Upload folder using huggingface_hub

.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

.meta/create_model.py

@@ -0,0 +1,83 @@
+def create_model(source_model_id: str, source_revision: str, save_folder: str) -> str:
+    import json
+    from pathlib import Path
+
+    import torch
+    from huggingface_hub import hf_hub_download
+    from safetensors.torch import save_file
+    from transformers import AutoConfig, AutoModelForSequenceClassification, set_seed
+
+    folder = Path(save_folder)
+    folder.mkdir(parents=True, exist_ok=True)
+    config = json.loads(
+        Path(hf_hub_download(source_model_id, "config.json", revision=source_revision)).read_text(encoding="utf-8")
+    )
+    text = config["text_config"]
+    text.update(
+        hidden_size=16,
+        intermediate_size=32,
+        head_dim=256,
+        num_hidden_layers=8,
+        num_attention_heads=8,
+        num_key_value_heads=2,
+        linear_key_head_dim=128,
+        linear_value_head_dim=128,
+        linear_num_key_heads=16,
+        linear_num_value_heads=16,
+        layer_types=["linear_attention", "linear_attention", "linear_attention", "full_attention"] * 2,
+    )
+    config["vision_config"].update(
+        hidden_size=128,
+        intermediate_size=256,
+        depth=4,
+        num_heads=4,
+        out_hidden_size=16,
+    )
+    config["hidden_size"] = 16
+    config["num_labels"] = 2
+    config["architectures"] = ["Qwen3_5ForSequenceClassification"]
+    config["problem_type"] = "single_label_classification"
+    (folder / "config.json").write_text(json.dumps(config, indent=2) + "\n", encoding="utf-8")
+    for name in (
+        "chat_template.jinja",
+        "generation_config.json",
+        "preprocessor_config.json",
+        "processor_config.json",
+        "tokenizer.json",
+        "tokenizer_config.json",
+    ):
+        (folder / name).write_bytes(Path(hf_hub_download(source_model_id, name, revision=source_revision)).read_bytes())
+
+    previous_dtype = torch.get_default_dtype()
+    try:
+        torch.set_default_dtype(torch.bfloat16)
+        set_seed(42)
+        model = AutoModelForSequenceClassification.from_config(AutoConfig.from_pretrained(folder))
+        with torch.no_grad():
+            for name, parameter in sorted(model.named_parameters()):
+                if name.endswith("A_log"):
+                    parameter.zero_()
+                elif name.endswith("dt_bias"):
+                    parameter.fill_(1)
+                elif name.endswith("weight") and "norm" in name:
+                    parameter.fill_(1)
+                elif name.endswith("bias"):
+                    parameter.zero_()
+                else:
+                    parameter.normal_(mean=0.0, std=0.02)
+        state = {name: value.detach().cpu().contiguous() for name, value in model.state_dict().items()}
+        save_file(state, folder / "model.safetensors", metadata={"format": "pt"})
+    finally:
+        torch.set_default_dtype(previous_dtype)
+    (folder / "config.json").write_text(json.dumps(config, indent=2) + "\n", encoding="utf-8")
+    (folder / "generation_config.json").write_bytes(
+        Path(hf_hub_download(source_model_id, "generation_config.json", revision=source_revision)).read_bytes()
+    )
+    return str(model)
+
+
+create_model(
+    source_model_id="openbmb/MiniCPM-OCR-Jev",
+    source_revision="bdb03f86182a2824d2632d129c719cdf780502e2",
+    save_folder="/tmp/minicpm-ocr-jev",
+)

.meta/env.json

@@ -0,0 +1,35 @@
+{
+  "source_model": {
+    "name": "openbmb/MiniCPM-OCR-Jev",
+    "commit_id": "bdb03f86182a2824d2632d129c719cdf780502e2"
+  },
+  "environments": {
+    "creation": {
+      "python": "3.12.13",
+      "packages": {
+        "huggingface_hub": "2.3.0",
+        "safetensors": "0.8.0",
+        "tokenizers": "0.23.3",
+        "torch": "2.13.0+cu126",
+        "transformers": "5.22.0.dev0"
+      },
+      "cuda": "12.6"
+    },
+    "transformers": {
+      "python": "3.11.2",
+      "packages": {
+        "torch": "2.7.1",
+        "transformers": "5.22.1",
+        "tokenizers": "0.23.3",
+        "huggingface_hub": "2.4.0",
+        "safetensors": "0.8.0",
+        "Pillow": "11.3.0",
+        "numpy": "2.3.2"
+      },
+      "cuda": "12.6",
+      "hardware": {
+        "gpu_model": "NVIDIA A800-SXM4-80GB"
+      }
+    }
+  }
+}

.meta/model.log

@@ -0,0 +1,114 @@
+Qwen3_5ForSequenceClassification(
+  (model): Qwen3_5Model(
+    (visual): Qwen3_5VisionModel(
+      (patch_embed): Qwen3_5VisionPatchEmbed(
+        (proj): Conv3d(3, 128, kernel_size=(2, 16, 16), stride=(2, 16, 16))
+      )
+      (pos_embed): Embedding(2304, 128)
+      (rotary_pos_emb): Qwen3_5VisionRotaryEmbedding()
+      (blocks): ModuleList(
+        (0-3): 4 x Qwen3_5VisionBlock(
+          (norm1): LayerNorm((128,), eps=1e-06, elementwise_affine=True, bias=True)
+          (norm2): LayerNorm((128,), eps=1e-06, elementwise_affine=True, bias=True)
+          (attn): Qwen3_5VisionAttention(
+            (qkv): Linear(in_features=128, out_features=384, bias=True)
+            (proj): Linear(in_features=128, out_features=128, bias=True)
+          )
+          (mlp): Qwen3_5VisionMLP(
+            (linear_fc1): Linear(in_features=128, out_features=256, bias=True)
+            (linear_fc2): Linear(in_features=256, out_features=128, bias=True)
+            (act_fn): GELUTanh()
+          )
+        )
+      )
+      (merger): Qwen3_5VisionPatchMerger(
+        (norm): LayerNorm((128,), eps=1e-06, elementwise_affine=True, bias=True)
+        (linear_fc1): Linear(in_features=512, out_features=512, bias=True)
+        (act_fn): GELU(approximate='none')
+        (linear_fc2): Linear(in_features=512, out_features=16, bias=True)
+      )
+    )
+    (language_model): Qwen3_5TextModel(
+      (embed_tokens): Embedding(248320, 16, padding_idx=248044)
+      (layers): ModuleList(
+        (0-2): 3 x Qwen3_5DecoderLayer(
+          (linear_attn): Qwen3_5GatedDeltaNet(
+            (conv1d): Conv1d(6144, 6144, kernel_size=(4,), stride=(1,), padding=(3,), groups=6144, bias=False)
+            (norm): Qwen3_5RMSNormGated()
+            (out_proj): Linear(in_features=2048, out_features=16, bias=False)
+            (in_proj_qkv): Linear(in_features=16, out_features=6144, bias=False)
+            (in_proj_z): Linear(in_features=16, out_features=2048, bias=False)
+            (in_proj_b): Linear(in_features=16, out_features=16, bias=False)
+            (in_proj_a): Linear(in_features=16, out_features=16, bias=False)
+          )
+          (mlp): Qwen3_5MLP(
+            (gate_proj): Linear(in_features=16, out_features=32, bias=False)
+            (up_proj): Linear(in_features=16, out_features=32, bias=False)
+            (down_proj): Linear(in_features=32, out_features=16, bias=False)
+            (act_fn): SiLUActivation()
+          )
+          (input_layernorm): Qwen3_5RMSNorm((16,), eps=1e-06)
+          (post_attention_layernorm): Qwen3_5RMSNorm((16,), eps=1e-06)
+        )
+        (3): Qwen3_5DecoderLayer(
+          (self_attn): Qwen3_5Attention(
+            (q_proj): Linear(in_features=16, out_features=4096, bias=False)
+            (k_proj): Linear(in_features=16, out_features=512, bias=False)
+            (v_proj): Linear(in_features=16, out_features=512, bias=False)
+            (o_proj): Linear(in_features=2048, out_features=16, bias=False)
+            (q_norm): Qwen3_5RMSNorm((256,), eps=1e-06)
+            (k_norm): Qwen3_5RMSNorm((256,), eps=1e-06)
+          )
+          (mlp): Qwen3_5MLP(
+            (gate_proj): Linear(in_features=16, out_features=32, bias=False)
+            (up_proj): Linear(in_features=16, out_features=32, bias=False)
+            (down_proj): Linear(in_features=32, out_features=16, bias=False)
+            (act_fn): SiLUActivation()
+          )
+          (input_layernorm): Qwen3_5RMSNorm((16,), eps=1e-06)
+          (post_attention_layernorm): Qwen3_5RMSNorm((16,), eps=1e-06)
+        )
+        (4-6): 3 x Qwen3_5DecoderLayer(
+          (linear_attn): Qwen3_5GatedDeltaNet(
+            (conv1d): Conv1d(6144, 6144, kernel_size=(4,), stride=(1,), padding=(3,), groups=6144, bias=False)
+            (norm): Qwen3_5RMSNormGated()
+            (out_proj): Linear(in_features=2048, out_features=16, bias=False)
+            (in_proj_qkv): Linear(in_features=16, out_features=6144, bias=False)
+            (in_proj_z): Linear(in_features=16, out_features=2048, bias=False)
+            (in_proj_b): Linear(in_features=16, out_features=16, bias=False)
+            (in_proj_a): Linear(in_features=16, out_features=16, bias=False)
+          )
+          (mlp): Qwen3_5MLP(
+            (gate_proj): Linear(in_features=16, out_features=32, bias=False)
+            (up_proj): Linear(in_features=16, out_features=32, bias=False)
+            (down_proj): Linear(in_features=32, out_features=16, bias=False)
+            (act_fn): SiLUActivation()
+          )
+          (input_layernorm): Qwen3_5RMSNorm((16,), eps=1e-06)
+          (post_attention_layernorm): Qwen3_5RMSNorm((16,), eps=1e-06)
+        )
+        (7): Qwen3_5DecoderLayer(
+          (self_attn): Qwen3_5Attention(
+            (q_proj): Linear(in_features=16, out_features=4096, bias=False)
+            (k_proj): Linear(in_features=16, out_features=512, bias=False)
+            (v_proj): Linear(in_features=16, out_features=512, bias=False)
+            (o_proj): Linear(in_features=2048, out_features=16, bias=False)
+            (q_norm): Qwen3_5RMSNorm((256,), eps=1e-06)
+            (k_norm): Qwen3_5RMSNorm((256,), eps=1e-06)
+          )
+          (mlp): Qwen3_5MLP(
+            (gate_proj): Linear(in_features=16, out_features=32, bias=False)
+            (up_proj): Linear(in_features=16, out_features=32, bias=False)
+            (down_proj): Linear(in_features=32, out_features=16, bias=False)
+            (act_fn): SiLUActivation()
+          )
+          (input_layernorm): Qwen3_5RMSNorm((16,), eps=1e-06)
+          (post_attention_layernorm): Qwen3_5RMSNorm((16,), eps=1e-06)
+        )
+      )
+      (norm): Qwen3_5RMSNorm((16,), eps=1e-06)
+      (rotary_emb): Qwen3_5TextRotaryEmbedding()
+    )
+  )
+  (score): Linear(in_features=16, out_features=2, bias=False)
+)

README.md

@@ -0,0 +1,101 @@
+---
+library_name: transformers
+pipeline_tag: image-text-to-text
+base_model:
+- openbmb/MiniCPM-OCR-Jev
+---
+
+This is a randomly initialized tiny model based on [openbmb/MiniCPM-OCR-Jev](https://huggingface.co/openbmb/MiniCPM-OCR-Jev) for testing and debugging.
+
+| Feature | Source | This repo |
+|---|---|---|
+| Checkpoint tensor elements | 2.21B BF16 | 6.64M BF16 |
+| Safetensors weight files | 4.43 GB (model.safetensors) | 13.31 MB (model.safetensors) |
+| Architecture / input | Qwen3.5 vision-language correctness scorer | Same |
+| Vocabulary rows / tied embeddings | 248,320 / false | Same |
+| Backbone layers / layer cadence | 24 / six 3-linear + 1-full cycles | 8 / two complete cycles |
+| Hidden width / MLP width | 2,048 / 6,144 | 16 / 32 |
+| Q heads / KV heads / head dimension | 8 / 2 / 256 | Same |
+| Linear-attention key/value heads and dimensions | 16/16, 128/128 | Same |
+| Vision depth / width / output width | 24 / 1,024 / 2,048 | 4 / 128 / 16 |
+| Vision patch / temporal patch / spatial merge | 16 / 2 / 2 | Same |
+| Task head | binary `score` [2, 2,048]; no `lm_head` | binary `score` [2, 16]; no `lm_head` |
+| MTP | config declares one layer; no MTP tensors | Same |
+| Checkpoint precision | BF16 | Same |
+
+Load this checkpoint with `AutoModelForSequenceClassification`; it keeps the source binary `score` head and does not contain `lm_head`. Two complete linear/linear/linear/full cycles are retained. The Qwen3.5 linear-attention path requires CUDA and Triton. The exact public snippet was verified on an NVIDIA A800-SXM4-80GB.
+
+| File path | Size |
+|------|------|
+| model.safetensors | 13.3MB |
+
+### Example usage
+
+#### Transformers (✅ verified)
+
+The example sends two images: the original block and a rendered image of the candidate text. Load with `AutoModelForSequenceClassification`; the checkpoint has a binary `score` head instead of `lm_head`. Install `transformers>=5.10.4` and `Pillow`; the Qwen3.5 linear-attention path requires CUDA and Triton.
+
+```python
+def run_transformers(model_id: str):
+    import torch
+    from PIL import Image, ImageDraw
+    from transformers import AutoModelForSequenceClassification, AutoProcessor
+
+    model_id = str(model_id)
+    processor = AutoProcessor.from_pretrained(model_id)
+    model = AutoModelForSequenceClassification.from_pretrained(
+        model_id,
+        dtype=torch.bfloat16,
+        device_map="cuda",
+        attn_implementation="sdpa",
+    )
+    candidate = "Hello"
+    original = Image.new("RGB", (448, 448), "white")
+    ImageDraw.Draw(original).text((20, 20), candidate, fill="black")
+    rendered = Image.new("RGB", (448, 448), "white")
+    ImageDraw.Draw(rendered).text((20, 20), candidate, fill="black")
+    instruction = (
+        "第一张图是原图，第二张图是上述 OCR 文本渲染得到的图片。\n"
+        "请判断该 OCR 文本及其对应渲染图是否与原图内容一致。\n"
+        "这是一个二分类任务：一致标为 1，不一致标为 0。"
+    )
+    messages = [
+        {
+            "role": "user",
+            "content": [
+                {"type": "image", "image": original},
+                {"type": "text", "text": f"\nOCR文本：\n{candidate}\n"},
+                {"type": "image", "image": rendered},
+                {"type": "text", "text": "\n" + instruction},
+            ],
+        }
+    ]
+    inputs = processor.apply_chat_template(
+        messages,
+        tokenize=True,
+        add_generation_prompt=True,
+        return_dict=True,
+        return_tensors="pt",
+    ).to(model.device)
+    with torch.no_grad():
+        logits = model(**inputs).logits
+        assert torch.isfinite(logits).all()
+        score = torch.softmax(logits.float(), dim=-1)[:, 1]
+    print(float(score[0]))
+
+
+if __name__ == "__main__":
+    run_transformers(model_id="tiny-random/minicpm-ocr-jev")
+```
+
+### Creating this repo
+
+- Code: [.meta/create_model.py](.meta/create_model.py)
+- Model structure: [.meta/model.log](.meta/model.log)
+- Environment: [.meta/env.json](.meta/env.json)
+
+### Change log
+
+- 2026-11-01: Initial tiny MiniCPM-OCR Jev checkpoint.
+
+*This repo is generated by DeepSeek-V4.1-Flash.*

chat_template.jinja

@@ -0,0 +1,154 @@
+{%- 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 %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- 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 true %}
+        {{- '<think>\n' }}
+    {%- else %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,91 @@
+{
+  "architectures": [
+    "Qwen3_5ForSequenceClassification"
+  ],
+  "dtype": "bfloat16",
+  "eos_token_id": 248046,
+  "hidden_size": 16,
+  "image_token_id": 248056,
+  "model_type": "qwen3_5",
+  "pad_token_id": 248044,
+  "problem_type": "single_label_classification",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_output_gate": true,
+    "bos_token_id": null,
+    "dtype": "bfloat16",
+    "eos_token_id": 248044,
+    "full_attention_interval": 4,
+    "head_dim": 256,
+    "hidden_act": "silu",
+    "hidden_size": 16,
+    "initializer_range": 0.02,
+    "intermediate_size": 32,
+    "layer_types": [
+      "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": 16,
+    "linear_value_head_dim": 128,
+    "mamba_ssm_dtype": "float32",
+    "max_position_embeddings": 262144,
+    "mlp_only_layers": [],
+    "model_type": "qwen3_5_text",
+    "mtp_num_hidden_layers": 1,
+    "mtp_use_dedicated_embeddings": false,
+    "num_attention_heads": 8,
+    "num_hidden_layers": 8,
+    "num_key_value_heads": 2,
+    "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"
+    },
+    "tie_word_embeddings": false,
+    "use_cache": false,
+    "vocab_size": 248320
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.10.4",
+  "use_cache": false,
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 4,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 128,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 256,
+    "model_type": "qwen3_5_vision",
+    "num_heads": 4,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 16,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053,
+  "num_labels": 2
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    248046,
+    248044,
+    248046
+  ],
+  "pad_token_id": 248044,
+  "transformers_version": "5.10.4",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:596753a5776151dc1ccea6b750958a0a405439fdd4d559b466a09147fc7b6117
+size 13306128

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 sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+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|>"
+}