Hugging Face's logo

hf-internal-testing
/
tiny-processor-minicpm-ocr

minicpm_ocr
Model card Files
xet
 Community
guarin HF Staff commited on
Commit
7e7f209
·
verified ·
1 Parent(s): 1c20a6a

Copy of openbmb/tiny-processor-minicpm-ocr

Browse files
Files changed (7) hide show
  1. chat_template.jinja +154 -0
  2. config.json +92 -0
  3. preprocessor_config.json +20 -0
  4. processor_config.json +3 -0
  5. tokenizer.json +1 -0
  6. tokenizer_config.json +41 -0
  7. video_preprocessor_config.json +20 -0
chat_template.jinja ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set image_count = namespace(value=0) %}
2
+ {%- set video_count = namespace(value=0) %}
3
+ {%- macro render_content(content, do_vision_count, is_system_content=false) %}
4
+ {%- if content is string %}
5
+ {{- content }}
6
+ {%- elif content is iterable and content is not mapping %}
7
+ {%- for item in content %}
8
+ {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
9
+ {%- if is_system_content %}
10
+ {{- raise_exception('System message cannot contain images.') }}
11
+ {%- endif %}
12
+ {%- if do_vision_count %}
13
+ {%- set image_count.value = image_count.value + 1 %}
14
+ {%- endif %}
15
+ {%- if add_vision_id %}
16
+ {{- 'Picture ' ~ image_count.value ~ ': ' }}
17
+ {%- endif %}
18
+ {{- '<|image_pad|>\n' }}
19
+ {%- elif 'video' in item or item.type == 'video' %}
20
+ {%- if is_system_content %}
21
+ {{- raise_exception('System message cannot contain videos.') }}
22
+ {%- endif %}
23
+ {%- if do_vision_count %}
24
+ {%- set video_count.value = video_count.value + 1 %}
25
+ {%- endif %}
26
+ {%- if add_vision_id %}
27
+ {{- 'Video ' ~ video_count.value ~ ': ' }}
28
+ {%- endif %}
29
+ {{- '<|video_pad|>' }}
30
+ {%- elif 'text' in item %}
31
+ {{- item.text }}
32
+ {%- else %}
33
+ {{- raise_exception('Unexpected item type in content.') }}
34
+ {%- endif %}
35
+ {%- endfor %}
36
+ {%- elif content is none or content is undefined %}
37
+ {{- '' }}
38
+ {%- else %}
39
+ {{- raise_exception('Unexpected content type.') }}
40
+ {%- endif %}
41
+ {%- endmacro %}
42
+ {%- if not messages %}
43
+ {{- raise_exception('No messages provided.') }}
44
+ {%- endif %}
45
+ {%- if tools and tools is iterable and tools is not mapping %}
46
+ {{- '<|im_start|>system\n' }}
47
+ {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
48
+ {%- for tool in tools %}
49
+ {{- "\n" }}
50
+ {{- tool | tojson }}
51
+ {%- endfor %}
52
+ {{- "\n</tools>" }}
53
+ {{- '\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>' }}
54
+ {%- if messages[0].role == 'system' %}
55
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
56
+ {%- if content %}
57
+ {{- '\n\n' + content }}
58
+ {%- endif %}
59
+ {%- endif %}
60
+ {{- '<|im_end|>\n' }}
61
+ {%- else %}
62
+ {%- if messages[0].role == 'system' %}
63
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
64
+ {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
65
+ {%- endif %}
66
+ {%- endif %}
67
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
68
+ {%- for message in messages[::-1] %}
69
+ {%- set index = (messages|length - 1) - loop.index0 %}
70
+ {%- if ns.multi_step_tool and message.role == "user" %}
71
+ {%- set content = render_content(message.content, false)|trim %}
72
+ {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
73
+ {%- set ns.multi_step_tool = false %}
74
+ {%- set ns.last_query_index = index %}
75
+ {%- endif %}
76
+ {%- endif %}
77
+ {%- endfor %}
78
+ {%- if ns.multi_step_tool %}
79
+ {{- raise_exception('No user query found in messages.') }}
80
+ {%- endif %}
81
+ {%- for message in messages %}
82
+ {%- set content = render_content(message.content, true)|trim %}
83
+ {%- if message.role == "system" %}
84
+ {%- if not loop.first %}
85
+ {{- raise_exception('System message must be at the beginning.') }}
86
+ {%- endif %}
87
+ {%- elif message.role == "user" %}
88
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
89
+ {%- elif message.role == "assistant" %}
90
+ {%- set reasoning_content = '' %}
91
+ {%- if message.reasoning_content is string %}
92
+ {%- set reasoning_content = message.reasoning_content %}
93
+ {%- else %}
94
+ {%- if '</think>' in content %}
95
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
96
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
97
+ {%- endif %}
98
+ {%- endif %}
99
+ {%- set reasoning_content = reasoning_content|trim %}
100
+ {%- if loop.index0 > ns.last_query_index %}
101
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
102
+ {%- else %}
103
+ {{- '<|im_start|>' + message.role + '\n' + content }}
104
+ {%- endif %}
105
+ {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
106
+ {%- for tool_call in message.tool_calls %}
107
+ {%- if tool_call.function is defined %}
108
+ {%- set tool_call = tool_call.function %}
109
+ {%- endif %}
110
+ {%- if loop.first %}
111
+ {%- if content|trim %}
112
+ {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
113
+ {%- else %}
114
+ {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
115
+ {%- endif %}
116
+ {%- else %}
117
+ {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
118
+ {%- endif %}
119
+ {%- if tool_call.arguments is defined %}
120
+ {%- for args_name, args_value in tool_call.arguments|items %}
121
+ {{- '<parameter=' + args_name + '>\n' }}
122
+ {%- 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 %}
123
+ {{- args_value }}
124
+ {{- '\n</parameter>\n' }}
125
+ {%- endfor %}
126
+ {%- endif %}
127
+ {{- '</function>\n</tool_call>' }}
128
+ {%- endfor %}
129
+ {%- endif %}
130
+ {{- '<|im_end|>\n' }}
131
+ {%- elif message.role == "tool" %}
132
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
133
+ {{- '<|im_start|>user' }}
134
+ {%- endif %}
135
+ {{- '\n<tool_response>\n' }}
136
+ {{- content }}
137
+ {{- '\n</tool_response>' }}
138
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
139
+ {{- '<|im_end|>\n' }}
140
+ {%- elif loop.last %}
141
+ {{- '<|im_end|>\n' }}
142
+ {%- endif %}
143
+ {%- else %}
144
+ {{- raise_exception('Unexpected message role.') }}
145
+ {%- endif %}
146
+ {%- endfor %}
147
+ {%- if add_generation_prompt %}
148
+ {{- '<|im_start|>assistant\n' }}
149
+ {%- if enable_thinking is defined and enable_thinking is true %}
150
+ {{- '<think>\n' }}
151
+ {%- else %}
152
+ {{- '<think>\n\n</think>\n\n' }}
153
+ {%- endif %}
154
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MiniCPMOcrForConditionalGeneration"
4
+ ],
5
+ "bos_token_id": 501,
6
+ "downsample_mode": "4x",
7
+ "eos_token_id": 502,
8
+ "image_size": 1120,
9
+ "model_type": "minicpm_ocr",
10
+ "pad_token_id": 248044,
11
+ "tie_word_embeddings": true,
12
+ "transformers_version": "5.2.0",
13
+ "use_cache": true,
14
+ "vision_config": {
15
+ "attention_dropout": 0.0,
16
+ "hidden_act": "gelu_pytorch_tanh",
17
+ "hidden_size": 1152,
18
+ "image_size": 980,
19
+ "intermediate_size": 4304,
20
+ "layer_norm_eps": 1e-06,
21
+ "model_type": "minicpm_ocr_vision",
22
+ "num_attention_heads": 16,
23
+ "num_channels": 3,
24
+ "num_hidden_layers": 27,
25
+ "patch_size": 14
26
+ },
27
+ "text_config": {
28
+ "attention_bias": false,
29
+ "attention_dropout": 0.0,
30
+ "attn_output_gate": true,
31
+ "full_attention_interval": 4,
32
+ "head_dim": 256,
33
+ "hidden_act": "silu",
34
+ "hidden_size": 1024,
35
+ "initializer_range": 0.02,
36
+ "intermediate_size": 3584,
37
+ "layer_types": [
38
+ "linear_attention",
39
+ "linear_attention",
40
+ "linear_attention",
41
+ "full_attention",
42
+ "linear_attention",
43
+ "linear_attention",
44
+ "linear_attention",
45
+ "full_attention",
46
+ "linear_attention",
47
+ "linear_attention",
48
+ "linear_attention",
49
+ "full_attention",
50
+ "linear_attention",
51
+ "linear_attention",
52
+ "linear_attention",
53
+ "full_attention",
54
+ "linear_attention",
55
+ "linear_attention",
56
+ "linear_attention",
57
+ "full_attention",
58
+ "linear_attention",
59
+ "linear_attention",
60
+ "linear_attention",
61
+ "full_attention"
62
+ ],
63
+ "linear_conv_kernel_dim": 4,
64
+ "linear_key_head_dim": 128,
65
+ "linear_num_key_heads": 16,
66
+ "linear_num_value_heads": 16,
67
+ "linear_value_head_dim": 128,
68
+ "mamba_ssm_dtype": "float32",
69
+ "max_position_embeddings": 262144,
70
+ "mlp_only_layers": [],
71
+ "mtp_num_hidden_layers": 0,
72
+ "mtp_use_dedicated_embeddings": false,
73
+ "num_attention_heads": 8,
74
+ "num_hidden_layers": 24,
75
+ "num_key_value_heads": 2,
76
+ "partial_rotary_factor": 0.25,
77
+ "rms_norm_eps": 1e-06,
78
+ "rope_parameters": {
79
+ "partial_rotary_factor": 0.25,
80
+ "rope_theta": 10000000,
81
+ "rope_type": "default"
82
+ },
83
+ "vocab_size": 556,
84
+ "model_type": "qwen3_5_text",
85
+ "tie_word_embeddings": true
86
+ },
87
+ "insert_layer_id": 6,
88
+ "image_token_id": 512,
89
+ "video_token_id": 513,
90
+ "dtype": "bfloat16",
91
+ "vocab_size": 556
92
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "downsample_mode": "4x",
3
+ "image_processor_type": "MiniCPMOcrImageProcessor",
4
+ "max_slice_nums": 9,
5
+ "patch_size": 14,
6
+ "scale_resolution": 448,
7
+ "slice_mode": true,
8
+ "use_image_id": true,
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "MiniCPMOcrProcessor"
20
+ }
processor_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "processor_class": "MiniCPMOcrProcessor"
3
+ }
tokenizer.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"version": "1.0", "truncation": null, "padding": null, "added_tokens": [{"id": 500, "content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 501, "content": "<|im_start|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 502, "content": "<|im_end|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 503, "content": "<|object_ref_start|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 504, "content": "<|object_ref_end|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 505, "content": "<|box_start|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 506, "content": "<|box_end|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 507, "content": "<|quad_start|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 508, "content": "<|quad_end|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 509, "content": "<|vision_start|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 510, "content": "<|vision_end|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 511, "content": "<|vision_pad|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 512, "content": "<|image_pad|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 513, "content": "<|video_pad|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 514, "content": "<tool_call>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 515, "content": "</tool_call>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 516, "content": "<|fim_prefix|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 517, "content": "<|fim_middle|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 518, "content": "<|fim_suffix|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 519, "content": "<|fim_pad|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 520, "content": "<|repo_name|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 521, "content": "<|file_sep|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 522, "content": "<tool_response>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 523, "content": "</tool_response>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 524, "content": "<think>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 525, "content": "</think>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 526, "content": "<|audio_start|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 527, "content": "<|audio_end|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 528, "content": "<tts_pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 529, "content": "<tts_text_bos>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 530, "content": "<tts_text_eod>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 531, "content": "<tts_text_bos_single>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 532, "content": "<|audio_pad|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 533, "content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 534, "content": "<image>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 535, "content": "</image>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 536, "content": "<ref>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 537, "content": "</ref>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 538, "content": "<box>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 539, "content": "</box>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 540, "content": "<quad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 541, "content": "</quad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 542, "content": "<point>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 543, "content": "</point>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 544, "content": "<slice>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 545, "content": "</slice>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 546, "content": "<image_id>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 547, "content": "</image_id>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 548, "content": "<timestamp>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 549, "content": "</timestamp>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 550, "content": "<ecel>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 551, "content": "<fcel>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 552, "content": "<xcel>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 553, "content": "<lcel>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 554, "content": "<ucel>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 555, "content": "<nl>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}], "normalizer": {"type": "NFC"}, "pre_tokenizer": {"type": "Sequence", "pretokenizers": [{"type": "Split", "pattern": {"Regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"}, "behavior": "Isolated", "invert": false}, {"type": "ByteLevel", "add_prefix_space": false, "trim_offsets": true, "use_regex": false}]}, "post_processor": {"type": "ByteLevel", "add_prefix_space": false, "trim_offsets": false, "use_regex": false}, "decoder": {"type": "ByteLevel", "add_prefix_space": true, "trim_offsets": true, "use_regex": true}, "model": {"type": "BPE", "dropout": null, "unk_token": null, "continuing_subword_prefix": "", "end_of_word_suffix": "", "fuse_unk": false, "byte_fallback": false, "ignore_merges": false, "vocab": {"!": 0, "\"": 1, "#": 2, "$": 3, "%": 4, "&": 5, "'": 6, "(": 7, ")": 8, "*": 9, "+": 10, ",": 11, "-": 12, ".": 13, "/": 14, "0": 15, "1": 16, "2": 17, "3": 18, "4": 19, "5": 20, "6": 21, "7": 22, "8": 23, "9": 24, ":": 25, ";": 26, "<": 27, "=": 28, ">": 29, "?": 30, "@": 31, "A": 32, "B": 33, "C": 34, "D": 35, "E": 36, "F": 37, "G": 38, "H": 39, "I": 40, "J": 41, "K": 42, "L": 43, "M": 44, "N": 45, "O": 46, "P": 47, "Q": 48, "R": 49, "S": 50, "T": 51, "U": 52, "V": 53, "W": 54, "X": 55, "Y": 56, "Z": 57, "[": 58, "\\": 59, "]": 60, "^": 61, "_": 62, "`": 63, "a": 64, "b": 65, "c": 66, "d": 67, "e": 68, "f": 69, "g": 70, "h": 71, "i": 72, "j": 73, "k": 74, "l": 75, "m": 76, "n": 77, "o": 78, "p": 79, "q": 80, "r": 81, "s": 82, "t": 83, "u": 84, "v": 85, "w": 86, "x": 87, "y": 88, "z": 89, "{": 90, "|": 91, "}": 92, "~": 93, "¡": 94, "¢": 95, "£": 96, "¤": 97, "¥": 98, "¦": 99, "§": 100, "¨": 101, "©": 102, "ª": 103, "«": 104, "¬": 105, "®": 106, "¯": 107, "°": 108, "±": 109, "²": 110, "³": 111, "´": 112, "µ": 113, "¶": 114, "·": 115, "¸": 116, "¹": 117, "º": 118, "»": 119, "¼": 120, "½": 121, "¾": 122, "¿": 123, "À": 124, "Á": 125, "Â": 126, "Ã": 127, "Ä": 128, "Å": 129, "Æ": 130, "Ç": 131, "È": 132, "É": 133, "Ê": 134, "Ë": 135, "Ì": 136, "Í": 137, "Î": 138, "Ï": 139, "Ð": 140, "Ñ": 141, "Ò": 142, "Ó": 143, "Ô": 144, "Õ": 145, "Ö": 146, "×": 147, "Ø": 148, "Ù": 149, "Ú": 150, "Û": 151, "Ü": 152, "Ý": 153, "Þ": 154, "ß": 155, "à": 156, "á": 157, "â": 158, "ã": 159, "ä": 160, "å": 161, "æ": 162, "ç": 163, "è": 164, "é": 165, "ê": 166, "ë": 167, "ì": 168, "í": 169, "î": 170, "ï": 171, "ð": 172, "ñ": 173, "ò": 174, "ó": 175, "ô": 176, "õ": 177, "ö": 178, "÷": 179, "ø": 180, "ù": 181, "ú": 182, "û": 183, "ü": 184, "ý": 185, "þ": 186, "ÿ": 187, "Ā": 188, "ā": 189, "Ă": 190, "ă": 191, "Ą": 192, "ą": 193, "Ć": 194, "ć": 195, "Ĉ": 196, "ĉ": 197, "Ċ": 198, "ċ": 199, "Č": 200, "č": 201, "Ď": 202, "ď": 203, "Đ": 204, "đ": 205, "Ē": 206, "ē": 207, "Ĕ": 208, "ĕ": 209, "Ė": 210, "ė": 211, "Ę": 212, "ę": 213, "Ě": 214, "ě": 215, "Ĝ": 216, "ĝ": 217, "Ğ": 218, "ğ": 219, "Ġ": 220, "ġ": 221, "Ģ": 222, "ģ": 223, "Ĥ": 224, "ĥ": 225, "Ħ": 226, "ħ": 227, "Ĩ": 228, "ĩ": 229, "Ī": 230, "ī": 231, "Ĭ": 232, "ĭ": 233, "Į": 234, "į": 235, "İ": 236, "ı": 237, "IJ": 238, "ij": 239, "Ĵ": 240, "ĵ": 241, "Ķ": 242, "ķ": 243, "ĸ": 244, "Ĺ": 245, "ĺ": 246, "Ļ": 247, "ļ": 248, "Ľ": 249, "ľ": 250, "Ŀ": 251, "ŀ": 252, "Ł": 253, "ł": 254, "Ń": 255, "ĠĠ": 256, "ĠĠĠĠ": 257, "in": 258, "Ġt": 259, "ĠĠĠĠĠĠĠĠ": 260, "er": 261, "ĠĠĠ": 262, "on": 263, "Ġa": 264, "re": 265, "at": 266, "st": 267, "en": 268, "or": 269, "Ġth": 270, "ĊĊ": 271, "Ġc": 272, "le": 273, "Ġs": 274, "it": 275, "an": 276, "ar": 277, "al": 278, "Ġthe": 279, "Ġp": 280, "Ġf": 281, "ou": 282, "Ġ=": 283, "is": 284, "ĠĠĠĠĠĠĠ": 285, "ing": 286, "es": 287, "Ġw": 288, "ion": 289, "ed": 290, "ic": 291, "Ġb": 292, "Ġd": 293, "et": 294, "Ġm": 295, "Ġo": 296, "ĉĉ": 297, "ro": 298, "as": 299, "el": 300, "ct": 301, "nd": 302, "Ġin": 303, "Ġh": 304, "ent": 305, "id": 306, "Ġn": 307, "am": 308, "ĠĠĠĠĠĠĠĠĠĠĠ": 309, "Ġto": 310, "Ġre": 311, "--": 312, "Ġ{": 313, "Ġof": 314, "om": 315, "im": 316, "čĊ": 317, "Ġ(": 318, "il": 319, "//": 320, "Ġand": 321, "ur": 322, "se": 323, "Ġl": 324, "ex": 325, "ĠS": 326, "ad": 327, "Ġ\"": 328, "ch": 329, "ut": 330, "if": 331, "**": 332, "Ġ}": 333, "em": 334, "ol": 335, "ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ": 336, "th": 337, "Ġg": 338, "ig": 339, "iv": 340, "ce": 341, "od": 342, "Ġv": 343, "ate": 344, "ĠT": 345, "ag": 346, "ay": 347, "Ġ*": 348, "ot": 349, "us": 350, "ĠC": 351, "Ġst": 352, "ĠI": 353, "un": 354, "ul": 355, "ue": 356, "ĠA": 357, "ow": 358, "Ġ'": 359, "ew": 360, "Ġ<": 361, "ation": 362, "()": 363, "Ġfor": 364, "ab": 365, "ort": 366, "um": 367, "ame": 368, "Ġis": 369, "pe": 370, "tr": 371, "ck": 372, "âĢ": 373, "Ġy": 374, "ist": 375, "----": 376, "he": 377, "Ġe": 378, "lo": 379, "ĠM": 380, "Ġbe": 381, "ers": 382, "Ġon": 383, "Ġcon": 384, "ap": 385, "ub": 386, "ĠP": 387, "ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ": 388, "ass": 389, "int": 390, "ly": 391, "urn": 392, "Ġ$": 393, "av": 394, "port": 395, "ir": 396, "->": 397, "nt": 398, "ction": 399, "end": 400, "Ġde": 401, "ith": 402, "out": 403, "turn": 404, "our": 405, "ĠĠĠĠĠ": 406, "lic": 407, "res": 408, "pt": 409, "==": 410, "Ġthis": 411, "Ġwh": 412, "Ġif": 413, "ĠD": 414, "ver": 415, "age": 416, "ĠB": 417, "ht": 418, "ext": 419, "=\"": 420, "Ġthat": 421, "****": 422, "ĠR": 423, "Ġit": 424, "ess": 425, "ĠF": 426, "Ġr": 427, "os": 428, "and": 429, "Ġas": 430, "ect": 431, "ke": 432, "rom": 433, "Ġ//": 434, "con": 435, "ĠL": 436, "(\"": 437, "qu": 438, "lass": 439, "Ġwith": 440, "iz": 441, "de": 442, "ĠN": 443, "Ġal": 444, "op": 445, "up": 446, "get": 447, "ile": 448, "Ġan": 449, "ata": 450, "ore": 451, "ri": 452, "Ġpro": 453, "ĉĉĉĉ": 454, "ter": 455, "ain": 456, "ĠW": 457, "ĠE": 458, "Ġcom": 459, "Ġreturn": 460, "art": 461, "ĠH": 462, "ack": 463, "import": 464, "ublic": 465, "Ġor": 466, "est": 467, "ment": 468, "ĠG": 469, "able": 470, "Ġ-": 471, "ine": 472, "ill": 473, "ind": 474, "ere": 475, "::": 476, "ity": 477, "Ġ+": 478, "Ġtr": 479, "elf": 480, "ight": 481, "('": 482, "orm": 483, "ult": 484, "str": 485, "..": 486, "\",": 487, "Ġyou": 488, "ype": 489, "pl": 490, "Ġnew": 491, "Ġj": 492, "ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ": 493, "Ġfrom": 494, "Ġex": 495, "ĠO": 496, "ld": 497, "Ġ[": 498, "oc": 499}, "merges": [["Ġ", "Ġ"], ["ĠĠ", "ĠĠ"], ["i", "n"], ["Ġ", "t"], ["ĠĠĠĠ", "ĠĠĠĠ"], ["e", "r"], ["ĠĠ", "Ġ"], ["o", "n"], ["Ġ", "a"], ["r", "e"], ["a", "t"], ["s", "t"], ["e", "n"], ["o", "r"], ["Ġt", "h"], ["Ċ", "Ċ"], ["Ġ", "c"], ["l", "e"], ["Ġ", "s"], ["i", "t"], ["a", "n"], ["a", "r"], ["a", "l"], ["Ġth", "e"], ["Ġ", "p"], ["Ġ", "f"], ["o", "u"], ["Ġ", "="], ["i", "s"], ["ĠĠĠĠ", "ĠĠĠ"], ["in", "g"], ["e", "s"], ["Ġ", "w"], ["i", "on"], ["e", "d"], ["i", "c"], ["Ġ", "b"], ["Ġ", "d"], ["e", "t"], ["Ġ", "m"], ["Ġ", "o"], ["ĉ", "ĉ"], ["r", "o"], ["a", "s"], ["e", "l"], ["c", "t"], ["n", "d"], ["Ġ", "in"], ["Ġ", "h"], ["en", "t"], ["i", "d"], ["Ġ", "n"], ["a", "m"], ["ĠĠĠĠĠĠĠĠ", "ĠĠĠ"], ["Ġt", "o"], ["Ġ", "re"], ["-", "-"], ["Ġ", "{"], ["Ġo", "f"], ["o", "m"], ["i", "m"], ["č", "Ċ"], ["Ġ", "("], ["i", "l"], ["/", "/"], ["Ġa", "nd"], ["u", "r"], ["s", "e"], ["Ġ", "l"], ["e", "x"], ["Ġ", "S"], ["a", "d"], ["Ġ", "\""], ["c", "h"], ["u", "t"], ["i", "f"], ["*", "*"], ["Ġ", "}"], ["e", "m"], ["o", "l"], ["ĠĠĠĠĠĠĠĠ", "ĠĠĠĠĠĠĠĠ"], ["t", "h"], ["Ġ", "g"], ["i", "g"], ["i", "v"], ["c", "e"], ["o", "d"], ["Ġ", "v"], ["at", "e"], ["Ġ", "T"], ["a", "g"], ["a", "y"], ["Ġ", "*"], ["o", "t"], ["u", "s"], ["Ġ", "C"], ["Ġ", "st"], ["Ġ", "I"], ["u", "n"], ["u", "l"], ["u", "e"], ["Ġ", "A"], ["o", "w"], ["Ġ", "'"], ["e", "w"], ["Ġ", "<"], ["at", "ion"], ["(", ")"], ["Ġf", "or"], ["a", "b"], ["or", "t"], ["u", "m"], ["am", "e"], ["Ġ", "is"], ["p", "e"], ["t", "r"], ["c", "k"], ["â", "Ģ"], ["Ġ", "y"], ["i", "st"], ["--", "--"], ["h", "e"], ["Ġ", "e"], ["l", "o"], ["Ġ", "M"], ["Ġb", "e"], ["er", "s"], ["Ġ", "on"], ["Ġc", "on"], ["a", "p"], ["u", "b"], ["Ġ", "P"], ["ĠĠĠĠĠĠĠĠ", "ĠĠĠĠĠĠĠ"], ["as", "s"], ["in", "t"], ["l", "y"], ["ur", "n"], ["Ġ", "$"], ["a", "v"], ["p", "ort"], ["i", "r"], ["-", ">"], ["n", "t"], ["ct", "ion"], ["en", "d"], ["Ġd", "e"], ["it", "h"], ["ou", "t"], ["t", "urn"], ["ou", "r"], ["ĠĠĠĠ", "Ġ"], ["l", "ic"], ["re", "s"], ["p", "t"], ["=", "="], ["Ġth", "is"], ["Ġw", "h"], ["Ġ", "if"], ["Ġ", "D"], ["v", "er"], ["ag", "e"], ["Ġ", "B"], ["h", "t"], ["ex", "t"], ["=", "\""], ["Ġth", "at"], ["**", "**"], ["Ġ", "R"], ["Ġ", "it"], ["es", "s"], ["Ġ", "F"], ["Ġ", "r"], ["o", "s"], ["an", "d"], ["Ġa", "s"], ["e", "ct"], ["k", "e"], ["ro", "m"], ["Ġ", "//"], ["c", "on"], ["Ġ", "L"], ["(", "\""], ["q", "u"], ["l", "ass"], ["Ġw", "ith"], ["i", "z"], ["d", "e"], ["Ġ", "N"], ["Ġa", "l"], ["o", "p"], ["u", "p"], ["g", "et"], ["i", "le"], ["Ġa", "n"], ["at", "a"], ["o", "re"], ["r", "i"], ["Ġp", "ro"], ["ĉĉ", "ĉĉ"], ["t", "er"], ["a", "in"], ["Ġ", "W"], ["Ġ", "E"], ["Ġc", "om"], ["Ġre", "turn"], ["ar", "t"], ["Ġ", "H"], ["a", "ck"], ["im", "port"], ["ub", "lic"], ["Ġ", "or"], ["e", "st"], ["m", "ent"], ["Ġ", "G"], ["ab", "le"], ["Ġ", "-"], ["in", "e"], ["il", "l"], ["in", "d"], ["er", "e"], [":", ":"], ["it", "y"], ["Ġ", "+"], ["Ġt", "r"], ["el", "f"], ["ig", "ht"], ["(", "'"], ["or", "m"], ["ul", "t"], ["st", "r"], [".", "."], ["\"", ","], ["Ġy", "ou"], ["y", "pe"], ["p", "l"], ["Ġn", "ew"], ["Ġ", "j"], ["ĠĠĠĠĠĠĠĠ", "ĠĠĠĠĠĠĠĠĠĠĠ"], ["Ġf", "rom"], ["Ġ", "ex"], ["Ġ", "O"], ["l", "d"], ["Ġ", "["], ["o", "c"]]}}
tokenizer_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "audio_bos_token": "<|audio_start|>",
4
+ "audio_eos_token": "<|audio_end|>",
5
+ "audio_token": "<|audio_pad|>",
6
+ "backend": "tokenizers",
7
+ "bos_token": "<|im_start|>",
8
+ "clean_up_tokenization_spaces": false,
9
+ "eos_token": "<|im_end|>",
10
+ "errors": "replace",
11
+ "extra_special_tokens": {
12
+ "image_token": "<|image_pad|>",
13
+ "video_token": "<|video_pad|>",
14
+ "image_start_token": "<image>",
15
+ "image_end_token": "</image>",
16
+ "slice_start_token": "<slice>",
17
+ "slice_end_token": "</slice>",
18
+ "image_id_start_token": "<image_id>",
19
+ "image_id_end_token": "</image_id>"
20
+ },
21
+ "image_token": "<|image_pad|>",
22
+ "model_max_length": 262144,
23
+ "model_specific_special_tokens": {
24
+ "audio_bos_token": "<|audio_start|>",
25
+ "audio_eos_token": "<|audio_end|>",
26
+ "audio_token": "<|audio_pad|>",
27
+ "image_token": "<|image_pad|>",
28
+ "video_token": "<|video_pad|>",
29
+ "vision_bos_token": "<|vision_start|>",
30
+ "vision_eos_token": "<|vision_end|>"
31
+ },
32
+ "pad_token": "<|endoftext|>",
33
+ "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+",
34
+ "processor_class": "MiniCPMOcrProcessor",
35
+ "split_special_tokens": false,
36
+ "tokenizer_class": "TokenizersBackend",
37
+ "unk_token": "<unk>",
38
+ "video_token": "<|video_pad|>",
39
+ "vision_bos_token": "<|vision_start|>",
40
+ "vision_eos_token": "<|vision_end|>"
41
+ }
video_preprocessor_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "max_slice_nums": 9,
3
+ "scale_resolution": 448,
4
+ "patch_size": 14,
5
+ "slice_mode": true,
6
+ "downsample_mode": "4x",
7
+ "use_image_id": true,
8
+ "image_mean": [
9
+ 0.5,
10
+ 0.5,
11
+ 0.5
12
+ ],
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "video_processor_type": "MiniCPMOcrVideoProcessor",
19
+ "processor_class": "MiniCPMOcrProcessor"
20
+ }