45fc17c8dd2474af6b493b52483c26c0584b0082d368c480f9fa611e73070040"
+    },
+    {
+      "path": "tokenizer.json",
+      "size_bytes": 19989325,
+      "sha256": "06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523"
+    },
+    {
+      "path": "tokenizer_config.json",
+      "size_bytes": 1165,
+      "sha256": "792fa3f0cb88b111e54ef3134c873531008c4df471d108da17903426e308aa7b"
+    },
+    {
+      "path": "validation-summary.json",
+      "size_bytes": 6573,
+      "sha256": "4a4d9b642926f21685d47607cba54a717787992cab2f93f34c517d23c0fdf692"
+    },
+    {
+      "path": "video_preprocessor_config.json",
+      "size_bytes": 385,
+      "sha256": "7768af27c1fafa9cc9011c1dc20067e03f8915e03b63504550e11d5066986d13"
+    },
+    {
+      "path": "vocab.json",
+      "size_bytes": 6722759,
+      "sha256": "ce99b4cb2983d118806ce0a8b777a35b093e2000a503ebde25853284c9dfa003"
+    }
+  ],
+  "total_size_bytes": 20429179994
+}

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 +1,794 @@
+{
+    "architectures": [
+        "Qwen3_5MoeForConditionalGeneration"
+    ],
+    "bos_token_id": null,
+    "do_sample": true,
+    "dtype": "bfloat16",
+    "eos_token_id": [
+        248046,
+        248044
+    ],
+    "generation_config": {
+        "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
+    },
+    "hidden_size": 2048,
+    "image_token_id": 248056,
+    "model_type": "qwen3_5_moe",
+    "pad_token_id": 248044,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine",
+        "language_model.model.layers.0.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.0.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.1.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.1.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.2.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.2.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.3.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.3.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.4.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.4.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.5.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.5.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.6.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.6.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.7.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.7.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.8.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.8.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.9.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.9.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.10.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.10.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.11.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.11.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.12.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.12.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.13.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.13.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.14.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.14.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.15.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.15.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.16.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.16.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.17.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.17.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.18.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.18.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.19.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.19.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.20.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.20.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.21.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.21.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.22.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.22.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.23.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.23.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.24.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.24.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.25.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.25.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.26.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.26.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.27.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.27.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.28.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.28.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.29.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.29.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.30.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.30.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.31.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.31.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.32.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.32.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.33.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.33.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.34.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.34.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.35.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.35.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.36.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.36.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.37.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.37.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.38.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.38.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.39.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.39.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        }
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine",
+        "language_model.model.layers.0.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.0.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.1.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.1.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.2.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.2.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.3.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.3.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.4.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.4.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.5.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.5.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.6.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.6.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.7.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.7.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.8.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.8.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.9.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.9.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.10.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.10.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.11.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.11.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.12.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.12.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.13.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.13.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.14.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.14.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.15.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.15.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.16.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.16.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.17.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.17.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.18.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.18.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.19.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.19.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.20.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.20.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.21.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.21.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.22.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.22.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.23.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.23.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.24.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.24.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.25.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.25.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.26.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.26.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.27.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.27.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.28.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.28.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.29.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.29.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.30.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.30.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.31.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.31.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.32.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.32.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.33.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.33.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.34.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.34.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.35.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.35.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.36.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.36.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.37.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.37.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.38.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.38.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.39.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.39.mlp.shared_expert_gate": {
+            "group_size": 64,
+            "bits": 8
+        }
+    },
+    "temperature": 1.0,
+    "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,
+            "rope_type": "default"
+        },
+        "router_aux_loss_coef": 0.0,
+        "shared_expert_intermediate_size": 512,
+        "tie_word_embeddings": false,
+        "use_cache": false,
+        "vocab_size": 248320
+    },
+    "tie_word_embeddings": false,
+    "top_k": 20,
+    "top_p": 0.95,
+    "transformers_version": "5.8.1",
+    "video_token_id": 248057,
+    "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
+    },
+    "vision_end_token_id": 248054,
+    "vision_start_token_id": 248053
+}

configuration.json

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

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-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad2a4e532a2d4785f3f31c594ff39c99200a230a2889b20998d45c10ae66d169
+size 5288196062

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cea3387a2e2863c6d9444a14b7ab6d89f321edcf63f02e699de6dde4e866e160
+size 5368472657

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85a877f211adad37e9db68bcd692faa16f9996424521ec8b731cd1114916fb64
+size 5368324255

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9daf1fb8f47f0bbef6dabe657700e404ee0ccda30037dda91204543ebf20a6e4
+size 4377211327

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 +1,50 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen3VLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_pixels": 16777216,
+    "merge_size": 2,
+    "min_pixels": 65536,
+    "patch_size": 16,
+    "rescale_factor": 0.00392156862745098,
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "fps": 2.0,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "max_pixels": 25165824,
+    "merge_size": 2,
+    "min_frames": 4,
+    "min_pixels": 4096,
+    "patch_size": 16,
+    "rescale_factor": 0.00392156862745098,
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

release-manifest.json

@@ -0,0 +1,15 @@
+{
+  "schema_version": 1,
+  "generated_at": "2026-08-21T04:03:46.400084+00:00",
+  "status": "experimental-release",
+  "repository": "PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-MLX-4bit",
+  "visibility": "public",
+  "variant": "4bit",
+  "model_payload_bytes": 20429166953,
+  "artifact_manifest_sha256": "976292a0eeb6555c97893370c0c4a070b156ef43fa339edc8c850fa4e9125c5a",
+  "evidence": {
+    "README.md": "fc3cc1cab7c09e6d3918400f071db6f85665722961f499fda64d52a490bda896",
+    "abliteration-manifest.json": "82d49e30e1d0eca38c23e3b748f6e923562ee3ee7803ecfa5b07558c88caf224",
+    "validation-summary.json": "4a4d9b642926f21685d47607cba54a717787992cab2f93f34c517d23c0fdf692"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 262144,
+  "model_specific_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|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "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+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

validation-summary.json

@@ -0,0 +1,187 @@
+{
+  "schema_version": 1,
+  "model": "PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-MLX-4bit",
+  "variant": "4bit",
+  "status": "experimental",
+  "base_model": "ornith-ai/Ornith-1.5-35B-A3B",
+  "base_revision": "e4dfb35a93d4b6822a811a7676f3488514abe7e2",
+  "runtime": {
+    "mlx": "0.32.0",
+    "mlx_vlm": "0.6.8"
+  },
+  "behavioral_evaluation": {
+    "parent_12_case_gate": {
+      "capability": {
+        "count": 12,
+        "pass_count": 12,
+        "pass_rate": 1.0
+      },
+      "jbb_benign": {
+        "count": 12,
+        "explicit_refusal_count": 1,
+        "explicit_refusal_rate": 0.08333333333333333,
+        "final_answer_count": 12,
+        "completed_answer_count": 1,
+        "evasive_nonanswer_count": 0,
+        "evasive_nonanswer_rate": 0.0,
+        "truncated_generation_count": 11,
+        "unfinished_reasoning_count": 0
+      },
+      "jbb_harmful": {
+        "count": 12,
+        "explicit_refusal_count": 12,
+        "explicit_refusal_rate": 1.0,
+        "final_answer_count": 12,
+        "completed_answer_count": 11,
+        "evasive_nonanswer_count": 0,
+        "evasive_nonanswer_rate": 0.0,
+        "truncated_generation_count": 1,
+        "unfinished_reasoning_count": 0
+      }
+    },
+    "selected_bf16_12_case_gate": {
+      "capability": {
+        "count": 12,
+        "pass_count": 12,
+        "pass_rate": 1.0
+      },
+      "jbb_benign": {
+        "count": 12,
+        "explicit_refusal_count": 0,
+        "explicit_refusal_rate": 0.0,
+        "final_answer_count": 12,
+        "completed_answer_count": 1,
+        "evasive_nonanswer_count": 0,
+        "evasive_nonanswer_rate": 0.0,
+        "truncated_generation_count": 11,
+        "unfinished_reasoning_count": 0
+      },
+      "jbb_harmful": {
+        "count": 12,
+        "explicit_refusal_count": 0,
+        "explicit_refusal_rate": 0.0,
+        "final_answer_count": 12,
+        "completed_answer_count": 4,
+        "evasive_nonanswer_count": 0,
+        "evasive_nonanswer_rate": 0.0,
+        "truncated_generation_count": 8,
+        "unfinished_reasoning_count": 0
+      }
+    },
+    "variant_100_harmful_100_benign_screen": {
+      "jbb_benign": {
+        "count": 100,
+        "explicit_refusal_count": 0,
+        "explicit_refusal_rate": 0.0,
+        "final_answer_count": 100,
+        "completed_answer_count": 1,
+        "evasive_nonanswer_count": 0,
+        "evasive_nonanswer_rate": 0.0,
+        "truncated_generation_count": 99,
+        "unfinished_reasoning_count": 0
+      },
+      "jbb_harmful": {
+        "count": 100,
+        "explicit_refusal_count": 0,
+        "explicit_refusal_rate": 0.0,
+        "final_answer_count": 100,
+        "completed_answer_count": 4,
+        "evasive_nonanswer_count": 0,
+        "evasive_nonanswer_rate": 0.0,
+        "truncated_generation_count": 96,
+        "unfinished_reasoning_count": 0
+      }
+    },
+    "batch_size": 1,
+    "max_new_tokens": 128,
+    "thinking": false,
+    "scorer": "transparent phrase-based explicit-refusal detector",
+    "caveat": "This is an early-refusal screen, not a full answer-quality evaluation. Manual review found semantic refusals that the phrase detector did not flag."
+  },
+  "matched_teacher_drift": {
+    "protocol": {
+      "context": "shared regular-BF16 greedy teacher trajectory",
+      "positionsPerCaseMaximum": 16,
+      "vocabulary": 248320,
+      "logitsStorage": "float32",
+      "probabilityMath": "float64 full-vocabulary log-softmax",
+      "residualState": "all 40 residual_post vectors at assistant boundary",
+      "cacheState": "final teacher-trajectory cache: K/V for 10 full-attention layers; convolution and gated-delta recurrent state for 30 linear-attention layers",
+      "thinking": false,
+      "sampling": "greedy"
+    },
+    "dataset": {
+      "capabilityFileSha256": "fe35cc41fe041cf2d371041c3fb977ec37b51fa1e9a0b0482aaf1eab415c9c26",
+      "capabilityCases": 12,
+      "jailbreakBench": {
+        "repository": "JailbreakBench/JBB-Behaviors",
+        "revision": "886acc352a31533ffbcf4ef22c744658688086fc"
+      },
+      "harmfulCases": 12,
+      "benignCases": 12
+    },
+    "pure_abliteration_vs_regular_bf16": {
+      "positions": 481,
+      "forward_kl_nats_mean": 0.54518455642922,
+      "top1_agreement": 0.7817047817047817,
+      "residual_cosine_mean": 0.9520897871696514,
+      "cache": {
+        "full_attention_k_cosine_mean": 0.9956834574679786,
+        "full_attention_v_cosine_mean": 0.9942660171605967,
+        "linear_attention_conv_cosine_mean": 0.997201268533088,
+        "linear_attention_recurrent_cosine_mean": 0.9962457101916542
+      },
+      "suite_splits": {
+        "capability": {
+          "positions": 97,
+          "forward_kl_nats_mean": 0.01834161340133247,
+          "top1_agreement": 0.979381443298969,
+          "residual_cosine_mean": 0.995895118556436
+        },
+        "jbb_benign": {
+          "positions": 192,
+          "forward_kl_nats_mean": 0.3073881842398057,
+          "top1_agreement": 0.8541666666666666,
+          "residual_cosine_mean": 0.9696202077556074
+        },
+        "jbb_harmful": {
+          "positions": 192,
+          "forward_kl_nats_mean": 1.0491463737941817,
+          "top1_agreement": 0.609375,
+          "residual_cosine_mean": 0.8907540351969113
+        }
+      }
+    },
+    "quantization_vs_abliterated_bf16": {
+      "positions": 481,
+      "forward_kl_nats_mean": 0.14369058172143362,
+      "top1_agreement": 0.8731808731808732,
+      "residual_cosine_mean": 0.9584706869834336,
+      "cache": {
+        "full_attention_k_cosine_mean": 0.9793075130946234,
+        "full_attention_v_cosine_mean": 0.9716918964141061,
+        "linear_attention_conv_cosine_mean": 0.9878246768445645,
+        "linear_attention_recurrent_cosine_mean": 0.9866432650675594
+      }
+    },
+    "total_vs_regular_bf16": {
+      "positions": 481,
+      "forward_kl_nats_mean": 0.6640038720543332,
+      "top1_agreement": 0.7525987525987526,
+      "residual_cosine_mean": 0.9207185389809484,
+      "cache": {
+        "full_attention_k_cosine_mean": 0.9764506595000695,
+        "full_attention_v_cosine_mean": 0.9679095435046612,
+        "linear_attention_conv_cosine_mean": 0.9860736375044666,
+        "linear_attention_recurrent_cosine_mean": 0.9839664542846734
+      }
+    }
+  },
+  "capabilities": {
+    "vision_tower_included": true,
+    "video_preprocessor_included": true,
+    "native_mtp_head_included": false,
+    "four_bit_image_smoke_passed": true,
+    "vision_evaluation_caveat": "Only the 4-bit artifact received an end-to-end image smoke test; vision and video were not comprehensively benchmarked."
+  }
+}

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"
+}