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

README.md

@@ -0,0 +1,145 @@
+---
+library_name: transformers
+pipeline_tag: image-text-to-text
+inference: true
+widget:
+  - text: Hello!
+    example_title: Hello world
+    group: Python
+base_model:
+- openbmb/MiniCPM-V-4_5
+---
+
+This tiny model is for debugging. It is randomly initialized with the config adapted from [openbmb/MiniCPM-V-4_5](https://huggingface.co/openbmb/MiniCPM-V-4_5).
+
+### Example usage:
+
+```python
+import numpy as np
+import torch
+from PIL import Image
+from transformers import AutoModel, AutoTokenizer
+
+model_id = "tiny-random/minicpm-v-4_5"
+model = AutoModel.from_pretrained(model_id, trust_remote_code=True,
+                                  attn_implementation='sdpa', torch_dtype=torch.bfloat16)
+model = model.eval().cuda()
+tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
+
+image = Image.fromarray(np.random.randint(0, 255, (224, 224, 3), dtype=np.uint8), 'RGB')
+question = "What is the landform in the picture?"
+msgs = [{'role': 'user', 'content': [image, question]}]
+answer = model.chat(
+    msgs=msgs,
+    image=image,
+    tokenizer=tokenizer,
+    max_new_tokens=32,
+)
+print(answer)
+
+# Second round chat, pass history context of multi-turn conversation
+msgs.append({"role": "assistant", "content": [answer]})
+msgs.append({"role": "user", "content": [
+            "What should I pay attention to when traveling here?"]})
+answer = model.chat(
+    msgs=msgs,
+    image=None,
+    tokenizer=tokenizer,
+    max_new_tokens=32,
+)
+print(answer)
+```
+
+### Codes to create this repo:
+
+```python
+import json
+from pathlib import Path
+
+import accelerate
+import torch
+from huggingface_hub import hf_hub_download
+from transformers import (
+    AutoConfig,
+    AutoModel,
+    AutoModelForCausalLM,
+    AutoProcessor,
+    AutoTokenizer,
+    GenerationConfig,
+    set_seed,
+)
+
+source_model_id = "openbmb/MiniCPM-V-4_5"
+save_folder = "/tmp/tiny-random/minicpm-v-4_5"
+
+processor = AutoProcessor.from_pretrained(source_model_id, trust_remote_code=True)
+processor.save_pretrained(save_folder)
+
+with open(hf_hub_download(source_model_id, filename='config.json', repo_type='model',), 'r', encoding='utf-8') as f:
+    config_json = json.load(f)
+for k, v in config_json['auto_map'].items():
+    config_json['auto_map'][k] = f'{source_model_id}--{v}'
+automap = config_json['auto_map']
+
+config_json['head_dim'] = 32
+config_json["hidden_size"] = 128  # required by Sampler -- num_heads=embed_dim // 128
+config_json['intermediate_size'] = 128
+config_json['num_attention_heads'] = 2
+config_json['num_key_value_heads'] = 1
+config_json['num_hidden_layers'] = 2
+config_json['tie_word_embeddings'] = True
+
+# factor = config_json['rope_scaling']['long_factor']
+# config_json['rope_scaling']['long_factor'] = factor[:16]
+# config_json['rope_scaling']['short_factor'] = factor[:16]
+
+config_json['vision_config']['intermediate_size'] = 128
+config_json['vision_config']['hidden_size'] = 64
+config_json['vision_config']['num_attention_heads'] = 2
+config_json['vision_config']['num_hidden_layers'] = 2
+
+with open(f"{save_folder}/config.json", "w", encoding='utf-8') as f:
+    json.dump(config_json, f, indent=2)
+
+config = AutoConfig.from_pretrained(
+    save_folder,
+    trust_remote_code=True,
+)
+print(config)
+torch.set_default_dtype(torch.bfloat16)
+model = AutoModel.from_config(config, trust_remote_code=True)
+torch.set_default_dtype(torch.float32)
+model.generation_config = GenerationConfig.from_pretrained(
+    source_model_id, trust_remote_code=True,
+)
+set_seed(42)
+num_params = sum(p.numel() for p in model.parameters())
+with torch.no_grad():
+    for name, p in sorted(model.named_parameters()):
+        torch.nn.init.normal_(p, 0, 0.1)
+        print(name, p.shape, p.dtype, p.device, f'{p.numel() / num_params * 100: .2f}%')
+        pass
+model.save_pretrained(save_folder)
+
+def modify_automap(path, source_model_id):
+    import json
+    with open(path, 'r', encoding='utf-8') as f:
+        content = json.load(f)
+    automap = {}
+    if content.get('auto_map', None) is not None:
+        for key, value in content.get('auto_map').items():
+            if isinstance(value, str):
+                value = source_model_id + '--' + value.split('--')[-1]
+            else:
+                value = [(source_model_id + '--' + v.split('--')[-1]) for v in value]
+            automap[key] = value
+        with open(path, 'w', encoding='utf-8') as f:
+            json.dump({**content, 'auto_map': automap}, f, indent=2)
+
+modify_automap(f"{save_folder}/config.json", source_model_id)
+modify_automap(f'{save_folder}/processor_config.json', source_model_id)
+modify_automap(f'{save_folder}/preprocessor_config.json', source_model_id)
+modify_automap(f'{save_folder}/tokenizer_config.json', source_model_id)
+for f in Path(save_folder).glob('*.py'):
+    f.unlink()
+```

added_tokens.json

@@ -0,0 +1,107 @@
+{
+  "</box>": 151674,
+  "</image>": 151670,
+  "</image_id>": 151682,
+  "</point>": 151678,
+  "</quad>": 151676,
+  "</ref>": 151672,
+  "</slice>": 151680,
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "</unit>": 151684,
+  "<box>": 151673,
+  "<image>": 151669,
+  "<image_id>": 151681,
+  "<point>": 151677,
+  "<quad>": 151675,
+  "<ref>": 151671,
+  "<slice>": 151679,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<unit>": 151683,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|reserved_0|>": 151685,
+  "<|reserved_10|>": 151695,
+  "<|reserved_11|>": 151696,
+  "<|reserved_12|>": 151697,
+  "<|reserved_13|>": 151698,
+  "<|reserved_14|>": 151699,
+  "<|reserved_15|>": 151700,
+  "<|reserved_16|>": 151701,
+  "<|reserved_17|>": 151702,
+  "<|reserved_18|>": 151703,
+  "<|reserved_19|>": 151704,
+  "<|reserved_1|>": 151686,
+  "<|reserved_20|>": 151705,
+  "<|reserved_21|>": 151706,
+  "<|reserved_22|>": 151707,
+  "<|reserved_23|>": 151708,
+  "<|reserved_24|>": 151709,
+  "<|reserved_25|>": 151710,
+  "<|reserved_26|>": 151711,
+  "<|reserved_27|>": 151712,
+  "<|reserved_28|>": 151713,
+  "<|reserved_29|>": 151714,
+  "<|reserved_2|>": 151687,
+  "<|reserved_30|>": 151715,
+  "<|reserved_31|>": 151716,
+  "<|reserved_32|>": 151717,
+  "<|reserved_33|>": 151718,
+  "<|reserved_34|>": 151719,
+  "<|reserved_35|>": 151720,
+  "<|reserved_36|>": 151721,
+  "<|reserved_37|>": 151722,
+  "<|reserved_38|>": 151723,
+  "<|reserved_39|>": 151724,
+  "<|reserved_3|>": 151688,
+  "<|reserved_40|>": 151725,
+  "<|reserved_41|>": 151726,
+  "<|reserved_42|>": 151727,
+  "<|reserved_43|>": 151728,
+  "<|reserved_44|>": 151729,
+  "<|reserved_45|>": 151730,
+  "<|reserved_46|>": 151731,
+  "<|reserved_47|>": 151732,
+  "<|reserved_48|>": 151733,
+  "<|reserved_49|>": 151734,
+  "<|reserved_4|>": 151689,
+  "<|reserved_50|>": 151735,
+  "<|reserved_51|>": 151736,
+  "<|reserved_52|>": 151737,
+  "<|reserved_53|>": 151738,
+  "<|reserved_54|>": 151739,
+  "<|reserved_55|>": 151740,
+  "<|reserved_56|>": 151741,
+  "<|reserved_57|>": 151742,
+  "<|reserved_58|>": 151743,
+  "<|reserved_59|>": 151744,
+  "<|reserved_5|>": 151690,
+  "<|reserved_60|>": 151745,
+  "<|reserved_61|>": 151746,
+  "<|reserved_62|>": 151747,
+  "<|reserved_6|>": 151691,
+  "<|reserved_7|>": 151692,
+  "<|reserved_8|>": 151693,
+  "<|reserved_9|>": 151694,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,88 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].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" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- 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' }}
+    {%- endif %}
+    {%- if enable_thinking is defined and enable_thinking is true %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "MiniCPMV"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "openbmb/MiniCPM-V-4_5--configuration_minicpm.MiniCPMVConfig",
+    "AutoModel": "openbmb/MiniCPM-V-4_5--modeling_minicpmv.MiniCPMV",
+    "AutoModelForCausalLM": "openbmb/MiniCPM-V-4_5--modeling_minicpmv.MiniCPMV"
+  },
+  "batch_3d_resampler": true,
+  "batch_vision_input": true,
+  "bos_token_id": 151643,
+  "drop_vision_last_layer": false,
+  "eos_token_id": 151645,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 128,
+  "image_size": 448,
+  "initializer_range": 0.02,
+  "intermediate_size": 128,
+  "layer_types": [
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "minicpmv",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 1,
+  "patch_size": 14,
+  "query_num": 64,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "slice_config": {
+    "max_slice_nums": 9,
+    "model_type": "minicpmv",
+    "patch_size": 14,
+    "scale_resolution": 448
+  },
+  "slice_mode": true,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.56.0.dev0",
+  "use_cache": true,
+  "use_image_id": true,
+  "use_sliding_window": false,
+  "version": 4.5,
+  "vision_batch_size": 16,
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 64,
+    "image_size": 980,
+    "intermediate_size": 128,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 2,
+    "num_channels": 3,
+    "num_hidden_layers": 2,
+    "patch_size": 14
+  },
+  "vocab_size": 151748
+}

generation_config.json

@@ -0,0 +1,17 @@
+{
+  "bos_token_id": 151643,
+  "chat_template_kwargs": {
+    "enable_thinking": false
+  },
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.56.0.dev0",
+  "trust_remote_code": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:312d7bc30c1ba56a4ec67fbceb21ee7d925bd51724d48d36b124acd695ba9dcf
+size 40187760

preprocessor_config.json

@@ -0,0 +1,47 @@
+{
+  "auto_map": {
+    "AutoImageProcessor": "openbmb/MiniCPM-V-4_5--image_processing_minicpmv.MiniCPMVImageProcessor",
+    "AutoProcessor": "openbmb/MiniCPM-V-4_5--processing_minicpmv.MiniCPMVProcessor"
+  },
+  "im_end": "</image>",
+  "im_end_token": "</image>",
+  "im_id_end": "</image_id>",
+  "im_id_start": "<image_id>",
+  "im_start": "<image>",
+  "im_start_token": "<image>",
+  "image_feature_size": 64,
+  "image_processor_type": "MiniCPMVImageProcessor",
+  "max_slice_nums": 9,
+  "mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "norm_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "norm_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "patch_size": 14,
+  "processor_class": "MiniCPMVProcessor",
+  "scale_resolution": 448,
+  "slice_end": "</slice>",
+  "slice_end_token": "</slice>",
+  "slice_mode": true,
+  "slice_start": "<slice>",
+  "slice_start_token": "<slice>",
+  "std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "unk": "<unk>",
+  "unk_token": "<unk>",
+  "use_image_id": true,
+  "version": 2.6
+}

processor_config.json

@@ -0,0 +1,6 @@
+{
+  "auto_map": {
+    "AutoProcessor": "openbmb/MiniCPM-V-4_5--processing_minicpmv.MiniCPMVProcessor"
+  },
+  "processor_class": "MiniCPMVProcessor"
+}

special_tokens_map.json

@@ -0,0 +1,112 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<image>",
+    "</image>",
+    "<ref>",
+    "</ref>",
+    "<box>",
+    "</box>",
+    "<quad>",
+    "</quad>",
+    "<point>",
+    "</point>",
+    "<slice>",
+    "</slice>",
+    "<image_id>",
+    "</image_id>",
+    "<unit>",
+    "</unit>",
+    "<|reserved_0|>",
+    "<|reserved_1|>",
+    "<|reserved_2|>",
+    "<|reserved_3|>",
+    "<|reserved_4|>",
+    "<|reserved_5|>",
+    "<|reserved_6|>",
+    "<|reserved_7|>",
+    "<|reserved_8|>",
+    "<|reserved_9|>",
+    "<|reserved_10|>",
+    "<|reserved_11|>",
+    "<|reserved_12|>",
+    "<|reserved_13|>",
+    "<|reserved_14|>",
+    "<|reserved_15|>",
+    "<|reserved_16|>",
+    "<|reserved_17|>",
+    "<|reserved_18|>",
+    "<|reserved_19|>",
+    "<|reserved_20|>",
+    "<|reserved_21|>",
+    "<|reserved_22|>",
+    "<|reserved_23|>",
+    "<|reserved_24|>",
+    "<|reserved_25|>",
+    "<|reserved_26|>",
+    "<|reserved_27|>",
+    "<|reserved_28|>",
+    "<|reserved_29|>",
+    "<|reserved_30|>",
+    "<|reserved_31|>",
+    "<|reserved_32|>",
+    "<|reserved_33|>",
+    "<|reserved_34|>",
+    "<|reserved_35|>",
+    "<|reserved_36|>",
+    "<|reserved_37|>",
+    "<|reserved_38|>",
+    "<|reserved_39|>",
+    "<|reserved_40|>",
+    "<|reserved_41|>",
+    "<|reserved_42|>",
+    "<|reserved_43|>",
+    "<|reserved_44|>",
+    "<|reserved_45|>",
+    "<|reserved_46|>",
+    "<|reserved_47|>",
+    "<|reserved_48|>",
+    "<|reserved_49|>",
+    "<|reserved_50|>",
+    "<|reserved_51|>",
+    "<|reserved_52|>",
+    "<|reserved_53|>",
+    "<|reserved_54|>",
+    "<|reserved_55|>",
+    "<|reserved_56|>",
+    "<|reserved_57|>",
+    "<|reserved_58|>",
+    "<|reserved_59|>",
+    "<|reserved_60|>",
+    "<|reserved_61|>",
+    "<|reserved_62|>"
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5a94a2c3913b8aa2175fffb5fd6cf4301958f323d06475bfd91037c13bdd74b
+size 11437868

tokenizer_config.json

@@ -0,0 +1,954 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "128244": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151669": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "</image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151671": {
+      "content": "<ref>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151672": {
+      "content": "</ref>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151673": {
+      "content": "<box>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151674": {
+      "content": "</box>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151675": {
+      "content": "<quad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151676": {
+      "content": "</quad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151677": {
+      "content": "<point>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151678": {
+      "content": "</point>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151679": {
+      "content": "<slice>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151680": {
+      "content": "</slice>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151681": {
+      "content": "<image_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151682": {
+      "content": "</image_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151683": {
+      "content": "<unit>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151684": {
+      "content": "</unit>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151685": {
+      "content": "<|reserved_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151686": {
+      "content": "<|reserved_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151687": {
+      "content": "<|reserved_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151688": {
+      "content": "<|reserved_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151689": {
+      "content": "<|reserved_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151690": {
+      "content": "<|reserved_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151691": {
+      "content": "<|reserved_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151692": {
+      "content": "<|reserved_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151693": {
+      "content": "<|reserved_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151694": {
+      "content": "<|reserved_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151695": {
+      "content": "<|reserved_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151696": {
+      "content": "<|reserved_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151697": {
+      "content": "<|reserved_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151698": {
+      "content": "<|reserved_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151699": {
+      "content": "<|reserved_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151700": {
+      "content": "<|reserved_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151701": {
+      "content": "<|reserved_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151702": {
+      "content": "<|reserved_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151703": {
+      "content": "<|reserved_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151704": {
+      "content": "<|reserved_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151705": {
+      "content": "<|reserved_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151706": {
+      "content": "<|reserved_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151707": {
+      "content": "<|reserved_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151708": {
+      "content": "<|reserved_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151709": {
+      "content": "<|reserved_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151710": {
+      "content": "<|reserved_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151711": {
+      "content": "<|reserved_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151712": {
+      "content": "<|reserved_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151713": {
+      "content": "<|reserved_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151714": {
+      "content": "<|reserved_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151715": {
+      "content": "<|reserved_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151716": {
+      "content": "<|reserved_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151717": {
+      "content": "<|reserved_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151718": {
+      "content": "<|reserved_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151719": {
+      "content": "<|reserved_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151720": {
+      "content": "<|reserved_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151721": {
+      "content": "<|reserved_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151722": {
+      "content": "<|reserved_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151723": {
+      "content": "<|reserved_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151724": {
+      "content": "<|reserved_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151725": {
+      "content": "<|reserved_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151726": {
+      "content": "<|reserved_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151727": {
+      "content": "<|reserved_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151728": {
+      "content": "<|reserved_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151729": {
+      "content": "<|reserved_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151730": {
+      "content": "<|reserved_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151731": {
+      "content": "<|reserved_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151732": {
+      "content": "<|reserved_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151733": {
+      "content": "<|reserved_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151734": {
+      "content": "<|reserved_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151735": {
+      "content": "<|reserved_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151736": {
+      "content": "<|reserved_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151737": {
+      "content": "<|reserved_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151738": {
+      "content": "<|reserved_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151739": {
+      "content": "<|reserved_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151740": {
+      "content": "<|reserved_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151741": {
+      "content": "<|reserved_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151742": {
+      "content": "<|reserved_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151743": {
+      "content": "<|reserved_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151744": {
+      "content": "<|reserved_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151745": {
+      "content": "<|reserved_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151746": {
+      "content": "<|reserved_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151747": {
+      "content": "<|reserved_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<image>",
+    "</image>",
+    "<ref>",
+    "</ref>",
+    "<box>",
+    "</box>",
+    "<quad>",
+    "</quad>",
+    "<point>",
+    "</point>",
+    "<slice>",
+    "</slice>",
+    "<image_id>",
+    "</image_id>",
+    "<unit>",
+    "</unit>",
+    "<|reserved_0|>",
+    "<|reserved_1|>",
+    "<|reserved_2|>",
+    "<|reserved_3|>",
+    "<|reserved_4|>",
+    "<|reserved_5|>",
+    "<|reserved_6|>",
+    "<|reserved_7|>",
+    "<|reserved_8|>",
+    "<|reserved_9|>",
+    "<|reserved_10|>",
+    "<|reserved_11|>",
+    "<|reserved_12|>",
+    "<|reserved_13|>",
+    "<|reserved_14|>",
+    "<|reserved_15|>",
+    "<|reserved_16|>",
+    "<|reserved_17|>",
+    "<|reserved_18|>",
+    "<|reserved_19|>",
+    "<|reserved_20|>",
+    "<|reserved_21|>",
+    "<|reserved_22|>",
+    "<|reserved_23|>",
+    "<|reserved_24|>",
+    "<|reserved_25|>",
+    "<|reserved_26|>",
+    "<|reserved_27|>",
+    "<|reserved_28|>",
+    "<|reserved_29|>",
+    "<|reserved_30|>",
+    "<|reserved_31|>",
+    "<|reserved_32|>",
+    "<|reserved_33|>",
+    "<|reserved_34|>",
+    "<|reserved_35|>",
+    "<|reserved_36|>",
+    "<|reserved_37|>",
+    "<|reserved_38|>",
+    "<|reserved_39|>",
+    "<|reserved_40|>",
+    "<|reserved_41|>",
+    "<|reserved_42|>",
+    "<|reserved_43|>",
+    "<|reserved_44|>",
+    "<|reserved_45|>",
+    "<|reserved_46|>",
+    "<|reserved_47|>",
+    "<|reserved_48|>",
+    "<|reserved_49|>",
+    "<|reserved_50|>",
+    "<|reserved_51|>",
+    "<|reserved_52|>",
+    "<|reserved_53|>",
+    "<|reserved_54|>",
+    "<|reserved_55|>",
+    "<|reserved_56|>",
+    "<|reserved_57|>",
+    "<|reserved_58|>",
+    "<|reserved_59|>",
+    "<|reserved_60|>",
+    "<|reserved_61|>",
+    "<|reserved_62|>"
+  ],
+  "auto_map": {
+    "AutoProcessor": "openbmb/MiniCPM-V-4_5--processing_minicpmv.MiniCPMVProcessor",
+    "AutoTokenizer": [
+      "openbmb/MiniCPM-V-4_5--tokenization_qwen2.Qwen2Tokenizer",
+      "openbmb/MiniCPM-V-4_5--tokenization_minicpmv_fast.MiniCPMVTokenizerFast"
+    ]
+  },
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "MiniCPMVProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "MiniCPMVTokenizer",
+  "unk_token": "<unk>"
+}