Hugging Face's logo

Alexanderrysky
/
tiny-random-MiniCPM-o-2_6-v2

PyTorch
minicpmo
custom_code
Model card Files
xet
Community
1
Alexanderrysky commited on
Commit
811c331
·
verified ·
1 Parent(s): d5ee5cb

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +59 -0
  3. config.json +200 -0
  4. generation_config.json +6 -0
  5. merges.txt +0 -0
  6. preprocessor_config.json +43 -0
  7. pytorch_model.bin +3 -0
  8. special_tokens_map.json +67 -0
  9. tokenizer.json +3 -0
  10. tokenizer_config.json +524 -0
  11. vocab.json +0 -0
.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
added_tokens.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</asr>": 151682,
3
+ "</box>": 151670,
4
+ "</image>": 151666,
5
+ "</image_id>": 151678,
6
+ "</point>": 151674,
7
+ "</quad>": 151672,
8
+ "</query>": 151684,
9
+ "</ref>": 151668,
10
+ "</slice>": 151676,
11
+ "</tool_call>": 151658,
12
+ "</unit>": 151680,
13
+ "<asr>": 151681,
14
+ "<box>": 151669,
15
+ "<image>": 151665,
16
+ "<image_id>": 151677,
17
+ "<point>": 151673,
18
+ "<quad>": 151671,
19
+ "<query>": 151683,
20
+ "<ref>": 151667,
21
+ "<reserved_43>": 151698,
22
+ "<reserved_53>": 151699,
23
+ "<slice>": 151675,
24
+ "<tool_call>": 151657,
25
+ "<unit>": 151679,
26
+ "<|audio_end|>": 151687,
27
+ "<|audio_start|>": 151685,
28
+ "<|audio|>": 151686,
29
+ "<|box_end|>": 151649,
30
+ "<|box_start|>": 151648,
31
+ "<|endoftext|>": 151643,
32
+ "<|file_sep|>": 151664,
33
+ "<|fim_middle|>": 151660,
34
+ "<|fim_pad|>": 151662,
35
+ "<|fim_prefix|>": 151659,
36
+ "<|fim_suffix|>": 151661,
37
+ "<|im_end|>": 151645,
38
+ "<|im_start|>": 151644,
39
+ "<|image_pad|>": 151655,
40
+ "<|interrupt|>": 151695,
41
+ "<|listen|>": 151693,
42
+ "<|object_ref_end|>": 151647,
43
+ "<|object_ref_start|>": 151646,
44
+ "<|quad_end|>": 151651,
45
+ "<|quad_start|>": 151650,
46
+ "<|repo_name|>": 151663,
47
+ "<|speak|>": 151694,
48
+ "<|spk_bos|>": 151688,
49
+ "<|spk_eos|>": 151690,
50
+ "<|spk|>": 151689,
51
+ "<|tts_bos|>": 151691,
52
+ "<|tts_eos|>": 151692,
53
+ "<|vad_end|>": 151697,
54
+ "<|vad_start|>": 151696,
55
+ "<|video_pad|>": 151656,
56
+ "<|vision_end|>": 151653,
57
+ "<|vision_pad|>": 151654,
58
+ "<|vision_start|>": 151652
59
+ }
config.json ADDED
@@ -0,0 +1,200 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openbmb/MiniCPM-o-2_6",
3
+ "architectures": [
4
+ "MiniCPMO"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "audio_chunk_length": 1.0,
8
+ "audio_config": {
9
+ "architectures": [
10
+ "MiniCPMWhisperEncoder"
11
+ ],
12
+ "begin_suppress_tokens": [
13
+ 220,
14
+ 50257
15
+ ],
16
+ "bos_token_id": 50257,
17
+ "d_model": 128,
18
+ "decoder_attention_heads": 16,
19
+ "decoder_ffn_dim": 128,
20
+ "decoder_layers": 1,
21
+ "decoder_start_token_id": 50258,
22
+ "encoder_attention_heads": 16,
23
+ "encoder_ffn_dim": 128,
24
+ "encoder_layers": 1,
25
+ "eos_token_id": 50257,
26
+ "forced_decoder_ids": [
27
+ [
28
+ 1,
29
+ 50259
30
+ ],
31
+ [
32
+ 2,
33
+ 50359
34
+ ],
35
+ [
36
+ 3,
37
+ 50363
38
+ ]
39
+ ],
40
+ "max_length": 448,
41
+ "model_type": "whisper",
42
+ "num_hidden_layers": 24,
43
+ "pad_token_id": 50257,
44
+ "suppress_tokens": [
45
+ 1,
46
+ 2,
47
+ 7,
48
+ 8,
49
+ 9,
50
+ 10,
51
+ 14,
52
+ 25,
53
+ 26,
54
+ 27,
55
+ 28,
56
+ 29,
57
+ 31,
58
+ 58,
59
+ 59,
60
+ 60,
61
+ 61,
62
+ 62,
63
+ 63,
64
+ 90,
65
+ 91,
66
+ 92,
67
+ 93,
68
+ 359,
69
+ 503,
70
+ 522,
71
+ 542,
72
+ 873,
73
+ 893,
74
+ 902,
75
+ 918,
76
+ 922,
77
+ 931,
78
+ 1350,
79
+ 1853,
80
+ 1982,
81
+ 2460,
82
+ 2627,
83
+ 3246,
84
+ 3253,
85
+ 3268,
86
+ 3536,
87
+ 3846,
88
+ 3961,
89
+ 4183,
90
+ 4667,
91
+ 6585,
92
+ 6647,
93
+ 7273,
94
+ 9061,
95
+ 9383,
96
+ 10428,
97
+ 10929,
98
+ 11938,
99
+ 12033,
100
+ 12331,
101
+ 12562,
102
+ 13793,
103
+ 14157,
104
+ 14635,
105
+ 15265,
106
+ 15618,
107
+ 16553,
108
+ 16604,
109
+ 18362,
110
+ 18956,
111
+ 20075,
112
+ 21675,
113
+ 22520,
114
+ 26130,
115
+ 26161,
116
+ 26435,
117
+ 28279,
118
+ 29464,
119
+ 31650,
120
+ 32302,
121
+ 32470,
122
+ 36865,
123
+ 42863,
124
+ 47425,
125
+ 49870,
126
+ 50254,
127
+ 50258,
128
+ 50358,
129
+ 50359,
130
+ 50360,
131
+ 50361,
132
+ 50362
133
+ ],
134
+ "torch_dtype": "float32",
135
+ "vocab_size": 512
136
+ },
137
+ "audio_pool_step": 2,
138
+ "auto_map": {
139
+ "AutoConfig": "openbmb/MiniCPM-o-2_6--configuration_minicpm.MiniCPMOConfig",
140
+ "AutoModel": "openbmb/MiniCPM-o-2_6--modeling_minicpmo.MiniCPMO",
141
+ "AutoModelForCausalLM": "openbmb/MiniCPM-o-2_6--modeling_minicpmo.MiniCPMO"
142
+ },
143
+ "batch_vision_input": true,
144
+ "bos_token_id": 151643,
145
+ "chunk_input": true,
146
+ "drop_vision_last_layer": false,
147
+ "eos_token_id": 151645,
148
+ "hidden_act": "silu",
149
+ "hidden_size": 128,
150
+ "image_size": 448,
151
+ "init_audio": true,
152
+ "init_tts": true,
153
+ "init_vision": true,
154
+ "initializer_range": 0.02,
155
+ "intermediate_size": 128,
156
+ "listen_speak_type": "asr",
157
+ "max_position_embeddings": 32768,
158
+ "max_window_layers": 28,
159
+ "model_type": "minicpmo",
160
+ "num_attention_heads": 4,
161
+ "num_hidden_layers": 1,
162
+ "num_key_value_heads": 2,
163
+ "patch_size": 14,
164
+ "query_num": 64,
165
+ "rms_norm_eps": 1e-06,
166
+ "rope_scaling": null,
167
+ "rope_theta": 1000000.0,
168
+ "slice_config": {
169
+ "max_slice_nums": 9,
170
+ "model_type": "minicpmv"
171
+ },
172
+ "slice_mode": true,
173
+ "sliding_window": null,
174
+ "stream_input": false,
175
+ "tie_word_embeddings": false,
176
+ "torch_dtype": "float32",
177
+ "transformers_version": "4.45.0",
178
+ "tts_config": {
179
+ "hidden_size": 128,
180
+ "intermediate_size": 128,
181
+ "llm_dim": 128,
182
+ "model_type": "conditional_chattts",
183
+ "num_hidden_layers": 1
184
+ },
185
+ "use_cache": true,
186
+ "use_image_id": true,
187
+ "use_sliding_window": false,
188
+ "version": 2.6,
189
+ "vision_batch_size": 16,
190
+ "vision_config": {
191
+ "hidden_size": 128,
192
+ "image_size": 980,
193
+ "intermediate_size": 128,
194
+ "model_type": "siglip_vision_model",
195
+ "num_attention_heads": 16,
196
+ "num_hidden_layers": 1,
197
+ "patch_size": 14
198
+ },
199
+ "vocab_size": 512
200
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151645,
5
+ "transformers_version": "4.45.0"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_map": {
3
+ "AutoImageProcessor": "openbmb/MiniCPM-o-2_6--image_processing_minicpmv.MiniCPMVImageProcessor",
4
+ "AutoProcessor": "openbmb/MiniCPM-o-2_6--processing_minicpmo.MiniCPMOProcessor"
5
+ },
6
+ "chunk_length": 30,
7
+ "feature_extractor_type": "WhisperFeatureExtractor",
8
+ "feature_size": 80,
9
+ "hop_length": 160,
10
+ "im_end": "</image>",
11
+ "im_id_end": "</image_id>",
12
+ "im_id_start": "<image_id>",
13
+ "im_start": "<image>",
14
+ "image_feature_size": 64,
15
+ "image_processor_type": "MiniCPMVImageProcessor",
16
+ "max_slice_nums": 9,
17
+ "n_fft": 400,
18
+ "n_samples": 480000,
19
+ "nb_max_frames": 3000,
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
