yujiepan commited on
Commit
7813daa
·
verified ·
1 Parent(s): 2480640

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,145 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ pipeline_tag: image-text-to-text
4
+ inference: true
5
+ widget:
6
+ - text: Hello!
7
+ example_title: Hello world
8
+ group: Python
9
+ base_model:
10
+ - openbmb/MiniCPM-V-4_5
11
+ ---
12
+
13
+ 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).
14
+
15
+ ### Example usage:
16
+
17
+ ```python
18
+ import numpy as np
19
+ import torch
20
+ from PIL import Image
21
+ from transformers import AutoModel, AutoTokenizer
22
+
23
+ model_id = "yujiepan/minicpm-v-4_5-tiny-random"
24
+ model = AutoModel.from_pretrained(model_id, trust_remote_code=True,
25
+ attn_implementation='sdpa', torch_dtype=torch.bfloat16)
26
+ model = model.eval().cuda()
27
+ tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
28
+
29
+ image = Image.fromarray(np.random.randint(0, 255, (224, 224, 3), dtype=np.uint8), 'RGB')
30
+ question = "What is the landform in the picture?"
31
+ msgs = [{'role': 'user', 'content': [image, question]}]
32
+ answer = model.chat(
33
+ msgs=msgs,
34
+ image=image,
35
+ tokenizer=tokenizer,
36
+ max_new_tokens=32,
37
+ )
38
+ print(answer)
39
+
40
+ # Second round chat, pass history context of multi-turn conversation
41
+ msgs.append({"role": "assistant", "content": [answer]})
42
+ msgs.append({"role": "user", "content": [
43
+ "What should I pay attention to when traveling here?"]})
44
+ answer = model.chat(
45
+ msgs=msgs,
46
+ image=None,
47
+ tokenizer=tokenizer,
48
+ max_new_tokens=32,
49
+ )
50
+ print(answer)
51
+ ```
52
+
53
+ ### Codes to create this repo:
54
+
55
+ ```python
56
+ import json
57
+ from pathlib import Path
58
+
59
+ import accelerate
60
+ import torch
61
+ from huggingface_hub import hf_hub_download
62
+ from transformers import (
63
+ AutoConfig,
64
+ AutoModel,
65
+ AutoModelForCausalLM,
66
+ AutoProcessor,
67
+ AutoTokenizer,
68
+ GenerationConfig,
69
+ set_seed,
70
+ )
71
+
72
+ source_model_id = "openbmb/MiniCPM-V-4_5"
73
+ save_folder = "/tmp/yujiepan/minicpm-v-4_5-tiny-random"
74
+
75
+ processor = AutoProcessor.from_pretrained(source_model_id, trust_remote_code=True)
76
+ processor.save_pretrained(save_folder)
77
+
78
+ with open(hf_hub_download(source_model_id, filename='config.json', repo_type='model',), 'r', encoding='utf-8') as f:
79
+ config_json = json.load(f)
80
+ for k, v in config_json['auto_map'].items():
81
+ config_json['auto_map'][k] = f'{source_model_id}--{v}'
82
+ automap = config_json['auto_map']
83
+
84
+ config_json['head_dim'] = 32
85
+ config_json["hidden_size"] = 128 # required by Sampler -- num_heads=embed_dim // 128
86
+ config_json['intermediate_size'] = 128
87
+ config_json['num_attention_heads'] = 2
88
+ config_json['num_key_value_heads'] = 1
89
+ config_json['num_hidden_layers'] = 2
90
+ config_json['tie_word_embeddings'] = True
91
+
92
+ # factor = config_json['rope_scaling']['long_factor']
93
+ # config_json['rope_scaling']['long_factor'] = factor[:16]
94
+ # config_json['rope_scaling']['short_factor'] = factor[:16]
95
+
96
+ config_json['vision_config']['intermediate_size'] = 128
97
+ config_json['vision_config']['hidden_size'] = 64
98
+ config_json['vision_config']['num_attention_heads'] = 2
99
+ config_json['vision_config']['num_hidden_layers'] = 2
100
+
101
+ with open(f"{save_folder}/config.json", "w", encoding='utf-8') as f:
102
+ json.dump(config_json, f, indent=2)
103
+
104
+ config = AutoConfig.from_pretrained(
105
+ save_folder,
106
+ trust_remote_code=True,
107
+ )
108
+ print(config)
109
+ torch.set_default_dtype(torch.bfloat16)
110
+ model = AutoModel.from_config(config, trust_remote_code=True)
111
+ torch.set_default_dtype(torch.float32)
112
+ model.generation_config = GenerationConfig.from_pretrained(
113
+ source_model_id, trust_remote_code=True,
114
+ )
115
+ set_seed(42)
116
+ num_params = sum(p.numel() for p in model.parameters())
117
+ with torch.no_grad():
118
+ for name, p in sorted(model.named_parameters()):
119
+ torch.nn.init.normal_(p, 0, 0.1)
120
+ print(name, p.shape, p.dtype, p.device, f'{p.numel() / num_params * 100: .2f}%')
121
+ pass
122
+ model.save_pretrained(save_folder)
123
+
124
+ def modify_automap(path, source_model_id):
125
+ import json
126
+ with open(path, 'r', encoding='utf-8') as f:
127
+ content = json.load(f)
128
+ automap = {}
129
+ if content.get('auto_map', None) is not None:
130
+ for key, value in content.get('auto_map').items():
131
+ if isinstance(value, str):
132
+ value = source_model_id + '--' + value.split('--')[-1]
133
+ else:
134
+ value = [(source_model_id + '--' + v.split('--')[-1]) for v in value]
135
+ automap[key] = value
136
+ with open(path, 'w', encoding='utf-8') as f:
137
+ json.dump({**content, 'auto_map': automap}, f, indent=2)
138
+
139
+ modify_automap(f"{save_folder}/config.json", source_model_id)
140
+ modify_automap(f'{save_folder}/processor_config.json', source_model_id)
141
+ modify_automap(f'{save_folder}/preprocessor_config.json', source_model_id)
142
+ modify_automap(f'{save_folder}/tokenizer_config.json', source_model_id)
143
+ for f in Path(save_folder).glob('*.py'):
144
+ f.unlink()
145
+ ```
added_tokens.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</box>": 151674,
3
+ "</image>": 151670,
4
+ "</image_id>": 151682,
5
+ "</point>": 151678,
6
+ "</quad>": 151676,
7
+ "</ref>": 151672,
8
+ "</slice>": 151680,
9
+ "</think>": 151668,
10
+ "</tool_call>": 151658,
11
+ "</tool_response>": 151666,
12
+ "</unit>": 151684,
13
+ "<box>": 151673,
14
+ "<image>": 151669,
15
+ "<image_id>": 151681,
16
+ "<point>": 151677,
17
+ "<quad>": 151675,
18
+ "<ref>": 151671,
19
+ "<slice>": 151679,
20
+ "<think>": 151667,
21
+ "<tool_call>": 151657,
22
+ "<tool_response>": 151665,
23
+ "<unit>": 151683,
24
+ "<|box_end|>": 151649,
25
+ "<|box_start|>": 151648,
26
+ "<|endoftext|>": 151643,
27
+ "<|file_sep|>": 151664,
28
+ "<|fim_middle|>": 151660,
29
+ "<|fim_pad|>": 151662,
30
+ "<|fim_prefix|>": 151659,
31
+ "<|fim_suffix|>": 151661,
32
+ "<|im_end|>": 151645,
33
+ "<|im_start|>": 151644,
34
+ "<|image_pad|>": 151655,
35
+ "<|object_ref_end|>": 151647,
36
+ "<|object_ref_start|>": 151646,
37
+ "<|quad_end|>": 151651,
38
+ "<|quad_start|>": 151650,
39
+ "<|repo_name|>": 151663,
40
+ "<|reserved_0|>": 151685,
41
+ "<|reserved_10|>": 151695,
42
+ "<|reserved_11|>": 151696,
43
+ "<|reserved_12|>": 151697,
44
+ "<|reserved_13|>": 151698,
45
+ "<|reserved_14|>": 151699,
46
+ "<|reserved_15|>": 151700,
47
+ "<|reserved_16|>": 151701,
48
+ "<|reserved_17|>": 151702,
49
+ "<|reserved_18|>": 151703,
50
+ "<|reserved_19|>": 151704,
51
+ "<|reserved_1|>": 151686,
52
+ "<|reserved_20|>": 151705,
53
+ "<|reserved_21|>": 151706,
54
+ "<|reserved_22|>": 151707,
55
+ "<|reserved_23|>": 151708,
56
+ "<|reserved_24|>": 151709,
57
+ "<|reserved_25|>": 151710,
58
+ "<|reserved_26|>": 151711,
59
+ "<|reserved_27|>": 151712,
60
+ "<|reserved_28|>": 151713,
61
+ "<|reserved_29|>": 151714,
62
+ "<|reserved_2|>": 151687,
63
+ "<|reserved_30|>": 151715,
64
+ "<|reserved_31|>": 151716,
65
+ "<|reserved_32|>": 151717,
66
+ "<|reserved_33|>": 151718,
67
+ "<|reserved_34|>": 151719,
68
+ "<|reserved_35|>": 151720,
69
+ "<|reserved_36|>": 151721,
70
+ "<|reserved_37|>": 151722,
71
+ "<|reserved_38|>": 151723,
72
+ "<|reserved_39|>": 151724,
73
+ "<|reserved_3|>": 151688,
74
+ "<|reserved_40|>": 151725,
75
+ "<|reserved_41|>": 151726,
76
+ "<|reserved_42|>": 151727,
77
+ "<|reserved_43|>": 151728,
78
+ "<|reserved_44|>": 151729,
79
+ "<|reserved_45|>": 151730,
80
+ "<|reserved_46|>": 151731,
81
+ "<|reserved_47|>": 151732,
82
+ "<|reserved_48|>": 151733,
83
+ "<|reserved_49|>": 151734,
84
+ "<|reserved_4|>": 151689,
85
+ "<|reserved_50|>": 151735,
86
+ "<|reserved_51|>": 151736,
87
+ "<|reserved_52|>": 151737,
88
+ "<|reserved_53|>": 151738,
89
+ "<|reserved_54|>": 151739,
90
+ "<|reserved_55|>": 151740,
91
+ "<|reserved_56|>": 151741,
92
+ "<|reserved_57|>": 151742,
93
+ "<|reserved_58|>": 151743,
94
+ "<|reserved_59|>": 151744,
95
+ "<|reserved_5|>": 151690,
96
+ "<|reserved_60|>": 151745,
97
+ "<|reserved_61|>": 151746,
98
+ "<|reserved_62|>": 151747,
99
+ "<|reserved_6|>": 151691,
100
+ "<|reserved_7|>": 151692,
101
+ "<|reserved_8|>": 151693,
102
+ "<|reserved_9|>": 151694,
103
+ "<|video_pad|>": 151656,
104
+ "<|vision_end|>": 151653,
105
+ "<|vision_pad|>": 151654,
106
+ "<|vision_start|>": 151652
107
+ }
chat_template.jinja ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# 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>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\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" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
27
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
28
+ {%- elif message.role == "assistant" %}
29
+ {%- set content = message.content %}
30
+ {%- set reasoning_content = '' %}
31
+ {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
32
+ {%- set reasoning_content = message.reasoning_content %}
33
+ {%- else %}
34
+ {%- if '</think>' in message.content %}
35
+ {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
36
+ {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
37
+ {%- endif %}
38
+ {%- endif %}
39
+ {%- if loop.index0 > ns.last_query_index %}
40
+ {%- if loop.last or (not loop.last and reasoning_content) %}
41
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
42
+ {%- else %}
43
+ {{- '<|im_start|>' + message.role + '\n' + content }}
44
+ {%- endif %}
45
+ {%- else %}
46
+ {{- '<|im_start|>' + message.role + '\n' + content }}
47
+ {%- endif %}
48
+ {%- if message.tool_calls %}
49
+ {%- for tool_call in message.tool_calls %}
50
+ {%- if (loop.first and content) or (not loop.first) %}
51
+ {{- '\n' }}
52
+ {%- endif %}
53
+ {%- if tool_call.function %}
54
+ {%- set tool_call = tool_call.function %}
55
+ {%- endif %}
56
+ {{- '<tool_call>\n{"name": "' }}
57
+ {{- tool_call.name }}
58
+ {{- '", "arguments": ' }}
59
+ {%- if tool_call.arguments is string %}
60
+ {{- tool_call.arguments }}
61
+ {%- else %}
62
+ {{- tool_call.arguments | tojson }}
63
+ {%- endif %}
64
+ {{- '}\n</tool_call>' }}
65
+ {%- endfor %}
66
+ {%- endif %}
67
+ {{- '<|im_end|>\n' }}
68
+ {%- elif message.role == "tool" %}
69
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
70
+ {{- '<|im_start|>user' }}
71
+ {%- endif %}
72
+ {{- '\n<tool_response>\n' }}
73
+ {{- message.content }}
74
+ {{- '\n</tool_response>' }}
75
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
76
+ {{- '<|im_end|>\n' }}
77
+ {%- endif %}
78
+ {%- endif %}
79
+ {%- endfor %}
80
+ {%- if add_generation_prompt %}
81
+ {{- '<|im_start|>assistant\n' }}
82
+ {%- if enable_thinking is defined and enable_thinking is false %}
83
+ {{- '<think>\n\n</think>\n\n' }}
84
+ {%- endif %}
85
+ {%- if enable_thinking is defined and enable_thinking is true %}
86
+ {{- '<think>\n' }}
87
+ {%- endif %}
88
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MiniCPMV"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "openbmb/MiniCPM-V-4_5--configuration_minicpm.MiniCPMVConfig",
9
+ "AutoModel": "openbmb/MiniCPM-V-4_5--modeling_minicpmv.MiniCPMV",
10
+ "AutoModelForCausalLM": "openbmb/MiniCPM-V-4_5--modeling_minicpmv.MiniCPMV"
11
+ },
12
+ "batch_3d_resampler": true,
13
+ "batch_vision_input": true,
14
+ "bos_token_id": 151643,
15
+ "drop_vision_last_layer": false,
16
+ "eos_token_id": 151645,
17
+ "head_dim": 32,
18
+ "hidden_act": "silu",
19
+ "hidden_size": 128,
20
+ "image_size": 448,
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 128,
23
+ "layer_types": [
24
+ "full_attention",
25
+ "full_attention"
26
+ ],
27
+ "max_position_embeddings": 40960,
28
+ "max_window_layers": 36,
29
+ "model_type": "minicpmv",
30
+ "num_attention_heads": 2,
31
+ "num_hidden_layers": 2,
32
+ "num_key_value_heads": 1,
33
+ "patch_size": 14,
34
+ "query_num": 64,
35
+ "rms_norm_eps": 1e-06,
36
+ "rope_scaling": null,
37
+ "rope_theta": 1000000,
38
+ "slice_config": {
39
+ "max_slice_nums": 9,
40
+ "model_type": "minicpmv",
41
+ "patch_size": 14,
42
+ "scale_resolution": 448
43
+ },
44
+ "slice_mode": true,
45
+ "sliding_window": null,
46
+ "tie_word_embeddings": true,
47
+ "torch_dtype": "bfloat16",
48
+ "transformers_version": "4.56.0.dev0",
49
+ "use_cache": true,
50
+ "use_image_id": true,
51
+ "use_sliding_window": false,
52
+ "version": 4.5,
53
+ "vision_batch_size": 16,
54
+ "vision_config": {
55
+ "attention_dropout": 0.0,
56
+ "hidden_act": "gelu_pytorch_tanh",
57
+ "hidden_size": 64,
58
+ "image_size": 980,
59
+ "intermediate_size": 128,
60
+ "layer_norm_eps": 1e-06,
61
+ "model_type": "siglip_vision_model",
62
+ "num_attention_heads": 2,
63
+ "num_channels": 3,
64
+ "num_hidden_layers": 2,
65
+ "patch_size": 14
66
+ },
67
+ "vocab_size": 151748
68
+ }
generation_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "chat_template_kwargs": {
4
+ "enable_thinking": false
5
+ },
6
+ "do_sample": true,
7
+ "eos_token_id": [
8
+ 151645,
9
+ 151643
10
+ ],
11
+ "pad_token_id": 151643,
12
+ "temperature": 0.6,
13
+ "top_k": 20,
14
+ "top_p": 0.95,
15
+ "transformers_version": "4.56.0.dev0",
16
+ "trust_remote_code": true
17
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:312d7bc30c1ba56a4ec67fbceb21ee7d925bd51724d48d36b124acd695ba9dcf
3
+ size 40187760
preprocessor_config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_map": {
3
+ "AutoImageProcessor": "openbmb/MiniCPM-V-4_5--image_processing_minicpmv.MiniCPMVImageProcessor",
4
+ "AutoProcessor": "openbmb/MiniCPM-V-4_5--processing_minicpmv.MiniCPMVProcessor"
5
+ },
6
+ "im_end": "</image>",
7
+ "im_end_token": "</image>",
8
+ "im_id_end": "</image_id>",
9
+ "im_id_start": "<image_id>",
10
+ "im_start": "<image>",
11
+ "im_start_token": "<image>",
12
+ "image_feature_size": 64,
13
+ "image_processor_type": "MiniCPMVImageProcessor",
14
+ "max_slice_nums": 9,
15
+ "mean": [
16
+ 0.5,
17
+ 0.5,
18
+ 0.5
19
+ ],
20
+ "norm_mean": [
21
+ 0.5,
22
+ 0.5,
23
+ 0.5
24
+ ],
25
+ "norm_std": [
26
+ 0.5,
27
+ 0.5,
28
+ 0.5
29
+ ],
30
+ "patch_size": 14,
31
+ "processor_class": "MiniCPMVProcessor",
32
+ "scale_resolution": 448,
33
+ "slice_end": "</slice>",
34
+ "slice_end_token": "</slice>",
35
+ "slice_mode": true,
36
+ "slice_start": "<slice>",
37
+ "slice_start_token": "<slice>",
38
+ "std": [
39
+ 0.5,
40
+ 0.5,
41
+ 0.5
42
+ ],
43
+ "unk": "<unk>",
44
+ "unk_token": "<unk>",
45
+ "use_image_id": true,
46
+ "version": 2.6
47
+ }
processor_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "auto_map": {
3
+ "AutoProcessor": "openbmb/MiniCPM-V-4_5--processing_minicpmv.MiniCPMVProcessor"
4
+ },
5
+ "processor_class": "MiniCPMVProcessor"
6
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<image>",
5
+ "</image>",
6
+ "<ref>",
7
+ "</ref>",
8
+ "<box>",
9
+ "</box>",
10
+ "<quad>",
11
+ "</quad>",
12
+ "<point>",
13
+ "</point>",
14
+ "<slice>",
15
+ "</slice>",
16
+ "<image_id>",
17
+ "</image_id>",
18
+ "<unit>",
19
+ "</unit>",
20
+ "<|reserved_0|>",
21
+ "<|reserved_1|>",
22
+ "<|reserved_2|>",
23
+ "<|reserved_3|>",
24
+ "<|reserved_4|>",
25
+ "<|reserved_5|>",
26
+ "<|reserved_6|>",
27
+ "<|reserved_7|>",
28
+ "<|reserved_8|>",
29
+ "<|reserved_9|>",
30
+ "<|reserved_10|>",
31
+ "<|reserved_11|>",
32
+ "<|reserved_12|>",
33
+ "<|reserved_13|>",
34
+ "<|reserved_14|>",
35
+ "<|reserved_15|>",
36
+ "<|reserved_16|>",
37
+ "<|reserved_17|>",
38
+ "<|reserved_18|>",
39
+ "<|reserved_19|>",
40
+ "<|reserved_20|>",
41
+ "<|reserved_21|>",
42
+ "<|reserved_22|>",
43
+ "<|reserved_23|>",
44
+ "<|reserved_24|>",
45
+ "<|reserved_25|>",
46
+ "<|reserved_26|>",
47
+ "<|reserved_27|>",
48
+ "<|reserved_28|>",
49
+ "<|reserved_29|>",
50
+ "<|reserved_30|>",
51
+ "<|reserved_31|>",
52
+ "<|reserved_32|>",
53
+ "<|reserved_33|>",
54
+ "<|reserved_34|>",
55
+ "<|reserved_35|>",
56
+ "<|reserved_36|>",
57
+ "<|reserved_37|>",
58
+ "<|reserved_38|>",
59
+ "<|reserved_39|>",
60
+ "<|reserved_40|>",
61
+ "<|reserved_41|>",
62
+ "<|reserved_42|>",
63
+ "<|reserved_43|>",
64
+ "<|reserved_44|>",
65
+ "<|reserved_45|>",
66
+ "<|reserved_46|>",
67
+ "<|reserved_47|>",
68
+ "<|reserved_48|>",
69
+ "<|reserved_49|>",
70
+ "<|reserved_50|>",
71
+ "<|reserved_51|>",
72
+ "<|reserved_52|>",
73
+ "<|reserved_53|>",
74
+ "<|reserved_54|>",
75
+ "<|reserved_55|>",
76
+ "<|reserved_56|>",
77
+ "<|reserved_57|>",
78
+ "<|reserved_58|>",
79
+ "<|reserved_59|>",
80
+ "<|reserved_60|>",
81
+ "<|reserved_61|>",
82
+ "<|reserved_62|>"
83
+ ],
84
+ "bos_token": {
85
+ "content": "<|im_start|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false
90
+ },
91
+ "eos_token": {
92
+ "content": "<|im_end|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false
97
+ },
98
+ "pad_token": {
99
+ "content": "<|endoftext|>",
100
+ "lstrip": false,
101
+ "normalized": false,
102
+ "rstrip": false,
103
+ "single_word": false
104
+ },
105
+ "unk_token": {
106
+ "content": "<unk>",
107
+ "lstrip": false,
108
+ "normalized": false,
109
+ "rstrip": false,
110
+ "single_word": false
111
+ }
112
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5a94a2c3913b8aa2175fffb5fd6cf4301958f323d06475bfd91037c13bdd74b
3
+ size 11437868
tokenizer_config.json ADDED
@@ -0,0 +1,954 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "128244": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151643": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151644": {
22
+ "content": "<|im_start|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151645": {
30
+ "content": "<|im_end|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151646": {
38
+ "content": "<|object_ref_start|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151647": {
46
+ "content": "<|object_ref_end|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151648": {
54
+ "content": "<|box_start|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151649": {
62
+ "content": "<|box_end|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151650": {
70
+ "content": "<|quad_start|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151651": {
78
+ "content": "<|quad_end|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151652": {
86
+ "content": "<|vision_start|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151653": {
94
+ "content": "<|vision_end|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151654": {
102
+ "content": "<|vision_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151655": {
110
+ "content": "<|image_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151656": {
118
+ "content": "<|video_pad|>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "151657": {
126
+ "content": "<tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151658": {
134
+ "content": "</tool_call>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151659": {
142
+ "content": "<|fim_prefix|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151660": {
150
+ "content": "<|fim_middle|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151661": {
158
+ "content": "<|fim_suffix|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151662": {
166
+ "content": "<|fim_pad|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151663": {
174
+ "content": "<|repo_name|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151664": {
182
+ "content": "<|file_sep|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151665": {
190
+ "content": "<tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151666": {
198
+ "content": "</tool_response>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151667": {
206
+ "content": "<think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "151668": {
214
+ "content": "</think>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": false
220
+ },
221
+ "151669": {
222
+ "content": "<image>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "151670": {
230
+ "content": "</image>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "151671": {
238
+ "content": "<ref>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "151672": {
246
+ "content": "</ref>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "151673": {
254
+ "content": "<box>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "151674": {
262
+ "content": "</box>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "151675": {
270
+ "content": "<quad>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "151676": {
278
+ "content": "</quad>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "151677": {
286
+ "content": "<point>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "151678": {
294
+ "content": "</point>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "151679": {
302
+ "content": "<slice>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "151680": {
310
+ "content": "</slice>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "151681": {
318
+ "content": "<image_id>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "151682": {
326
+ "content": "</image_id>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": true
332
+ },
333
+ "151683": {
334
+ "content": "<unit>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": true
340
+ },
341
+ "151684": {
342
+ "content": "</unit>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": true
348
+ },
349
+ "151685": {
350
+ "content": "<|reserved_0|>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": true
356
+ },
357
+ "151686": {
358
+ "content": "<|reserved_1|>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": true
364
+ },
365
+ "151687": {
366
+ "content": "<|reserved_2|>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": true
372
+ },
373
+ "151688": {
374
+ "content": "<|reserved_3|>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": true
380
+ },
381
+ "151689": {
382
+ "content": "<|reserved_4|>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": true
388
+ },
389
+ "151690": {
390
+ "content": "<|reserved_5|>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": true
396
+ },
397
+ "151691": {
398
+ "content": "<|reserved_6|>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": true
404
+ },
405
+ "151692": {
406
+ "content": "<|reserved_7|>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": true
412
+ },
413
+ "151693": {
414
+ "content": "<|reserved_8|>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": true
420
+ },
421
+ "151694": {
422
+ "content": "<|reserved_9|>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": true
428
+ },
429
+ "151695": {
430
+ "content": "<|reserved_10|>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": true
436
+ },
437
+ "151696": {
438
+ "content": "<|reserved_11|>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": true
444
+ },
445
+ "151697": {
446
+ "content": "<|reserved_12|>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": true
452
+ },
453
+ "151698": {
454
+ "content": "<|reserved_13|>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": true
460
+ },
461
+ "151699": {
462
+ "content": "<|reserved_14|>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": true
468
+ },
469
+ "151700": {
470
+ "content": "<|reserved_15|>",
471
+ "lstrip": false,
472
+ "normalized": false,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": true
476
+ },
477
+ "151701": {
478
+ "content": "<|reserved_16|>",
479
+ "lstrip": false,
480
+ "normalized": false,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": true
484
+ },
485
+ "151702": {
486
+ "content": "<|reserved_17|>",
487
+ "lstrip": false,
488
+ "normalized": false,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": true
492
+ },
493
+ "151703": {
494
+ "content": "<|reserved_18|>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": true
500
+ },
501
+ "151704": {
502
+ "content": "<|reserved_19|>",
503
+ "lstrip": false,
504
+ "normalized": false,
505
+ "rstrip": false,
506
+ "single_word": false,
507
+ "special": true
508
+ },
509
+ "151705": {
510
+ "content": "<|reserved_20|>",
511
+ "lstrip": false,
512
+ "normalized": false,
513
+ "rstrip": false,
514
+ "single_word": false,
515
+ "special": true
516
+ },
517
+ "151706": {
518
+ "content": "<|reserved_21|>",
519
+ "lstrip": false,
520
+ "normalized": false,
521
+ "rstrip": false,
522
+ "single_word": false,
523
+ "special": true
524
+ },
525
+ "151707": {
526
+ "content": "<|reserved_22|>",
527
+ "lstrip": false,
528
+ "normalized": false,
529
+ "rstrip": false,
530
+ "single_word": false,
531
+ "special": true
532
+ },
533
+ "151708": {
534
+ "content": "<|reserved_23|>",
535
+ "lstrip": false,
536
+ "normalized": false,
537
+ "rstrip": false,
538
+ "single_word": false,
539
+ "special": true
540
+ },
541
+ "151709": {
542
+ "content": "<|reserved_24|>",
543
+ "lstrip": false,
544
+ "normalized": false,
545
+ "rstrip": false,
546
+ "single_word": false,
547
+ "special": true
548
+ },
549
+ "151710": {
550
+ "content": "<|reserved_25|>",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false,
555
+ "special": true
556
+ },
557
+ "151711": {
558
+ "content": "<|reserved_26|>",
559
+ "lstrip": false,
560
+ "normalized": false,
561
+ "rstrip": false,
562
+ "single_word": false,
563
+ "special": true
564
+ },
565
+ "151712": {
566
+ "content": "<|reserved_27|>",
567
+ "lstrip": false,
568
+ "normalized": false,
569
+ "rstrip": false,
570
+ "single_word": false,
571
+ "special": true
572
+ },
573
+ "151713": {
574
+ "content": "<|reserved_28|>",
575
+ "lstrip": false,
576
+ "normalized": false,
577
+ "rstrip": false,
578
+ "single_word": false,
579
+ "special": true
580
+ },
581
+ "151714": {
582
+ "content": "<|reserved_29|>",
583
+ "lstrip": false,
584
+ "normalized": false,
585
+ "rstrip": false,
586
+ "single_word": false,
587
+ "special": true
588
+ },
589
+ "151715": {
590
+ "content": "<|reserved_30|>",
591
+ "lstrip": false,
592
+ "normalized": false,
593
+ "rstrip": false,
594
+ "single_word": false,
595
+ "special": true
596
+ },
597
+ "151716": {
598
+ "content": "<|reserved_31|>",
599
+ "lstrip": false,
600
+ "normalized": false,
601
+ "rstrip": false,
602
+ "single_word": false,
603
+ "special": true
604
+ },
605
+ "151717": {
606
+ "content": "<|reserved_32|>",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false,
611
+ "special": true
612
+ },
613
+ "151718": {
614
+ "content": "<|reserved_33|>",
615
+ "lstrip": false,
616
+ "normalized": false,
617
+ "rstrip": false,
618
+ "single_word": false,
619
+ "special": true
620
+ },
621
+ "151719": {
622
+ "content": "<|reserved_34|>",
623
+ "lstrip": false,
624
+ "normalized": false,
625
+ "rstrip": false,
626
+ "single_word": false,
627
+ "special": true
628
+ },
629
+ "151720": {
630
+ "content": "<|reserved_35|>",
631
+ "lstrip": false,
632
+ "normalized": false,
633
+ "rstrip": false,
634
+ "single_word": false,
635
+ "special": true
636
+ },
637
+ "151721": {
638
+ "content": "<|reserved_36|>",
639
+ "lstrip": false,
640
+ "normalized": false,
641
+ "rstrip": false,
642
+ "single_word": false,
643
+ "special": true
644
+ },
645
+ "151722": {
646
+ "content": "<|reserved_37|>",
647
+ "lstrip": false,
648
+ "normalized": false,
649
+ "rstrip": false,
650
+ "single_word": false,
651
+ "special": true
652
+ },
653
+ "151723": {
654
+ "content": "<|reserved_38|>",
655
+ "lstrip": false,
656
+ "normalized": false,
657
+ "rstrip": false,
658
+ "single_word": false,
659
+ "special": true
660
+ },
661
+ "151724": {
662
+ "content": "<|reserved_39|>",
663
+ "lstrip": false,
664
+ "normalized": false,
665
+ "rstrip": false,
666
+ "single_word": false,
667
+ "special": true
668
+ },
669
+ "151725": {
670
+ "content": "<|reserved_40|>",
671
+ "lstrip": false,
672
+ "normalized": false,
673
+ "rstrip": false,
674
+ "single_word": false,
675
+ "special": true
676
+ },
677
+ "151726": {
678
+ "content": "<|reserved_41|>",
679
+ "lstrip": false,
680
+ "normalized": false,
681
+ "rstrip": false,
682
+ "single_word": false,
683
+ "special": true
684
+ },
685
+ "151727": {
686
+ "content": "<|reserved_42|>",
687
+ "lstrip": false,
688
+ "normalized": false,
689
+ "rstrip": false,
690
+ "single_word": false,
691
+ "special": true
692
+ },
693
+ "151728": {
694
+ "content": "<|reserved_43|>",
695
+ "lstrip": false,
696
+ "normalized": false,
697
+ "rstrip": false,
698
+ "single_word": false,
699
+ "special": true
700
+ },
701
+ "151729": {
702
+ "content": "<|reserved_44|>",
703
+ "lstrip": false,
704
+ "normalized": false,
705
+ "rstrip": false,
706
+ "single_word": false,
707
+ "special": true
708
+ },
709
+ "151730": {
710
+ "content": "<|reserved_45|>",
711
+ "lstrip": false,
712
+ "normalized": false,
713
+ "rstrip": false,
714
+ "single_word": false,
715
+ "special": true
716
+ },
717
+ "151731": {
718
+ "content": "<|reserved_46|>",
719
+ "lstrip": false,
720
+ "normalized": false,
721
+ "rstrip": false,
722
+ "single_word": false,
723
+ "special": true
724
+ },
725
+ "151732": {
726
+ "content": "<|reserved_47|>",
727
+ "lstrip": false,
728
+ "normalized": false,
729
+ "rstrip": false,
730
+ "single_word": false,
731
+ "special": true
732
+ },
733
+ "151733": {
734
+ "content": "<|reserved_48|>",
735
+ "lstrip": false,
736
+ "normalized": false,
737
+ "rstrip": false,
738
+ "single_word": false,
739
+ "special": true
740
+ },
741
+ "151734": {
742
+ "content": "<|reserved_49|>",
743
+ "lstrip": false,
744
+ "normalized": false,
745
+ "rstrip": false,
746
+ "single_word": false,
747
+ "special": true
748
+ },
749
+ "151735": {
750
+ "content": "<|reserved_50|>",
751
+ "lstrip": false,
752
+ "normalized": false,
753
+ "rstrip": false,
754
+ "single_word": false,
755
+ "special": true
756
+ },
757
+ "151736": {
758
+ "content": "<|reserved_51|>",
759
+ "lstrip": false,
760
+ "normalized": false,
761
+ "rstrip": false,
762
+ "single_word": false,
763
+ "special": true
764
+ },
765
+ "151737": {
766
+ "content": "<|reserved_52|>",
767
+ "lstrip": false,
768
+ "normalized": false,
769
+ "rstrip": false,
770
+ "single_word": false,
771
+ "special": true
772
+ },
773
+ "151738": {
774
+ "content": "<|reserved_53|>",
775
+ "lstrip": false,
776
+ "normalized": false,
777
+ "rstrip": false,
778
+ "single_word": false,
779
+ "special": true
780
+ },
781
+ "151739": {
782
+ "content": "<|reserved_54|>",
783
+ "lstrip": false,
784
+ "normalized": false,
785
+ "rstrip": false,
786
+ "single_word": false,
787
+ "special": true
788
+ },
789
+ "151740": {
790
+ "content": "<|reserved_55|>",
791
+ "lstrip": false,
792
+ "normalized": false,
793
+ "rstrip": false,
794
+ "single_word": false,
795
+ "special": true
796
+ },
797
+ "151741": {
798
+ "content": "<|reserved_56|>",
799
+ "lstrip": false,
800
+ "normalized": false,
801
+ "rstrip": false,
802
+ "single_word": false,
803
+ "special": true
804
+ },
805
+ "151742": {
806
+ "content": "<|reserved_57|>",
807
+ "lstrip": false,
808
+ "normalized": false,
809
+ "rstrip": false,
810
+ "single_word": false,
811
+ "special": true
812
+ },
813
+ "151743": {
814
+ "content": "<|reserved_58|>",
815
+ "lstrip": false,
816
+ "normalized": false,
817
+ "rstrip": false,
818
+ "single_word": false,
819
+ "special": true
820
+ },
821
+ "151744": {
822
+ "content": "<|reserved_59|>",
823
+ "lstrip": false,
824
+ "normalized": false,
825
+ "rstrip": false,
826
+ "single_word": false,
827
+ "special": true
828
+ },
829
+ "151745": {
830
+ "content": "<|reserved_60|>",
831
+ "lstrip": false,
832
+ "normalized": false,
833
+ "rstrip": false,
834
+ "single_word": false,
835
+ "special": true
836
+ },
837
+ "151746": {
838
+ "content": "<|reserved_61|>",
839
+ "lstrip": false,
840
+ "normalized": false,
841
+ "rstrip": false,
842
+ "single_word": false,
843
+ "special": true
844
+ },
845
+ "151747": {
846
+ "content": "<|reserved_62|>",
847
+ "lstrip": false,
848
+ "normalized": false,
849
+ "rstrip": false,
850
+ "single_word": false,
851
+ "special": true
852
+ }
853
+ },
854
+ "additional_special_tokens": [
855
+ "<unk>",
856
+ "<image>",
857
+ "</image>",
858
+ "<ref>",
859
+ "</ref>",
860
+ "<box>",
861
+ "</box>",
862
+ "<quad>",
863
+ "</quad>",
864
+ "<point>",
865
+ "</point>",
866
+ "<slice>",
867
+ "</slice>",
868
+ "<image_id>",
869
+ "</image_id>",
870
+ "<unit>",
871
+ "</unit>",
872
+ "<|reserved_0|>",
873
+ "<|reserved_1|>",
874
+ "<|reserved_2|>",
875
+ "<|reserved_3|>",
876
+ "<|reserved_4|>",
877
+ "<|reserved_5|>",
878
+ "<|reserved_6|>",
879
+ "<|reserved_7|>",
880
+ "<|reserved_8|>",
881
+ "<|reserved_9|>",
882
+ "<|reserved_10|>",
883
+ "<|reserved_11|>",
884
+ "<|reserved_12|>",
885
+ "<|reserved_13|>",
886
+ "<|reserved_14|>",
887
+ "<|reserved_15|>",
888
+ "<|reserved_16|>",
889
+ "<|reserved_17|>",
890
+ "<|reserved_18|>",
891
+ "<|reserved_19|>",
892
+ "<|reserved_20|>",
893
+ "<|reserved_21|>",
894
+ "<|reserved_22|>",
895
+ "<|reserved_23|>",
896
+ "<|reserved_24|>",
897
+ "<|reserved_25|>",
898
+ "<|reserved_26|>",
899
+ "<|reserved_27|>",
900
+ "<|reserved_28|>",
901
+ "<|reserved_29|>",
902
+ "<|reserved_30|>",
903
+ "<|reserved_31|>",
904
+ "<|reserved_32|>",
905
+ "<|reserved_33|>",
906
+ "<|reserved_34|>",
907
+ "<|reserved_35|>",
908
+ "<|reserved_36|>",
909
+ "<|reserved_37|>",
910
+ "<|reserved_38|>",
911
+ "<|reserved_39|>",
912
+ "<|reserved_40|>",
913
+ "<|reserved_41|>",
914
+ "<|reserved_42|>",
915
+ "<|reserved_43|>",
916
+ "<|reserved_44|>",
917
+ "<|reserved_45|>",
918
+ "<|reserved_46|>",
919
+ "<|reserved_47|>",
920
+ "<|reserved_48|>",
921
+ "<|reserved_49|>",
922
+ "<|reserved_50|>",
923
+ "<|reserved_51|>",
924
+ "<|reserved_52|>",
925
+ "<|reserved_53|>",
926
+ "<|reserved_54|>",
927
+ "<|reserved_55|>",
928
+ "<|reserved_56|>",
929
+ "<|reserved_57|>",
930
+ "<|reserved_58|>",
931
+ "<|reserved_59|>",
932
+ "<|reserved_60|>",
933
+ "<|reserved_61|>",
934
+ "<|reserved_62|>"
935
+ ],
936
+ "auto_map": {
937
+ "AutoProcessor": "openbmb/MiniCPM-V-4_5--processing_minicpmv.MiniCPMVProcessor",
938
+ "AutoTokenizer": [
939
+ "openbmb/MiniCPM-V-4_5--tokenization_qwen2.Qwen2Tokenizer",
940
+ "openbmb/MiniCPM-V-4_5--tokenization_minicpmv_fast.MiniCPMVTokenizerFast"
941
+ ]
942
+ },
943
+ "bos_token": "<|im_start|>",
944
+ "clean_up_tokenization_spaces": false,
945
+ "eos_token": "<|im_end|>",
946
+ "errors": "replace",
947
+ "extra_special_tokens": {},
948
+ "model_max_length": 131072,
949
+ "pad_token": "<|endoftext|>",
950
+ "processor_class": "MiniCPMVProcessor",
951
+ "split_special_tokens": false,
952
+ "tokenizer_class": "MiniCPMVTokenizer",
953
+ "unk_token": "<unk>"
954
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff