hf-transformers-bot commited on
Commit
a95b63e
·
verified ·
1 Parent(s): 2d7bd09

Add tiny processor fixture for testing

Browse files
.eval_results/olmocrbench.yaml ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ - dataset:
2
+ id: allenai/olmOCR-bench
3
+ task_id: overall
4
+ value: 76.1
5
+ notes: "Excluding Headers & Footers category"
6
+ source:
7
+ url: https://huggingface.co/papers/2601.14251
8
+ name: LightOnOCR technical report
9
+ user: Bapt120
10
+ - dataset:
11
+ id: allenai/olmOCR-bench
12
+ task_id: arxiv_math
13
+ value: 81.4
14
+ source:
15
+ url: https://huggingface.co/papers/2601.14251
16
+ name: LightOnOCR technical report
17
+ user: Bapt120
18
+ - dataset:
19
+ id: allenai/olmOCR-bench
20
+ task_id: old_scans_math
21
+ value: 71.6
22
+ source:
23
+ url: https://huggingface.co/papers/2601.14251
24
+ name: LightOnOCR technical report
25
+ user: Bapt120
26
+ - dataset:
27
+ id: allenai/olmOCR-bench
28
+ task_id: table_tests
29
+ value: 76.4
30
+ source:
31
+ url: https://huggingface.co/papers/2601.14251
32
+ name: LightOnOCR technical report
33
+ user: Bapt120
34
+ - dataset:
35
+ id: allenai/olmOCR-bench
36
+ task_id: old_scans
37
+ value: 35.2
38
+ source:
39
+ url: https://huggingface.co/papers/2601.14251
40
+ name: LightOnOCR technical report
41
+ user: Bapt120
42
+ - dataset:
43
+ id: allenai/olmOCR-bench
44
+ task_id: multi_column
45
+ value: 80.0
46
+ source:
47
+ url: https://huggingface.co/papers/2601.14251
48
+ name: LightOnOCR technical report
49
+ user: Bapt120
50
+ - dataset:
51
+ id: allenai/olmOCR-bench
52
+ task_id: long_tiny_text
53
+ value: 88.7
54
+ source:
55
+ url: https://huggingface.co/papers/2601.14251
56
+ name: LightOnOCR technical report
57
+ user: Bapt120
58
+ - dataset:
59
+ id: allenai/olmOCR-bench
60
+ task_id: headers_footers
61
+ value: 35.5
62
+ notes: "Instead of removing headers and footers, our model is trained for full-page transcription and explicitly rewards their presence (via flipped RLVR tests), which lowers this score under the original benchmark scoring."
63
+ source:
64
+ url: https://huggingface.co/papers/2601.14251
65
+ name: LightOnOCR technical report
66
+ user: Bapt120
67
+ - dataset:
68
+ id: allenai/olmOCR-bench
69
+ task_id: baseline
70
+ value: 99.6
71
+ source:
72
+ url: https://huggingface.co/papers/2601.14251
73
+ name: LightOnOCR technical report
74
+ user: Bapt120
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ lightonocr-banner.png filter=lfs diff=lfs merge=lfs -text
chat_template.jinja ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {% set image_count = namespace(value=0) %}
2
+ {% for message in messages %}
3
+ {% if loop.first and message['role'] != 'system' %}
4
+ <|im_start|>system<|im_end|>
5
+ {% endif %}
6
+ <|im_start|>{{ message['role'] }}
7
+ {% if message['content'] is string %}
8
+ {{ message['content'] }}<|im_end|>
9
+ {% else %}
10
+ {% for content in message['content'] %}
11
+ {% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}
12
+ {% set image_count.value = image_count.value + 1 %}
13
+ {% if add_vision_id %}
14
+ Picture {{ image_count.value }}:
15
+ {% endif -%}
16
+ <|image_pad|>
17
+ {%- elif 'text' in content %}
18
+ {{ content['text'] }}
19
+ {% endif %}
20
+ {% endfor %}
21
+ <|im_end|>
22
+ {% endif %}
23
+ {% endfor %}
24
+ {% if add_generation_prompt %}
25
+ <|im_start|>assistant
26
+ {% endif %}
config.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LightOnOCRForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "image_token_id": 151655,
7
+ "model_type": "mistral3",
8
+ "multimodal_projector_bias": false,
9
+ "projector_hidden_act": "gelu",
10
+ "spatial_merge_size": 2,
11
+ "text_config": {
12
+ "architectures": [
13
+ "Qwen3ForCausalLM"
14
+ ],
15
+ "attention_bias": false,
16
+ "attention_dropout": 0,
17
+ "head_dim": 128,
18
+ "hidden_act": "silu",
19
+ "hidden_size": 1024,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "layer_types": [
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention"
51
+ ],
52
+ "max_position_embeddings": 8192,
53
+ "max_window_layers": 28,
54
+ "model_type": "qwen3",
55
+ "num_attention_heads": 16,
56
+ "num_hidden_layers": 28,
57
+ "num_key_value_heads": 8,
58
+ "rms_norm_eps": 1e-06,
59
+ "rope_scaling": null,
60
+ "rope_theta": 1000000,
61
+ "sliding_window": null,
62
+ "use_cache": true,
63
+ "use_sliding_window": false,
64
+ "use_qk_norm": true,
65
+ "tie_word_embeddings": true,
66
+ "vocab_size": 151936
67
+ },
68
+ "transformers_version": "4.57.0.dev0",
69
+ "vision_config": {
70
+ "attention_dropout": 0,
71
+ "head_dim": 64,
72
+ "hidden_act": "silu",
73
+ "hidden_size": 1024,
74
+ "image_size": 1540,
75
+ "initializer_range": 0.02,
76
+ "intermediate_size": 4096,
77
+ "model_type": "pixtral",
78
+ "num_attention_heads": 16,
79
+ "num_channels": 3,
80
+ "num_hidden_layers": 24,
81
+ "patch_size": 14,
82
+ "rope_theta": 10000
83
+ },
84
+ "vision_feature_layer": -1,
85
+ "vocab_size": 500
86
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.2,
10
+ "top_k": 0,
11
+ "top_p": 0.9,
12
+ "transformers_version": "4.55.3"
13
+ }
notebook.ipynb ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "disable_grouping": null,
7
+ "do_center_crop": null,
8
+ "do_convert_rgb": true,
9
+ "do_normalize": true,
10
+ "do_pad": null,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "image_mean": [
14
+ 0.48145466,
15
+ 0.4578275,
16
+ 0.40821073
17
+ ],
18
+ "image_processor_type": "PixtralImageProcessorFast",
19
+ "image_std": [
20
+ 0.26862954,
21
+ 0.26130258,
22
+ 0.27577711
23
+ ],
24
+ "input_data_format": null,
25
+ "pad_size": null,
26
+ "patch_size": 14,
27
+ "processor_class": "LightOnOCRProcessor",
28
+ "resample": 3,
29
+ "rescale_factor": 0.00392156862745098,
30
+ "return_tensors": null,
31
+ "size": {
32
+ "longest_edge": 1540
33
+ }
34
+ }
processor_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_break_token": "<|vision_pad|>",
3
+ "image_end_token": "<|vision_end|>",
4
+ "image_token": "<|image_pad|>",
5
+ "patch_size": 14,
6
+ "processor_class": "LightOnOCRProcessor",
7
+ "spatial_merge_size": 2
8
+ }
tokenizer.json ADDED
@@ -0,0 +1,1765 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 500,
8
+ "content": "<|endoftext|>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 501,
17
+ "content": "<|im_start|>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 502,
26
+ "content": "<|im_end|>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 503,
35
+ "content": "<|object_ref_start|>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 504,
44
+ "content": "<|object_ref_end|>",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 505,
53
+ "content": "<|box_start|>",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ },
60
+ {
61
+ "id": 506,
62
+ "content": "<|box_end|>",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": false,
67
+ "special": true
68
+ },
69
+ {
70
+ "id": 507,
71
+ "content": "<|quad_start|>",
72
+ "single_word": false,
73
+ "lstrip": false,
74
+ "rstrip": false,
75
+ "normalized": false,
76
+ "special": true
77
+ },
78
+ {
79
+ "id": 508,
80
+ "content": "<|quad_end|>",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": false,
85
+ "special": true
86
+ },
87
+ {
88
+ "id": 509,
89
+ "content": "<|vision_start|>",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": false,
94
+ "special": true
95
+ },
96
+ {
97
+ "id": 510,
98
+ "content": "<|vision_end|>",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ {
106
+ "id": 511,
107
+ "content": "<|vision_pad|>",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
+ },
114
+ {
115
+ "id": 512,
116
+ "content": "<|image_pad|>",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": false,
121
+ "special": true
122
+ },
123
+ {
124
+ "id": 513,
125
+ "content": "<|video_pad|>",
126
+ "single_word": false,
127
+ "lstrip": false,
128
+ "rstrip": false,
129
+ "normalized": false,
130
+ "special": true
131
+ },
132
+ {
133
+ "id": 514,
134
+ "content": "<tool_call>",
135
+ "single_word": false,
136
+ "lstrip": false,
137
+ "rstrip": false,
138
+ "normalized": false,
139
+ "special": false
140
+ },
141
+ {
142
+ "id": 515,
143
+ "content": "</tool_call>",
144
+ "single_word": false,
145
+ "lstrip": false,
146
+ "rstrip": false,
147
+ "normalized": false,
148
+ "special": false
149
+ },
150
+ {
151
+ "id": 516,
152
+ "content": "<|fim_prefix|>",
153
+ "single_word": false,
154
+ "lstrip": false,
155
+ "rstrip": false,
156
+ "normalized": false,
157
+ "special": false
158
+ },
159
+ {
160
+ "id": 517,
161
+ "content": "<|fim_middle|>",
162
+ "single_word": false,
163
+ "lstrip": false,
164
+ "rstrip": false,
165
+ "normalized": false,
166
+ "special": false
167
+ },
168
+ {
169
+ "id": 518,
170
+ "content": "<|fim_suffix|>",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": false,
175
+ "special": false
176
+ },
177
+ {
178
+ "id": 519,
179
+ "content": "<|fim_pad|>",
180
+ "single_word": false,
181
+ "lstrip": false,
182
+ "rstrip": false,
183
+ "normalized": false,
184
+ "special": false
185
+ },
186
+ {
187
+ "id": 520,
188
+ "content": "<|repo_name|>",
189
+ "single_word": false,
190
+ "lstrip": false,
191
+ "rstrip": false,
192
+ "normalized": false,
193
+ "special": false
194
+ },
195
+ {
196
+ "id": 521,
197
+ "content": "<|file_sep|>",
198
+ "single_word": false,
199
+ "lstrip": false,
200
+ "rstrip": false,
201
+ "normalized": false,
202
+ "special": false
203
+ },
204
+ {
205
+ "id": 522,
206
+ "content": "<tool_response>",
207
+ "single_word": false,
208
+ "lstrip": false,
209
+ "rstrip": false,
210
+ "normalized": false,
211
+ "special": false
212
+ },
213
+ {
214
+ "id": 523,
215
+ "content": "</tool_response>",
216
+ "single_word": false,
217
+ "lstrip": false,
218
+ "rstrip": false,
219
+ "normalized": false,
220
+ "special": false
221
+ },
222
+ {
223
+ "id": 524,
224
+ "content": "<think>",
225
+ "single_word": false,
226
+ "lstrip": false,
227
+ "rstrip": false,
228
+ "normalized": false,
229
+ "special": false
230
+ },
231
+ {
232
+ "id": 525,
233
+ "content": "</think>",
234
+ "single_word": false,
235
+ "lstrip": false,
236
+ "rstrip": false,
237
+ "normalized": false,
238
+ "special": false
239
+ }
240
+ ],
241
+ "normalizer": {
242
+ "type": "NFC"
243
+ },
244
+ "pre_tokenizer": {
245
+ "type": "Sequence",
246
+ "pretokenizers": [
247
+ {
248
+ "type": "Split",
249
+ "pattern": {
250
+ "Regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"
251
+ },
252
+ "behavior": "Isolated",
253
+ "invert": false
254
+ },
255
+ {
256
+ "type": "ByteLevel",
257
+ "add_prefix_space": false,
258
+ "trim_offsets": false,
259
+ "use_regex": false
260
+ }
261
+ ]
262
+ },
263
+ "post_processor": {
264
+ "type": "ByteLevel",
265
+ "add_prefix_space": false,
266
+ "trim_offsets": false,
267
+ "use_regex": false
268
+ },
269
+ "decoder": {
270
+ "type": "ByteLevel",
271
+ "add_prefix_space": false,
272
+ "trim_offsets": false,
273
+ "use_regex": false
274
+ },
275
+ "model": {
276
+ "type": "BPE",
277
+ "dropout": null,
278
+ "unk_token": null,
279
+ "continuing_subword_prefix": "",
280
+ "end_of_word_suffix": "",
281
+ "fuse_unk": false,
282
+ "byte_fallback": false,
283
+ "ignore_merges": false,
284
+ "vocab": {
285
+ "!": 0,
286
+ "\"": 1,
287
+ "#": 2,
288
+ "$": 3,
289
+ "%": 4,
290
+ "&": 5,
291
+ "'": 6,
292
+ "(": 7,
293
+ ")": 8,
294
+ "*": 9,
295
+ "+": 10,
296