+ "padding_side": "right",
31
+ "padding_value": 0.0,
32
+ "patch_size": 14,
33
+ "processor_class": "MiniCPMOProcessor",
34
+ "return_attention_mask": false,
35
+ "sampling_rate": 16000,
36
+ "scale_resolution": 448,
37
+ "slice_end": "</slice>",
38
+ "slice_mode": true,
39
+ "slice_start": "<slice>",
40
+ "unk": "<unk>",
41
+ "use_image_id": true,
42
+ "version": 2.6
43
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8279db20236d1fb035a443f178ebc9b521e9b2efbbf6b21b08447eeaa366a9aa
3
+ size 4719995
special_tokens_map.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<image>",
4
+ "</image>",
5
+ "<ref>",
6
+ "</ref>",
7
+ "<box>",
8
+ "</box>",
9
+ "<quad>",
10
+ "</quad>",
11
+ "<point>",
12
+ "</point>",
13
+ "<slice>",
14
+ "</slice>",
15
+ "<image_id>",
16
+ "</image_id>",
17
+ "<unit>",
18
+ "</unit>",
19
+ "<asr>",
20
+ "</asr>",
21
+ "<query>",
22
+ "</query>",
23
+ "<|audio_start|>",
24
+ "<|audio|>",
25
+ "<|audio_end|>",
26
+ "<|spk_bos|>",
27
+ "<|spk|>",
28
+ "<|spk_eos|>",
29
+ "<|tts_bos|>",
30
+ "<|tts_eos|>",
31
+ "<|listen|>",
32
+ "<|speak|>",
33
+ "<|interrupt|>",
34
+ "<|vad_start|>",
35
+ "<|vad_end|>",
36
+ "<reserved_43>",
37
+ "<reserved_53>"
38
+ ],
39
+ "bos_token": {
40
+ "content": "<|im_start|>",
41
+ "lstrip": false,
42
+ "normalized": false,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "eos_token": {
47
+ "content": "<|im_end|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ },
53
+ "pad_token": {
54
+ "content": "<|endoftext|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false
59
+ },
60
+ "unk_token": {
61
+ "content": "<unk>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false
66
+ }
67
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e43057e8380937b8edf2c9ea6ad34a3875d89c390e97024dfac307f3a4a11321
3
+ size 11428583
tokenizer_config.json ADDED
@@ -0,0 +1,524 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<image>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "151666": {
198
+ "content": "</image>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "151667": {
206
+ "content": "<ref>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "151668": {
214
+ "content": "</ref>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "151669": {
222
+ "content": "<box>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "151670": {
230
+ "content": "</box>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "151671": {
238
+ "content": "<quad>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "151672": {
246
+ "content": "</quad>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "151673": {
254
+ "content": "<point>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "151674": {
262
+ "content": "</point>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "151675": {
270
+ "content": "<slice>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "151676": {
278
+ "content": "</slice>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "151677": {
286
+ "content": "<image_id>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "151678": {
294
+ "content": "</image_id>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "151679": {
302
+ "content": "<unit>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "151680": {
310
+ "content": "</unit>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "151681": {
318
+ "content": "<asr>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "151682": {
326
+ "content": "</asr>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": true
