Any-to-Any
Transformers
Safetensors
minicpmo
feature-extraction
minicpm-o
minicpm-v
multimodal
full-duplex
custom_code
8-bit precision
Instructions to use Edith08/MiniCPM-o-4_5-q4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Edith08/MiniCPM-o-4_5-q4 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Edith08/MiniCPM-o-4_5-q4", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- added_tokens.json +107 -0
- config.json +285 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
- model_q4.safetensors +3 -0
- special_tokens_map.json +110 -0
- tokenizer.json +3 -0
- tokenizer_config.json +951 -0
- 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 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</answer>": 151686,
|
| 3 |
+
"</box>": 151674,
|
| 4 |
+
"</focus>": 151688,
|
| 5 |
+
"</image>": 151670,
|
| 6 |
+
"</image_id>": 151682,
|
| 7 |
+
"</image_save_to>": 151696,
|
| 8 |
+
"</line>": 151690,
|
| 9 |
+
"</perception>": 151692,
|
| 10 |
+
"</point>": 151678,
|
| 11 |
+
"</quad>": 151676,
|
| 12 |
+
"</ref>": 151672,
|
| 13 |
+
"</slice>": 151680,
|
| 14 |
+
"</source_image>": 151694,
|
| 15 |
+
"</think>": 151668,
|
| 16 |
+
"</tool_call>": 151658,
|
| 17 |
+
"</tool_response>": 151666,
|
| 18 |
+
"</unit>": 151684,
|
| 19 |
+
"<answer>": 151685,
|
| 20 |
+
"<box>": 151673,
|
| 21 |
+
"<focus>": 151687,
|
| 22 |
+
"<image>": 151669,
|
| 23 |
+
"<image_id>": 151681,
|
| 24 |
+
"<image_save_to>": 151695,
|
| 25 |
+
"<line>": 151689,
|
| 26 |
+
"<perception>": 151691,
|
| 27 |
+
"<point>": 151677,
|
| 28 |
+
"<quad>": 151675,
|
| 29 |
+
"<ref>": 151671,
|
| 30 |
+
"<slice>": 151679,
|
| 31 |
+
"<source_image>": 151693,
|
| 32 |
+
"<think>": 151667,
|
| 33 |
+
"<tool_call>": 151657,
|
| 34 |
+
"<tool_response>": 151665,
|
| 35 |
+
"<unit>": 151683,
|
| 36 |
+
"<|audio_end|>": 151699,
|
| 37 |
+
"<|audio_start|>": 151697,
|
| 38 |
+
"<|audio|>": 151698,
|
| 39 |
+
"<|box_end|>": 151649,
|
| 40 |
+
"<|box_start|>": 151648,
|
| 41 |
+
"<|chunk_bos|>": 151719,
|
| 42 |
+
"<|chunk_eos|>": 151718,
|
| 43 |
+
"<|chunk_tts_bos|>": 151720,
|
| 44 |
+
"<|chunk_tts_eos|>": 151721,
|
| 45 |
+
"<|emotion_end|>": 151711,
|
| 46 |
+
"<|emotion_start|>": 151710,
|
| 47 |
+
"<|endoftext|>": 151643,
|
| 48 |
+
"<|file_sep|>": 151664,
|
| 49 |
+
"<|fim_middle|>": 151660,
|
| 50 |
+
"<|fim_pad|>": 151662,
|
| 51 |
+
"<|fim_prefix|>": 151659,
|
| 52 |
+
"<|fim_suffix|>": 151661,
|
| 53 |
+
"<|im_end|>": 151645,
|
| 54 |
+
"<|im_start|>": 151644,
|
| 55 |
+
"<|image_pad|>": 151655,
|
| 56 |
+
"<|interrupt|>": 151707,
|
| 57 |
+
"<|listen|>": 151705,
|
| 58 |
+
"<|object_ref_end|>": 151647,
|
| 59 |
+
"<|object_ref_start|>": 151646,
|
| 60 |
+
"<|pitch_end|>": 151715,
|
| 61 |
+
"<|pitch_start|>": 151714,
|
| 62 |
+
"<|quad_end|>": 151651,
|
| 63 |
+
"<|quad_start|>": 151650,
|
| 64 |
+
"<|repo_name|>": 151663,
|
| 65 |
+
"<|speak|>": 151706,
|
| 66 |
+
"<|speed_end|>": 151713,
|
| 67 |
+
"<|speed_start|>": 151712,
|
| 68 |
+
"<|spk_bos|>": 151700,
|
| 69 |
+
"<|spk_eos|>": 151702,
|
| 70 |
+
"<|spk|>": 151701,
|
| 71 |
+
"<|timbre_10|>": 151726,
|
| 72 |
+
"<|timbre_11|>": 151727,
|
| 73 |
+
"<|timbre_12|>": 151728,
|
| 74 |
+
"<|timbre_13|>": 151729,
|
| 75 |
+
"<|timbre_14|>": 151730,
|
| 76 |
+
"<|timbre_15|>": 151731,
|
| 77 |
+
"<|timbre_16|>": 151732,
|
| 78 |
+
"<|timbre_17|>": 151733,
|
| 79 |
+
"<|timbre_18|>": 151734,
|
| 80 |
+
"<|timbre_19|>": 151735,
|
| 81 |
+
"<|timbre_20|>": 151736,
|
| 82 |
+
"<|timbre_21|>": 151737,
|
| 83 |
+
"<|timbre_22|>": 151738,
|
| 84 |
+
"<|timbre_23|>": 151739,
|
| 85 |
+
"<|timbre_24|>": 151740,
|
| 86 |
+
"<|timbre_25|>": 151741,
|
| 87 |
+
"<|timbre_26|>": 151742,
|
| 88 |
+
"<|timbre_27|>": 151743,
|
| 89 |
+
"<|timbre_28|>": 151744,
|
| 90 |
+
"<|timbre_29|>": 151745,
|
| 91 |
+
"<|timbre_30|>": 151746,
|
| 92 |
+
"<|timbre_31|>": 151747,
|
| 93 |
+
"<|timbre_7|>": 151723,
|
| 94 |
+
"<|timbre_8|>": 151724,
|
| 95 |
+
"<|timbre_9|>": 151725,
|
| 96 |
+
"<|tts_bos|>": 151703,
|
| 97 |
+
"<|tts_eos|>": 151704,
|
| 98 |
+
"<|tts_pad|>": 151722,
|
| 99 |
+
"<|turn_bos|>": 151716,
|
| 100 |
+
"<|turn_eos|>": 151717,
|
| 101 |
+
"<|vad_end|>": 151709,
|
| 102 |
+
"<|vad_start|>": 151708,
|
| 103 |
+
"<|video_pad|>": 151656,
|
| 104 |
+
"<|vision_end|>": 151653,
|
| 105 |
+
"<|vision_pad|>": 151654,
|
| 106 |
+
"<|vision_start|>": 151652
|
| 107 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,285 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"MiniCPMO"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"audio_chunk_length": 1.0,
|
| 8 |
+
"audio_config": {
|
| 9 |
+
"_attn_implementation_autoset": true,
|
| 10 |
+
"_name_or_path": "openai/whisper-medium",
|
| 11 |
+
"activation_dropout": 0.0,
|
| 12 |
+
"activation_function": "gelu",
|
| 13 |
+
"apply_spec_augment": false,
|
| 14 |
+
"architectures": [
|
| 15 |
+
"MiniCPMWhisperEncoder"
|
| 16 |
+
],
|
| 17 |
+
"attention_dropout": 0.0,
|
| 18 |
+
"begin_suppress_tokens": [
|
| 19 |
+
220,
|
| 20 |
+
50257
|
| 21 |
+
],
|
| 22 |
+
"bos_token_id": 50257,
|
| 23 |
+
"classifier_proj_size": 256,
|
| 24 |
+
"d_model": 1024,
|
| 25 |
+
"decoder_attention_heads": 16,
|
| 26 |
+
"decoder_ffn_dim": 4096,
|
| 27 |
+
"decoder_layerdrop": 0.0,
|
| 28 |
+
"decoder_layers": 24,
|
| 29 |
+
"decoder_start_token_id": 50258,
|
| 30 |
+
"dropout": 0.0,
|
| 31 |
+
"encoder_attention_heads": 16,
|
| 32 |
+
"encoder_ffn_dim": 4096,
|
| 33 |
+
"encoder_layerdrop": 0.0,
|
| 34 |
+
"encoder_layers": 24,
|
| 35 |
+
"eos_token_id": 50257,
|
| 36 |
+
"forced_decoder_ids": [
|
| 37 |
+
[
|
| 38 |
+
1,
|
| 39 |
+
50259
|
| 40 |
+
],
|
| 41 |
+
[
|
| 42 |
+
2,
|
| 43 |
+
50359
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
3,
|
| 47 |
+
50363
|
| 48 |
+
]
|
| 49 |
+
],
|
| 50 |
+
"init_std": 0.02,
|
| 51 |
+
"mask_feature_length": 10,
|
| 52 |
+
"mask_feature_min_masks": 0,
|
| 53 |
+
"mask_feature_prob": 0.0,
|
| 54 |
+
"mask_time_length": 10,
|
| 55 |
+
"mask_time_min_masks": 2,
|
| 56 |
+
"mask_time_prob": 0.05,
|
| 57 |
+
"max_length": 448,
|
| 58 |
+
"max_source_positions": 1500,
|
| 59 |
+
"max_target_positions": 448,
|
| 60 |
+
"median_filter_width": 7,
|
| 61 |
+
"model_type": "whisper",
|
| 62 |
+
"num_hidden_layers": 24,
|
| 63 |
+
"num_mel_bins": 80,
|
| 64 |
+
"pad_token_id": 50257,
|
| 65 |
+
"scale_embedding": false,
|
| 66 |
+
"suppress_tokens": [
|
| 67 |
+
1,
|
| 68 |
+
2,
|
| 69 |
+
7,
|
| 70 |
+
8,
|
| 71 |
+
9,
|
| 72 |
+
10,
|
| 73 |
+
14,
|
| 74 |
+
25,
|
| 75 |
+
26,
|
| 76 |
+
27,
|
| 77 |
+
28,
|
| 78 |
+
29,
|
| 79 |
+
31,
|
| 80 |
+
58,
|
| 81 |
+
59,
|
| 82 |
+
60,
|
| 83 |
+
61,
|
| 84 |
+
62,
|
| 85 |
+
63,
|
| 86 |
+
90,
|
| 87 |
+
91,
|
| 88 |
+
92,
|
| 89 |
+
93,
|
| 90 |
+
359,
|
| 91 |
+
503,
|
| 92 |
+
522,
|
| 93 |
+
542,
|
| 94 |
+
873,
|
| 95 |
+
893,
|
| 96 |
+
902,
|
| 97 |
+
918,
|
| 98 |
+
922,
|
| 99 |
+
931,
|
| 100 |
+
1350,
|
| 101 |
+
1853,
|
| 102 |
+
1982,
|
| 103 |
+
2460,
|
| 104 |
+
2627,
|
| 105 |
+
3246,
|
| 106 |
+
3253,
|
| 107 |
+
3268,
|
| 108 |
+
3536,
|
| 109 |
+
3846,
|
| 110 |
+
3961,
|
| 111 |
+
4183,
|
| 112 |
+
4667,
|
| 113 |
+
6585,
|
| 114 |
+
6647,
|
| 115 |
+
7273,
|
| 116 |
+
9061,
|
| 117 |
+
9383,
|
| 118 |
+
10428,
|
| 119 |
+
10929,
|
| 120 |
+
11938,
|
| 121 |
+
12033,
|
| 122 |
+
12331,
|
| 123 |
+
12562,
|
| 124 |
+
13793,
|
| 125 |
+
14157,
|
| 126 |
+
14635,
|
| 127 |
+
15265,
|
| 128 |
+
15618,
|
| 129 |
+
16553,
|
| 130 |
+
16604,
|
| 131 |
+
18362,
|
| 132 |
+
18956,
|
| 133 |
+
20075,
|
| 134 |
+
21675,
|
| 135 |
+
22520,
|
| 136 |
+
26130,
|
| 137 |
+
26161,
|
| 138 |
+
26435,
|
| 139 |
+
28279,
|
| 140 |
+
29464,
|
| 141 |
+
31650,
|
| 142 |
+
32302,
|
| 143 |
+
32470,
|
| 144 |
+
36865,
|
| 145 |
+
42863,
|
| 146 |
+
47425,
|
| 147 |
+
49870,
|
| 148 |
+
50254,
|
| 149 |
+
50258,
|
| 150 |
+
50358,
|
| 151 |
+
50359,
|
| 152 |
+
50360,
|
| 153 |
+
50361,
|
| 154 |
+
50362
|
| 155 |
+
],
|
| 156 |
+
"torch_dtype": "float32",
|
| 157 |
+
"use_cache": true,
|
| 158 |
+
"use_weighted_layer_sum": false,
|
| 159 |
+
"vocab_size": 51865
|
| 160 |
+
},
|
| 161 |
+
"audio_pool_step": 5,
|
| 162 |
+
"auto_map": {
|
| 163 |
+
"AutoConfig": "openbmb/MiniCPM-o-4_5--configuration_minicpmo.MiniCPMOConfig",
|
| 164 |
+
"AutoModel": "openbmb/MiniCPM-o-4_5--modeling_minicpmo.MiniCPMO",
|
| 165 |
+
"AutoModelForCausalLM": "openbmb/MiniCPM-o-4_5--modeling_minicpmo.MiniCPMO"
|
| 166 |
+
},
|
| 167 |
+
"batch_vision_input": true,
|
| 168 |
+
"bos_token_id": 151643,
|
| 169 |
+
"drop_vision_last_layer": false,
|
| 170 |
+
"eos_token_id": 151645,
|
| 171 |
+
"head_dim": 128,
|
| 172 |
+
"hidden_act": "silu",
|
| 173 |
+
"hidden_size": 4096,
|
| 174 |
+
"image_size": 448,
|
| 175 |
+
"init_audio": false,
|
| 176 |
+
"init_tts": false,
|
| 177 |
+
"init_vision": true,
|
| 178 |
+
"initializer_range": 0.02,
|
| 179 |
+
"intermediate_size": 12288,
|
| 180 |
+
"listen_speak_type": "asr",
|
| 181 |
+
"max_position_embeddings": 40960,
|
| 182 |
+
"max_window_layers": 36,
|
| 183 |
+
"model_type": "minicpmo",
|
| 184 |
+
"num_attention_heads": 32,
|
| 185 |
+
"num_hidden_layers": 36,
|
| 186 |
+
"num_key_value_heads": 8,
|
| 187 |
+
"patch_size": 14,
|
| 188 |
+
"query_num": 64,
|
| 189 |
+
"rms_norm_eps": 1e-06,
|
| 190 |
+
"rope_scaling": null,
|
| 191 |
+
"rope_theta": 1000000,
|
| 192 |
+
"slice_config": {
|
| 193 |
+
"max_slice_nums": 1,
|
| 194 |
+
"model_type": "minicpmv",
|
| 195 |
+
"patch_size": 14,
|
| 196 |
+
"scale_resolution": 448
|
| 197 |
+
},
|
| 198 |
+
"slice_mode": true,
|
| 199 |
+
"sliding_window": null,
|
| 200 |
+
"stream_input": true,
|
| 201 |
+
"tie_word_embeddings": false,
|
| 202 |
+
"torch_dtype": "float16",
|
| 203 |
+
"transformers_version": "4.51.0",
|
| 204 |
+
"tts_config": {
|
| 205 |
+
"_attn_implementation_autoset": true,
|
| 206 |
+
"attention_type": "full_attention",
|
| 207 |
+
"attn_implementation": "sdpa",
|
| 208 |
+
"audio_bos_token_id": 151687,
|
| 209 |
+
"audio_tokenizer_sample_rate": 16000,
|
| 210 |
+
"audio_tokenizer_type": "s3tokenizer",
|
| 211 |
+
"aug_layer_loss_weight": false,
|
| 212 |
+
"aug_loss_weight": false,
|
| 213 |
+
"backbone_model": "llama",
|
| 214 |
+
"condition_type": "hidden_text_merge",
|
| 215 |
+
"cosyvoice_config_path": null,
|
| 216 |
+
"cosyvoice_model_dir": null,
|
| 217 |
+
"filter_tts_loss": false,
|
| 218 |
+
"hidden_act": "silu",
|
| 219 |
+
"hidden_size": 768,
|
| 220 |
+
"interleaved": false,
|
| 221 |
+
"intermediate_size": 3072,
|
| 222 |
+
"llm_dim": 4096,
|
| 223 |
+
"llm_dim_model_base": 256,
|
| 224 |
+
"llm_down_scale": false,
|
| 225 |
+
"llm_hidden_size": 4096,
|
| 226 |
+
"llm_intermediate_size": 768,
|
| 227 |
+
"long_weight": 0.1,
|
| 228 |
+
"max_position_embeddings": 4096,
|
| 229 |
+
"model_type": "minicpmtts",
|
| 230 |
+
"normalize_projected_hidden": true,
|
| 231 |
+
"num_attention_heads": 12,
|
| 232 |
+
"num_audio_tokens": 6562,
|
| 233 |
+
"num_hidden_layers": 20,
|
| 234 |
+
"num_key_value_heads": 12,
|
| 235 |
+
"num_mel_bins": 100,
|
| 236 |
+
"num_text_tokens": 152064,
|
| 237 |
+
"num_vq": 1,
|
| 238 |
+
"projector_type": "mlp",
|
| 239 |
+
"recomputed_chunks": 1,
|
| 240 |
+
"s3_stream_chunk_size": 25,
|
| 241 |
+
"s3_stream_generate": false,
|
| 242 |
+
"s3_stream_n_timesteps": 10,
|
| 243 |
+
"s3_stream_prelook_size": 3,
|
| 244 |
+
"short_weight": 0.1,
|
| 245 |
+
"streaming": false,
|
| 246 |
+
"streaming_audio_chunk_size": 50,
|
| 247 |
+
"streaming_sliding_window": false,
|
| 248 |
+
"streaming_sliding_window_audio_frame_rate": 50,
|
| 249 |
+
"streaming_sliding_window_audio_init_text_length": 10,
|
| 250 |
+
"streaming_sliding_window_audio_window_size": 300,
|
| 251 |
+
"streaming_sliding_window_average_speed": 5,
|
| 252 |
+
"streaming_sliding_window_fast_speed": 7,
|
| 253 |
+
"streaming_sliding_window_max_text_len": 500,
|
| 254 |
+
"streaming_sliding_window_slow_speed": 3,
|
| 255 |
+
"streaming_sliding_window_text_window_size": 50,
|
| 256 |
+
"streaming_text_chunk_max": 7,
|
| 257 |
+
"streaming_text_chunk_min": 3,
|
| 258 |
+
"streaming_text_reserved_len": 300,
|
| 259 |
+
"text_eos_token_id": 151692,
|
| 260 |
+
"tts_filter_loss_fix": false,
|
| 261 |
+
"use_llm_hidden_state": false,
|
| 262 |
+
"use_text": true,
|
| 263 |
+
"window_size": 2
|
| 264 |
+
},
|
| 265 |
+
"use_cache": true,
|
| 266 |
+
"use_image_id": true,
|
| 267 |
+
"use_sliding_window": false,
|
| 268 |
+
"version": "4.5",
|
| 269 |
+
"vision_batch_size": 16,
|
| 270 |
+
"vision_config": {
|
| 271 |
+
"_attn_implementation_autoset": true,
|
| 272 |
+
"attention_dropout": 0.0,
|
| 273 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 274 |
+
"hidden_size": 1152,
|
| 275 |
+
"image_size": 980,
|
| 276 |
+
"intermediate_size": 4304,
|
| 277 |
+
"layer_norm_eps": 1e-06,
|
| 278 |
+
"model_type": "siglip_vision_model",
|
| 279 |
+
"num_attention_heads": 16,
|
| 280 |
+
"num_channels": 3,
|
| 281 |
+
"num_hidden_layers": 27,
|
| 282 |
+
"patch_size": 14
|
| 283 |
+
},
|
| 284 |
+
"vocab_size": 151748
|
| 285 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"temperature": 0.6,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.95,
|
| 12 |
+
"transformers_version": "4.51.0"
|
| 13 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4029b6c64c2c3920df3f5a6291a9f4b414a65bbcabf061a2b2b1532e8a0d851d
|
| 3 |
+
size 4933847224
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e8c252d1ad2fa5a3a8ded44484647ace9681e8457cbf76de67dae1b9982a37e
|
| 3 |
+
size 703333128
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model_q4.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:488f990365d4d0cc2b8e93526847f10f58251a69bf97e78a98c95c35f88bffd9
|
| 3 |
+
size 5637182512
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"<answer>",
|
| 21 |
+
"</answer>",
|
| 22 |
+
"<focus>",
|
| 23 |
+
"</focus>",
|
| 24 |
+
"<line>",
|
| 25 |
+
"</line>",
|
| 26 |
+
"<perception>",
|
| 27 |
+
"</perception>",
|
| 28 |
+
"<source_image>",
|
| 29 |
+
"</source_image>",
|
| 30 |
+
"<image_save_to>",
|
| 31 |
+
"</image_save_to>",
|
| 32 |
+
"<|audio_start|>",
|
| 33 |
+
"<|audio|>",
|
| 34 |
+
"<|audio_end|>",
|
| 35 |
+
"<|spk_bos|>",
|
| 36 |
+
"<|spk|>",
|
| 37 |
+
"<|spk_eos|>",
|
| 38 |
+
"<|tts_bos|>",
|
| 39 |
+
"<|tts_eos|>",
|
| 40 |
+
"<|listen|>",
|
| 41 |
+
"<|speak|>",
|
| 42 |
+
"<|interrupt|>",
|
| 43 |
+
"<|vad_start|>",
|
| 44 |
+
"<|vad_end|>",
|
| 45 |
+
"<|emotion_start|>",
|
| 46 |
+
"<|emotion_end|>",
|
| 47 |
+
"<|speed_start|>",
|
| 48 |
+
"<|speed_end|>",
|
| 49 |
+
"<|pitch_start|>",
|
| 50 |
+
"<|pitch_end|>",
|
| 51 |
+
"<|chunk_eos|>",
|
| 52 |
+
"<|chunk_bos|>",
|
| 53 |
+
"<|chunk_tts_bos|>",
|
| 54 |
+
"<|chunk_tts_eos|>",
|
| 55 |
+
"<|tts_pad|>",
|
| 56 |
+
"<|timbre_7|>",
|
| 57 |
+
"<|timbre_8|>",
|
| 58 |
+
"<|timbre_9|>",
|
| 59 |
+
"<|timbre_10|>",
|
| 60 |
+
"<|timbre_11|>",
|
| 61 |
+
"<|timbre_12|>",
|
| 62 |
+
"<|timbre_13|>",
|
| 63 |
+
"<|timbre_14|>",
|
| 64 |
+
"<|timbre_15|>",
|
| 65 |
+
"<|timbre_16|>",
|
| 66 |
+
"<|timbre_17|>",
|
| 67 |
+
"<|timbre_18|>",
|
| 68 |
+
"<|timbre_19|>",
|
| 69 |
+
"<|timbre_20|>",
|
| 70 |
+
"<|timbre_21|>",
|
| 71 |
+
"<|timbre_22|>",
|
| 72 |
+
"<|timbre_23|>",
|
| 73 |
+
"<|timbre_24|>",
|
| 74 |
+
"<|timbre_25|>",
|
| 75 |
+
"<|timbre_26|>",
|
| 76 |
+
"<|timbre_27|>",
|
| 77 |
+
"<|timbre_28|>",
|
| 78 |
+
"<|timbre_29|>",
|
| 79 |
+
"<|timbre_30|>",
|
| 80 |
+
"<|timbre_31|>"
|
| 81 |
+
],
|
| 82 |
+
"bos_token": {
|
| 83 |
+
"content": "<|im_start|>",
|
| 84 |
+
"lstrip": false,
|
| 85 |
+
"normalized": false,
|
| 86 |
+
"rstrip": false,
|
| 87 |
+
"single_word": false
|
| 88 |
+
},
|
| 89 |
+
"eos_token": {
|
| 90 |
+
"content": "<|im_end|>",
|
| 91 |
+
"lstrip": false,
|
| 92 |
+
"normalized": false,
|
| 93 |
+
"rstrip": false,
|
| 94 |
+
"single_word": false
|
| 95 |
+
},
|
| 96 |
+
"pad_token": {
|
| 97 |
+
"content": "<|endoftext|>",
|
| 98 |
+
"lstrip": false,
|
| 99 |
+
"normalized": false,
|
| 100 |
+
"rstrip": false,
|
| 101 |
+
"single_word": false
|
| 102 |
+
},
|
| 103 |
+
"unk_token": {
|
| 104 |
+
"content": "<unk>",
|
| 105 |
+
"lstrip": false,
|
| 106 |
+
"normalized": false,
|
| 107 |
+
"rstrip": false,
|
| 108 |
+
"single_word": false
|
| 109 |
+
}
|
| 110 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d55eb34389b8c87403763cc1d80447d91c85c7cd39cd5e3c0dc2d49edad989d
|
| 3 |
+
size 11437712
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,951 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "<answer>",
|
| 351 |
+
"lstrip": false,
|
| 352 |
+
"normalized": false,
|
| 353 |
+
"rstrip": false,
|
| 354 |
+
"single_word": false,
|
| 355 |
+
"special": true
|
| 356 |
+
},
|
| 357 |
+
"151686": {
|
| 358 |
+
"content": "</answer>",
|
| 359 |
+
"lstrip": false,
|
| 360 |
+
"normalized": false,
|
| 361 |
+
"rstrip": false,
|
| 362 |
+
"single_word": false,
|
| 363 |
+
"special": true
|
| 364 |
+
},
|
| 365 |
+
"151687": {
|
| 366 |
+
"content": "<focus>",
|
| 367 |
+
"lstrip": false,
|
| 368 |
+
"normalized": false,
|
| 369 |
+
"rstrip": false,
|
| 370 |
+
"single_word": false,
|
| 371 |
+
"special": true
|
| 372 |
+
},
|
| 373 |
+
"151688": {
|
| 374 |
+
"content": "</focus>",
|
| 375 |
+
"lstrip": false,
|
| 376 |
+
"normalized": false,
|
| 377 |
+
"rstrip": false,
|
| 378 |
+
"single_word": false,
|
| 379 |
+
"special": true
|
| 380 |
+
},
|
| 381 |
+
"151689": {
|
| 382 |
+
"content": "<line>",
|
| 383 |
+
"lstrip": false,
|
| 384 |
+
"normalized": false,
|
| 385 |
+
"rstrip": false,
|
| 386 |
+
"single_word": false,
|
| 387 |
+
"special": true
|
| 388 |
+
},
|
| 389 |
+
"151690": {
|
| 390 |
+
"content": "</line>",
|
| 391 |
+
"lstrip": false,
|
| 392 |
+
"normalized": false,
|
| 393 |
+
"rstrip": false,
|
| 394 |
+
"single_word": false,
|
| 395 |
+
"special": true
|
| 396 |
+
},
|
| 397 |
+
"151691": {
|
| 398 |
+
"content": "<perception>",
|
| 399 |
+
"lstrip": false,
|
| 400 |
+
"normalized": false,
|
| 401 |
+
"rstrip": false,
|
| 402 |
+
"single_word": false,
|
| 403 |
+
"special": true
|
| 404 |
+
},
|
| 405 |
+
"151692": {
|
| 406 |
+
"content": "</perception>",
|
| 407 |
+
"lstrip": false,
|
| 408 |
+
"normalized": false,
|
| 409 |
+
"rstrip": false,
|
| 410 |
+
"single_word": false,
|
| 411 |
+
"special": true
|
| 412 |
+
},
|
| 413 |
+
"151693": {
|
| 414 |
+
"content": "<source_image>",
|
| 415 |
+
"lstrip": false,
|
| 416 |
+
"normalized": false,
|
| 417 |
+
"rstrip": false,
|
| 418 |
+
"single_word": false,
|
| 419 |
+
"special": true
|
| 420 |
+
},
|
| 421 |
+
"151694": {
|
| 422 |
+
"content": "</source_image>",
|
| 423 |
+
"lstrip": false,
|
| 424 |
+
"normalized": false,
|
| 425 |
+
"rstrip": false,
|
| 426 |
+
"single_word": false,
|
| 427 |
+
"special": true
|
| 428 |
+
},
|
| 429 |
+
"151695": {
|
| 430 |
+
"content": "<image_save_to>",
|
| 431 |
+
"lstrip": false,
|
| 432 |
+
"normalized": false,
|
| 433 |
+
"rstrip": false,
|
| 434 |
+
"single_word": false,
|
| 435 |
+
"special": true
|
| 436 |
+
},
|
| 437 |
+
"151696": {
|
| 438 |
+
"content": "</image_save_to>",
|
| 439 |
+
"lstrip": false,
|
| 440 |
+
"normalized": false,
|
| 441 |
+
"rstrip": false,
|
| 442 |
+
"single_word": false,
|
| 443 |
+
"special": true
|
| 444 |
+
},
|
| 445 |
+
"151697": {
|
| 446 |
+
"content": "<|audio_start|>",
|
| 447 |
+
"lstrip": false,
|
| 448 |
+
"normalized": false,
|
| 449 |
+
"rstrip": false,
|
| 450 |
+
"single_word": false,
|
| 451 |
+
"special": true
|
| 452 |
+
},
|
| 453 |
+
"151698": {
|
| 454 |
+
"content": "<|audio|>",
|
| 455 |
+
"lstrip": false,
|
| 456 |
+
"normalized": false,
|
| 457 |
+
"rstrip": false,
|
| 458 |
+
"single_word": false,
|
| 459 |
+
"special": true
|
| 460 |
+
},
|
| 461 |
+
"151699": {
|
| 462 |
+
"content": "<|audio_end|>",
|
| 463 |
+
"lstrip": false,
|
| 464 |
+
"normalized": false,
|
| 465 |
+
"rstrip": false,
|
| 466 |
+
"single_word": false,
|
| 467 |
+
"special": true
|
| 468 |
+
},
|
| 469 |
+
"151700": {
|
| 470 |
+
"content": "<|spk_bos|>",
|
| 471 |
+
"lstrip": false,
|
| 472 |
+
"normalized": false,
|
| 473 |
+
"rstrip": false,
|
| 474 |
+
"single_word": false,
|
| 475 |
+
"special": true
|
| 476 |
+
},
|
| 477 |
+
"151701": {
|
| 478 |
+
"content": "<|spk|>",
|
| 479 |
+
"lstrip": false,
|
| 480 |
+
"normalized": false,
|
| 481 |
+
"rstrip": false,
|
| 482 |
+
"single_word": false,
|
| 483 |
+
"special": true
|
| 484 |
+
},
|
| 485 |
+
"151702": {
|
| 486 |
+
"content": "<|spk_eos|>",
|
| 487 |
+
"lstrip": false,
|
| 488 |
+
"normalized": false,
|
| 489 |
+
"rstrip": false,
|
| 490 |
+
"single_word": false,
|
| 491 |
+
"special": true
|
| 492 |
+
},
|
| 493 |
+
"151703": {
|
| 494 |
+
"content": "<|tts_bos|>",
|
| 495 |
+
"lstrip": false,
|
| 496 |
+
"normalized": false,
|
| 497 |
+
"rstrip": false,
|
| 498 |
+
"single_word": false,
|
| 499 |
+
"special": true
|
| 500 |
+
},
|
| 501 |
+
"151704": {
|
| 502 |
+
"content": "<|tts_eos|>",
|
| 503 |
+
"lstrip": false,
|
| 504 |
+
"normalized": false,
|
| 505 |
+
"rstrip": false,
|
| 506 |
+
"single_word": false,
|
| 507 |
+
"special": true
|
| 508 |
+
},
|
| 509 |
+
"151705": {
|
| 510 |
+
"content": "<|listen|>",
|
| 511 |
+
"lstrip": false,
|
| 512 |
+
"normalized": false,
|
| 513 |
+
"rstrip": false,
|
| 514 |
+
"single_word": false,
|
| 515 |
+
"special": true
|
| 516 |
+
},
|
| 517 |
+
"151706": {
|
| 518 |
+
"content": "<|speak|>",
|
| 519 |
+
"lstrip": false,
|
| 520 |
+
"normalized": false,
|
| 521 |
+
"rstrip": false,
|
| 522 |
+
"single_word": false,
|
| 523 |
+
"special": true
|
| 524 |
+
},
|
| 525 |
+
"151707": {
|
| 526 |
+
"content": "<|interrupt|>",
|
| 527 |
+
"lstrip": false,
|
| 528 |
+
"normalized": false,
|
| 529 |
+
"rstrip": false,
|
| 530 |
+
"single_word": false,
|
| 531 |
+
"special": true
|
| 532 |
+
},
|
| 533 |
+
"151708": {
|
| 534 |
+
"content": "<|vad_start|>",
|
| 535 |
+
"lstrip": false,
|
| 536 |
+
"normalized": false,
|
| 537 |
+
"rstrip": false,
|
| 538 |
+
"single_word": false,
|
| 539 |
+
"special": true
|
| 540 |
+
},
|
| 541 |
+
"151709": {
|
| 542 |
+
"content": "<|vad_end|>",
|
| 543 |
+
"lstrip": false,
|
| 544 |
+
"normalized": false,
|
| 545 |
+
"rstrip": false,
|
| 546 |
+
"single_word": false,
|
| 547 |
+
"special": true
|
| 548 |
+
},
|
| 549 |
+
"151710": {
|
| 550 |
+
"content": "<|emotion_start|>",
|
| 551 |
+
"lstrip": false,
|
| 552 |
+
"normalized": false,
|
| 553 |
+
"rstrip": false,
|
| 554 |
+
"single_word": false,
|
| 555 |
+
"special": true
|
| 556 |
+
},
|
| 557 |
+
"151711": {
|
| 558 |
+
"content": "<|emotion_end|>",
|
| 559 |
+
"lstrip": false,
|
| 560 |
+
"normalized": false,
|
| 561 |
+
"rstrip": false,
|
| 562 |
+
"single_word": false,
|
| 563 |
+
"special": true
|
| 564 |
+
},
|
| 565 |
+
"151712": {
|
| 566 |
+
"content": "<|speed_start|>",
|
| 567 |
+
"lstrip": false,
|
| 568 |
+
"normalized": false,
|
| 569 |
+
"rstrip": false,
|
| 570 |
+
"single_word": false,
|
| 571 |
+
"special": true
|
| 572 |
+
},
|
| 573 |
+
"151713": {
|
| 574 |
+
"content": "<|speed_end|>",
|
| 575 |
+
"lstrip": false,
|
| 576 |
+
"normalized": false,
|
| 577 |
+
"rstrip": false,
|
| 578 |
+
"single_word": false,
|
| 579 |
+
"special": true
|
| 580 |
+
},
|
| 581 |
+
"151714": {
|
| 582 |
+
"content": "<|pitch_start|>",
|
| 583 |
+
"lstrip": false,
|
| 584 |
+
"normalized": false,
|
| 585 |
+
"rstrip": false,
|
| 586 |
+
"single_word": false,
|
| 587 |
+
"special": true
|
| 588 |
+
},
|
| 589 |
+
"151715": {
|
| 590 |
+
"content": "<|pitch_end|>",
|
| 591 |
+
"lstrip": false,
|
| 592 |
+
"normalized": false,
|
| 593 |
+
"rstrip": false,
|
| 594 |
+
"single_word": false,
|
| 595 |
+
"special": true
|
| 596 |
+
},
|
| 597 |
+
"151716": {
|
| 598 |
+
"content": "<|turn_bos|>",
|
| 599 |
+
"lstrip": false,
|
| 600 |
+
"normalized": false,
|
| 601 |
+
"rstrip": false,
|
| 602 |
+
"single_word": false,
|
| 603 |
+
"special": true
|
| 604 |
+
},
|
| 605 |
+
"151717": {
|
| 606 |
+
"content": "<|turn_eos|>",
|
| 607 |
+
"lstrip": false,
|
| 608 |
+
"normalized": false,
|
| 609 |
+
"rstrip": false,
|
| 610 |
+
"single_word": false,
|
| 611 |
+
"special": true
|
| 612 |
+
},
|
| 613 |
+
"151718": {
|
| 614 |
+
"content": "<|chunk_eos|>",
|
| 615 |
+
"lstrip": false,
|
| 616 |
+
"normalized": false,
|
| 617 |
+
"rstrip": false,
|
| 618 |
+
"single_word": false,
|
| 619 |
+
"special": true
|
| 620 |
+
},
|
| 621 |
+
"151719": {
|
| 622 |
+
"content": "<|chunk_bos|>",
|
| 623 |
+
"lstrip": false,
|
| 624 |
+
"normalized": false,
|
| 625 |
+
"rstrip": false,
|
| 626 |
+
"single_word": false,
|
| 627 |
+
"special": true
|
| 628 |
+
},
|
| 629 |
+
"151720": {
|
| 630 |
+
"content": "<|chunk_tts_bos|>",
|
| 631 |
+
"lstrip": false,
|
| 632 |
+
"normalized": false,
|
| 633 |
+
"rstrip": false,
|
| 634 |
+
"single_word": false,
|
| 635 |
+
"special": true
|
| 636 |
+
},
|
| 637 |
+
"151721": {
|
| 638 |
+
"content": "<|chunk_tts_eos|>",
|
| 639 |
+
"lstrip": false,
|
| 640 |
+
"normalized": false,
|
| 641 |
+
"rstrip": false,
|
| 642 |
+
"single_word": false,
|
| 643 |
+
"special": true
|
| 644 |
+
},
|
| 645 |
+
"151722": {
|
| 646 |
+
"content": "<|tts_pad|>",
|
| 647 |
+
"lstrip": false,
|
| 648 |
+
"normalized": false,
|
| 649 |
+
"rstrip": false,
|
| 650 |
+
"single_word": false,
|
| 651 |
+
"special": true
|
| 652 |
+
},
|
| 653 |
+
"151723": {
|
| 654 |
+
"content": "<|timbre_7|>",
|
| 655 |
+
"lstrip": false,
|
| 656 |
+
"normalized": false,
|
| 657 |
+
"rstrip": false,
|
| 658 |
+
"single_word": false,
|
| 659 |
+
"special": true
|
| 660 |
+
},
|
| 661 |
+
"151724": {
|
| 662 |
+
"content": "<|timbre_8|>",
|
| 663 |
+
"lstrip": false,
|
| 664 |
+
"normalized": false,
|
| 665 |
+
"rstrip": false,
|
| 666 |
+
"single_word": false,
|
| 667 |
+
"special": true
|
| 668 |
+
},
|
| 669 |
+
"151725": {
|
| 670 |
+
"content": "<|timbre_9|>",
|
| 671 |
+
"lstrip": false,
|
| 672 |
+
"normalized": false,
|
| 673 |
+
"rstrip": false,
|
| 674 |
+
"single_word": false,
|
| 675 |
+
"special": true
|
| 676 |
+
},
|
| 677 |
+
"151726": {
|
| 678 |
+
"content": "<|timbre_10|>",
|
| 679 |
+
"lstrip": false,
|
| 680 |
+
"normalized": false,
|
| 681 |
+
"rstrip": false,
|
| 682 |
+
"single_word": false,
|
| 683 |
+
"special": true
|
| 684 |
+
},
|
| 685 |
+
"151727": {
|
| 686 |
+
"content": "<|timbre_11|>",
|
| 687 |
+
"lstrip": false,
|
| 688 |
+
"normalized": false,
|
| 689 |
+
"rstrip": false,
|
| 690 |
+
"single_word": false,
|
| 691 |
+
"special": true
|
| 692 |
+
},
|
| 693 |
+
"151728": {
|
| 694 |
+
"content": "<|timbre_12|>",
|
| 695 |
+
"lstrip": false,
|
| 696 |
+
"normalized": false,
|
| 697 |
+
"rstrip": false,
|
| 698 |
+
"single_word": false,
|
| 699 |
+
"special": true
|
| 700 |
+
},
|
| 701 |
+
"151729": {
|
| 702 |
+
"content": "<|timbre_13|>",
|
| 703 |
+
"lstrip": false,
|
| 704 |
+
"normalized": false,
|
| 705 |
+
"rstrip": false,
|
| 706 |
+
"single_word": false,
|
| 707 |
+
"special": true
|
| 708 |
+
},
|
| 709 |
+
"151730": {
|
| 710 |
+
"content": "<|timbre_14|>",
|
| 711 |
+
"lstrip": false,
|
| 712 |
+
"normalized": false,
|
| 713 |
+
"rstrip": false,
|
| 714 |
+
"single_word": false,
|
| 715 |
+
"special": true
|
| 716 |
+
},
|
| 717 |
+
"151731": {
|
| 718 |
+
"content": "<|timbre_15|>",
|
| 719 |
+
"lstrip": false,
|
| 720 |
+
"normalized": false,
|
| 721 |
+
"rstrip": false,
|
| 722 |
+
"single_word": false,
|
| 723 |
+
"special": true
|
| 724 |
+
},
|
| 725 |
+
"151732": {
|
| 726 |
+
"content": "<|timbre_16|>",
|
| 727 |
+
"lstrip": false,
|
| 728 |
+
"normalized": false,
|
| 729 |
+
"rstrip": false,
|
| 730 |
+
"single_word": false,
|
| 731 |
+
"special": true
|
| 732 |
+
},
|
| 733 |
+
"151733": {
|
| 734 |
+
"content": "<|timbre_17|>",
|
| 735 |
+
"lstrip": false,
|
| 736 |
+
"normalized": false,
|
| 737 |
+
"rstrip": false,
|
| 738 |
+
"single_word": false,
|
| 739 |
+
"special": true
|
| 740 |
+
},
|
| 741 |
+
"151734": {
|
| 742 |
+
"content": "<|timbre_18|>",
|
| 743 |
+
"lstrip": false,
|
| 744 |
+
"normalized": false,
|
| 745 |
+
"rstrip": false,
|
| 746 |
+
"single_word": false,
|
| 747 |
+
"special": true
|
| 748 |
+
},
|
| 749 |
+
"151735": {
|
| 750 |
+
"content": "<|timbre_19|>",
|
| 751 |
+
"lstrip": false,
|
| 752 |
+
"normalized": false,
|
| 753 |
+
"rstrip": false,
|
| 754 |
+
"single_word": false,
|
| 755 |
+
"special": true
|
| 756 |
+
},
|
| 757 |
+
"151736": {
|
| 758 |
+
"content": "<|timbre_20|>",
|
| 759 |
+
"lstrip": false,
|
| 760 |
+
"normalized": false,
|
| 761 |
+
"rstrip": false,
|
| 762 |
+
"single_word": false,
|
| 763 |
+
"special": true
|
| 764 |
+
},
|
| 765 |
+
"151737": {
|
| 766 |
+
"content": "<|timbre_21|>",
|
| 767 |
+
"lstrip": false,
|
| 768 |
+
"normalized": false,
|
| 769 |
+
"rstrip": false,
|
| 770 |
+
"single_word": false,
|
| 771 |
+
"special": true
|
| 772 |
+
},
|
| 773 |
+
"151738": {
|
| 774 |
+
"content": "<|timbre_22|>",
|
| 775 |
+
"lstrip": false,
|
| 776 |
+
"normalized": false,
|
| 777 |
+
"rstrip": false,
|
| 778 |
+
"single_word": false,
|
| 779 |
+
"special": true
|
| 780 |
+
},
|
| 781 |
+
"151739": {
|
| 782 |
+
"content": "<|timbre_23|>",
|
| 783 |
+
"lstrip": false,
|
| 784 |
+
"normalized": false,
|
| 785 |
+
"rstrip": false,
|
| 786 |
+
"single_word": false,
|
| 787 |
+
"special": true
|
| 788 |
+
},
|
| 789 |
+
"151740": {
|
| 790 |
+
"content": "<|timbre_24|>",
|
| 791 |
+
"lstrip": false,
|
| 792 |
+
"normalized": false,
|
| 793 |
+
"rstrip": false,
|
| 794 |
+
"single_word": false,
|
| 795 |
+
"special": true
|
| 796 |
+
},
|
| 797 |
+
"151741": {
|
| 798 |
+
"content": "<|timbre_25|>",
|
| 799 |
+
"lstrip": false,
|
| 800 |
+
"normalized": false,
|
| 801 |
+
"rstrip": false,
|
| 802 |
+
"single_word": false,
|
| 803 |
+
"special": true
|
| 804 |
+
},
|
| 805 |
+
"151742": {
|
| 806 |
+
"content": "<|timbre_26|>",
|
| 807 |
+
"lstrip": false,
|
| 808 |
+
"normalized": false,
|
| 809 |
+
"rstrip": false,
|
| 810 |
+
"single_word": false,
|
| 811 |
+
"special": true
|
| 812 |
+
},
|
| 813 |
+
"151743": {
|
| 814 |
+
"content": "<|timbre_27|>",
|
| 815 |
+
"lstrip": false,
|
| 816 |
+
"normalized": false,
|
| 817 |
+
"rstrip": false,
|
| 818 |
+
"single_word": false,
|
| 819 |
+
"special": true
|
| 820 |
+
},
|
| 821 |
+
"151744": {
|
| 822 |
+
"content": "<|timbre_28|>",
|
| 823 |
+
"lstrip": false,
|
| 824 |
+
"normalized": false,
|
| 825 |
+
"rstrip": false,
|
| 826 |
+
"single_word": false,
|
| 827 |
+
"special": true
|
| 828 |
+
},
|
| 829 |
+
"151745": {
|
| 830 |
+
"content": "<|timbre_29|>",
|
| 831 |
+
"lstrip": false,
|
| 832 |
+
"normalized": false,
|
| 833 |
+
"rstrip": false,
|
| 834 |
+
"single_word": false,
|
| 835 |
+
"special": true
|
| 836 |
+
},
|
| 837 |
+
"151746": {
|
| 838 |
+
"content": "<|timbre_30|>",
|
| 839 |
+
"lstrip": false,
|
| 840 |
+
"normalized": false,
|
| 841 |
+
"rstrip": false,
|
| 842 |
+
"single_word": false,
|
| 843 |
+
"special": true
|
| 844 |
+
},
|
| 845 |
+
"151747": {
|
| 846 |
+
"content": "<|timbre_31|>",
|
| 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 |
+
"<answer>",
|
| 873 |
+
"</answer>",
|
| 874 |
+
"<focus>",
|
| 875 |
+
"</focus>",
|
| 876 |
+
"<line>",
|
| 877 |
+
"</line>",
|
| 878 |
+
"<perception>",
|
| 879 |
+
"</perception>",
|
| 880 |
+
"<source_image>",
|
| 881 |
+
"</source_image>",
|
| 882 |
+
"<image_save_to>",
|
| 883 |
+
"</image_save_to>",
|
| 884 |
+
"<|audio_start|>",
|
| 885 |
+
"<|audio|>",
|
| 886 |
+
"<|audio_end|>",
|
| 887 |
+
"<|spk_bos|>",
|
| 888 |
+
"<|spk|>",
|
| 889 |
+
"<|spk_eos|>",
|
| 890 |
+
"<|tts_bos|>",
|
| 891 |
+
"<|tts_eos|>",
|
| 892 |
+
"<|listen|>",
|
| 893 |
+
"<|speak|>",
|
| 894 |
+
"<|interrupt|>",
|
| 895 |
+
"<|vad_start|>",
|
| 896 |
+
"<|vad_end|>",
|
| 897 |
+
"<|emotion_start|>",
|
| 898 |
+
"<|emotion_end|>",
|
| 899 |
+
"<|speed_start|>",
|
| 900 |
+
"<|speed_end|>",
|
| 901 |
+
"<|pitch_start|>",
|
| 902 |
+
"<|pitch_end|>",
|
| 903 |
+
"<|chunk_eos|>",
|
| 904 |
+
"<|chunk_bos|>",
|
| 905 |
+
"<|chunk_tts_bos|>",
|
| 906 |
+
"<|chunk_tts_eos|>",
|
| 907 |
+
"<|tts_pad|>",
|
| 908 |
+
"<|timbre_7|>",
|
| 909 |
+
"<|timbre_8|>",
|
| 910 |
+
"<|timbre_9|>",
|
| 911 |
+
"<|timbre_10|>",
|
| 912 |
+
"<|timbre_11|>",
|
| 913 |
+
"<|timbre_12|>",
|
| 914 |
+
"<|timbre_13|>",
|
| 915 |
+
"<|timbre_14|>",
|
| 916 |
+
"<|timbre_15|>",
|
| 917 |
+
"<|timbre_16|>",
|
| 918 |
+
"<|timbre_17|>",
|
| 919 |
+
"<|timbre_18|>",
|
| 920 |
+
"<|timbre_19|>",
|
| 921 |
+
"<|timbre_20|>",
|
| 922 |
+
"<|timbre_21|>",
|
| 923 |
+
"<|timbre_22|>",
|
| 924 |
+
"<|timbre_23|>",
|
| 925 |
+
"<|timbre_24|>",
|
| 926 |
+
"<|timbre_25|>",
|
| 927 |
+
"<|timbre_26|>",
|
| 928 |
+
"<|timbre_27|>",
|
| 929 |
+
"<|timbre_28|>",
|
| 930 |
+
"<|timbre_29|>",
|
| 931 |
+
"<|timbre_30|>",
|
| 932 |
+
"<|timbre_31|>"
|
| 933 |
+
],
|
| 934 |
+
"auto_map": {
|
| 935 |
+
"AutoTokenizer": [
|
| 936 |
+
"openbmb/MiniCPM-o-4_5--tokenization_minicpmo_fast.MiniCPMOTokenizerFast",
|
| 937 |
+
null
|
| 938 |
+
]
|
| 939 |
+
},
|
| 940 |
+
"bos_token": "<|im_start|>",
|
| 941 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\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 {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first 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 {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n {%- if use_tts_template is defined and use_tts_template is true %}\n {{- '<|tts_bos|>' }}\n {%- endif %}\n{%- endif %}",
|
| 942 |
+
"clean_up_tokenization_spaces": false,
|
| 943 |
+
"eos_token": "<|im_end|>",
|
| 944 |
+
"errors": "replace",
|
| 945 |
+
"extra_special_tokens": {},
|
| 946 |
+
"model_max_length": 131072,
|
| 947 |
+
"pad_token": "<|endoftext|>",
|
| 948 |
+
"split_special_tokens": false,
|
| 949 |
+
"tokenizer_class": "MiniCPMOTokenizer",
|
| 950 |
+
"unk_token": "<unk>"
|
| 951 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|