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 +1,82 @@
+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, AutoModelForImageTextToText, 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,
+        num_hidden_layers=4,
+        num_attention_heads=4,
+    )
+    config["insert_layer_id"] = 2
+    (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 = AutoModelForImageTextToText.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()}
+        # The source ties the language-model head to the token table and does not
+        # serialize a separate `lm_head.weight`.
+        state.pop("lm_head.weight", None)
+        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-1.0",
+    source_revision="c5833cddb363aa62f1cb60ddde48c832e8f1a92c",
+    save_folder="/tmp/minicpm-ocr-1.0",
+)

.meta/env.json

@@ -0,0 +1,35 @@
+{
+  "source_model": {
+    "name": "openbmb/MiniCPM-OCR-1.0",
+    "commit_id": "c5833cddb363aa62f1cb60ddde48c832e8f1a92c"
+  },
+  "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 +1,135 @@
+MiniCPMOcrForConditionalGeneration(
+  (model): MiniCPMOcrModel(
+    (vision_tower): MiniCPMOcrVisionModel(
+      (embeddings): MiniCPMOcrVisionEmbeddings(
+        (patch_embedding): Conv2d(3, 128, kernel_size=(14, 14), stride=(14, 14), padding=valid)
+        (position_embedding): Embedding(4900, 128)
+      )
+      (encoder): MiniCPMOcrVisionEncoder(
+        (layers): ModuleList(
+          (0-3): 4 x MiniCPMOcrVisionEncoderLayer(
+            (layer_norm1): LayerNorm((128,), eps=1e-06, elementwise_affine=True, bias=True)
+            (self_attn): MiniCPMOcrVisionAttention(
+              (k_proj): Linear(in_features=128, out_features=128, bias=True)
+              (v_proj): Linear(in_features=128, out_features=128, bias=True)
+              (q_proj): Linear(in_features=128, out_features=128, bias=True)
+              (out_proj): Linear(in_features=128, out_features=128, bias=True)
+            )
+            (layer_norm2): LayerNorm((128,), eps=1e-06, elementwise_affine=True, bias=True)
+            (mlp): MiniCPMOcrVisionMLP(
+              (activation_fn): GELUTanh()
+              (fc1): Linear(in_features=128, out_features=256, bias=True)
+              (fc2): Linear(in_features=256, out_features=128, bias=True)
+            )
+          )
+        )
+      )
+      (post_layernorm): LayerNorm((128,), eps=1e-06, elementwise_affine=True, bias=True)
+      (vit_merger): MiniCPMOcrViTWindowAttentionMerger(
+        (self_attn): MiniCPMOcrVisionAttention(
+          (k_proj): Linear(in_features=128, out_features=128, bias=True)
+          (v_proj): Linear(in_features=128, out_features=128, bias=True)
+          (q_proj): Linear(in_features=128, out_features=128, bias=True)
+          (out_proj): Linear(in_features=128, out_features=128, bias=True)
+        )
+        (layer_norm1): LayerNorm((128,), eps=1e-06, elementwise_affine=True, bias=True)
+        (pre_norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True, bias=True)
+        (linear_1): Linear(in_features=512, out_features=1024, bias=True)
+        (act): GELUTanh()
+        (linear_2): Linear(in_features=1024, out_features=128, bias=True)
+      )
+    )
+    (language_model): Qwen3_5TextModel(
+      (embed_tokens): Embedding(248100, 16)
+      (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()
+    )
+    (merger): MiniCPMOcrMerger(
+      (mlp): ModuleList(
+        (0): MiniCPMOcrDownsampleMLP(
+          (pre_norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True, bias=True)
+          (linear_1): Linear(in_features=512, out_features=512, bias=True)
+          (act): GELU(approximate='none')
+          (linear_2): Linear(in_features=512, out_features=16, bias=True)
+        )
+      )
+    )
+  )
+  (lm_head): Linear(in_features=16, out_features=248100, bias=False)
+)

README.md

@@ -0,0 +1,94 @@
+---
+library_name: transformers
+pipeline_tag: image-text-to-text
+base_model:
+- openbmb/MiniCPM-OCR-1.0
+---
+
+This is a randomly initialized tiny model based on [openbmb/MiniCPM-OCR-1.0](https://huggingface.co/openbmb/MiniCPM-OCR-1.0) for testing and debugging.
+
+| Feature | Source | This repo |
+|---|---|---|
+| Checkpoint tensor elements | 1.30B BF16 | 7.58M BF16 |
+| Safetensors weight files | 2.60 GB (model.safetensors) | 15.18 MB (model.safetensors) |
+| Architecture / input | MiniCPM-OCR; text and document image | Same |
+| Vocabulary rows / tied embeddings | 248,100 / tied | Same |
+| Backbone layers / layer cadence | 24 / six 3-linear + 1-full cycles | 8 / two complete cycles |
+| Hidden width / MLP width | 1,024 / 3,584 | 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 layers / width / insert merger | 27 / 1,152 / after layer 6 | 4 / 128 / after layer 2 |
+| Visual downsampling | 4x | Same |
+| M-RoPE | sections 11/11/10; partial 0.25 | sections 11/11/10; partial 0.25 |
+| MTP | disabled | Same |
+| Checkpoint precision | BF16 | Same |
+
+The tokenizer embedding and output head stay tied, so the checkpoint contains one BF16 token table. 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 | 15.2MB |
+
+### Example usage
+
+#### Transformers (✅ verified)
+
+The Qwen3.5 linear-attention path requires CUDA and Triton. Install `transformers[torch]>=5.21.0` and `Pillow`.
+
+```python
+def run_transformers(model_id: str):
+    import torch
+    from PIL import Image, ImageDraw
+    from transformers import AutoModelForImageTextToText, AutoProcessor
+
+    model_id = str(model_id)
+    processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)
+    model = AutoModelForImageTextToText.from_pretrained(
+        model_id,
+        dtype=torch.bfloat16,
+        device_map="cuda",
+        attn_implementation="sdpa",
+    )
+    image = Image.new("RGB", (448, 448), "white")
+    ImageDraw.Draw(image).text((20, 20), "Hello OCR", fill="black")
+    messages = [
+        {
+            "role": "user",
+            "content": [
+                {"type": "image", "image": image},
+                {"type": "text", "text": "Read this document."},
+            ],
+        }
+    ]
+    inputs = processor.apply_chat_template(
+        messages,
+        tokenize=True,
+        add_generation_prompt=True,
+        return_dict=True,
+        return_tensors="pt",
+        downsample_mode="4x",
+        max_slice_nums=1,
+        use_image_id=False,
+    ).to(model.device)
+    with torch.no_grad():
+        logits = model(**inputs).logits
+        assert torch.isfinite(logits).all()
+        output = model.generate(**inputs, downsample_mode="4x", do_sample=False, max_new_tokens=10)
+    print(processor.decode(output[0, inputs["input_ids"].shape[1] :], skip_special_tokens=True))
+
+
+if __name__ == "__main__":
+    run_transformers(model_id="tiny-random/minicpm-ocr-1.0")
+```
+
+### 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 1.0 checkpoint.
+
+*This repo is generated by DeepSeek-V4.1-Flash.*

chat_template.jinja

@@ -0,0 +1,145 @@
+{%- if enable_thinking is not defined -%}
+    {%- set enable_thinking = false -%}
+{%- endif -%}
+{%- macro render_content(content, is_system_content=false) -%}
+    {%- if content is string -%}
+        {{- content -}}
+    {%- elif content is iterable and content is not mapping -%}
+        {%- set ns = namespace(parts=[]) -%}
+        {%- 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 -%}
+                {%- set ns.parts = ns.parts + ['<|image_pad|>'] -%}
+            {%- elif 'video' in item or item.type == 'video' -%}
+                {%- if is_system_content -%}
+                    {{- raise_exception('System message cannot contain videos.') -}}
+                {%- endif -%}
+                {%- set ns.parts = ns.parts + ['<|video_pad|>'] -%}
+            {%- elif 'text' in item -%}
+                {%- set ns.parts = ns.parts + [item.text] -%}
+            {%- else -%}
+                {{- raise_exception('Unexpected item type in content.') -}}
+            {%- endif -%}
+        {%- endfor -%}
+        {{- ns.parts | join('\n') -}}
+    {%- 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, 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, 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)|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)|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 and reasoning_content %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n\n</think>\n\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 +1,70 @@
+{
+  "architectures": [
+    "MiniCPMOcrForConditionalGeneration"
+  ],
+  "downsample_mode": "4x",
+  "model_type": "minicpm_ocr",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.21.0",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 128,
+    "image_size": 980,
+    "intermediate_size": 256,
+    "layer_norm_eps": 1e-06,
+    "model_type": "minicpm_ocr_vision",
+    "num_attention_heads": 4,
+    "num_channels": 3,
+    "num_hidden_layers": 4,
+    "patch_size": 14
+  },
+  "insert_layer_id": 2,
+  "image_token_id": 248056,
+  "video_token_id": 248057,
+  "dtype": "bfloat16",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_output_gate": true,
+    "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": [],
+    "mtp_num_hidden_layers": 0,
+    "mtp_use_dedicated_embeddings": false,
+    "num_attention_heads": 8,
+    "num_hidden_layers": 8,
+    "num_key_value_heads": 2,
+    "partial_rotary_factor": 0.25,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "partial_rotary_factor": 0.25,
+      "rope_theta": 10000000,
+      "rope_type": "default"
+    },
+    "vocab_size": 248100,
+    "model_type": "qwen3_5_text",
+    "tie_word_embeddings": true
+  }
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 248045,
+  "eos_token_id": [
+    248044,
+    248046
+  ],
+  "transformers_version": "5.21.0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b776367cbaa20f17cab9341fcc42217f51e822f27f59d4a9b8af13907f64341
+size 15175584

preprocessor_config.json

@@ -0,0 +1,20 @@
+{
+  "downsample_mode": "4x",
+  "max_slice_nums": 9,
+  "patch_size": 14,
+  "scale_resolution": 448,
+  "slice_mode": true,
+  "use_image_id": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "MiniCPMOcrImageProcessor",
+  "processor_class": "MiniCPMOcrProcessor"
+}

processor_config.json

@@ -0,0 +1,3 @@
+{
+  "processor_class": "MiniCPMOcrProcessor"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6269eb38f25c20c0f2ba676577f2e5603f79eab3be573dfdaa727ca6eeb5522d
+size 19993565

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "image_start_token": "<image>",
+    "image_end_token": "</image>",
+    "slice_start_token": "<slice>",
+    "slice_end_token": "</slice>",
+    "image_id_start_token": "<image_id>",
+    "image_id_end_token": "</image_id>"
+  },
+  "image_token": "<|image_pad|>",
+  "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": "MiniCPMOcrProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}