hf-transformers-bot commited on
Commit
e1e2000
·
verified ·
1 Parent(s): 068fd96

Add tiny processor fixture for testing

Browse files
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "<|im_start|>{% for message in messages %}{{message['role'] | capitalize}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>\n{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}"
3
+ }
config.json ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SmolVLMForConditionalGeneration"
4
+ ],
5
+ "image_token_id": 49190,
6
+ "model_type": "smolvlm",
7
+ "pad_token_id": 128002,
8
+ "scale_factor": 4,
9
+ "text_config": {
10
+ "_flash_attn_2_enabled": true,
11
+ "_name_or_path": "None",
12
+ "architectures": [
13
+ "VLlama3ForCausalLM"
14
+ ],
15
+ "head_dim": 64,
16
+ "hidden_size": 576,
17
+ "initializer_range": 0.041666666666666664,
18
+ "intermediate_size": 1536,
19
+ "is_llama_config": true,
20
+ "max_position_embeddings": 8192,
21
+ "model_type": "llama",
22
+ "neftune_noise_alpha": 0.0,
23
+ "num_attention_heads": 9,
24
+ "num_hidden_layers": 30,
25
+ "num_key_value_heads": 3,
26
+ "pad_token_id": 2,
27
+ "perceiver_config": {
28
+ "_attn_implementation_autoset": false,
29
+ "_name_or_path": "",
30
+ "add_cross_attention": false,
31
+ "architectures": null,
32
+ "attention_dropout": 0.0,
33
+ "bad_words_ids": null,
34
+ "begin_suppress_tokens": null,
35
+ "bos_token_id": null,
36
+ "chunk_size_feed_forward": 0,
37
+ "cross_attention_hidden_size": null,
38
+ "decoder_start_token_id": null,
39
+ "diversity_penalty": 0.0,
40
+ "do_sample": false,
41
+ "early_stopping": false,
42
+ "encoder_no_repeat_ngram_size": 0,
43
+ "eos_token_id": null,
44
+ "exponential_decay_length_penalty": null,
45
+ "finetuning_task": null,
46
+ "forced_bos_token_id": null,
47
+ "forced_eos_token_id": null,
48
+ "hidden_act": "silu",
49
+ "id2label": {
50
+ "0": "LABEL_0",
51
+ "1": "LABEL_1"
52
+ },
53
+ "is_decoder": false,
54
+ "is_encoder_decoder": false,
55
+ "label2id": {
56
+ "LABEL_0": 0,
57
+ "LABEL_1": 1
58
+ },
59
+ "length_penalty": 1.0,
60
+ "max_length": 20,
61
+ "min_length": 0,
62
+ "model_type": "vllama3",
63
+ "no_repeat_ngram_size": 0,
64
+ "num_beam_groups": 1,
65
+ "num_beams": 1,
66
+ "num_key_value_heads": 1,
67
+ "num_return_sequences": 1,
68
+ "output_attentions": false,
69
+ "output_hidden_states": false,
70
+ "output_scores": false,
71
+ "pad_token_id": null,
72
+ "prefix": null,
73
+ "problem_type": null,
74
+ "pruned_heads": {},
75
+ "qk_layer_norms_perceiver": false,
76
+ "remove_invalid_values": false,
77
+ "repetition_penalty": 1.0,
78
+ "resampler_depth": 6,
79
+ "resampler_head_dim": 96,
80
+ "resampler_n_heads": 16,
81
+ "resampler_n_latents": 64,
82
+ "return_dict": true,
83
+ "return_dict_in_generate": false,
84
+ "sep_token_id": null,
85
+ "suppress_tokens": null,
86
+ "task_specific_params": null,
87
+ "temperature": 1.0,
88
+ "tf_legacy_loss": false,
89
+ "tie_encoder_decoder": false,
90
+ "tie_word_embeddings": true,
91
+ "tokenizer_class": null,
92
+ "top_k": 50,
93
+ "top_p": 1.0,
94
+ "torch_dtype": null,
95
+ "torchscript": false,
96
+ "transformers_version": "4.46.0",
97
+ "typical_p": 1.0,
98
+ "use_bfloat16": false
99
+ },
100
+ "pixel_shuffle_factor": 4,
101
+ "qk_layer_norms": false,
102
+ "rms_norm_eps": 1e-05,
103
+ "rope_interleaved": false,
104
+ "rope_theta": 100000,
105
+ "torch_dtype": "bfloat16",
106
+ "transformers.js_config": {
107
+ "kv_cache_dtype": {
108
+ "fp16": "float16",
109
+ "q4f16": "float16"
110
+ }
111
+ },
112
+ "use_resampler": false,
113
+ "vocab_size": 49280
114
+ },
115
+ "tie_word_embeddings": false,
116
+ "torch_dtype": "float32",
117
+ "transformers.js_config": {
118
+ "kv_cache_dtype": {
119
+ "fp16": "float16",
120
+ "q4f16": "float16"
121
+ }
122
+ },
123
+ "transformers_version": "4.47.1",
124
+ "use_cache": false,
125
+ "use_reentrant_checkpointing": false,
126
+ "vision_config": {
127
+ "hidden_size": 768,
128
+ "image_size": 512,
129
+ "max_image_size": {
130
+ "longest_edge": 512
131
+ },
132
+ "model_type": "smolvlm_vision",
133
+ "num_attention_heads": 12,
134
+ "patch_size": 16,
135
+ "size": {
136
+ "longest_edge": 2048
137
+ },
138
+ "tie_word_embeddings": false,
139
+ "use_base_siglip": true
140
+ },
141
+ "vocab_size": 500
142
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 49279,
5
+ "pad_token_id": 2,
6
+ "transformers_version": "4.47.1"
7
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_image_splitting": true,
4
+ "do_normalize": true,
5
+ "do_pad": true,
6
+ "do_rescale": true,
7
+ "do_resize": true,
8
+ "image_mean": [
9
+ 0.5,
10
+ 0.5,
11
+ 0.5
12
+ ],
13
+ "image_processor_type": "SmolVLMImageProcessor",
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "max_image_size": {
20
+ "longest_edge": 512
21
+ },
22
+ "processor_class": "SmolVLMProcessor",
23
+ "resample": 1,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "longest_edge": 2048
27
+ },
28
+ "video_sampling": {
29
+ "fps": 1,
30
+ "max_frames": 64,
31
+ "video_size": {
32
+ "longest_edge": 512
33
+ }
34
+ }
35
+ }
processor_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "image_seq_len": 64,
3
+ "processor_class": "SmolVLMProcessor"
4
+ }
tokenizer.json ADDED
@@ -0,0 +1,2841 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<|endoftext|>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "<|im_start|>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "<|im_end|>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "<repo_name>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 4,
44
+ "content": "<reponame>",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 5,
53
+ "content": "<file_sep>",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ },
60
+ {
61
+ "id": 6,
62
+ "content": "<filename>",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": false,
67
+ "special": true
68
+ },
69
+ {
70
+ "id": 7,
71
+ "content": "<gh_stars>",
72
+ "single_word": false,
73
+ "lstrip": false,
74
+ "rstrip": false,
75
+ "normalized": false,
76
+ "special": true
77
+ },
78
+ {
79
+ "id": 8,
80
+ "content": "<issue_start>",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": false,
85
+ "special": true
86
+ },
87
+ {
88
+ "id": 9,
89
+ "content": "<issue_comment>",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": false,
94
+ "special": true
95
+ },
96
+ {
97
+ "id": 10,
98
+ "content": "<issue_closed>",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ {
106
+ "id": 11,
107
+ "content": "<jupyter_start>",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
+ },
114
+ {
115
+ "id": 12,
116
+ "content": "<jupyter_text>",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": false,
121
+ "special": true
122
+ },
123
+ {
124
+ "id": 13,
125
+ "content": "<jupyter_code>",
126
+ "single_word": false,
127
+ "lstrip": false,
128
+ "rstrip": false,
129
+ "normalized": false,
130
+ "special": true
131
+ },
132
+ {
133
+ "id": 14,
134
+ "content": "<jupyter_output>",
135
+ "single_word": false,
136
+ "lstrip": false,
137
+ "rstrip": false,
138
+ "normalized": false,
139
+ "special": true
140
+ },
141
+ {
142
+ "id": 15,
143
+ "content": "<jupyter_script>",
144
+ "single_word": false,
145
+ "lstrip": false,
146
+ "rstrip": false,
147
+ "normalized": false,
148
+ "special": true
149
+ },
150
+ {
151
+ "id": 16,
152
+ "content": "<empty_output>",
153
+ "single_word": false,
154
+ "lstrip": false,
155
+ "rstrip": false,
156
+ "normalized": false,
157
+ "special": true
158
+ },
159
+ {
160
+ "id": 500,
161
+ "content": "<global-img>",
162
+ "single_word": false,
163
+ "lstrip": false,
164
+ "rstrip": false,
165
+ "normalized": false,
166
+ "special": true
167
+ },
168
+ {
169
+ "id": 501,
170
+ "content": "<row_1_col_1>",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": false,
175
+ "special": true
176
+ },
177
+ {
178
+ "id": 502,
179
+ "content": "<row_1_col_2>",
180
+ "single_word": false,
181
+ "lstrip": false,
182
+ "rstrip": false,
183
+ "normalized": false,
184
+ "special": true
185
+ },
186
+ {
187
+ "id": 503,
188
+ "content": "<row_1_col_3>",
189
+ "single_word": false,
190
+ "lstrip": false,
191
+ "rstrip": false,
192
+ "normalized": false,
193
+ "special": true
194
+ },
195
+ {
196
+ "id": 504,
197
+ "content": "<row_1_col_4>",
198
+ "single_word": false,
199
+ "lstrip": false,
200
+ "rstrip": false,
201
+ "normalized": false,
202
+ "special": true
203
+ },
204
+ {
205
+ "id": 505,
206
+ "content": "<row_1_col_5>",
207
+ "single_word": false,
208
+ "lstrip": false,
209
+ "rstrip": false,
210
+ "normalized": false,
211
+ "special": true
212
+ },
213
+ {
214
+ "id": 506,
215
+ "content": "<row_1_col_6>",
216
+ "single_word": false,
217
+ "lstrip": false,
218
+ "rstrip": false,
219
+ "normalized": false,
220
+ "special": true
221
+ },
222
+ {
223
+ "id": 507,
224
+ "content": "<row_2_col_1>",
225
+ "single_word": false,
226
+ "lstrip": false,
227
+ "rstrip": false,
228
+ "normalized": false,
229
+ "special": true
230
+ },
231
+ {
232
+ "id": 508,
233
+ "content": "<row_2_col_2>",
234
+ "single_word": false,
235
+ "lstrip": false,
236
+ "rstrip": false,
237
+ "normalized": false,
238
+ "special": true
239
+ },
240
+ {
241
+ "id": 509,
242
+ "content": "<row_2_col_3>",
243
+ "single_word": false,
244
+ "lstrip": false,
245
+ "rstrip": false,
246
+ "normalized": false,
247
+ "special": true
248
+ },
249
+ {
250
+ "id": 510,
251
+ "content": "<row_2_col_4>",
252
+ "single_word": false,
253
+ "lstrip": false,
254
+ "rstrip": false,
255
+ "normalized": false,
256
+ "special": true
257
+ },
258
+ {
259
+ "id": 511,
260
+ "content": "<row_2_col_5>",
261
+ "single_word": false,
262
+ "lstrip": false,
263
+ "rstrip": false,
264
+ "normalized": false,
265
+ "special": true
266
+ },
267
+ {
268
+ "id": 512,
269
+ "content": "<row_2_col_6>",
270
+ "single_word": false,
271
+ "lstrip": false,
272
+ "rstrip": false,
273
+ "normalized": false,
274
+ "special": true
275
+ },
276
+ {
277
+ "id": 513,
278
+ "content": "<row_3_col_1>",
279
+ "single_word": false,
280
+ "lstrip": false,
281
+ "rstrip": false,
282
+ "normalized": false,
283
+ "special": true
284
+ },
285
+ {
286
+ "id": 514,
287
+ "content": "<row_3_col_2>",
288
+ "single_word": false,
289
+ "lstrip": false,
290
+ "rstrip": false,
291
+ "normalized": false,
292
+ "special": true
293
+ },
294
+ {
295
+ "id": 515,
296
+ "content": "<row_3_col_3>",
297
+ "single_word": false,
298
+ "lstrip": false,
299
+ "rstrip": false,
300
+ "normalized": false,
301
+ "special": true
302
+ },
303
+ {
304
+ "id": 516,
305
+ "content": "<row_3_col_4>",
306
+ "single_word": false,
307
+ "lstrip": false,
308
+ "rstrip": false,
309
+ "normalized": false,
310
+ "special": true
311
+ },
312
+ {
313
+ "id": 517,
314
+ "content": "<row_3_col_5>",
315
+ "single_word": false,
316
+ "lstrip": false,
317
+ "rstrip": false,
318
+ "normalized": false,
319
+ "special": true
320
+ },
321
+ {
322
+ "id": 518,
323
+ "content": "<row_3_col_6>",
324
+ "single_word": false,
325
+ "lstrip": false,
326
+ "rstrip": false,
327
+ "normalized": false,
328
+ "special": true
329
+ },
330
+ {
331
+ "id": 519,
332
+ "content": "<row_4_col_1>",
333
+ "single_word": false,
334
+ "lstrip": false,
335
+ "rstrip": false,
336
+ "normalized": false,
337
+ "special": true
338
+ },
339
+ {
340
+ "id": 520,
341
+ "content": "<row_4_col_2>",
342
+ "single_word": false,
343
+ "lstrip": false,
344
+ "rstrip": false,
345
+ "normalized": false,
346
+ "special": true
347
+ },
348
+ {
349
+ "id": 521,
350
+ "content": "<row_4_col_3>",
351
+ "single_word": false,
352
+ "lstrip": false,
353
+ "rstrip": false,
354
+ "normalized": false,
355
+ "special": true
356
+ },
357
+ {
358
+ "id": 522,
359
+ "content": "<row_4_col_4>",
360
+ "single_word": false,
361
+ "lstrip": false,
362
+ "rstrip": false,
363
+ "normalized": false,
364
+ "special": true
365
+ },
366
+ {
367
+ "id": 523,
368
+ "content": "<row_4_col_5>",
369
+ "single_word": false,
370
+ "lstrip": false,
371
+ "rstrip": false,
372
+ "normalized": false,
373
+ "special": true
374
+ },
375
+ {
376
+ "id": 524,
377
+ "content": "<row_4_col_6>",
378
+ "single_word": false,
379
+ "lstrip": false,
380
+ "rstrip": false,
381
+ "normalized": false,
382
+ "special": true
383
+ },
384
+ {
385
+ "id": 525,
386
+ "content": "<row_5_col_1>",
387
+ "single_word": false,
388
+ "lstrip": false,
389
+ "rstrip": false,
390
+ "normalized": false,
391
+ "special": true
392
+ },
393
+ {
394
+ "id": 526,
395
+ "content": "<row_5_col_2>",
396
+ "single_word": false,
397
+ "lstrip": false,
398
+ "rstrip": false,
399
+ "normalized": false,
400
+ "special": true
401
+ },
402
+ {
403
+ "id": 527,
404
+ "content": "<row_5_col_3>",
405
+ "single_word": false,
406
+ "lstrip": false,
407
+ "rstrip": false,
408
+ "normalized": false,
409
+ "special": true
410
+ },
411
+ {
412
+ "id": 528,
413
+ "content": "<row_5_col_4>",
414
+ "single_word": false,
415
+ "lstrip": false,
416
+ "rstrip": false,
417
+ "normalized": false,
418
+ "special": true
419
+ },
420
+ {
421
+ "id": 529,
422
+ "content": "<row_5_col_5>",
423
+ "single_word": false,
424
+ "lstrip": false,
425
+ "rstrip": false,
426
+ "normalized": false,
427
+ "special": true
428
+ },
429
+ {
430
+ "id": 530,
431
+ "content": "<row_5_col_6>",
432
+ "single_word": false,
433
+ "lstrip": false,
434
+ "rstrip": false,
435
+ "normalized": false,
436
+ "special": true
437
+ },
438
+ {
439
+ "id": 531,
440
+ "content": "<row_6_col_1>",
441
+ "single_word": false,
442
+ "lstrip": false,
443
+ "rstrip": false,
444
+ "normalized": false,
445
+ "special": true
446
+ },
447
+ {
448
+ "id": 532,
449
+ "content": "<row_6_col_2>",
450
+ "single_word": false,
451
+ "lstrip": false,
452
+ "rstrip": false,
453
+ "normalized": false,
454
+ "special": true
455
+ },
456
+ {
457
+ "id": 533,
458
+ "content": "<row_6_col_3>",
459
+ "single_word": false,
460
+ "lstrip": false,
461
+ "rstrip": false,
462
+ "normalized": false,
463
+ "special": true
464
+ },
465
+ {
466
+ "id": 534,
467
+ "content": "<row_6_col_4>",
468
+ "single_word": false,
469
+ "lstrip": false,
470
+ "rstrip": false,
471
+ "normalized": false,
472
+ "special": true
473
+ },
474
+ {
475
+ "id": 535,
476
+ "content": "<row_6_col_5>",
477
+ "single_word": false,
478
+ "lstrip": false,
479
+ "rstrip": false,
480
+ "normalized": false,
481
+ "special": true
482
+ },
483
+ {
484
+ "id": 536,
485
+ "content": "<row_6_col_6>",
486
+ "single_word": false,
487
+ "lstrip": false,
488
+ "rstrip": false,
489
+ "normalized": false,
490
+ "special": true
491
+ },
492
+ {
493
+ "id": 537,
494
+ "content": "<fake_token_around_image>",
495
+ "single_word": false,
496
+ "lstrip": false,
497
+ "rstrip": false,
498
+ "normalized": false,
499
+ "special": true
500
+ },
501
+ {
502
+ "id": 538,
503
+ "content": "<image>",
504
+ "single_word": false,
505
+ "lstrip": false,
506
+ "rstrip": false,
507
+ "normalized": false,
508
+ "special": true
509
+ },
510
+ {
511
+ "id": 539,
512
+ "content": "<|reserved_special_token_0|>",
513
+ "single_word": false,
514
+ "lstrip": false,
515
+ "rstrip": false,
516
+ "normalized": false,
517
+ "special": true
518
+ },
519
+ {
520
+ "id": 540,
521
+ "content": "<|reserved_special_token_1|>",
522
+ "single_word": false,
523
+ "lstrip": false,
524
+ "rstrip": false,
525
+ "normalized": false,
526
+ "special": true
527
+ },
528
+ {
529
+ "id": 541,
530
+ "content": "<|reserved_special_token_2|>",
531
+ "single_word": false,
532
+ "lstrip": false,
533
+ "rstrip": false,
534
+ "normalized": false,
535
+ "special": true
536
+ },
537
+ {
538
+ "id": 542,
539
+ "content": "<|reserved_special_token_3|>",
540
+ "single_word": false,
541
+ "lstrip": false,
542
+ "rstrip": false,
543
+ "normalized": false,
544
+ "special": true
545
+ },
546
+ {
547
+ "id": 543,
548
+ "content": "<|reserved_special_token_4|>",
549
+ "single_word": false,
550
+ "lstrip": false,
551
+ "rstrip": false,
552
+ "normalized": false,
553
+ "special": true
554
+ },
555
+ {
556
+ "id": 544,
557
+ "content": "<|reserved_special_token_5|>",
558
+ "single_word": false,
559
+ "lstrip": false,
560
+ "rstrip": false,
561
+ "normalized": false,
562
+ "special": true
563
+ },
564
+ {
565
+ "id": 545,
566
+ "content": "<|reserved_special_token_6|>",
567
+ "single_word": false,
568
+ "lstrip": false,
569
+ "rstrip": false,
570
+ "normalized": false,
571
+ "special": true
572
+ },
573
+ {
574
+ "id": 546,
575
+ "content": "<|reserved_special_token_7|>",
576
+ "single_word": false,
577
+ "lstrip": false,
578
+ "rstrip": false,
579
+ "normalized": false,
580
+ "special": true
581
+ },
582
+ {
583
+ "id": 547,
584
+ "content": "<|reserved_special_token_8|>",
585
+ "single_word": false,
586
+ "lstrip": false,
587
+ "rstrip": false,
588
+ "normalized": false,
589
+ "special": true
590
+ },
591
+ {
592
+ "id": 548,
593
+ "content": "<|reserved_special_token_9|>",
594
+ "single_word": false,
595
+ "lstrip": false,
596
+ "rstrip": false,
597
+ "normalized": false,
598
+ "special": true
599
+ },
600
+ {
601
+ "id": 549,
602
+ "content": "<|reserved_special_token_10|>",
603
+ "single_word": false,
604
+ "lstrip": false,
605
+ "rstrip": false,
606
+ "normalized": false,
607
+ "special": true
608
+ },
609
+ {
610
+ "id": 550,
611
+ "content": "<|reserved_special_token_11|>",
612
+ "single_word": false,
613
+ "lstrip": false,
614
+ "rstrip": false,
615
+ "normalized": false,
616
+ "special": true
617
+ },
618
+ {
619
+ "id": 551,
620
+ "content": "<|reserved_special_token_12|>",
621
+ "single_word": false,
622
+ "lstrip": false,
623
+ "rstrip": false,
624
+ "normalized": false,
625
+ "special": true
626
+ },
627
+ {
628
+ "id": 552,
629
+ "content": "<|reserved_special_token_13|>",
630
+ "single_word": false,
631
+ "lstrip": false,
632
+ "rstrip": false,
633
+ "normalized": false,
634
+ "special": true
635
+ },
636
+ {
637
+ "id": 553,
638
+ "content": "<|reserved_special_token_14|>",
639
+ "single_word": false,
640
+ "lstrip": false,
641
+ "rstrip": false,
642
+ "normalized": false,
643
+ "special": true
644
+ },
645
+ {
646
+ "id": 554,
647
+ "content": "<|reserved_special_token_15|>",
648
+ "single_word": false,
649
+ "lstrip": false,
650
+ "rstrip": false,
651
+ "normalized": false,
652
+ "special": true
653
+ },
654
+ {
655
+ "id": 555,
656
+ "content": "<|reserved_special_token_16|>",
657
+ "single_word": false,
658
+ "lstrip": false,
659
+ "rstrip": false,
660
+ "normalized": false,
661
+ "special": true
662
+ },
663
+ {
664
+ "id": 556,
665
+ "content": "<|reserved_special_token_17|>",
666
+ "single_word": false,
667
+ "lstrip": false,
668
+ "rstrip": false,
669
+ "normalized": false,
670
+ "special": true
671
+ },
672
+ {
673
+ "id": 557,
674
+ "content": "<|reserved_special_token_18|>",
675
+ "single_word": false,
676
+ "lstrip": false,
677
+ "rstrip": false,
678
+ "normalized": false,
679
+ "special": true
680
+ },
681
+ {
682
+ "id": 558,
683
+ "content": "<|reserved_special_token_19|>",
684
+ "single_word": false,
685
+ "lstrip": false,
686
+ "rstrip": false,
687
+ "normalized": false,
688
+ "special": true
689
+ },
690
+ {
691
+ "id": 559,
692
+ "content": "<|reserved_special_token_20|>",
693
+ "single_word": false,
694
+ "lstrip": false,
695
+ "rstrip": false,
696
+ "normalized": false,
697
+ "special": true
698
+ },
699
+ {
700
+ "id": 560,
701
+ "content": "<|reserved_special_token_21|>",
702
+ "single_word": false,
703
+ "lstrip": false,
704
+ "rstrip": false,
705
+ "normalized": false,
706
+ "special": true
707
+ },
708
+ {
709
+ "id": 561,
710
+ "content": "<|reserved_special_token_22|>",
711
+ "single_word": false,
712
+ "lstrip": false,
713
+ "rstrip": false,
714
+ "normalized": false,
715
+ "special": true
716
+ },
717
+ {
718
+ "id": 562,
719
+ "content": "<|reserved_special_token_23|>",
720
+ "single_word": false,
721
+ "lstrip": false,
722
+ "rstrip": false,
723
+ "normalized": false,
724
+ "special": true
725
+ },
726
+ {
727
+ "id": 563,
728
+ "content": "<|reserved_special_token_24|>",
729
+ "single_word": false,
730
+ "lstrip": false,
731
+ "rstrip": false,
732
+ "normalized": false,
733
+ "special": true
734
+ },
735
+ {
736
+ "id": 564,
737
+ "content": "<|reserved_special_token_25|>",
738
+ "single_word": false,
739
+ "lstrip": false,
740
+ "rstrip": false,
741
+ "normalized": false,
742
+ "special": true
743
+ },
744
+ {
745
+ "id": 565,
746
+ "content": "<|reserved_special_token_26|>",
747
+ "single_word": false,
748
+ "lstrip": false,
749
+ "rstrip": false,
750
+ "normalized": false,
751
+ "special": true
752
+ },
753
+ {
754
+ "id": 566,
755
+ "content": "<|reserved_special_token_27|>",
756
+ "single_word": false,
757
+ "lstrip": false,
758
+ "rstrip": false,
759
+ "normalized": false,
760
+ "special": true
761
+ },
762
+ {
763
+ "id": 567,
764
+ "content": "<|reserved_special_token_28|>",
765
+ "single_word": false,
766
+ "lstrip": false,
767
+ "rstrip": false,
768
+ "normalized": false,
769
+ "special": true
770
+ },
771
+ {
772
+ "id": 568,
773
+ "content": "<|reserved_special_token_29|>",
774
+ "single_word": false,
775
+ "lstrip": false,
776
+ "rstrip": false,
777
+ "normalized": false,
778
+ "special": true
779
+ },
780
+ {
781
+ "id": 569,
782
+ "content": "<|reserved_special_token_30|>",
783
+ "single_word": false,
784
+ "lstrip": false,
785
+ "rstrip": false,
786
+ "normalized": false,
787
+ "special": true
788
+ },
789
+ {
790
+ "id": 570,
791
+ "content": "<|reserved_special_token_31|>",
792
+ "single_word": false,
793
+ "lstrip": false,
794
+ "rstrip": false,
795
+ "normalized": false,
796
+ "special": true
797
+ },
798
+ {
799
+ "id": 571,
800
+ "content": "<|reserved_special_token_32|>",
801
+ "single_word": false,
802
+ "lstrip": false,
803
+ "rstrip": false,
804
+ "normalized": false,
805
+ "special": true
806
+ },
807
+ {
808
+ "id": 572,
809
+ "content": "<|reserved_special_token_33|>",
810
+ "single_word": false,
811
+ "lstrip": false,
812
+ "rstrip": false,
813
+ "normalized": false,
814
+ "special": true
815
+ },
816
+ {
817
+ "id": 573,
818
+ "content": "<|reserved_special_token_34|>",
819
+ "single_word": false,
820
+ "lstrip": false,
821
+ "rstrip": false,
822
+ "normalized": false,
823
+ "special": true
824
+ },
825
+ {
826
+ "id": 574,
827
+ "content": "<|reserved_special_token_35|>",
828
+ "single_word": false,
829
+ "lstrip": false,
830
+ "rstrip": false,
831
+ "normalized": false,
832
+ "special": true
833
+ },
834
+ {
835
+ "id": 575,
836
+ "content": "<|reserved_special_token_36|>",
837
+ "single_word": false,
838
+ "lstrip": false,
839
+ "rstrip": false,
840
+ "normalized": false,
841
+ "special": true
842
+ },
843
+ {
844
+ "id": 576,
845
+ "content": "<|reserved_special_token_37|>",
846
+ "single_word": false,
847
+ "lstrip": false,
848
+ "rstrip": false,
849
+ "normalized": false,
850
+ "special": true
851
+ },
852
+ {
853
+ "id": 577,
854
+ "content": "<|reserved_special_token_38|>",
855
+ "single_word": false,
856
+ "lstrip": false,
857
+ "rstrip": false,
858
+ "normalized": false,
859
+ "special": true
860
+ },
861
+ {
862
+ "id": 578,
863
+ "content": "<|reserved_special_token_39|>",
864
+ "single_word": false,
865
+ "lstrip": false,
866
+ "rstrip": false,
867
+ "normalized": false,
868
+ "special": true
869
+ },
870
+ {
871
+ "id": 579,
872
+ "content": "<|reserved_special_token_40|>",
873
+ "single_word": false,
874
+ "lstrip": false,
875
+ "rstrip": false,
876
+ "normalized": false,
877
+ "special": true
878
+ },
879
+ {
880
+ "id": 580,
881
+ "content": "<|reserved_special_token_41|>",
882
+ "single_word": false,
883
+ "lstrip": false,
884
+ "rstrip": false,
885
+ "normalized": false,
886
+ "special": true
887
+ },
888
+ {
889
+ "id": 581,
890
+ "content": "<|reserved_special_token_42|>",
891
+ "single_word": false,
892
+ "lstrip": false,
893
+ "rstrip": false,
894
+ "normalized": false,
895
+ "special": true
896
+ },
897
+ {
898
+ "id": 582,
899
+ "content": "<|reserved_special_token_43|>",
900
+ "single_word": false,
901
+ "lstrip": false,
902
+ "rstrip": false,
903
+ "normalized": false,
904
+ "special": true
905
+ },
906
+ {
907
+ "id": 583,
908
+ "content": "<|reserved_special_token_44|>",
909
+ "single_word": false,
910
+ "lstrip": false,
911
+ "rstrip": false,
912
+ "normalized": false,
913
+ "special": true
914
+ },
915
+ {
916
+ "id": 584,
917
+ "content": "<|reserved_special_token_45|>",
918
+ "single_word": false,
919
+ "lstrip": false,
920
+ "rstrip": false,
921
+ "normalized": false,
922
+ "special": true
923
+ },
924
+ {
925
+ "id": 585,
926
+ "content": "<|reserved_special_token_46|>",
927
+ "single_word": false,
928
+ "lstrip": false,
929
+ "rstrip": false,
930
+ "normalized": false,
931
+ "special": true
932
+ },
933
+ {
934
+ "id": 586,
935
+ "content": "<|reserved_special_token_47|>",
936
+ "single_word": false,
937
+ "lstrip": false,
938
+ "rstrip": false,
939
+ "normalized": false,
940
+ "special": true
941
+ },
942
+ {
943
+ "id": 587,
944
+ "content": "<|reserved_special_token_48|>",
945
+ "single_word": false,
946
+ "lstrip": false,
947
+ "rstrip": false,
948
+ "normalized": false,
949
+ "special": true
950
+ },
951
+ {
952
+ "id": 588,
953
+ "content": "<|reserved_special_token_49|>",
954
+ "single_word": false,
955
+ "lstrip": false,
956
+ "rstrip": false,
957
+ "normalized": false,
958
+ "special": true
959
+ },
960
+ {
961
+ "id": 589,
962
+ "content": "<|reserved_special_token_50|>",
963
+ "single_word": false,
964
+ "lstrip": false,
965
+ "rstrip": false,
966
+ "normalized": false,
967
+ "special": true
968
+ },
969
+ {
970
+ "id": 590,
971
+ "content": "<|reserved_special_token_51|>",
972
+ "single_word": false,
973
+ "lstrip": false,
974
+ "rstrip": false,
975
+ "normalized": false,
976
+ "special": true
977
+ },
978
+ {
979
+ "id": 591,
980
+ "content": "<|reserved_special_token_52|>",
981
+ "single_word": false,
982
+ "lstrip": false,
983
+ "rstrip": false,
984
+ "normalized": false,
985
+ "special": true
986
+ },
987
+ {
988
+ "id": 592,
989
+ "content": "<|reserved_special_token_53|>",
990
+ "single_word": false,
991
+ "lstrip": false,
992
+ "rstrip": false,
993
+ "normalized": false,
994
+ "special": true
995
+ },
996
+ {
997
+ "id": 593,
998
+ "content": "<|reserved_special_token_54|>",
999
+ "single_word": false,
1000
+ "lstrip": false,
1001
+ "rstrip": false,
1002
+ "normalized": false,
1003
+ "special": true
1004
+ },
1005
+ {
1006
+ "id": 594,
1007
+ "content": "<|reserved_special_token_55|>",
1008
+ "single_word": false,
1009
+ "lstrip": false,
1010
+ "rstrip": false,
1011
+ "normalized": false,
1012
+ "special": true
1013
+ },
1014
+ {
1015
+ "id": 595,
1016
+ "content": "<|reserved_special_token_56|>",
1017
+ "single_word": false,
1018
+ "lstrip": false,
1019
+ "rstrip": false,
1020
+ "normalized": false,
1021
+ "special": true
1022
+ },
1023
+ {
1024
+ "id": 596,
1025
+ "content": "<|reserved_special_token_57|>",
1026
+ "single_word": false,
1027
+ "lstrip": false,
1028
+ "rstrip": false,
1029
+ "normalized": false,
1030
+ "special": true
1031
+ },
1032
+ {
1033
+ "id": 597,
1034
+ "content": "<|reserved_special_token_58|>",
1035
+ "single_word": false,
1036
+ "lstrip": false,
1037
+ "rstrip": false,
1038
+ "normalized": false,
1039
+ "special": true
1040
+ },
1041
+ {
1042
+ "id": 598,
1043
+ "content": "<|reserved_special_token_59|>",
1044
+ "single_word": false,
1045
+ "lstrip": false,
1046
+ "rstrip": false,
1047
+ "normalized": false,
1048
+ "special": true
1049
+ },
1050
+ {
1051
+ "id": 599,
1052
+ "content": "<|reserved_special_token_60|>",
1053
+ "single_word": false,
1054
+ "lstrip": false,
1055
+ "rstrip": false,
1056
+ "normalized": false,
1057
+ "special": true
1058
+ },
1059
+ {
1060
+ "id": 600,
1061
+ "content": "<|reserved_special_token_61|>",
1062
+ "single_word": false,
1063
+ "lstrip": false,
1064
+ "rstrip": false,
1065
+ "normalized": false,
1066
+ "special": true
1067
+ },
1068
+ {
1069
+ "id": 601,
1070
+ "content": "<|reserved_special_token_62|>",
1071
+ "single_word": false,
1072
+ "lstrip": false,
1073
+ "rstrip": false,
1074
+ "normalized": false,
1075
+ "special": true
1076
+ },
1077
+ {
1078
+ "id": 602,
1079
+ "content": "<|reserved_special_token_63|>",
1080
+ "single_word": false,
1081
+ "lstrip": false,
1082
+ "rstrip": false,
1083
+ "normalized": false,
1084
+ "special": true
1085
+ },
1086
+ {
1087
+ "id": 603,
1088
+ "content": "<|reserved_special_token_64|>",
1089
+ "single_word": false,
1090
+ "lstrip": false,
1091
+ "rstrip": false,
1092
+ "normalized": false,
1093
+ "special": true
1094
+ },
1095
+ {
1096
+ "id": 604,
1097
+ "content": "<|reserved_special_token_65|>",
1098
+ "single_word": false,
1099
+ "lstrip": false,
1100
+ "rstrip": false,
1101
+ "normalized": false,
1102
+ "special": true
1103
+ },
1104
+ {
1105
+ "id": 605,
1106
+ "content": "<|reserved_special_token_66|>",
1107
+ "single_word": false,
1108
+ "lstrip": false,
1109
+ "rstrip": false,
1110
+ "normalized": false,
1111
+ "special": true
1112
+ },
1113
+ {
1114
+ "id": 606,
1115
+ "content": "<|reserved_special_token_67|>",
1116
+ "single_word": false,
1117
+ "lstrip": false,
1118
+ "rstrip": false,
1119
+ "normalized": false,
1120
+ "special": true
1121
+ },
1122
+ {
1123
+ "id": 607,
1124
+ "content": "<|reserved_special_token_68|>",
1125
+ "single_word": false,
1126
+ "lstrip": false,
1127
+ "rstrip": false,
1128
+ "normalized": false,
1129
+ "special": true
1130
+ },
1131
+ {
1132
+ "id": 608,
1133
+ "content": "<|reserved_special_token_69|>",
1134
+ "single_word": false,
1135
+ "lstrip": false,
1136
+ "rstrip": false,
1137
+ "normalized": false,
1138
+ "special": true
1139
+ },
1140
+ {
1141
+ "id": 609,
1142
+ "content": "<|reserved_special_token_70|>",
1143
+ "single_word": false,
1144
+ "lstrip": false,
1145
+ "rstrip": false,
1146
+ "normalized": false,
1147
+ "special": true
1148
+ },
1149
+ {
1150
+ "id": 610,
1151
+ "content": "<|reserved_special_token_71|>",
1152
+ "single_word": false,
1153
+ "lstrip": false,
1154
+ "rstrip": false,
1155
+ "normalized": false,
1156
+ "special": true
1157
+ },
1158
+ {
1159
+ "id": 611,
1160
+ "content": "<|reserved_special_token_72|>",
1161
+ "single_word": false,
1162
+ "lstrip": false,
1163
+ "rstrip": false,
1164
+ "normalized": false,
1165
+ "special": true
1166
+ },
1167
+ {
1168
+ "id": 612,
1169
+ "content": "<|reserved_special_token_73|>",
1170
+ "single_word": false,
1171
+ "lstrip": false,
1172
+ "rstrip": false,
1173
+ "normalized": false,
1174
+ "special": true
1175
+ },
1176
+ {
1177
+ "id": 613,
1178
+ "content": "<|reserved_special_token_74|>",
1179
+ "single_word": false,
1180
+ "lstrip": false,
1181
+ "rstrip": false,
1182
+ "normalized": false,
1183
+ "special": true
1184
+ },
1185
+ {
1186
+ "id": 614,
1187
+ "content": "<|reserved_special_token_75|>",
1188
+ "single_word": false,
1189
+ "lstrip": false,
1190
+ "rstrip": false,
1191
+ "normalized": false,
1192
+ "special": true
1193
+ },
1194
+ {
1195
+ "id": 615,
1196
+ "content": "<|reserved_special_token_76|>",
1197
+ "single_word": false,
1198
+ "lstrip": false,
1199
+ "rstrip": false,
1200
+ "normalized": false,
1201
+ "special": true
1202
+ },
1203
+ {
1204
+ "id": 616,
1205
+ "content": "<|reserved_special_token_77|>",
1206
+ "single_word": false,
1207
+ "lstrip": false,
1208
+ "rstrip": false,
1209
+ "normalized": false,
1210
+ "special": true
1211
+ },
1212
+ {
1213
+ "id": 617,
1214
+ "content": "<|reserved_special_token_78|>",
1215
+ "single_word": false,
1216
+ "lstrip": false,
1217
+ "rstrip": false,
1218
+ "normalized": false,
1219
+ "special": true
1220
+ },
1221
+ {
1222
+ "id": 618,
1223
+ "content": "<|reserved_special_token_79|>",
1224
+ "single_word": false,
1225
+ "lstrip": false,
1226
+ "rstrip": false,
1227
+ "normalized": false,
1228
+ "special": true
1229
+ },
1230
+ {
1231
+ "id": 619,
1232
+ "content": "<|reserved_special_token_80|>",
1233
+ "single_word": false,
1234
+ "lstrip": false,
1235
+ "rstrip": false,
1236
+ "normalized": false,
1237
+ "special": true
1238
+ },
1239
+ {
1240
+ "id": 620,
1241
+ "content": "<|reserved_special_token_81|>",
1242
+ "single_word": false,
1243
+ "lstrip": false,
1244
+ "rstrip": false,
1245
+ "normalized": false,
1246
+ "special": true
1247
+ },
1248
+ {
1249
+ "id": 621,
1250
+ "content": "<|reserved_special_token_82|>",
1251
+ "single_word": false,
1252
+ "lstrip": false,
1253
+ "rstrip": false,
1254
+ "normalized": false,
1255
+ "special": true
1256
+ },
1257
+ {
1258
+ "id": 622,
1259
+ "content": "<|reserved_special_token_83|>",
1260
+ "single_word": false,
1261
+ "lstrip": false,
1262
+ "rstrip": false,
1263
+ "normalized": false,
1264
+ "special": true
1265
+ },
1266
+ {
1267
+ "id": 623,
1268
+ "content": "<|reserved_special_token_84|>",
1269
+ "single_word": false,
1270
+ "lstrip": false,
1271
+ "rstrip": false,
1272
+ "normalized": false,
1273
+ "special": true
1274
+ },
1275
+ {
1276
+ "id": 624,
1277
+ "content": "<|reserved_special_token_85|>",
1278
+ "single_word": false,
1279
+ "lstrip": false,
1280
+ "rstrip": false,
1281
+ "normalized": false,
1282
+ "special": true
1283
+ },
1284
+ {
1285
+ "id": 625,
1286
+ "content": "<|reserved_special_token_86|>",
1287
+ "single_word": false,
1288
+ "lstrip": false,
1289
+ "rstrip": false,
1290
+ "normalized": false,
1291
+ "special": true
1292
+ },
1293
+ {
1294
+ "id": 626,
1295
+ "content": "<|reserved_special_token_87|>",
1296
+ "single_word": false,
1297
+ "lstrip": false,
1298
+ "rstrip": false,
1299
+ "normalized": false,
1300
+ "special": true
1301
+ },
1302
+ {
1303
+ "id": 627,
1304
+ "content": "<end_of_utterance>",
1305
+ "single_word": false,
1306
+ "lstrip": false,
1307
+ "rstrip": false,
1308
+ "normalized": false,
1309
+ "special": true
1310
+ }
1311
+ ],
1312
+ "normalizer": null,
1313
+ "pre_tokenizer": {
1314
+ "type": "Sequence",
1315
+ "pretokenizers": [
1316
+ {
1317
+ "type": "Digits",
1318
+ "individual_digits": true
1319
+ },
1320
+ {
1321
+ "type": "ByteLevel",
1322
+ "add_prefix_space": false,
1323
+ "trim_offsets": true,
1324
+ "use_regex": true
1325
+ }
1326
+ ]
1327
+ },
1328
+ "post_processor": null,
1329
+ "decoder": {
1330
+ "type": "ByteLevel",
1331
+ "add_prefix_space": true,
1332
+ "trim_offsets": true,
1333
+ "use_regex": true
1334
+ },
1335
+ "model": {
1336
+ "type": "BPE",
1337
+ "dropout": null,
1338
+ "unk_token": null,
1339
+ "continuing_subword_prefix": null,
1340
+ "end_of_word_suffix": null,
1341
+ "fuse_unk": false,
1342
+ "byte_fallback": false,
1343
+ "ignore_merges": false,
1344
+ "vocab": {
1345
+ "<|endoftext|>": 0,
1346
+ "<|im_start|>": 1,
1347
+ "<|im_end|>": 2,
1348
+ "<repo_name>": 3,
1349
+ "<reponame>": 4,
1350
+ "<file_sep>": 5,
1351
+ "<filename>": 6,
1352
+ "<gh_stars>": 7,
1353
+ "<issue_start>": 8,
1354
+ "<issue_comment>": 9,
1355
+ "<issue_closed>": 10,
1356
+ "<jupyter_start>": 11,
1357
+ "<jupyter_text>": 12,
1358
+ "<jupyter_code>": 13,
1359
+ "<jupyter_output>": 14,
1360
+ "<jupyter_script>": 15,
1361
+ "<empty_output>": 16,
1362
+ "!": 17,
1363
+ "\"": 18,
1364
+ "#": 19,
1365
+ "$": 20,
1366
+ "%": 21,
1367
+ "&": 22,
1368
+ "'": 23,
1369
+ "(": 24,
1370
+ ")": 25,
1371
+ "*": 26,
1372
+ "+": 27,
1373
+ ",": 28,
1374
+ "-": 29,
1375
+ ".": 30,
1376
+ "/": 31,
1377
+ "0": 32,
1378
+ "1": 33,
1379
+ "2": 34,
1380
+ "3": 35,
1381
+ "4": 36,
1382
+ "5": 37,
1383
+ "6": 38,
1384
+ "7": 39,
1385
+ "8": 40,
1386
+ "9": 41,
1387
+ ":": 42,
1388
+ ";": 43,
1389
+ "<": 44,
1390
+ "=": 45,
1391
+ ">": 46,
1392
+ "?": 47,
1393
+ "@": 48,
1394
+ "A": 49,
1395
+ "B": 50,
1396
+ "C": 51,
1397
+ "D": 52,
1398
+ "E": 53,
1399
+ "F": 54,
1400
+ "G": 55,
1401
+ "H": 56,
1402
+ "I": 57,
1403
+ "J": 58,
1404
+ "K": 59,
1405
+ "L": 60,
1406
+ "M": 61,
1407
+ "N": 62,
1408
+ "O": 63,
1409
+ "P": 64,
1410
+ "Q": 65,
1411
+ "R": 66,
1412
+ "S": 67,
1413
+ "T": 68,
1414
+ "U": 69,
1415
+ "V": 70,
1416
+ "W": 71,
1417
+ "X": 72,
1418
+ "Y": 73,
1419
+ "Z": 74,
1420
+ "[": 75,
1421
+ "\\": 76,
1422
+ "]": 77,
1423
+ "^": 78,
1424
+ "_": 79,
1425
+ "`": 80,
1426
+ "a": 81,
1427
+ "b": 82,
1428
+ "c": 83,
1429
+ "d": 84,
1430
+ "e": 85,
1431
+ "f": 86,
1432
+ "g": 87,
1433
+ "h": 88,
1434
+ "i": 89,
1435
+ "j": 90,
1436
+ "k": 91,
1437
+ "l": 92,
1438
+ "m": 93,
1439
+ "n": 94,
1440
+ "o": 95,
1441
+ "p": 96,
1442
+ "q": 97,
1443
+ "r": 98,
1444
+ "s": 99,
1445
+ "t": 100,
1446
+ "u": 101,
1447
+ "v": 102,
1448
+ "w": 103,
1449
+ "x": 104,
1450
+ "y": 105,
1451
+ "z": 106,
1452
+ "{": 107,
1453
+ "|": 108,
1454
+ "}": 109,
1455
+ "~": 110,
1456
+ "¡": 111,
1457
+ "¢": 112,
1458
+ "£": 113,
1459
+ "¤": 114,
1460
+ "¥": 115,
1461
+ "¦": 116,
1462
+ "§": 117,
1463
+ "¨": 118,
1464
+ "©": 119,
1465
+ "ª": 120,
1466
+ "«": 121,
1467
+ "¬": 122,
1468
+ "®": 123,
1469
+ "¯": 124,
1470
+ "°": 125,
1471
+ "±": 126,
1472
+ "²": 127,
1473
+ "³": 128,
1474
+ "´": 129,
1475
+ "µ": 130,
1476
+ "¶": 131,
1477
+ "·": 132,
1478
+ "¸": 133,
1479
+ "¹": 134,
1480
+ "º": 135,
1481
+ "»": 136,
1482
+ "¼": 137,
1483
+ "½": 138,
1484
+ "¾": 139,
1485
+ "¿": 140,
1486
+ "Â": 141,
1487
+ "Ã": 142,
1488
+ "Ä": 143,
1489
+ "Å": 144,
1490
+ "Æ": 145,
1491
+ "Ç": 146,
1492
+ "È": 147,
1493
+ "É": 148,
1494
+ "Ê": 149,
1495
+ "Ë": 150,
1496
+ "Ì": 151,
1497
+ "Í": 152,
1498
+ "Î": 153,
1499
+ "Ï": 154,
1500
+ "Ð": 155,
1501
+ "Ñ": 156,
1502
+ "Ò": 157,
1503
+ "Ó": 158,
1504
+ "Ô": 159,
1505
+ "Õ": 160,
1506
+ "Ö": 161,
1507
+ "×": 162,
1508
+ "Ø": 163,
1509
+ "Ù": 164,
1510
+ "Ú": 165,
1511
+ "Û": 166,
1512
+ "Ü": 167,
1513
+ "Ý": 168,
1514
+ "Þ": 169,
1515
+ "ß": 170,
1516
+ "à": 171,
1517
+ "á": 172,
1518
+ "â": 173,
1519
+ "ã": 174,
1520
+ "ä": 175,
1521
+ "å": 176,
1522
+ "æ": 177,
1523
+ "ç": 178,
1524
+ "è": 179,
1525
+ "é": 180,
1526
+ "ê": 181,
1527
+ "ë": 182,
1528
+ "ì": 183,
1529
+ "í": 184,
1530
+ "î": 185,
1531
+ "ï": 186,
1532
+ "ð": 187,
1533
+ "ó": 188,
1534
+ "ô": 189,
1535
+ "Ā": 190,
1536
+ "ā": 191,
1537
+ "Ă": 192,
1538
+ "ă": 193,
1539
+ "ą": 194,
1540
+ "ć": 195,
1541
+ "Ĉ": 196,
1542
+ "ĉ": 197,
1543
+ "Ċ": 198,
1544
+ "ċ": 199,
1545
+ "Č": 200,
1546
+ "č": 201,
1547
+ "Ď": 202,
1548
+ "ď": 203,
1549
+ "Đ": 204,
1550
+ "đ": 205,
1551
+ "Ē": 206,
1552
+ "ĕ": 207,
1553
+ "ė": 208,
1554
+ "Ę": 209,
1555
+ "ę": 210,
1556
+ "Ě": 211,
1557
+ "ě": 212,
1558
+ "Ĝ": 213,
1559
+ "Ğ": 214,
1560
+ "ğ": 215,
1561
+ "Ġ": 216,
1562
+ "ġ": 217,
1563
+ "Ģ": 218,
1564
+ "ģ": 219,
1565
+ "Ĥ": 220,
1566
+ "ĥ": 221,
1567
+ "Ħ": 222,
1568
+ "ħ": 223,
1569
+ "Ĩ": 224,
1570
+ "ĩ": 225,
1571
+ "Ī": 226,
1572
+ "ī": 227,
1573
+ "Ĭ": 228,
1574
+ "ĭ": 229,
1575
+ "Į": 230,
1576
+ "į": 231,
1577
+ "İ": 232,
1578
+ "ı": 233,
1579
+ "IJ": 234,
1580
+ "ij": 235,
1581
+ "Ĵ": 236,
1582
+ "ĵ": 237,
1583
+ "Ķ": 238,
1584
+ "ķ": 239,
1585
+ "ĸ": 240,
1586
+ "Ĺ": 241,
1587
+ "ĺ": 242,
1588
+ "Ļ": 243,
1589
+ "ļ": 244,
1590
+ "Ľ": 245,
1591
+ "ľ": 246,
1592
+ "Ŀ": 247,
1593
+ "ŀ": 248,
1594
+ "Ł": 249,
1595
+ "ł": 250,
1596
+ "Ń": 251,
1597
+ "Ġt": 252,
1598
+ "Ġa": 253,
1599
+ "in": 254,
1600
+ "he": 255,
1601
+ "ĠĠ": 256,
1602
+ "re": 257,
1603
+ "on": 258,
1604
+ "er": 259,
1605
+ "Ġthe": 260,
1606
+ "at": 261,
1607
+ "Ġs": 262,
1608
+ "Ġo": 263,
1609
+ "en": 264,
1610
+ "Ġc": 265,
1611
+ "es": 266,
1612
+ "Ġw": 267,
1613
+ "nd": 268,
1614
+ "it": 269,
1615
+ "or": 270,
1616
+ "is": 271,
1617
+ "al": 272,
1618
+ "Ġp": 273,
1619
+ "ing": 274,
1620
+ "Ġf": 275,
1621
+ "an": 276,
1622
+ "ed": 277,
1623
+ "Ġb": 278,
1624
+ "ou": 279,
1625
+ "ar": 280,
1626
+ "Ġin": 281,
1627
+ "Ġof": 282,
1628
+ "Ġm": 283,
1629
+ "Ġand": 284,
1630
+ "ion": 285,
1631
+ "ic": 286,
1632
+ "Ġd": 287,
1633
+ "Ġto": 288,
1634
+ "ĠĠĠĠ": 289,
1635
+ "le": 290,
1636
+ "ro": 291,
1637
+ "as": 292,
1638
+ "ent": 293,
1639
+ "Ġh": 294,
1640
+ "Ġth": 295,
1641
+ "ct": 296,
1642
+ "Ġe": 297,
1643
+ "Ġre": 298,
1644
+ "el": 299,
1645
+ "om": 300,
1646
+ "il": 301,
1647
+ "st": 302,
1648
+ "Ġl": 303,
1649
+ "Ġn": 304,
1650
+ "et": 305,
1651
+ "im": 306,
1652
+ "ve": 307,
1653
+ "ol": 308,
1654
+ "ation": 309,
1655
+ "Ġg": 310,
1656
+ "id": 311,
1657
+ "ĠT": 312,
1658
+ "se": 313,
1659
+ "Ġis": 314,
1660
+ "ur": 315,
1661
+ "ut": 316,
1662
+ "ra": 317,
1663
+ "ly": 318,
1664
+ "ce": 319,
1665
+ "ot": 320,
1666
+ "âĢ": 321,
1667
+ "ch": 322,
1668
+ "ow": 323,
1669
+ "ig": 324,
1670
+ "Ġbe": 325,
1671
+ "Ġu": 326,
1672
+ "Ġfor": 327,
1673
+ "Ġst": 328,
1674
+ "Ġy": 329,
1675
+ "ĠA": 330,
1676
+ "ver": 331,
1677
+ "am": 332,
1678
+ "ĠĠĠ": 333,
1679
+ "ĠS": 334,
1680
+ "Ġon": 335,
1681
+ "ul": 336,
1682
+ "ir": 337,
1683
+ "Ġthat": 338,
1684
+ "ĠI": 339,
1685
+ "ĠC": 340,
1686
+ "ay": 341,
1687
+ "if": 342,
1688
+ "ith": 343,
1689
+ "ad": 344,
1690
+ "Ġcon": 345,
1691
+ "Ġyou": 346,
1692
+ "Ġas": 347,
1693
+ "Ġpro": 348,
1694
+ "her": 349,
1695
+ "od": 350,
1696
+ "Ġwith": 351,
1697
+ "ter": 352,
1698
+ "ĠĠĠĠĠĠĠĠ": 353,
1699
+ "Ġan": 354,
1700
+ "Ġor": 355,
1701
+ "Ġwh": 356,
1702
+ "Ġit": 357,
1703
+ "ment": 358,
1704
+ "Ġare": 359,
1705
+ "Ġal": 360,
1706
+ "ge": 361,
1707
+ "ess": 362,
1708
+ "ist": 363,
1709
+ "Ġex": 364,
1710
+ "Ġ(": 365,
1711
+ "ers": 366,
1712
+ "Ġde": 367,
1713
+ "ate": 368,
1714
+ "ab": 369,
1715
+ "ies": 370,
1716
+ "op": 371,
1717
+ "ĠM": 372,
1718
+ "th": 373,
1719
+ "ect": 374,
1720
+ "res": 375,
1721
+ "us": 376,
1722
+ "ĠP": 377,
1723
+ "ĠThe": 378,
1724
+ "Ġcom": 379,
1725
+ "iv": 380,
1726
+ "est": 381,
1727
+ "um": 382,
1728
+ "ity": 383,
1729
+ "Ġhe": 384,
1730
+ "qu": 385,
1731
+ "Ġv": 386,
1732
+ "ac": 387,
1733
+ "ill": 388,
1734
+ "ĠB": 389,
1735
+ "ore": 390,
1736
+ "em": 391,
1737
+ "Ġwe": 392,
1738
+ "Ġsu": 393,
1739
+ "pp": 394,
1740
+ "os": 395,
1741
+ "ke": 396,
1742
+ "and": 397,
1743
+ "rom": 398,
1744
+ "nt": 399,
1745
+ "ld": 400,
1746
+ "ort": 401,
1747
+ "ain": 402,
1748
+ "ant": 403,
1749
+ "ive": 404,
1750
+ "igh": 405,
1751
+ "oc": 406,
1752
+ "ĠH": 407,
1753
+ "ĠW": 408,
1754
+ "ial": 409,
1755
+ "Ġch": 410,
1756
+ "Ġby": 411,
1757
+ "Ġr": 412,
1758
+ "ud": 413,
1759
+ "ĠE": 414,
1760
+ "ĠĠĠĠĠĠĠ": 415,
1761
+ "Ġcan": 416,
1762
+ "âĢĻ": 417,
1763
+ "Ġat": 418,
1764
+ "un": 419,
1765
+ "Ġne": 420,
1766
+ "Ġha": 421,
1767
+ "ĠD": 422,
1768
+ "--": 423,
1769
+ "ure": 424,
1770
+ "Ġle": 425,
1771
+ "ĠF": 426,
1772
+ "Ġse": 427,
1773
+ "ĠR": 428,
1774
+ "Ġfrom": 429,
1775
+ "Ġen": 430,
1776
+ "ri": 431,
1777
+ "pe": 432,
1778
+ "ical": 433,
1779
+ "art": 434,
1780
+ "og": 435,
1781
+ "Ġwas": 436,
1782
+ "pt": 437,
1783
+ "ions": 438,
1784
+ "pl": 439,
1785
+ "rou": 440,
1786
+ "Ġnot": 441,
1787
+ "ĠN": 442,
1788
+ "Ġsh": 443,
1789
+ "Ġim": 444,
1790
+ "ight": 445,
1791
+ "Ġ=": 446,
1792
+ "out": 447,
1793
+ "ĊĠĠĠĠĠĠĠ": 448,
1794
+ "all": 449,
1795
+ "ĠL": 450,
1796
+ "Ġthis": 451,
1797
+ "ĠG": 452,
1798
+ "Ġab": 453,
1799
+ "ag": 454,
1800
+ "red": 455,
1801
+ "per": 456,
1802
+ "Ġhave": 457,
1803
+ "Ġwor": 458,
1804
+ "ĠâĢ": 459,
1805
+ "gh": 460,
1806
+ "our": 461,
1807
+ "ine": 462,
1808
+ "iz": 463,
1809
+ "Ġint": 464,
1810
+ "ome": 465,
1811
+ "ĊĠĠĠĠĠĠĠĠ": 466,
1812
+ "ust": 467,
1813
+ "Ġus": 468,
1814
+ "Ġyour": 469,
1815
+ "ould": 470,
1816
+ "act": 471,
1817
+ "ĊĠĠĠ": 472,
1818
+ "age": 473,
1819
+ "ost": 474,
1820
+ "Ġpl": 475,
1821
+ "Ġ\"": 476,
1822
+ "ard": 477,
1823
+ "ell": 478,
1824
+ "ther": 479,
1825
+ "Ġtheir": 480,
1826
+ "ult": 481,
1827
+ "elf": 482,
1828
+ "ated": 483,
1829
+ "ff": 484,
1830
+ "ich": 485,
1831
+ "end": 486,
1832
+ "ans": 487,
1833
+ "ous": 488,
1834
+ "ide": 489,
1835
+ "ru": 490,
1836
+ "ations": 491,
1837
+ "ĠO": 492,
1838
+ "Ġad": 493,
1839
+ "ak": 494,
1840
+ "Ġwhe": 495,
1841
+ "du": 496,
1842
+ "cl": 497,
1843
+ "Ġcont": 498,
1844
+ "Ġres": 499
1845
+ },
1846
+ "merges": [
1847
+ [
1848
+ "Ġ",
1849
+ "t"
1850
+ ],
1851
+ [
1852
+ "Ġ",
1853
+ "a"
1854
+ ],
1855
+ [
1856
+ "i",
1857
+ "n"
1858
+ ],
1859
+ [
1860
+ "h",
1861
+ "e"
1862
+ ],
1863
+ [
1864
+ "Ġ",
1865
+ "Ġ"
1866
+ ],
1867
+ [
1868
+ "r",
1869
+ "e"
1870
+ ],
1871
+ [
1872
+ "o",
1873
+ "n"
1874
+ ],
1875
+ [
1876
+ "e",
1877
+ "r"
1878
+ ],
1879
+ [
1880
+ "Ġt",
1881
+ "he"
1882
+ ],
1883
+ [
1884
+ "a",
1885
+ "t"
1886
+ ],
1887
+ [
1888
+ "Ġ",
1889
+ "s"
1890
+ ],
1891
+ [
1892
+ "Ġ",
1893
+ "o"
1894
+ ],
1895
+ [
1896
+ "e",
1897
+ "n"
1898
+ ],
1899
+ [
1900
+ "Ġ",
1901
+ "c"
1902
+ ],
1903
+ [
1904
+ "e",
1905
+ "s"
1906
+ ],
1907
+ [
1908
+ "Ġ",
1909
+ "w"
1910
+ ],
1911
+ [
1912
+ "n",
1913
+ "d"
1914
+ ],
1915
+ [
1916
+ "i",
1917
+ "t"
1918
+ ],
1919
+ [
1920
+ "o",
1921
+ "r"
1922
+ ],
1923
+ [
1924
+ "i",
1925
+ "s"
1926
+ ],
1927
+ [
1928
+ "a",
1929
+ "l"
1930
+ ],
1931
+ [
1932
+ "Ġ",
1933
+ "p"
1934
+ ],
1935
+ [
1936
+ "in",
1937
+ "g"
1938
+ ],
1939
+ [
1940
+ "Ġ",
1941
+ "f"
1942
+ ],
1943
+ [
1944
+ "a",
1945
+ "n"
1946
+ ],
1947
+ [
1948
+ "e",
1949
+ "d"
1950
+ ],
1951
+ [
1952
+ "Ġ",
1953
+ "b"
1954
+ ],
1955
+ [
1956
+ "o",
1957
+ "u"
1958
+ ],
1959
+ [
1960
+ "a",
1961
+ "r"
1962
+ ],
1963
+ [
1964
+ "Ġ",
1965
+ "in"
1966
+ ],
1967
+ [
1968
+ "Ġo",
1969
+ "f"
1970
+ ],
1971
+ [
1972
+ "Ġ",
1973
+ "m"
1974
+ ],
1975
+ [
1976
+ "Ġa",
1977
+ "nd"
1978
+ ],
1979
+ [
1980
+ "i",
1981
+ "on"
1982
+ ],
1983
+ [
1984
+ "i",
1985
+ "c"
1986
+ ],
1987
+ [
1988
+ "Ġ",
1989
+ "d"
1990
+ ],
1991
+ [
1992
+ "Ġt",
1993
+ "o"
1994
+ ],
1995
+ [
1996
+ "ĠĠ",
1997
+ "ĠĠ"
1998
+ ],
1999
+ [
2000
+ "l",
2001
+ "e"
2002
+ ],
2003
+ [
2004
+ "r",
2005
+ "o"
2006
+ ],
2007
+ [
2008
+ "a",
2009
+ "s"
2010
+ ],
2011
+ [
2012
+ "en",
2013
+ "t"
2014
+ ],
2015
+ [
2016
+ "Ġ",
2017
+ "h"
2018
+ ],
2019
+ [
2020
+ "Ġt",
2021
+ "h"
2022
+ ],
2023
+ [
2024
+ "c",
2025
+ "t"
2026
+ ],
2027
+ [
2028
+ "Ġ",
2029
+ "e"
2030
+ ],
2031
+ [
2032
+ "Ġ",
2033
+ "re"
2034
+ ],
2035
+ [
2036
+ "e",
2037
+ "l"
2038
+ ],
2039
+ [
2040
+ "o",
2041
+ "m"
2042
+ ],
2043
+ [
2044
+ "i",
2045
+ "l"
2046
+ ],
2047
+ [
2048
+ "s",
2049
+ "t"
2050
+ ],
2051
+ [
2052
+ "Ġ",
2053
+ "l"
2054
+ ],
2055
+ [
2056
+ "Ġ",
2057
+ "n"
2058
+ ],
2059
+ [
2060
+ "e",
2061
+ "t"
2062
+ ],
2063
+ [
2064
+ "i",
2065
+ "m"
2066
+ ],
2067
+ [
2068
+ "v",
2069
+ "e"
2070
+ ],
2071
+ [
2072
+ "o",
2073
+ "l"
2074
+ ],
2075
+ [
2076
+ "at",
2077
+ "ion"
2078
+ ],
2079
+ [
2080
+ "Ġ",
2081
+ "g"
2082
+ ],
2083
+ [
2084
+ "i",
2085
+ "d"
2086
+ ],
2087
+ [
2088
+ "Ġ",
2089
+ "T"
2090
+ ],
2091
+ [
2092
+ "s",
2093
+ "e"
2094
+ ],
2095
+ [
2096
+ "Ġ",
2097
+ "is"
2098
+ ],
2099
+ [
2100
+ "u",
2101
+ "r"
2102
+ ],
2103
+ [
2104
+ "u",
2105
+ "t"
2106
+ ],
2107
+ [
2108
+ "r",
2109
+ "a"
2110
+ ],
2111
+ [
2112
+ "l",
2113
+ "y"
2114
+ ],
2115
+ [
2116
+ "c",
2117
+ "e"
2118
+ ],
2119
+ [
2120
+ "o",
2121
+ "t"
2122
+ ],
2123
+ [
2124
+ "â",
2125
+ "Ģ"
2126
+ ],
2127
+ [
2128
+ "c",
2129
+ "h"
2130
+ ],
2131
+ [
2132
+ "o",
2133
+ "w"
2134
+ ],
2135
+ [
2136
+ "i",
2137
+ "g"
2138
+ ],
2139
+ [
2140
+ "Ġb",
2141
+ "e"
2142
+ ],
2143
+ [
2144
+ "Ġ",
2145
+ "u"
2146
+ ],
2147
+ [
2148
+ "Ġf",
2149
+ "or"
2150
+ ],
2151
+ [
2152
+ "Ġs",
2153
+ "t"
2154
+ ],
2155
+ [
2156
+ "Ġ",
2157
+ "y"
2158
+ ],
2159
+ [
2160
+ "Ġ",
2161
+ "A"
2162
+ ],
2163
+ [
2164
+ "v",
2165
+ "er"
2166
+ ],
2167
+ [
2168
+ "a",
2169
+ "m"
2170
+ ],
2171
+ [
2172
+ "ĠĠ",
2173
+ "Ġ"
2174
+ ],
2175
+ [
2176
+ "Ġ",
2177
+ "S"
2178
+ ],
2179
+ [
2180
+ "��",
2181
+ "on"
2182
+ ],
2183
+ [
2184
+ "u",
2185
+ "l"
2186
+ ],
2187
+ [
2188
+ "i",
2189
+ "r"
2190
+ ],
2191
+ [
2192
+ "Ġth",
2193
+ "at"
2194
+ ],
2195
+ [
2196
+ "Ġ",
2197
+ "I"
2198
+ ],
2199
+ [
2200
+ "Ġ",
2201
+ "C"
2202
+ ],
2203
+ [
2204
+ "a",
2205
+ "y"
2206
+ ],
2207
+ [
2208
+ "i",
2209
+ "f"
2210
+ ],
2211
+ [
2212
+ "it",
2213
+ "h"
2214
+ ],
2215
+ [
2216
+ "a",
2217
+ "d"
2218
+ ],
2219
+ [
2220
+ "Ġc",
2221
+ "on"
2222
+ ],
2223
+ [
2224
+ "Ġy",
2225
+ "ou"
2226
+ ],
2227
+ [
2228
+ "Ġa",
2229
+ "s"
2230
+ ],
2231
+ [
2232
+ "Ġp",
2233
+ "ro"
2234
+ ],
2235
+ [
2236
+ "he",
2237
+ "r"
2238
+ ],
2239
+ [
2240
+ "o",
2241
+ "d"
2242
+ ],
2243
+ [
2244
+ "Ġw",
2245
+ "ith"
2246
+ ],
2247
+ [
2248
+ "t",
2249
+ "er"
2250
+ ],
2251
+ [
2252
+ "ĠĠĠĠ",
2253
+ "ĠĠĠĠ"
2254
+ ],
2255
+ [
2256
+ "Ġa",
2257
+ "n"
2258
+ ],
2259
+ [
2260
+ "Ġo",
2261
+ "r"
2262
+ ],
2263
+ [
2264
+ "Ġw",
2265
+ "h"
2266
+ ],
2267
+ [
2268
+ "Ġ",
2269
+ "it"
2270
+ ],
2271
+ [
2272
+ "m",
2273
+ "ent"
2274
+ ],
2275
+ [
2276
+ "Ġa",
2277
+ "re"
2278
+ ],
2279
+ [
2280
+ "Ġa",
2281
+ "l"
2282
+ ],
2283
+ [
2284
+ "g",
2285
+ "e"
2286
+ ],
2287
+ [
2288
+ "es",
2289
+ "s"
2290
+ ],
2291
+ [
2292
+ "is",
2293
+ "t"
2294
+ ],
2295
+ [
2296
+ "Ġe",
2297
+ "x"
2298
+ ],
2299
+ [
2300
+ "Ġ",
2301
+ "("
2302
+ ],
2303
+ [
2304
+ "er",
2305
+ "s"
2306
+ ],
2307
+ [
2308
+ "Ġd",
2309
+ "e"
2310
+ ],
2311
+ [
2312
+ "at",
2313
+ "e"
2314
+ ],
2315
+ [
2316
+ "a",
2317
+ "b"
2318
+ ],
2319
+ [
2320
+ "i",
2321
+ "es"
2322
+ ],
2323
+ [
2324
+ "o",
2325
+ "p"
2326
+ ],
2327
+ [
2328
+ "Ġ",
2329
+ "M"
2330
+ ],
2331
+ [
2332
+ "t",
2333
+ "h"
2334
+ ],
2335
+ [
2336
+ "e",
2337
+ "ct"
2338
+ ],
2339
+ [
2340
+ "re",
2341
+ "s"
2342
+ ],
2343
+ [
2344
+ "u",
2345
+ "s"
2346
+ ],
2347
+ [
2348
+ "Ġ",
2349
+ "P"
2350
+ ],
2351
+ [
2352
+ "ĠT",
2353
+ "he"
2354
+ ],
2355
+ [
2356
+ "Ġc",
2357
+ "om"
2358
+ ],
2359
+ [
2360
+ "i",
2361
+ "v"
2362
+ ],
2363
+ [
2364
+ "es",
2365
+ "t"
2366
+ ],
2367
+ [
2368
+ "u",
2369
+ "m"
2370
+ ],
2371
+ [
2372
+ "it",
2373
+ "y"
2374
+ ],
2375
+ [
2376
+ "Ġ",
2377
+ "he"
2378
+ ],
2379
+ [
2380
+ "q",
2381
+ "u"
2382
+ ],
2383
+ [
2384
+ "Ġ",
2385
+ "v"
2386
+ ],
2387
+ [
2388
+ "a",
2389
+ "c"
2390
+ ],
2391
+ [
2392
+ "il",
2393
+ "l"
2394
+ ],
2395
+ [
2396
+ "Ġ",
2397
+ "B"
2398
+ ],
2399
+ [
2400
+ "o",
2401
+ "re"
2402
+ ],
2403
+ [
2404
+ "e",
2405
+ "m"
2406
+ ],
2407
+ [
2408
+ "Ġw",
2409
+ "e"
2410
+ ],
2411
+ [
2412
+ "Ġs",
2413
+ "u"
2414
+ ],
2415
+ [
2416
+ "p",
2417
+ "p"
2418
+ ],
2419
+ [
2420
+ "o",
2421
+ "s"
2422
+ ],
2423
+ [
2424
+ "k",
2425
+ "e"
2426
+ ],
2427
+ [
2428
+ "a",
2429
+ "nd"
2430
+ ],
2431
+ [
2432
+ "ro",
2433
+ "m"
2434
+ ],
2435
+ [
2436
+ "n",
2437
+ "t"
2438
+ ],
2439
+ [
2440
+ "l",
2441
+ "d"
2442
+ ],
2443
+ [
2444
+ "or",
2445
+ "t"
2446
+ ],
2447
+ [
2448
+ "a",
2449
+ "in"
2450
+ ],
2451
+ [
2452
+ "an",
2453
+ "t"
2454
+ ],
2455
+ [
2456
+ "i",
2457
+ "ve"
2458
+ ],
2459
+ [
2460
+ "ig",
2461
+ "h"
2462
+ ],
2463
+ [
2464
+ "o",
2465
+ "c"
2466
+ ],
2467
+ [
2468
+ "Ġ",
2469
+ "H"
2470
+ ],
2471
+ [
2472
+ "Ġ",
2473
+ "W"
2474
+ ],
2475
+ [
2476
+ "i",
2477
+ "al"
2478
+ ],
2479
+ [
2480
+ "Ġc",
2481
+ "h"
2482
+ ],
2483
+ [
2484
+ "Ġb",
2485
+ "y"
2486
+ ],
2487
+ [
2488
+ "Ġ",
2489
+ "r"
2490
+ ],
2491
+ [
2492
+ "u",
2493
+ "d"
2494
+ ],
2495
+ [
2496
+ "Ġ",
2497
+ "E"
2498
+ ],
2499
+ [
2500
+ "ĠĠĠĠ",
2501
+ "ĠĠĠ"
2502
+ ],
2503
+ [
2504
+ "Ġc",
2505
+ "an"
2506
+ ],
2507
+ [
2508
+ "âĢ",
2509
+ "Ļ"
2510
+ ],
2511
+ [
2512
+ "Ġa",
2513
+ "t"
2514
+ ],
2515
+ [
2516
+ "u",
2517
+ "n"
2518
+ ],
2519
+ [
2520
+ "Ġn",
2521
+ "e"
2522
+ ],
2523
+ [
2524
+ "Ġh",
2525
+ "a"
2526
+ ],
2527
+ [
2528
+ "Ġ",
2529
+ "D"
2530
+ ],
2531
+ [
2532
+ "-",
2533
+ "-"
2534
+ ],
2535
+ [
2536
+ "u",
2537
+ "re"
2538
+ ],
2539
+ [
2540
+ "Ġ",
2541
+ "le"
2542
+ ],
2543
+ [
2544
+ "Ġ",
2545
+ "F"
2546
+ ],
2547
+ [
2548
+ "Ġs",
2549
+ "e"
2550
+ ],
2551
+ [
2552
+ "Ġ",
2553
+ "R"
2554
+ ],
2555
+ [
2556
+ "Ġf",
2557
+ "rom"
2558
+ ],
2559
+ [
2560
+ "Ġ",
2561
+ "en"
2562
+ ],
2563
+ [
2564
+ "r",
2565
+ "i"
2566
+ ],
2567
+ [
2568
+ "p",
2569
+ "e"
2570
+ ],
2571
+ [
2572
+ "ic",
2573
+ "al"
2574
+ ],
2575
+ [
2576
+ "ar",
2577
+ "t"
2578
+ ],
2579
+ [
2580
+ "o",
2581
+ "g"
2582
+ ],
2583
+ [
2584
+ "Ġw",
2585
+ "as"
2586
+ ],
2587
+ [
2588
+ "p",
2589
+ "t"
2590
+ ],
2591
+ [
2592
+ "ion",
2593
+ "s"
2594
+ ],
2595
+ [
2596
+ "p",
2597
+ "l"
2598
+ ],
2599
+ [
2600
+ "r",
2601
+ "ou"
2602
+ ],
2603
+ [
2604
+ "Ġn",
2605
+ "ot"
2606
+ ],
2607
+ [
2608
+ "Ġ",
2609
+ "N"
2610
+ ],
2611
+ [
2612
+ "Ġs",
2613
+ "h"
2614
+ ],
2615
+ [
2616
+ "Ġ",
2617
+ "im"
2618
+ ],
2619
+ [
2620
+ "igh",
2621
+ "t"
2622
+ ],
2623
+ [
2624
+ "Ġ",
2625
+ "="
2626
+ ],
2627
+ [
2628
+ "ou",
2629
+ "t"
2630
+ ],
2631
+ [
2632
+ "Ċ",
2633
+ "ĠĠĠĠĠĠĠ"
2634
+ ],
2635
+ [
2636
+ "al",
2637
+ "l"
2638
+ ],
2639
+ [
2640
+ "Ġ",
2641
+ "L"
2642
+ ],
2643
+ [
2644
+ "Ġth",
2645
+ "is"
2646
+ ],
2647
+ [
2648
+ "Ġ",
2649
+ "G"
2650
+ ],
2651
+ [
2652
+ "Ġa",
2653
+ "b"
2654
+ ],
2655
+ [
2656
+ "a",
2657
+ "g"
2658
+ ],
2659
+ [
2660
+ "re",
2661
+ "d"
2662
+ ],
2663
+ [
2664
+ "p",
2665
+ "er"
2666
+ ],
2667
+ [
2668
+ "Ġha",
2669
+ "ve"
2670
+ ],
2671
+ [
2672
+ "Ġw",
2673
+ "or"
2674
+ ],
2675
+ [
2676
+ "Ġ",
2677
+ "âĢ"
2678
+ ],
2679
+ [
2680
+ "g",
2681
+ "h"
2682
+ ],
2683
+ [
2684
+ "ou",
2685
+ "r"
2686
+ ],
2687
+ [
2688
+ "in",
2689
+ "e"
2690
+ ],
2691
+ [
2692
+ "i",
2693
+ "z"
2694
+ ],
2695
+ [
2696
+ "Ġin",
2697
+ "t"
2698
+ ],
2699
+ [
2700
+ "om",
2701
+ "e"
2702
+ ],
2703
+ [
2704
+ "Ċ",
2705
+ "ĠĠĠĠĠĠĠĠ"
2706
+ ],
2707
+ [
2708
+ "u",
2709
+ "st"
2710
+ ],
2711
+ [
2712
+ "Ġu",
2713
+ "s"
2714
+ ],
2715
+ [
2716
+ "Ġyou",
2717
+ "r"
2718
+ ],
2719
+ [
2720
+ "ou",
2721
+ "ld"
2722
+ ],
2723
+ [
2724
+ "a",
2725
+ "ct"
2726
+ ],
2727
+ [
2728
+ "Ċ",
2729
+ "ĠĠĠ"
2730
+ ],
2731
+ [
2732
+ "a",
2733
+ "ge"
2734
+ ],
2735
+ [
2736
+ "o",
2737
+ "st"
2738
+ ],
2739
+ [
2740
+ "Ġp",
2741
+ "l"
2742
+ ],
2743
+ [
2744
+ "Ġ",
2745
+ "\""
2746
+ ],
2747
+ [
2748
+ "ar",
2749
+ "d"
2750
+ ],
2751
+ [
2752
+ "el",
2753
+ "l"
2754
+ ],
2755
+ [
2756
+ "t",
2757
+ "her"
2758
+ ],
2759
+ [
2760
+ "Ġthe",
2761
+ "ir"
2762
+ ],
2763
+ [
2764
+ "ul",
2765
+ "t"
2766
+ ],
2767
+ [
2768
+ "el",
2769
+ "f"
2770
+ ],
2771
+ [
2772
+ "at",
2773
+ "ed"
2774
+ ],
2775
+ [
2776
+ "f",
2777
+ "f"
2778
+ ],
2779
+ [
2780
+ "ic",
2781
+ "h"
2782
+ ],
2783
+ [
2784
+ "en",
2785
+ "d"
2786
+ ],
2787
+ [
2788
+ "an",
2789
+ "s"
2790
+ ],
2791
+ [
2792
+ "ou",
2793
+ "s"
2794
+ ],
2795
+ [
2796
+ "id",
2797
+ "e"
2798
+ ],
2799
+ [
2800
+ "r",
2801
+ "u"
2802
+ ],
2803
+ [
2804
+ "ation",
2805
+ "s"
2806
+ ],
2807
+ [
2808
+ "Ġ",
2809
+ "O"
2810
+ ],
2811
+ [
2812
+ "Ġa",
2813
+ "d"
2814
+ ],
2815
+ [
2816
+ "a",
2817
+ "k"
2818
+ ],
2819
+ [
2820
+ "Ġw",
2821
+ "he"
2822
+ ],
2823
+ [
2824
+ "d",
2825
+ "u"
2826
+ ],
2827
+ [
2828
+ "c",
2829
+ "l"
2830
+ ],
2831
+ [
2832
+ "Ġcon",
2833
+ "t"
2834
+ ],
2835
+ [
2836
+ "Ġre",
2837
+ "s"
2838
+ ]
2839
+ ]
2840
+ }
2841
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,1192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<repo_name>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<reponame>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<file_sep>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<filename>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<gh_stars>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<issue_start>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_comment>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<issue_closed>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_start>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_text>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_code>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<jupyter_output>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<jupyter_script>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<empty_output>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "49152": {
141
+ "content": "<global-img>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "49153": {
149
+ "content": "<row_1_col_1>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "49154": {
157
+ "content": "<row_1_col_2>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "49155": {
165
+ "content": "<row_1_col_3>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "49156": {
173
+ "content": "<row_1_col_4>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "49157": {
181
+ "content": "<row_1_col_5>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "49158": {
189
+ "content": "<row_1_col_6>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "49159": {
197
+ "content": "<row_2_col_1>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "49160": {
205
+ "content": "<row_2_col_2>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "49161": {
213
+ "content": "<row_2_col_3>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "49162": {
221
+ "content": "<row_2_col_4>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "49163": {
229
+ "content": "<row_2_col_5>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "49164": {
237
+ "content": "<row_2_col_6>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "49165": {
245
+ "content": "<row_3_col_1>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "49166": {
253
+ "content": "<row_3_col_2>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "49167": {
261
+ "content": "<row_3_col_3>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "49168": {
269
+ "content": "<row_3_col_4>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "49169": {
277
+ "content": "<row_3_col_5>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "49170": {
285
+ "content": "<row_3_col_6>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "49171": {
293
+ "content": "<row_4_col_1>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "49172": {
301
+ "content": "<row_4_col_2>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "49173": {
309
+ "content": "<row_4_col_3>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "49174": {
317
+ "content": "<row_4_col_4>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "49175": {
325
+ "content": "<row_4_col_5>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "49176": {
333
+ "content": "<row_4_col_6>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "49177": {
341
+ "content": "<row_5_col_1>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "49178": {
349
+ "content": "<row_5_col_2>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "49179": {
357
+ "content": "<row_5_col_3>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "49180": {
365
+ "content": "<row_5_col_4>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "49181": {
373
+ "content": "<row_5_col_5>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "49182": {
381
+ "content": "<row_5_col_6>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "49183": {
389
+ "content": "<row_6_col_1>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "49184": {
397
+ "content": "<row_6_col_2>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "49185": {
405
+ "content": "<row_6_col_3>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "49186": {
413
+ "content": "<row_6_col_4>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "49187": {
421
+ "content": "<row_6_col_5>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "49188": {
429
+ "content": "<row_6_col_6>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "49189": {
437
+ "content": "<fake_token_around_image>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "49190": {
445
+ "content": "<image>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "49191": {
453
+ "content": "<|reserved_special_token_0|>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "49192": {
461
+ "content": "<|reserved_special_token_1|>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "49193": {
469
+ "content": "<|reserved_special_token_2|>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "49194": {
477
+ "content": "<|reserved_special_token_3|>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "49195": {
485
+ "content": "<|reserved_special_token_4|>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "49196": {
493
+ "content": "<|reserved_special_token_5|>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "49197": {
501
+ "content": "<|reserved_special_token_6|>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "49198": {
509
+ "content": "<|reserved_special_token_7|>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "49199": {
517
+ "content": "<|reserved_special_token_8|>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "49200": {
525
+ "content": "<|reserved_special_token_9|>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "49201": {
533
+ "content": "<|reserved_special_token_10|>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "49202": {
541
+ "content": "<|reserved_special_token_11|>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "49203": {
549
+ "content": "<|reserved_special_token_12|>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "49204": {
557
+ "content": "<|reserved_special_token_13|>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "49205": {
565
+ "content": "<|reserved_special_token_14|>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "49206": {
573
+ "content": "<|reserved_special_token_15|>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "49207": {
581
+ "content": "<|reserved_special_token_16|>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "49208": {
589
+ "content": "<|reserved_special_token_17|>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "49209": {
597
+ "content": "<|reserved_special_token_18|>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "49210": {
605
+ "content": "<|reserved_special_token_19|>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "49211": {
613
+ "content": "<|reserved_special_token_20|>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "49212": {
621
+ "content": "<|reserved_special_token_21|>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "49213": {
629
+ "content": "<|reserved_special_token_22|>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "49214": {
637
+ "content": "<|reserved_special_token_23|>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "49215": {
645
+ "content": "<|reserved_special_token_24|>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "49216": {
653
+ "content": "<|reserved_special_token_25|>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "49217": {
661
+ "content": "<|reserved_special_token_26|>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "49218": {
669
+ "content": "<|reserved_special_token_27|>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "49219": {
677
+ "content": "<|reserved_special_token_28|>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "49220": {
685
+ "content": "<|reserved_special_token_29|>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "49221": {
693
+ "content": "<|reserved_special_token_30|>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "49222": {
701
+ "content": "<|reserved_special_token_31|>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "49223": {
709
+ "content": "<|reserved_special_token_32|>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "49224": {
717
+ "content": "<|reserved_special_token_33|>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "49225": {
725
+ "content": "<|reserved_special_token_34|>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "49226": {
733
+ "content": "<|reserved_special_token_35|>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "49227": {
741
+ "content": "<|reserved_special_token_36|>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "49228": {
749
+ "content": "<|reserved_special_token_37|>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "49229": {
757
+ "content": "<|reserved_special_token_38|>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "49230": {
765
+ "content": "<|reserved_special_token_39|>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "49231": {
773
+ "content": "<|reserved_special_token_40|>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "49232": {
781
+ "content": "<|reserved_special_token_41|>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "49233": {
789
+ "content": "<|reserved_special_token_42|>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "49234": {
797
+ "content": "<|reserved_special_token_43|>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "49235": {
805
+ "content": "<|reserved_special_token_44|>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "49236": {
813
+ "content": "<|reserved_special_token_45|>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "49237": {
821
+ "content": "<|reserved_special_token_46|>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "49238": {
829
+ "content": "<|reserved_special_token_47|>",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "49239": {
837
+ "content": "<|reserved_special_token_48|>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ },
844
+ "49240": {
845
+ "content": "<|reserved_special_token_49|>",
846
+ "lstrip": false,
847
+ "normalized": false,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": true
851
+ },
852
+ "49241": {
853
+ "content": "<|reserved_special_token_50|>",
854
+ "lstrip": false,
855
+ "normalized": false,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": true
859
+ },
860
+ "49242": {
861
+ "content": "<|reserved_special_token_51|>",
862
+ "lstrip": false,
863
+ "normalized": false,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": true
867
+ },
868
+ "49243": {
869
+ "content": "<|reserved_special_token_52|>",
870
+ "lstrip": false,
871
+ "normalized": false,
872
+ "rstrip": false,
873
+ "single_word": false,
874
+ "special": true
875
+ },
876
+ "49244": {
877
+ "content": "<|reserved_special_token_53|>",
878
+ "lstrip": false,
879
+ "normalized": false,
880
+ "rstrip": false,
881
+ "single_word": false,
882
+ "special": true
883
+ },
884
+ "49245": {
885
+ "content": "<|reserved_special_token_54|>",
886
+ "lstrip": false,
887
+ "normalized": false,
888
+ "rstrip": false,
889
+ "single_word": false,
890
+ "special": true
891
+ },
892
+ "49246": {
893
+ "content": "<|reserved_special_token_55|>",
894
+ "lstrip": false,
895
+ "normalized": false,
896
+ "rstrip": false,
897
+ "single_word": false,
898
+ "special": true
899
+ },
900
+ "49247": {
901
+ "content": "<|reserved_special_token_56|>",
902
+ "lstrip": false,
903
+ "normalized": false,
904
+ "rstrip": false,
905
+ "single_word": false,
906
+ "special": true
907
+ },
908
+ "49248": {
909
+ "content": "<|reserved_special_token_57|>",
910
+ "lstrip": false,
911
+ "normalized": false,
912
+ "rstrip": false,
913
+ "single_word": false,
914
+ "special": true
915
+ },
916
+ "49249": {
917
+ "content": "<|reserved_special_token_58|>",
918
+ "lstrip": false,
919
+ "normalized": false,
920
+ "rstrip": false,
921
+ "single_word": false,
922
+ "special": true
923
+ },
924
+ "49250": {
925
+ "content": "<|reserved_special_token_59|>",
926
+ "lstrip": false,
927
+ "normalized": false,
928
+ "rstrip": false,
929
+ "single_word": false,
930
+ "special": true
931
+ },
932
+ "49251": {
933
+ "content": "<|reserved_special_token_60|>",
934
+ "lstrip": false,
935
+ "normalized": false,
936
+ "rstrip": false,
937
+ "single_word": false,
938
+ "special": true
939
+ },
940
+ "49252": {
941
+ "content": "<|reserved_special_token_61|>",
942
+ "lstrip": false,
943
+ "normalized": false,
944
+ "rstrip": false,
945
+ "single_word": false,
946
+ "special": true
947
+ },
948
+ "49253": {
949
+ "content": "<|reserved_special_token_62|>",
950
+ "lstrip": false,
951
+ "normalized": false,
952
+ "rstrip": false,
953
+ "single_word": false,
954
+ "special": true
955
+ },
956
+ "49254": {
957
+ "content": "<|reserved_special_token_63|>",
958
+ "lstrip": false,
959
+ "normalized": false,
960
+ "rstrip": false,
961
+ "single_word": false,
962
+ "special": true
963
+ },
964
+ "49255": {
965
+ "content": "<|reserved_special_token_64|>",
966
+ "lstrip": false,
967
+ "normalized": false,
968
+ "rstrip": false,
969
+ "single_word": false,
970
+ "special": true
971
+ },
972
+ "49256": {
973
+ "content": "<|reserved_special_token_65|>",
974
+ "lstrip": false,
975
+ "normalized": false,
976
+ "rstrip": false,
977
+ "single_word": false,
978
+ "special": true
979
+ },
980
+ "49257": {
981
+ "content": "<|reserved_special_token_66|>",
982
+ "lstrip": false,
983
+ "normalized": false,
984
+ "rstrip": false,
985
+ "single_word": false,
986
+ "special": true
987
+ },
988
+ "49258": {
989
+ "content": "<|reserved_special_token_67|>",
990
+ "lstrip": false,
991
+ "normalized": false,
992
+ "rstrip": false,
993
+ "single_word": false,
994
+ "special": true
995
+ },
996
+ "49259": {
997
+ "content": "<|reserved_special_token_68|>",
998
+ "lstrip": false,
999
+ "normalized": false,
1000
+ "rstrip": false,
1001
+ "single_word": false,
1002
+ "special": true
1003
+ },
1004
+ "49260": {
1005
+ "content": "<|reserved_special_token_69|>",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false,
1010
+ "special": true
1011
+ },
1012
+ "49261": {
1013
+ "content": "<|reserved_special_token_70|>",
1014
+ "lstrip": false,
1015
+ "normalized": false,
1016
+ "rstrip": false,
1017
+ "single_word": false,
1018
+ "special": true
1019
+ },
1020
+ "49262": {
1021
+ "content": "<|reserved_special_token_71|>",
1022
+ "lstrip": false,
1023
+ "normalized": false,
1024
+ "rstrip": false,
1025
+ "single_word": false,
1026
+ "special": true
1027
+ },
1028
+ "49263": {
1029
+ "content": "<|reserved_special_token_72|>",
1030
+ "lstrip": false,
1031
+ "normalized": false,
1032
+ "rstrip": false,
1033
+ "single_word": false,
1034
+ "special": true
1035
+ },
1036
+ "49264": {
1037
+ "content": "<|reserved_special_token_73|>",
1038
+ "lstrip": false,
1039
+ "normalized": false,
1040
+ "rstrip": false,
1041
+ "single_word": false,
1042
+ "special": true
1043
+ },
1044
+ "49265": {
1045
+ "content": "<|reserved_special_token_74|>",
1046
+ "lstrip": false,
1047
+ "normalized": false,
1048
+ "rstrip": false,
1049
+ "single_word": false,
1050
+ "special": true
1051
+ },
1052
+ "49266": {
1053
+ "content": "<|reserved_special_token_75|>",
1054
+ "lstrip": false,
1055
+ "normalized": false,
1056
+ "rstrip": false,
1057
+ "single_word": false,
1058
+ "special": true
1059
+ },
1060
+ "49267": {
1061
+ "content": "<|reserved_special_token_76|>",
1062
+ "lstrip": false,
1063
+ "normalized": false,
1064
+ "rstrip": false,
1065
+ "single_word": false,
1066
+ "special": true
1067
+ },
1068
+ "49268": {
1069
+ "content": "<|reserved_special_token_77|>",
1070
+ "lstrip": false,
1071
+ "normalized": false,
1072
+ "rstrip": false,
1073
+ "single_word": false,
1074
+ "special": true
1075
+ },
1076
+ "49269": {
1077
+ "content": "<|reserved_special_token_78|>",
1078
+ "lstrip": false,
1079
+ "normalized": false,
1080
+ "rstrip": false,
1081
+ "single_word": false,
1082
+ "special": true
1083
+ },
1084
+ "49270": {
1085
+ "content": "<|reserved_special_token_79|>",
1086
+ "lstrip": false,
1087
+ "normalized": false,
1088
+ "rstrip": false,
1089
+ "single_word": false,
1090
+ "special": true
1091
+ },
1092
+ "49271": {
1093
+ "content": "<|reserved_special_token_80|>",
1094
+ "lstrip": false,
1095
+ "normalized": false,
1096
+ "rstrip": false,
1097
+ "single_word": false,
1098
+ "special": true
1099
+ },
1100
+ "49272": {
1101
+ "content": "<|reserved_special_token_81|>",
1102
+ "lstrip": false,
1103
+ "normalized": false,
1104
+ "rstrip": false,
1105
+ "single_word": false,
1106
+ "special": true
1107
+ },
1108
+ "49273": {
1109
+ "content": "<|reserved_special_token_82|>",
1110
+ "lstrip": false,
1111
+ "normalized": false,
1112
+ "rstrip": false,
1113
+ "single_word": false,
1114
+ "special": true
1115
+ },
1116
+ "49274": {
1117
+ "content": "<|reserved_special_token_83|>",
1118
+ "lstrip": false,
1119
+ "normalized": false,
1120
+ "rstrip": false,
1121
+ "single_word": false,
1122
+ "special": true
1123
+ },
1124
+ "49275": {
1125
+ "content": "<|reserved_special_token_84|>",
1126
+ "lstrip": false,
1127
+ "normalized": false,
1128
+ "rstrip": false,
1129
+ "single_word": false,
1130
+ "special": true
1131
+ },
1132
+ "49276": {
1133
+ "content": "<|reserved_special_token_85|>",
1134
+ "lstrip": false,
1135
+ "normalized": false,
1136
+ "rstrip": false,
1137
+ "single_word": false,
1138
+ "special": true
1139
+ },
1140
+ "49277": {
1141
+ "content": "<|reserved_special_token_86|>",
1142
+ "lstrip": false,
1143
+ "normalized": false,
1144
+ "rstrip": false,
1145
+ "single_word": false,
1146
+ "special": true
1147
+ },
1148
+ "49278": {
1149
+ "content": "<|reserved_special_token_87|>",
1150
+ "lstrip": false,
1151
+ "normalized": false,
1152
+ "rstrip": false,
1153
+ "single_word": false,
1154
+ "special": true
1155
+ },
1156
+ "49279": {
1157
+ "content": "<end_of_utterance>",
1158
+ "lstrip": false,
1159
+ "normalized": false,
1160
+ "rstrip": false,
1161
+ "single_word": false,
1162
+ "special": true
1163
+ }
1164
+ },
1165
+ "additional_special_tokens": [
1166
+ "<fake_token_around_image>",
1167
+ "<image>",
1168
+ "<end_of_utterance>"
1169
+ ],
1170
+ "bos_token": "<|im_start|>",
1171
+ "chat_template": "<|im_start|>{% for message in messages %}{{message['role'] | capitalize}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>\n{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
1172
+ "clean_up_tokenization_spaces": false,
1173
+ "end_of_utterance_token": "<end_of_utterance>",
1174
+ "eos_token": "<end_of_utterance>",
1175
+ "extra_special_tokens": {
1176
+ "end_of_utterance_token": "<end_of_utterance>",
1177
+ "fake_image_token": "<fake_token_around_image>",
1178
+ "global_image_token": "<global-img>",
1179
+ "image_token": "<image>"
1180
+ },
1181
+ "fake_image_token": "<fake_token_around_image>",
1182
+ "global_image_token": "<global-img>",
1183
+ "image_token": "<image>",
1184
+ "legacy": false,
1185
+ "model_max_length": 8192,
1186
+ "pad_token": "<|im_end|>",
1187
+ "processor_class": "SmolVLMProcessor",
1188
+ "tokenizer_class": "GPT2Tokenizer",
1189
+ "truncation_side": "left",
1190
+ "unk_token": "<|endoftext|>",
1191
+ "vocab_size": 500
1192
+ }