+ ",": 11,
297
+ "-": 12,
298
+ ".": 13,
299
+ "/": 14,
300
+ "0": 15,
301
+ "1": 16,
302
+ "2": 17,
303
+ "3": 18,
304
+ "4": 19,
305
+ "5": 20,
306
+ "6": 21,
307
+ "7": 22,
308
+ "8": 23,
309
+ "9": 24,
310
+ ":": 25,
311
+ ";": 26,
312
+ "<": 27,
313
+ "=": 28,
314
+ ">": 29,
315
+ "?": 30,
316
+ "@": 31,
317
+ "A": 32,
318
+ "B": 33,
319
+ "C": 34,
320
+ "D": 35,
321
+ "E": 36,
322
+ "F": 37,
323
+ "G": 38,
324
+ "H": 39,
325
+ "I": 40,
326
+ "J": 41,
327
+ "K": 42,
328
+ "L": 43,
329
+ "M": 44,
330
+ "N": 45,
331
+ "O": 46,
332
+ "P": 47,
333
+ "Q": 48,
334
+ "R": 49,
335
+ "S": 50,
336
+ "T": 51,
337
+ "U": 52,
338
+ "V": 53,
339
+ "W": 54,
340
+ "X": 55,
341
+ "Y": 56,
342
+ "Z": 57,
343
+ "[": 58,
344
+ "\\": 59,
345
+ "]": 60,
346
+ "^": 61,
347
+ "_": 62,
348
+ "`": 63,
349
+ "a": 64,
350
+ "b": 65,
351
+ "c": 66,
352
+ "d": 67,
353
+ "e": 68,
354
+ "f": 69,
355
+ "g": 70,
356
+ "h": 71,
357
+ "i": 72,
358
+ "j": 73,
359
+ "k": 74,
360
+ "l": 75,
361
+ "m": 76,
362
+ "n": 77,
363
+ "o": 78,
364
+ "p": 79,
365
+ "q": 80,
366
+ "r": 81,
367
+ "s": 82,
368
+ "t": 83,
369
+ "u": 84,
370
+ "v": 85,
371
+ "w": 86,
372
+ "x": 87,
373
+ "y": 88,
374
+ "z": 89,
375
+ "{": 90,
376
+ "|": 91,
377
+ "}": 92,
378
+ "~": 93,
379
+ "¡": 94,
380
+ "¢": 95,
381
+ "£": 96,
382
+ "¤": 97,
383
+ "¥": 98,
384
+ "¦": 99,
385
+ "§": 100,
386
+ "¨": 101,
387
+ "©": 102,
388
+ "ª": 103,
389
+ "«": 104,
390
+ "¬": 105,
391
+ "®": 106,
392
+ "¯": 107,
393
+ "°": 108,
394
+ "±": 109,
395
+ "²": 110,
396
+ "³": 111,
397
+ "´": 112,
398
+ "µ": 113,
399
+ "¶": 114,
400
+ "·": 115,
401
+ "¸": 116,
402
+ "¹": 117,
403
+ "º": 118,
404
+ "»": 119,
405
+ "¼": 120,
406
+ "½": 121,
407
+ "¾": 122,
408
+ "¿": 123,
409
+ "À": 124,
410
+ "Á": 125,
411
+ "Â": 126,
412
+ "Ã": 127,
413
+ "Ä": 128,
414
+ "Å": 129,
415
+ "Æ": 130,
416
+ "Ç": 131,
417
+ "È": 132,
418
+ "É": 133,
419
+ "Ê": 134,
420
+ "Ë": 135,
421
+ "Ì": 136,
422
+ "Í": 137,
423
+ "Î": 138,
424
+ "Ï": 139,
425
+ "Ð": 140,
426
+ "Ñ": 141,
427
+ "Ò": 142,
428
+ "Ó": 143,
429
+ "Ô": 144,
430
+ "Õ": 145,
431
+ "Ö": 146,
432
+ "×": 147,
433
+ "Ø": 148,
434
+ "Ù": 149,
435
+ "Ú": 150,
436
+ "Û": 151,
437
+ "Ü": 152,
438
+ "Ý": 153,
439
+ "Þ": 154,
440
+ "ß": 155,
441
+ "à": 156,
442
+ "á": 157,
443
+ "â": 158,
444
+ "ã": 159,
445
+ "ä": 160,
446
+ "å": 161,
447
+ "æ": 162,
448
+ "ç": 163,
449
+ "è": 164,
450
+ "é": 165,
451
+ "ê": 166,
452
+ "ë": 167,
453
+ "ì": 168,
454
+ "í": 169,
455
+ "î": 170,
456
+ "ï": 171,
457
+ "ð": 172,
458
+ "ñ": 173,
459
+ "ò": 174,
460
+ "ó": 175,
461
+ "ô": 176,
462
+ "õ": 177,
463
+ "ö": 178,
464
+ "÷": 179,
465
+ "ø": 180,
466
+ "ù": 181,
467
+ "ú": 182,
468
+ "û": 183,
469
+ "ü": 184,
470
+ "ý": 185,
471
+ "þ": 186,
472
+ "ÿ": 187,
473
+ "Ā": 188,
474
+ "ā": 189,
475
+ "Ă": 190,
476
+ "ă": 191,
477
+ "Ą": 192,
478
+ "ą": 193,
479
+ "Ć": 194,
480
+ "ć": 195,
481
+ "Ĉ": 196,
482
+ "ĉ": 197,
483
+ "Ċ": 198,
484
+ "ċ": 199,
485
+ "Č": 200,
486
+ "č": 201,
487
+ "Ď": 202,
488
+ "ď": 203,
489
+ "Đ": 204,
490
+ "đ": 205,
491
+ "Ē": 206,
492
+ "ē": 207,
493
+ "Ĕ": 208,
494
+ "ĕ": 209,
495
+ "Ė": 210,
496
+ "ė": 211,
497
+ "Ę": 212,
498
+ "ę": 213,
499
+ "Ě": 214,
500
+ "ě": 215,
501
+ "Ĝ": 216,
502
+ "ĝ": 217,
503
+ "Ğ": 218,
504
+ "ğ": 219,
505
+ "Ġ": 220,
506
+ "ġ": 221,
507
+ "Ģ": 222,
508
+ "ģ": 223,
509
+ "Ĥ": 224,
510
+ "ĥ": 225,
511
+ "Ħ": 226,
512
+ "ħ": 227,
513
+ "Ĩ": 228,
514
+ "ĩ": 229,
515
+ "Ī": 230,
516
+ "ī": 231,
517
+ "Ĭ": 232,
518
+ "ĭ": 233,
519
+ "Į": 234,
520
+ "į": 235,
521
+ "İ": 236,
522
+ "ı": 237,
523
+ "IJ": 238,
524
+ "ij": 239,
525
+ "Ĵ": 240,
526
+ "ĵ": 241,
527
+ "Ķ": 242,
528
+ "ķ": 243,
529
+ "ĸ": 244,
530
+ "Ĺ": 245,
531
+ "ĺ": 246,
532
+ "Ļ": 247,
533
+ "ļ": 248,
534
+ "Ľ": 249,
535
+ "ľ": 250,
536
+ "Ŀ": 251,
537
+ "ŀ": 252,
538
+ "Ł": 253,
539
+ "ł": 254,
540
+ "Ń": 255,
541
+ "ĠĠ": 256,
542
+ "ĠĠĠĠ": 257,
543
+ "in": 258,
544
+ "Ġt": 259,
545
+ "ĠĠĠĠĠĠĠĠ": 260,
546
+ "er": 261,
547
+ "ĠĠĠ": 262,
548
+ "on": 263,
549
+ "Ġa": 264,
550
+ "re": 265,
551
+ "at": 266,
552
+ "st": 267,
553
+ "en": 268,
554
+ "or": 269,
555
+ "Ġth": 270,
556
+ "ĊĊ": 271,
557
+ "Ġc": 272,
558
+ "le": 273,
559
+ "Ġs": 274,
560
+ "it": 275,
561
+ "an": 276,
562
+ "ar": 277,
563
+ "al": 278,
564
+ "Ġthe": 279,
565
+ ";Ċ": 280,
566
+ "Ġp": 281,
567
+ "Ġf": 282,
568
+ "ou": 283,
569
+ "Ġ=": 284,
570
+ "is": 285,
571
+ "ĠĠĠĠĠĠĠ": 286,
572
+ "ing": 287,
573
+ "es": 288,
574
+ "Ġw": 289,
575
+ "ion": 290,
576
+ "ed": 291,
577
+ "ic": 292,
578
+ "Ġb": 293,
579
+ "Ġd": 294,
580
+ "et": 295,
581
+ "Ġm": 296,
582
+ "Ġo": 297,
583
+ "ĉĉ": 298,
584
+ "ro": 299,
585
+ "as": 300,
586
+ "el": 301,
587
+ "ct": 302,
588
+ "nd": 303,
589
+ "Ġin": 304,
590
+ "Ġh": 305,
591
+ "ent": 306,
592
+ "id": 307,
593
+ "Ġn": 308,
594
+ "am": 309,
595
+ "ĠĠĠĠĠĠĠĠĠĠĠ": 310,
596
+ "Ġto": 311,
597
+ "Ġre": 312,
598
+ "--": 313,
599
+ "Ġ{": 314,
600
+ "Ġof": 315,
601
+ "om": 316,
602
+ ");Ċ": 317,
603
+ "im": 318,
604
+ "čĊ": 319,
605
+ "Ġ(": 320,
606
+ "il": 321,
607
+ "//": 322,
608
+ "Ġand": 323,
609
+ "ur": 324,
610
+ "se": 325,
611
+ "Ġl": 326,
612
+ "ex": 327,
613
+ "ĠS": 328,
614
+ "ad": 329,
615
+ "Ġ\"": 330,
616
+ "ch": 331,
617
+ "ut": 332,
618
+ "if": 333,
619
+ "**": 334,
620
+ "Ġ}": 335,
621
+ "em": 336,
622
+ "ol": 337,
623
+ "ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ": 338,
624
+ "th": 339,
625
+ ")Ċ": 340,
626
+ "Ġ{Ċ": 341,
627
+ "Ġg": 342,
628
+ "ig": 343,
629
+ "iv": 344,
630
+ ",Ċ": 345,
631
+ "ce": 346,
632
+ "od": 347,
633
+ "Ġv": 348,
634
+ "ate": 349,
635
+ "ĠT": 350,
636
+ "ag": 351,
637
+ "ay": 352,
638
+ "Ġ*": 353,
639
+ "ot": 354,
640
+ "us": 355,
641
+ "ĠC": 356,
642
+ "Ġst": 357,
643
+ "ĠI": 358,
644
+ "un": 359,
645
+ "ul": 360,
646
+ "ue": 361,
647
+ "ĠA": 362,
648
+ "ow": 363,
649
+ "Ġ'": 364,
650
+ "ew": 365,
651
+ "Ġ<": 366,
652
+ "ation": 367,
653
+ "()": 368,
654
+ "Ġfor": 369,
655
+ "ab": 370,
656
+ "ort": 371,
657
+ "um": 372,
658
+ "ame": 373,
659
+ "Ġis": 374,
660
+ "pe": 375,
661
+ "tr": 376,
662
+ "ck": 377,
663
+ "âĢ": 378,
664
+ "Ġy": 379,
665
+ "ist": 380,
666
+ "----": 381,
667
+ ".ĊĊ": 382,
668
+ "he": 383,
669
+ "Ġe": 384,
670
+ "lo": 385,
671
+ "ĠM": 386,
672
+ "Ġbe": 387,
673
+ "ers": 388,
674
+ "Ġon": 389,
675
+ "Ġcon": 390,
676
+ "ap": 391,
677
+ "ub": 392,
678
+ "ĠP": 393,
679
+ "ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ": 394,
680
+ "ass": 395,
681
+ "int": 396,
682
+ ">Ċ": 397,
683
+ "ly": 398,
684
+ "urn": 399,
685
+ "Ġ$": 400,
686
+ ";ĊĊ": 401,
687
+ "av": 402,
688
+ "port": 403,
689
+ "ir": 404,
690
+ "->": 405,
691
+ "nt": 406,
692
+ "ction": 407,
693
+ "end": 408,
694
+ "Ġde": 409,
695
+ "ith": 410,
696
+ "out": 411,
697
+ "turn": 412,
698
+ "our": 413,
699
+ "ĠĠĠĠĠ": 414,
700
+ "lic": 415,
701
+ "res": 416,
702
+ "pt": 417,
703
+ "==": 418,
704
+ "Ġthis": 419,
705
+ "Ġwh": 420,
706
+ "Ġif": 421,
707
+ "ĠD": 422,
708
+ "ver": 423,
709
+ "age": 424,
710
+ "ĠB": 425,
711
+ "ht": 426,
712
+ "ext": 427,
713
+ "=\"": 428,
714
+ "Ġthat": 429,
715
+ "****": 430,
716
+ "ĠR": 431,
717
+ "Ġit": 432,
718
+ "ess": 433,
719
+ "ĠF": 434,
720
+ "Ġr": 435,
721
+ "os": 436,
722
+ "and": 437,
723
+ "Ġas": 438,
724
+ "ect": 439,
725
+ "ke": 440,
726
+ "rom": 441,
727
+ "Ġ//": 442,
728
+ "con": 443,
729
+ "ĠL": 444,
730
+ "(\"": 445,
731
+ "qu": 446,
732
+ "lass": 447,
733
+ "Ġwith": 448,
734
+ "iz": 449,
735
+ "de": 450,
736
+ "ĠN": 451,
737
+ "Ġal": 452,
738
+ "op": 453,
739
+ "up": 454,
740
+ "get": 455,
741
+ "Ġ}Ċ": 456,
742
+ "ile": 457,
743
+ "Ġan": 458,
744
+ "ata": 459,
745
+ "ore": 460,
746
+ "ri": 461,
747
+ "Ġpro": 462,
748
+ ";čĊ": 463,
749
+ "ĉĉĉĉ": 464,
750
+ "ter": 465,
751
+ "ain": 466,
752
+ "ĠW": 467,
753
+ "ĠE": 468,
754
+ "Ġcom": 469,
755
+ "Ġreturn": 470,
756
+ "art": 471,
757
+ "ĠH": 472,
758
+ "ack": 473,
759
+ "import": 474,
760
+ "ublic": 475,
761
+ "Ġor": 476,
762
+ "est": 477,
763
+ "ment": 478,
764
+ "ĠG": 479,
765
+ "able": 480,
766
+ "Ġ-": 481,
767
+ "ine": 482,
768
+ "ill": 483,
769
+ "ind": 484,
770
+ "ere": 485,
771
+ "::": 486,
772
+ "ity": 487,
773
+ "Ġ+": 488,
774
+ "Ġtr": 489,
775
+ "elf": 490,
776
+ "ight": 491,
777
+ "('": 492,
778
+ "orm": 493,
779
+ "ult": 494,
780
+ "str": 495,
781
+ "..": 496,
782
+ "\",": 497,
783
+ "Ġyou": 498,
784
+ "ype": 499
785
+ },
786
+ "merges": [
787
+ [
788
+ "Ġ",
789
+ "Ġ"
790
+ ],
791
+ [
792
+ "ĠĠ",
793
+ "ĠĠ"
794
+ ],
795
+ [
796
+ "i",
797
+ "n"
798
+ ],
799
+ [
800
+ "Ġ",
801
+ "t"
802
+ ],
803
+ [
804
+ "ĠĠĠĠ",
805
+ "ĠĠĠĠ"
806
+ ],
807
+ [
808
+ "e",
809
+ "r"
810
+ ],
811
+ [
812
+ "ĠĠ",
813
+ "Ġ"
814
+ ],
815
+ [
816
+ "o",
817
+ "n"
818
+ ],
819
+ [
820
+ "Ġ",
821
+ "a"
822
+ ],
823
+ [
824
+ "r",
825
+ "e"
826
+ ],
827
+ [
828
+ "a",
829
+ "t"
830
+ ],
831
+ [
832
+ "s",
833
+ "t"
834
+ ],
835
+ [
836
+ "e",
837
+ "n"
838
+ ],
839
+ [
840
+ "o",
841
+ "r"
842
+ ],
843
+ [
844
+ "Ġt",
845
+ "h"
846
+ ],
847
+ [
848
+ "Ċ",
849
+ "Ċ"
850
+ ],
851
+ [
852
+ "Ġ",
853
+ "c"
854
+ ],
855
+ [
856
+ "l",
857
+ "e"
858
+ ],
859
+ [
860
+ "Ġ",
861
+ "s"
862
+ ],
863
+ [
864
+ "i",
865
+ "t"
866
+ ],
867
+ [
868
+ "a",
869
+ "n"
870
+ ],
871
+ [
872
+ "a",
873
+ "r"
874
+ ],
875
+ [
876
+ "a",
877
+ "l"
878
+ ],
879
+ [
880
+ "Ġth",
881
+ "e"
882
+ ],
883
+ [
884
+ ";",
885
+ "Ċ"
886
+ ],
887
+ [
888
+ "Ġ",
889
+ "p"
890
+ ],
891
+ [
892
+ "Ġ",
893
+ "f"
894
+ ],
895
+ [
896
+ "o",
897
+ "u"
898
+ ],
899
+ [
900
+ "Ġ",
901
+ "="
902
+ ],
903
+ [
904
+ "i",
905
+ "s"
906
+ ],
907
+ [
908
+ "ĠĠĠĠ",
909
+ "ĠĠĠ"
910
+ ],
911
+ [
912
+ "in",
913
+ "g"
914
+ ],
915
+ [
916
+ "e",
917
+ "s"
918
+ ],
919
+ [
920
+ "Ġ",
921
+ "w"
922
+ ],
923
+ [
924
+ "i",
925
+ "on"
926
+ ],
927
+ [
928
+ "e",
929
+ "d"
930
+ ],
931
+ [
932
+ "i",
933
+ "c"
934
+ ],
935
+ [
936
+ "Ġ",
937
+ "b"
938
+ ],
939
+ [
940
+ "Ġ",
941
+ "d"
942
+ ],
943
+ [
944
+ "e",
945
+ "t"
946
+ ],
947
+ [
948
+ "Ġ",
949
+ "m"
950
+ ],
951
+ [
952
+ "Ġ",
953
+ "o"
954
+ ],
955
+ [
956
+ "ĉ",
957
+ "ĉ"
958
+ ],
959
+ [
960
+ "r",
961
+ "o"
962
+ ],
963
+ [
964
+ "a",
965
+ "s"
966
+ ],
967
+ [
968
+ "e",
969
+ "l"
970
+ ],
971
+ [
972
+ "c",
973
+ "t"
974
+ ],
975
+ [
976
+ "n",
977
+ "d"
978
+ ],
979
+ [
980
+ "Ġ",
981
+ "in"
982
+ ],
983
+ [
984
+ "Ġ",
985
+ "h"
986
+ ],
987
+ [
988
+ "en",
989
+ "t"
990
+ ],
991
+ [
992
+ "i",
993
+ "d"
994
+ ],
995
+ [
996
+ "Ġ",
997
+ "n"
998
+ ],
999
+ [
1000
+ "a",
1001
+ "m"
1002
+ ],
1003
+ [
1004
+ "ĠĠĠĠĠĠĠĠ",
1005
+ "ĠĠĠ"
1006
+ ],
1007
+ [
1008
+ "Ġt",
1009
+ "o"
1010
+ ],
1011
+ [
1012
+ "Ġ",
1013
+ "re"
1014
+ ],
1015
+ [
1016
+ "-",
1017
+ "-"
1018
+ ],
1019
+ [
1020
+ "Ġ",
1021
+ "{"
1022
+ ],
1023
+ [
1024
+ "Ġo",
1025
+ "f"
1026
+ ],
1027
+ [
1028
+ "o",
1029
+ "m"
1030
+ ],
1031
+ [
1032
+ ")",
1033
+ ";Ċ"
1034
+ ],
1035
+ [
1036
+ "i",
1037
+ "m"
1038
+ ],
1039
+ [
1040
+ "č",
1041
+ "Ċ"
1042
+ ],
1043
+ [
1044
+ "Ġ",
1045
+ "("
1046
+ ],
1047
+ [
1048
+ "i",
1049
+ "l"
1050
+ ],
1051
+ [
1052
+ "/",
1053
+ "/"
1054
+ ],
1055
+ [
1056
+ "Ġa",
1057
+ "nd"
1058
+ ],
1059
+ [
1060
+ "u",
1061
+ "r"
1062
+ ],
1063
+ [
1064
+ "s",
1065
+ "e"
1066
+ ],
1067
+ [
1068
+ "Ġ",
1069
+ "l"
1070
+ ],
1071
+ [
1072
+ "e",
1073
+ "x"
1074
+ ],
1075
+ [
1076
+ "Ġ",
1077
+ "S"
1078
+ ],
1079
+ [
1080
+ "a",
1081
+ "d"
1082
+ ],
1083
+ [
1084
+ "Ġ",
1085
+ "\""
1086
+ ],
1087
+ [
1088
+ "c",
1089
+ "h"
1090
+ ],
1091
+ [
1092
+ "u",
1093
+ "t"
1094
+ ],
1095
+ [
1096
+ "i",
1097
+ "f"
1098
+ ],
1099
+ [
1100
+ "*",
1101
+ "*"
1102
+ ],
1103
+ [
1104
+ "Ġ",
1105
+ "}"
1106
+ ],
1107
+ [
1108
+ "e",
1109
+ "m"
1110
+ ],
1111
+ [
1112
+ "o",
1113
+ "l"
1114
+ ],
1115
+ [
1116
+ "ĠĠĠĠĠĠĠĠ",
1117
+ "ĠĠĠĠĠĠĠĠ"
1118
+ ],
1119
+ [
1120
+ "t",
1121
+ "h"
1122
+ ],
1123
+ [
1124
+ ")",
1125
+ "Ċ"
1126
+ ],
1127
+ [
1128
+ "Ġ{",
1129
+ "Ċ"
1130
+ ],
1131
+ [
1132
+ "Ġ",
1133
+ "g"
1134
+ ],
1135
+ [
1136
+ "i",
1137
+ "g"
1138
+ ],
1139
+ [
1140
+ "i",
1141
+ "v"
1142
+ ],
1143
+ [
1144
+ ",",
1145
+ "Ċ"
1146
+ ],
1147
+ [
1148
+ "c",
1149
+ "e"
1150
+ ],
1151
+ [
1152
+ "o",
1153
+ "d"
1154
+ ],
1155
+ [
1156
+ "Ġ",
1157
+ "v"
1158
+ ],
1159
+ [
1160
+ "at",
1161
+ "e"
1162
+ ],
1163
+ [
1164
+ "Ġ",
1165
+ "T"
1166
+ ],
1167
+ [
1168
+ "a",
1169
+ "g"
1170
+ ],
1171
+ [
1172
+ "a",
1173
+ "y"
1174
+ ],
1175
+ [
1176
+ "Ġ",
1177
+ "*"
1178
+ ],
1179
+ [
1180
+ "o",
1181
+ "t"
1182
+ ],
1183
+ [
1184
+ "u",
1185
+ "s"
1186
+ ],
1187
+ [
1188
+ "Ġ",
1189
+ "C"
1190
+ ],
1191
+ [
1192
+ "Ġ",
1193
+ "st"
1194
+ ],
1195
+ [
1196
+ "Ġ",
1197
+ "I"
1198
+ ],
1199
+ [
1200
+ "u",
1201
+ "n"
1202
+ ],
1203
+ [
1204
+ "u",
1205
+ "l"
1206
+ ],
1207
+ [
1208
+ "u",
1209
+ "e"
1210
+ ],
1211
+ [
1212
+ "Ġ",
1213
+ "A"
1214
+ ],
1215
+ [
1216
+ "o",
1217
+ "w"
1218
+ ],
1219
+ [
1220
+ "Ġ",
1221
+ "'"
1222
+ ],
1223
+ [
1224
+ "e",
1225
+ "w"
1226
+ ],
1227
+ [
1228
+ "Ġ",
1229
+ "<"
1230
+ ],
1231
+ [
1232
+ "at",
1233
+ "ion"
1234
+ ],
1235
+ [
1236
+ "(",
1237
+ ")"
1238
+ ],
1239
+ [
1240
+ "Ġf",
1241
+ "or"
1242
+ ],
1243
+ [
1244
+ "a",
1245
+ "b"
1246
+ ],
1247
+ [
1248
+ "or",
1249
+ "t"
1250
+ ],
1251
+ [
1252
+ "u",
1253
+ "m"
1254
+ ],
1255
+ [
1256
+ "am",
1257
+ "e"
1258
+ ],
1259
+ [
1260
+ "Ġ",
1261
+ "is"
1262
+ ],
1263
+ [
1264
+ "p",
1265
+ "e"
1266
+ ],
1267
+ [
1268
+ "t",
1269
+ "r"
1270
+ ],
1271
+ [
1272
+ "c",
1273
+ "k"
1274
+ ],
1275
+ [
1276
+ "â",
1277
+ "Ģ"
1278
+ ],
1279
+ [
1280
+ "Ġ",
1281
+ "y"
1282
+ ],
1283
+ [
1284
+ "i",
1285
+ "st"
1286
+ ],
1287
+ [
1288
+ "--",
1289
+ "--"
1290
+ ],
1291
+ [
1292
+ ".",
1293
+ "ĊĊ"
1294
+ ],
1295
+ [
1296
+ "h",
1297
+ "e"
1298
+ ],
1299
+ [
1300
+ "Ġ",
1301
+ "e"
1302
+ ],
1303
+ [
1304
+ "l",
1305
+ "o"
1306
+ ],
1307
+ [
1308
+ "Ġ",
1309
+ "M"
1310
+ ],
1311
+ [
1312
+ "Ġb",
1313
+ "e"
1314
+ ],
1315
+ [
1316
+ "er",
1317
+ "s"
1318
+ ],
1319
+ [
1320
+ "Ġ",
1321
+ "on"
1322
+ ],
1323
+ [
1324
+ "Ġc",
1325
+ "on"
1326
+ ],
1327
+ [
1328
+ "a",
1329
+ "p"
1330
+ ],
1331
+ [
1332
+ "u",
1333
+ "b"
1334
+ ],
1335
+ [
1336
+ "Ġ",
1337
+ "P"
1338
+ ],
1339
+ [
1340
+ "ĠĠĠĠĠĠĠĠ",
1341
+ "ĠĠĠĠĠĠĠ"
1342
+ ],
1343
+ [
1344
+ "as",
1345
+ "s"
1346
+ ],
1347
+ [
1348
+ "in",
1349
+ "t"
1350
+ ],
1351
+ [
1352
+ ">",
1353
+ "Ċ"
1354
+ ],
1355
+ [
1356
+ "l",
1357
+ "y"
1358
+ ],
1359
+ [
1360
+ "ur",
1361
+ "n"
1362
+ ],
1363
+ [
1364
+ "Ġ",
1365
+ "$"
1366
+ ],
1367
+ [
1368
+ ";",
1369
+ "ĊĊ"
1370
+ ],
1371
+ [
1372
+ "a",
1373
+ "v"
1374
+ ],
1375
+ [
1376
+ "p",
1377
+ "ort"
1378
+ ],
1379
+ [
1380
+ "i",
1381
+ "r"
1382
+ ],
1383
+ [
1384
+ "-",
1385
+ ">"
1386
+ ],
1387
+ [
1388
+ "n",
1389
+ "t"
1390
+ ],
1391
+ [
1392
+ "ct",
1393
+ "ion"
1394
+ ],
1395
+ [
1396
+ "en",
1397
+ "d"
1398
+ ],
1399
+ [
1400
+ "Ġd",
1401
+ "e"
1402
+ ],
1403
+ [
1404
+ "it",
1405
+ "h"
1406
+ ],
1407
+ [
1408
+ "ou",
1409
+ "t"
1410
+ ],
1411
+ [
1412
+ "t",
1413
+ "urn"
1414
+ ],
1415
+ [
1416
+ "ou",
1417
+ "r"
1418
+ ],
1419
+ [
1420
+ "ĠĠĠĠ",
1421
+ "Ġ"
1422
+ ],
1423
+ [
1424
+ "l",
1425
+ "ic"
1426
+ ],
1427
+ [
1428
+ "re",
1429
+ "s"
1430
+ ],
1431
+ [
1432
+ "p",
1433
+ "t"
1434
+ ],
1435
+ [
1436
+ "=",
1437
+ "="
1438
+ ],
1439
+ [
1440
+ "Ġth",
1441
+ "is"
1442
+ ],
1443
+ [
1444
+ "Ġw",
1445
+ "h"
1446
+ ],
1447
+ [
1448
+ "Ġ",
1449
+ "if"
1450
+ ],
1451
+ [
1452
+ "Ġ",
1453
+ "D"
1454
+ ],
1455
+ [
1456
+ "v",
1457
+ "er"
1458
+ ],
1459
+ [
1460
+ "ag",
1461
+ "e"
1462
+ ],
1463
+ [
1464
+ "Ġ",
1465
+ "B"
1466
+ ],
1467
+ [
1468
+ "h",
1469
+ "t"
1470
+ ],
1471
+ [
1472
+ "ex",
1473
+ "t"
1474
+ ],
1475
+ [
1476
+ "=",
1477
+ "\""
1478
+ ],
1479
+ [
1480
+ "Ġth",
1481
+ "at"
1482
+ ],
1483
+ [
1484
+ "**",
1485
+ "**"
1486
+ ],
1487
+ [
1488
+ "Ġ",
1489
+ "R"
1490
+ ],
1491
+ [
1492
+ "Ġ",
1493
+ "it"
1494
+ ],
1495
+ [
1496
+ "es",
1497
+ "s"
1498
+ ],
1499
+ [
1500
+ "Ġ",
1501
+ "F"
1502
+ ],
1503
+ [
1504
+ "Ġ",
1505
+ "r"
1506
+ ],
1507
+ [
1508
+ "o",
1509
+ "s"
1510
+ ],
1511
+ [
1512
+ "an",
1513
+ "d"
1514
+ ],
1515
+ [
1516
+ "Ġa",
1517
+ "s"
1518
+ ],
1519
+ [
1520
+ "e",
1521
+ "ct"
1522
+ ],
1523
+ [
1524
+ "k",
1525
+ "e"
1526
+ ],
1527
+ [
1528
+ "ro",
1529
+ "m"
1530
+ ],
1531
+ [
1532
+ "Ġ",
1533
+ "//"
1534
+ ],
1535
+ [
1536
+ "c",
1537
+ "on"
1538
+ ],
1539
+ [
1540
+ "Ġ",
1541
+ "L"
1542
+ ],
1543
+ [
1544
+ "(",
1545
+ "\""
1546
+ ],
1547
+ [
1548
+ "q",
1549
+ "u"
1550
+ ],
1551
+ [
1552
+ "l",
1553
+ "ass"
1554
+ ],
1555
+ [
1556
+ "Ġw",
1557
+ "ith"
1558
+ ],
1559
+ [
1560
+ "i",
1561
+ "z"
1562
+ ],
1563
+ [
1564
+ "d",
1565
+ "e"
1566
+ ],
1567
+ [
1568
+ "Ġ",
1569
+ "N"
1570
+ ],
1571
+ [
1572
+ "Ġa",
1573
+ "l"
1574
+ ],
1575
+ [
1576
+ "o",
1577
+ "p"
1578
+ ],
1579
+ [
1580
+ "u",
1581
+ "p"
1582
+ ],
1583
+ [
1584
+ "g",
1585
+ "et"
1586
+ ],
1587
+ [
1588
+ "Ġ}",
1589
+ "Ċ"
1590
+ ],
1591
+ [
1592
+ "i",
1593
+ "le"
1594
+ ],
1595
+ [
1596
+ "Ġa",
1597
+ "n"
1598
+ ],
1599
+ [
1600
+ "at",
1601
+ "a"
1602
+ ],
1603
+ [
1604
+ "o",
1605
+ "re"
1606
+ ],
1607
+ [
1608
+ "r",
1609
+ "i"
1610
+ ],
1611
+ [
1612
+ "Ġp",
1613
+ "ro"
1614
+ ],
1615
+ [
1616
+ ";",
1617
+ "čĊ"
1618
+ ],
1619
+ [
1620
+ "ĉĉ",
1621
+ "ĉĉ"
1622
+ ],
1623
+ [
1624
+ "t",
1625
+ "er"
1626
+ ],
1627
+ [
1628
+ "a",
1629
+ "in"
1630
+ ],
1631
+ [
1632
+ "Ġ",
1633
+ "W"
1634
+ ],
1635
+ [
1636
+ "Ġ",
1637
+ "E"
1638
+ ],
1639
+ [
1640
+ "Ġc",
1641
+ "om"
1642
+ ],
1643
+ [
1644
+ "Ġre",
1645
+ "turn"
1646
+ ],
1647
+ [
1648
+ "ar",
1649
+ "t"
1650
+ ],
1651
+ [
1652
+ "Ġ",
1653
+ "H"
1654
+ ],
1655
+ [
1656
+ "a",
1657
+ "ck"
1658
+ ],
1659
+ [
1660
+ "im",
1661
+ "port"
1662
+ ],
1663
+ [
1664
+ "ub",
1665
+ "lic"
1666
+ ],
1667
+ [
1668
+ "Ġ",
1669
+ "or"
1670
+ ],
1671
+ [
1672
+ "e",
1673
+ "st"
1674
+ ],
1675
+ [
1676
+ "m",
1677
+ "ent"
1678
+ ],
1679
+ [
1680
+ "Ġ",
1681
+ "G"
1682
+ ],
1683
+ [
1684
+ "ab",
1685
+ "le"
1686
+ ],
1687
+ [
1688
+ "Ġ",
1689
+ "-"
1690
+ ],
1691
+ [
1692
+ "in",
1693
+ "e"
1694
+ ],
1695
+ [
1696
+ "il",
1697
+ "l"
1698
+ ],
1699
+ [
1700
+ "in",
1701
+ "d"
1702
+ ],
1703
+ [
1704
+ "er",
1705
+ "e"
1706
+ ],
1707
+ [
1708
+ ":",
1709
+ ":"
1710
+ ],
1711
+ [
1712
+ "it",
1713
+ "y"
1714
+ ],
1715
+ [
1716
+ "Ġ",
1717
+ "+"
1718
+ ],
1719
+ [
1720
+ "Ġt",
1721
+ "r"
1722
+ ],
1723
+ [
1724
+ "el",
1725
+ "f"
1726
+ ],
1727
+ [
1728
+ "ig",
1729
+ "ht"
1730
+ ],
1731
+ [
1732
+ "(",
1733
+ "'"
1734
+ ],
1735
+ [
1736
+ "or",
1737
+ "m"
1738
+ ],
1739
+ [
1740
+ "ul",
1741
+ "t"
1742
+ ],
1743
+ [
1744
+ "st",
1745
+ "r"
1746
+ ],
1747
+ [
1748
+ ".",
1749
+ "."
1750
+ ],
1751
+ [
1752
+ "\"",
1753
+ ","
1754
+ ],
1755
+ [
1756
+ "Ġy",
1757
+ "ou"
1758
+ ],
1759
+ [
1760
+ "y",
1761
+ "pe"
1762
+ ]
1763
+ ]
1764
+ }
1765
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,243 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "image_token": "<|image_pad|>",
235
+ "image_break_token": "<|vision_pad|>",
236
+ "image_end_token": "<|vision_end|>",
237
+ "model_max_length": 131072,
238
+ "pad_token": "<|endoftext|>",
239
+ "processor_class": "LightOnOCRProcessor",
240
+ "split_special_tokens": false,
241
+ "tokenizer_class": "Qwen2Tokenizer",
242
+ "unk_token": null
243
+ }