332
+ },
333
+ "151683": {
334
+ "content": "<query>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": true
340
+ },
341
+ "151684": {
342
+ "content": "</query>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": true
348
+ },
349
+ "151685": {
350
+ "content": "<|audio_start|>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": true
356
+ },
357
+ "151686": {
358
+ "content": "<|audio|>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": true
364
+ },
365
+ "151687": {
366
+ "content": "<|audio_end|>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": true
372
+ },
373
+ "151688": {
374
+ "content": "<|spk_bos|>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": true
380
+ },
381
+ "151689": {
382
+ "content": "<|spk|>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": true
388
+ },
389
+ "151690": {
390
+ "content": "<|spk_eos|>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": true
396
+ },
397
+ "151691": {
398
+ "content": "<|tts_bos|>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": true
404
+ },
405
+ "151692": {
406
+ "content": "<|tts_eos|>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": true
412
+ },
413
+ "151693": {
414
+ "content": "<|listen|>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": true
420
+ },
421
+ "151694": {
422
+ "content": "<|speak|>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": true
428
+ },
429
+ "151695": {
430
+ "content": "<|interrupt|>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": true
436
+ },
437
+ "151696": {
438
+ "content": "<|vad_start|>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": true
444
+ },
445
+ "151697": {
446
+ "content": "<|vad_end|>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": true
452
+ },
453
+ "151698": {
454
+ "content": "<reserved_43>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": true
460
+ },
461
+ "151699": {
462
+ "content": "<reserved_53>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": true
468
+ }
469
+ },
470
+ "additional_special_tokens": [
471
+ "<image>",
472
+ "</image>",
473
+ "<ref>",
474
+ "</ref>",
475
+ "<box>",
476
+ "</box>",
477
+ "<quad>",
478
+ "</quad>",
479
+ "<point>",
480
+ "</point>",
481
+ "<slice>",
482
+ "</slice>",
483
+ "<image_id>",
484
+ "</image_id>",
485
+ "<unit>",
486
+ "</unit>",
487
+ "<asr>",
488
+ "</asr>",
489
+ "<query>",
490
+ "</query>",
491
+ "<|audio_start|>",
492
+ "<|audio|>",
493
+ "<|audio_end|>",
494
+ "<|spk_bos|>",
495
+ "<|spk|>",
496
+ "<|spk_eos|>",
497
+ "<|tts_bos|>",
498
+ "<|tts_eos|>",
499
+ "<|listen|>",
500
+ "<|speak|>",
501
+ "<|interrupt|>",
502
+ "<|vad_start|>",
503
+ "<|vad_end|>",
504
+ "<reserved_43>",
505
+ "<reserved_53>"
506
+ ],
507
+ "auto_map": {
508
+ "AutoTokenizer": [
509
+ "openbmb/MiniCPM-o-2_6--tokenization_minicpmo_fast.MiniCPMOTokenizerFast",
510
+ null
511
+ ]
512
+ },
513
+ "bos_token": "<|im_start|>",
514
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# 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>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
515
+ "clean_up_tokenization_spaces": false,
516
+ "eos_token": "<|im_end|>",
517
+ "errors": "replace",
518
+ "model_max_length": 131072,
519
+ "pad_token": "<|endoftext|>",
520
+ "processor_class": "MiniCPMOProcessor",
521
+ "split_special_tokens": false,
522
+ "tokenizer_class": "MiniCPMOTokenizer",
523
+ "unk_token": "<unk>"
524
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff