lbourdoispro commited on
Commit
68c2048
·
verified ·
1 Parent(s): ac5eb4c

Trimmed google/gemma-3-4b-it for Scottish_Gaelic (16384 tokens)

Browse files
README.md ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: gla
3
+ license: gemma
4
+ tags:
5
+ - trimmed
6
+ - gemma
7
+ - gemma-3
8
+ base_model: google/gemma-3-4b-it
9
+ base_model_relation: quantized
10
+ datasets:
11
+ - Lumberjackk/fineweb-2-trimming
12
+ ---
13
+
14
+ # gemma-3-4b-it-gla-16384
15
+
16
+ This model is a **14.63% smaller** version of [google/gemma-3-4b-it](https://huggingface.co/google/gemma-3-4b-it) optimized for Scottish_Gaelic language via vocabulary size reduction using the [trimming](https://huggingface.co/blog/introduction-to-trimming) method.
17
+
18
+ This trimmed model should perform similarly to the original model with only **16,384 tokens** and a much smaller memory footprint. However, it may not perform well for other languages as tokens not commonly used in Scottish_Gaelic were removed from the vocabulary.
19
+
20
+ ## Model Statistics
21
+
22
+ | Metric | Original | Trimmed | Reduction |
23
+ |--------|----------|---------|-----------|
24
+ | **Vocabulary size** | 262,144 tokens | 16,384 tokens | **93.75%** |
25
+ | **Model size** | 4,300,079,472 params | 3,670,770,032 params | **14.63%** |
26
+
27
+ ## Mining Dataset Statistics
28
+
29
+ - **Number of texts used for mining**: 200,000 texts
30
+ - **Dataset**: [Lumberjackk/fineweb-2-trimming](https://huggingface.co/datasets/Lumberjackk/fineweb-2-trimming)
31
+
32
+ ## Usage
33
+ ```python
34
+ from transformers import AutoModelForCausalLM, AutoTokenizer
35
+
36
+ model_name = "AlphaEdge-AI/gemma-3-4b-it-gla-16384"
37
+
38
+ tokenizer = AutoTokenizer.from_pretrained(model_name)
39
+ model = AutoModelForCausalLM.from_pretrained(
40
+ model_name,
41
+ torch_dtype="auto",
42
+ device_map="auto"
43
+ )
44
+
45
+ prompt = "Your prompt in Scottish_Gaelic."
46
+ messages = [{"role": "user", "content": prompt}]
47
+ text = tokenizer.apply_chat_template(
48
+ messages,
49
+ tokenize=False,
50
+ add_generation_prompt=True
51
+ )
52
+ model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
53
+
54
+ generated_ids = model.generate(**model_inputs, max_new_tokens=256)
55
+ output_ids = generated_ids[0][len(model_inputs.input_ids[0]):]
56
+ response = tokenizer.decode(output_ids, skip_special_tokens=True)
57
+ print(response)
58
+ ```
59
+
60
+ ## Citation
61
+
62
+ #### Gemma 3
63
+ ```bibtex
64
+ @misc{gemmateam2025gemma3technicalreport,
65
+ title={Gemma 3 Technical Report},
66
+ author={Gemma Team},
67
+ year={2025},
68
+ eprint={2503.19786},
69
+ archivePrefix={arXiv},
70
+ primaryClass={cs.CL},
71
+ url={https://arxiv.org/abs/2503.19786},
72
+ }
73
+ ```
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<image_soft_token>": 16384
3
+ }
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n {%- if messages[0]['content'] is string -%}\n {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n {%- else -%}\n {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n {%- endif -%}\n {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n {%- set first_user_prefix = \"\" -%}\n {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n {%- endif -%}\n {%- if (message['role'] == 'assistant') -%}\n {%- set role = \"model\" -%}\n {%- else -%}\n {%- set role = message['role'] -%}\n {%- endif -%}\n {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n {%- if message['content'] is string -%}\n {{ message['content'] | trim }}\n {%- elif message['content'] is iterable -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'image' -%}\n {{ '<start_of_image>' }}\n {%- elif item['type'] == 'text' -%}\n {{ item['text'] | trim }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ raise_exception(\"Invalid content type\") }}\n {%- endif -%}\n {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{'<start_of_turn>model\n'}}\n{%- endif -%}\n"
3
+ }
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma3ForConditionalGeneration"
4
+ ],
5
+ "boi_token_index": 16382,
6
+ "eoi_token_index": 16383,
7
+ "eos_token_id": [
8
+ 1,
9
+ 106
10
+ ],
11
+ "image_token_index": 16384,
12
+ "initializer_range": 0.02,
13
+ "mm_tokens_per_image": 256,
14
+ "model_type": "gemma3",
15
+ "text_config": {
16
+ "hidden_size": 2560,
17
+ "intermediate_size": 10240,
18
+ "model_type": "gemma3_text",
19
+ "num_hidden_layers": 34,
20
+ "rope_scaling": {
21
+ "factor": 8.0,
22
+ "rope_type": "linear"
23
+ },
24
+ "sliding_window": 1024,
25
+ "vocab_size": 16384
26
+ },
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.50.0.dev0",
29
+ "vision_config": {
30
+ "hidden_size": 1152,
31
+ "image_size": 896,
32
+ "intermediate_size": 4304,
33
+ "model_type": "siglip_vision_model",
34
+ "num_attention_heads": 16,
35
+ "num_hidden_layers": 27,
36
+ "patch_size": 14,
37
+ "vision_use_head": false
38
+ },
39
+ "vocab_size": 16384
40
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2,
3
+ "cache_implementation": "hybrid",
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 1,
7
+ 106
8
+ ],
9
+ "pad_token_id": 0,
10
+ "top_k": 64,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.50.0.dev0"
13
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:536590541b1a092472bcdb2319ec2ec779199bd70eb004b475487db334ebe7ba
3
+ size 7341659000
preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_pan_and_scan": null,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "Gemma3ImageProcessor",
13
+ "image_seq_length": 256,
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "pan_and_scan_max_num_crops": null,
20
+ "pan_and_scan_min_crop_size": null,
21
+ "pan_and_scan_min_ratio_to_activate": null,
22
+ "processor_class": "Gemma3Processor",
23
+ "resample": 2,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "height": 896,
27
+ "width": 896
28
+ }
29
+ }
processor_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "image_seq_length": 256,
3
+ "processor_class": "Gemma3Processor"
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "boi_token": "<start_of_image>",
3
+ "bos_token": {
4
+ "content": "<bos>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "eoi_token": "<end_of_image>",
11
+ "eos_token": {
12
+ "content": "<eos>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "image_token": "<image_soft_token>",
19
+ "pad_token": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "unk_token": {
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,2195 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true,
12
+ "id": 0
13
+ },
14
+ "1": {
15
+ "content": "<eos>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true,
21
+ "id": 1
22
+ },
23
+ "2": {
24
+ "content": "<bos>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false,
29
+ "special": true,
30
+ "id": 2
31
+ },
32
+ "3": {
33
+ "content": "<unk>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false,
38
+ "special": true,
39
+ "id": 3
40
+ },
41
+ "4": {
42
+ "content": "<mask>",
43
+ "lstrip": false,
44
+ "normalized": false,
45
+ "rstrip": false,
46
+ "single_word": false,
47
+ "special": false,
48
+ "id": 4
49
+ },
50
+ "5": {
51
+ "content": "[multimodal]",
52
+ "lstrip": false,
53
+ "normalized": false,
54
+ "rstrip": false,
55
+ "single_word": false,
56
+ "special": false,
57
+ "id": 5
58
+ },
59
+ "6": {
60
+ "content": "<unused0>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false,
66
+ "id": 6
67
+ },
68
+ "7": {
69
+ "content": "<unused1>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false,
75
+ "id": 7
76
+ },
77
+ "8": {
78
+ "content": "<unused2>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": false,
84
+ "id": 8
85
+ },
86
+ "9": {
87
+ "content": "<unused3>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false,
93
+ "id": 9
94
+ },
95
+ "10": {
96
+ "content": "<unused4>",
97
+ "lstrip": false,
98
+ "normalized": false,
99
+ "rstrip": false,
100
+ "single_word": false,
101
+ "special": false,
102
+ "id": 10
103
+ },
104
+ "11": {
105
+ "content": "<unused5>",
106
+ "lstrip": false,
107
+ "normalized": false,
108
+ "rstrip": false,
109
+ "single_word": false,
110
+ "special": false,
111
+ "id": 11
112
+ },
113
+ "12": {
114
+ "content": "<unused6>",
115
+ "lstrip": false,
116
+ "normalized": false,
117
+ "rstrip": false,
118
+ "single_word": false,
119
+ "special": false,
120
+ "id": 12
121
+ },
122
+ "13": {
123
+ "content": "<unused7>",
124
+ "lstrip": false,
125
+ "normalized": false,
126
+ "rstrip": false,
127
+ "single_word": false,
128
+ "special": false,
129
+ "id": 13
130
+ },
131
+ "14": {
132
+ "content": "<unused8>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false,
138
+ "id": 14
139
+ },
140
+ "15": {
141
+ "content": "<unused9>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false,
147
+ "id": 15
148
+ },
149
+ "16": {
150
+ "content": "<unused10>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false,
156
+ "id": 16
157
+ },
158
+ "17": {
159
+ "content": "<unused11>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false,
165
+ "id": 17
166
+ },
167
+ "18": {
168
+ "content": "<unused12>",
169
+ "lstrip": false,
170
+ "normalized": false,
171
+ "rstrip": false,
172
+ "single_word": false,
173
+ "special": false,
174
+ "id": 18
175
+ },
176
+ "19": {
177
+ "content": "<unused13>",
178
+ "lstrip": false,
179
+ "normalized": false,
180
+ "rstrip": false,
181
+ "single_word": false,
182
+ "special": false,
183
+ "id": 19
184
+ },
185
+ "20": {
186
+ "content": "<unused14>",
187
+ "lstrip": false,
188
+ "normalized": false,
189
+ "rstrip": false,
190
+ "single_word": false,
191
+ "special": false,
192
+ "id": 20
193
+ },
194
+ "21": {
195
+ "content": "<unused15>",
196
+ "lstrip": false,
197
+ "normalized": false,
198
+ "rstrip": false,
199
+ "single_word": false,
200
+ "special": false,
201
+ "id": 21
202
+ },
203
+ "22": {
204
+ "content": "<unused16>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false,
210
+ "id": 22
211
+ },
212
+ "23": {
213
+ "content": "<unused17>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": false,
219
+ "id": 23
220
+ },
221
+ "24": {
222
+ "content": "<unused18>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": false,
228
+ "id": 24
229
+ },
230
+ "25": {
231
+ "content": "<unused19>",
232
+ "lstrip": false,
233
+ "normalized": false,
234
+ "rstrip": false,
235
+ "single_word": false,
236
+ "special": false,
237
+ "id": 25
238
+ },
239
+ "26": {
240
+ "content": "<unused20>",
241
+ "lstrip": false,
242
+ "normalized": false,
243
+ "rstrip": false,
244
+ "single_word": false,
245
+ "special": false,
246
+ "id": 26
247
+ },
248
+ "27": {
249
+ "content": "<unused21>",
250
+ "lstrip": false,
251
+ "normalized": false,
252
+ "rstrip": false,
253
+ "single_word": false,
254
+ "special": false,
255
+ "id": 27
256
+ },
257
+ "28": {
258
+ "content": "<unused22>",
259
+ "lstrip": false,
260
+ "normalized": false,
261
+ "rstrip": false,
262
+ "single_word": false,
263
+ "special": false,
264
+ "id": 28
265
+ },
266
+ "29": {
267
+ "content": "<unused23>",
268
+ "lstrip": false,
269
+ "normalized": false,
270
+ "rstrip": false,
271
+ "single_word": false,
272
+ "special": false,
273
+ "id": 29
274
+ },
275
+ "30": {
276
+ "content": "<unused24>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false,
282
+ "id": 30
283
+ },
284
+ "31": {
285
+ "content": "<unused25>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": false,
291
+ "id": 31
292
+ },
293
+ "32": {
294
+ "content": "<unused26>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": false,
300
+ "id": 32
301
+ },
302
+ "33": {
303
+ "content": "<unused27>",
304
+ "lstrip": false,
305
+ "normalized": false,
306
+ "rstrip": false,
307
+ "single_word": false,
308
+ "special": false,
309
+ "id": 33
310
+ },
311
+ "34": {
312
+ "content": "<unused28>",
313
+ "lstrip": false,
314
+ "normalized": false,
315
+ "rstrip": false,
316
+ "single_word": false,
317
+ "special": false,
318
+ "id": 34
319
+ },
320
+ "35": {
321
+ "content": "<unused29>",
322
+ "lstrip": false,
323
+ "normalized": false,
324
+ "rstrip": false,
325
+ "single_word": false,
326
+ "special": false,
327
+ "id": 35
328
+ },
329
+ "36": {
330
+ "content": "<unused30>",
331
+ "lstrip": false,
332
+ "normalized": false,
333
+ "rstrip": false,
334
+ "single_word": false,
335
+ "special": false,
336
+ "id": 36
337
+ },
338
+ "37": {
339
+ "content": "<unused31>",
340
+ "lstrip": false,
341
+ "normalized": false,
342
+ "rstrip": false,
343
+ "single_word": false,
344
+ "special": false,
345
+ "id": 37
346
+ },
347
+ "38": {
348
+ "content": "<unused32>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": false,
354
+ "id": 38
355
+ },
356
+ "39": {
357
+ "content": "<unused33>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": false,
363
+ "id": 39
364
+ },
365
+ "40": {
366
+ "content": "<unused34>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": false,
372
+ "id": 40
373
+ },
374
+ "41": {
375
+ "content": "<unused35>",
376
+ "lstrip": false,
377
+ "normalized": false,
378
+ "rstrip": false,
379
+ "single_word": false,
380
+ "special": false,
381
+ "id": 41
382
+ },
383
+ "42": {
384
+ "content": "<unused36>",
385
+ "lstrip": false,
386
+ "normalized": false,
387
+ "rstrip": false,
388
+ "single_word": false,
389
+ "special": false,
390
+ "id": 42
391
+ },
392
+ "43": {
393
+ "content": "<unused37>",
394
+ "lstrip": false,
395
+ "normalized": false,
396
+ "rstrip": false,
397
+ "single_word": false,
398
+ "special": false,
399
+ "id": 43
400
+ },
401
+ "44": {
402
+ "content": "<unused38>",
403
+ "lstrip": false,
404
+ "normalized": false,
405
+ "rstrip": false,
406
+ "single_word": false,
407
+ "special": false,
408
+ "id": 44
409
+ },
410
+ "45": {
411
+ "content": "<unused39>",
412
+ "lstrip": false,
413
+ "normalized": false,
414
+ "rstrip": false,
415
+ "single_word": false,
416
+ "special": false,
417
+ "id": 45
418
+ },
419
+ "46": {
420
+ "content": "<unused40>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": false,
426
+ "id": 46
427
+ },
428
+ "47": {
429
+ "content": "<unused41>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": false,
435
+ "id": 47
436
+ },
437
+ "48": {
438
+ "content": "<unused42>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": false,
444
+ "id": 48
445
+ },
446
+ "49": {
447
+ "content": "<unused43>",
448
+ "lstrip": false,
449
+ "normalized": false,
450
+ "rstrip": false,
451
+ "single_word": false,
452
+ "special": false,
453
+ "id": 49
454
+ },
455
+ "50": {
456
+ "content": "<unused44>",
457
+ "lstrip": false,
458
+ "normalized": false,
459
+ "rstrip": false,
460
+ "single_word": false,
461
+ "special": false,
462
+ "id": 50
463
+ },
464
+ "51": {
465
+ "content": "<unused45>",
466
+ "lstrip": false,
467
+ "normalized": false,
468
+ "rstrip": false,
469
+ "single_word": false,
470
+ "special": false,
471
+ "id": 51
472
+ },
473
+ "52": {
474
+ "content": "<unused46>",
475
+ "lstrip": false,
476
+ "normalized": false,
477
+ "rstrip": false,
478
+ "single_word": false,
479
+ "special": false,
480
+ "id": 52
481
+ },
482
+ "53": {
483
+ "content": "<unused47>",
484
+ "lstrip": false,
485
+ "normalized": false,
486
+ "rstrip": false,
487
+ "single_word": false,
488
+ "special": false,
489
+ "id": 53
490
+ },
491
+ "54": {
492
+ "content": "<unused48>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": false,
498
+ "id": 54
499
+ },
500
+ "55": {
501
+ "content": "<unused49>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": false,
507
+ "id": 55
508
+ },
509
+ "56": {
510
+ "content": "<unused50>",
511
+ "lstrip": false,
512
+ "normalized": false,
513
+ "rstrip": false,
514
+ "single_word": false,
515
+ "special": false,
516
+ "id": 56
517
+ },
518
+ "57": {
519
+ "content": "<unused51>",
520
+ "lstrip": false,
521
+ "normalized": false,
522
+ "rstrip": false,
523
+ "single_word": false,
524
+ "special": false,
525
+ "id": 57
526
+ },
527
+ "58": {
528
+ "content": "<unused52>",
529
+ "lstrip": false,
530
+ "normalized": false,
531
+ "rstrip": false,
532
+ "single_word": false,
533
+ "special": false,
534
+ "id": 58
535
+ },
536
+ "59": {
537
+ "content": "<unused53>",
538
+ "lstrip": false,
539
+ "normalized": false,
540
+ "rstrip": false,
541
+ "single_word": false,
542
+ "special": false,
543
+ "id": 59
544
+ },
545
+ "60": {
546
+ "content": "<unused54>",
547
+ "lstrip": false,
548
+ "normalized": false,
549
+ "rstrip": false,
550
+ "single_word": false,
551
+ "special": false,
552
+ "id": 60
553
+ },
554
+ "61": {
555
+ "content": "<unused55>",
556
+ "lstrip": false,
557
+ "normalized": false,
558
+ "rstrip": false,
559
+ "single_word": false,
560
+ "special": false,
561
+ "id": 61
562
+ },
563
+ "62": {
564
+ "content": "<unused56>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": false,
570
+ "id": 62
571
+ },
572
+ "63": {
573
+ "content": "<unused57>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": false,
579
+ "id": 63
580
+ },
581
+ "64": {
582
+ "content": "<unused58>",
583
+ "lstrip": false,
584
+ "normalized": false,
585
+ "rstrip": false,
586
+ "single_word": false,
587
+ "special": false,
588
+ "id": 64
589
+ },
590
+ "65": {
591
+ "content": "<unused59>",
592
+ "lstrip": false,
593
+ "normalized": false,
594
+ "rstrip": false,
595
+ "single_word": false,
596
+ "special": false,
597
+ "id": 65
598
+ },
599
+ "66": {
600
+ "content": "<unused60>",
601
+ "lstrip": false,
602
+ "normalized": false,
603
+ "rstrip": false,
604
+ "single_word": false,
605
+ "special": false,
606
+ "id": 66
607
+ },
608
+ "67": {
609
+ "content": "<unused61>",
610
+ "lstrip": false,
611
+ "normalized": false,
612
+ "rstrip": false,
613
+ "single_word": false,
614
+ "special": false,
615
+ "id": 67
616
+ },
617
+ "68": {
618
+ "content": "<unused62>",
619
+ "lstrip": false,
620
+ "normalized": false,
621
+ "rstrip": false,
622
+ "single_word": false,
623
+ "special": false,
624
+ "id": 68
625
+ },
626
+ "69": {
627
+ "content": "<unused63>",
628
+ "lstrip": false,
629
+ "normalized": false,
630
+ "rstrip": false,
631
+ "single_word": false,
632
+ "special": false,
633
+ "id": 69
634
+ },
635
+ "70": {
636
+ "content": "<unused64>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": false,
642
+ "id": 70
643
+ },
644
+ "71": {
645
+ "content": "<unused65>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": false,
651
+ "id": 71
652
+ },
653
+ "72": {
654
+ "content": "<unused66>",
655
+ "lstrip": false,
656
+ "normalized": false,
657
+ "rstrip": false,
658
+ "single_word": false,
659
+ "special": false,
660
+ "id": 72
661
+ },
662
+ "73": {
663
+ "content": "<unused67>",
664
+ "lstrip": false,
665
+ "normalized": false,
666
+ "rstrip": false,
667
+ "single_word": false,
668
+ "special": false,
669
+ "id": 73
670
+ },
671
+ "74": {
672
+ "content": "<unused68>",
673
+ "lstrip": false,
674
+ "normalized": false,
675
+ "rstrip": false,
676
+ "single_word": false,
677
+ "special": false,
678
+ "id": 74
679
+ },
680
+ "75": {
681
+ "content": "<unused69>",
682
+ "lstrip": false,
683
+ "normalized": false,
684
+ "rstrip": false,
685
+ "single_word": false,
686
+ "special": false,
687
+ "id": 75
688
+ },
689
+ "76": {
690
+ "content": "<unused70>",
691
+ "lstrip": false,
692
+ "normalized": false,
693
+ "rstrip": false,
694
+ "single_word": false,
695
+ "special": false,
696
+ "id": 76
697
+ },
698
+ "77": {
699
+ "content": "<unused71>",
700
+ "lstrip": false,
701
+ "normalized": false,
702
+ "rstrip": false,
703
+ "single_word": false,
704
+ "special": false,
705
+ "id": 77
706
+ },
707
+ "78": {
708
+ "content": "<unused72>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": false,
714
+ "id": 78
715
+ },
716
+ "79": {
717
+ "content": "<unused73>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": false,
723
+ "id": 79
724
+ },
725
+ "80": {
726
+ "content": "<unused74>",
727
+ "lstrip": false,
728
+ "normalized": false,
729
+ "rstrip": false,
730
+ "single_word": false,
731
+ "special": false,
732
+ "id": 80
733
+ },
734
+ "81": {
735
+ "content": "<unused75>",
736
+ "lstrip": false,
737
+ "normalized": false,
738
+ "rstrip": false,
739
+ "single_word": false,
740
+ "special": false,
741
+ "id": 81
742
+ },
743
+ "82": {
744
+ "content": "<unused76>",
745
+ "lstrip": false,
746
+ "normalized": false,
747
+ "rstrip": false,
748
+ "single_word": false,
749
+ "special": false,
750
+ "id": 82
751
+ },
752
+ "83": {
753
+ "content": "<unused77>",
754
+ "lstrip": false,
755
+ "normalized": false,
756
+ "rstrip": false,
757
+ "single_word": false,
758
+ "special": false,
759
+ "id": 83
760
+ },
761
+ "84": {
762
+ "content": "<unused78>",
763
+ "lstrip": false,
764
+ "normalized": false,
765
+ "rstrip": false,
766
+ "single_word": false,
767
+ "special": false,
768
+ "id": 84
769
+ },
770
+ "85": {
771
+ "content": "<unused79>",
772
+ "lstrip": false,
773
+ "normalized": false,
774
+ "rstrip": false,
775
+ "single_word": false,
776
+ "special": false,
777
+ "id": 85
778
+ },
779
+ "86": {
780
+ "content": "<unused80>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": false,
786
+ "id": 86
787
+ },
788
+ "87": {
789
+ "content": "<unused81>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": false,
795
+ "id": 87
796
+ },
797
+ "88": {
798
+ "content": "<unused82>",
799
+ "lstrip": false,
800
+ "normalized": false,
801
+ "rstrip": false,
802
+ "single_word": false,
803
+ "special": false,
804
+ "id": 88
805
+ },
806
+ "89": {
807
+ "content": "<unused83>",
808
+ "lstrip": false,
809
+ "normalized": false,
810
+ "rstrip": false,
811
+ "single_word": false,
812
+ "special": false,
813
+ "id": 89
814
+ },
815
+ "90": {
816
+ "content": "<unused84>",
817
+ "lstrip": false,
818
+ "normalized": false,
819
+ "rstrip": false,
820
+ "single_word": false,
821
+ "special": false,
822
+ "id": 90
823
+ },
824
+ "91": {
825
+ "content": "<unused85>",
826
+ "lstrip": false,
827
+ "normalized": false,
828
+ "rstrip": false,
829
+ "single_word": false,
830
+ "special": false,
831
+ "id": 91
832
+ },
833
+ "92": {
834
+ "content": "<unused86>",
835
+ "lstrip": false,
836
+ "normalized": false,
837
+ "rstrip": false,
838
+ "single_word": false,
839
+ "special": false,
840
+ "id": 92
841
+ },
842
+ "93": {
843
+ "content": "<unused87>",
844
+ "lstrip": false,
845
+ "normalized": false,
846
+ "rstrip": false,
847
+ "single_word": false,
848
+ "special": false,
849
+ "id": 93
850
+ },
851
+ "94": {
852
+ "content": "<unused88>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": false,
858
+ "id": 94
859
+ },
860
+ "95": {
861
+ "content": "<unused89>",
862
+ "lstrip": false,
863
+ "normalized": false,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": false,
867
+ "id": 95
868
+ },
869
+ "96": {
870
+ "content": "<unused90>",
871
+ "lstrip": false,
872
+ "normalized": false,
873
+ "rstrip": false,
874
+ "single_word": false,
875
+ "special": false,
876
+ "id": 96
877
+ },
878
+ "97": {
879
+ "content": "<unused91>",
880
+ "lstrip": false,
881
+ "normalized": false,
882
+ "rstrip": false,
883
+ "single_word": false,
884
+ "special": false,
885
+ "id": 97
886
+ },
887
+ "98": {
888
+ "content": "<unused92>",
889
+ "lstrip": false,
890
+ "normalized": false,
891
+ "rstrip": false,
892
+ "single_word": false,
893
+ "special": false,
894
+ "id": 98
895
+ },
896
+ "99": {
897
+ "content": "<unused93>",
898
+ "lstrip": false,
899
+ "normalized": false,
900
+ "rstrip": false,
901
+ "single_word": false,
902
+ "special": false,
903
+ "id": 99
904
+ },
905
+ "100": {
906
+ "content": "<unused94>",
907
+ "lstrip": false,
908
+ "normalized": false,
909
+ "rstrip": false,
910
+ "single_word": false,
911
+ "special": false,
912
+ "id": 100
913
+ },
914
+ "101": {
915
+ "content": "<unused95>",
916
+ "lstrip": false,
917
+ "normalized": false,
918
+ "rstrip": false,
919
+ "single_word": false,
920
+ "special": false,
921
+ "id": 101
922
+ },
923
+ "102": {
924
+ "content": "<unused96>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": false,
930
+ "id": 102
931
+ },
932
+ "103": {
933
+ "content": "<unused97>",
934
+ "lstrip": false,
935
+ "normalized": false,
936
+ "rstrip": false,
937
+ "single_word": false,
938
+ "special": false,
939
+ "id": 103
940
+ },
941
+ "104": {
942
+ "content": "<unused98>",
943
+ "lstrip": false,
944
+ "normalized": false,
945
+ "rstrip": false,
946
+ "single_word": false,
947
+ "special": false,
948
+ "id": 104
949
+ },
950
+ "105": {
951
+ "content": "<start_of_turn>",
952
+ "lstrip": false,
953
+ "normalized": false,
954
+ "rstrip": false,
955
+ "single_word": false,
956
+ "special": true,
957
+ "id": 105
958
+ },
959
+ "106": {
960
+ "content": "<end_of_turn>",
961
+ "lstrip": false,
962
+ "normalized": false,
963
+ "rstrip": false,
964
+ "single_word": false,
965
+ "special": true,
966
+ "id": 106
967
+ },
968
+ "107": {
969
+ "content": "\n",
970
+ "lstrip": false,
971
+ "normalized": false,
972
+ "rstrip": false,
973
+ "single_word": false,
974
+ "special": false,
975
+ "id": 107
976
+ },
977
+ "108": {
978
+ "content": "\n\n",
979
+ "lstrip": false,
980
+ "normalized": false,
981
+ "rstrip": false,
982
+ "single_word": false,
983
+ "special": false,
984
+ "id": 108
985
+ },
986
+ "109": {
987
+ "content": "\n\n\n",
988
+ "lstrip": false,
989
+ "normalized": false,
990
+ "rstrip": false,
991
+ "single_word": false,
992
+ "special": false,
993
+ "id": 109
994
+ },
995
+ "110": {
996
+ "content": "\n\n\n\n",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": false,
1002
+ "id": 110
1003
+ },
1004
+ "111": {
1005
+ "content": "\n\n\n\n\n",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false,
1010
+ "special": false,
1011
+ "id": 111
1012
+ },
1013
+ "112": {
1014
+ "content": "\n\n\n\n\n\n",
1015
+ "lstrip": false,
1016
+ "normalized": false,
1017
+ "rstrip": false,
1018
+ "single_word": false,
1019
+ "special": false,
1020
+ "id": 112
1021
+ },
1022
+ "113": {
1023
+ "content": "\n\n\n\n\n\n\n",
1024
+ "lstrip": false,
1025
+ "normalized": false,
1026
+ "rstrip": false,
1027
+ "single_word": false,
1028
+ "special": false,
1029
+ "id": 113
1030
+ },
1031
+ "114": {
1032
+ "content": "\n\n\n\n\n\n\n\n",
1033
+ "lstrip": false,
1034
+ "normalized": false,
1035
+ "rstrip": false,
1036
+ "single_word": false,
1037
+ "special": false,
1038
+ "id": 114
1039
+ },
1040
+ "115": {
1041
+ "content": "\n\n\n\n\n\n\n\n\n",
1042
+ "lstrip": false,
1043
+ "normalized": false,
1044
+ "rstrip": false,
1045
+ "single_word": false,
1046
+ "special": false,
1047
+ "id": 115
1048
+ },
1049
+ "116": {
1050
+ "content": "\n\n\n\n\n\n\n\n\n\n",
1051
+ "lstrip": false,
1052
+ "normalized": false,
1053
+ "rstrip": false,
1054
+ "single_word": false,
1055
+ "special": false,
1056
+ "id": 116
1057
+ },
1058
+ "117": {
1059
+ "content": "\n\n\n\n\n\n\n\n\n\n\n",
1060
+ "lstrip": false,
1061
+ "normalized": false,
1062
+ "rstrip": false,
1063
+ "single_word": false,
1064
+ "special": false,
1065
+ "id": 117
1066
+ },
1067
+ "118": {
1068
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": false,
1074
+ "id": 118
1075
+ },
1076
+ "119": {
1077
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
1078
+ "lstrip": false,
1079
+ "normalized": false,
1080
+ "rstrip": false,
1081
+ "single_word": false,
1082
+ "special": false,
1083
+ "id": 119
1084
+ },
1085
+ "120": {
1086
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1087
+ "lstrip": false,
1088
+ "normalized": false,
1089
+ "rstrip": false,
1090
+ "single_word": false,
1091
+ "special": false,
1092
+ "id": 120
1093
+ },
1094
+ "121": {
1095
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1096
+ "lstrip": false,
1097
+ "normalized": false,
1098
+ "rstrip": false,
1099
+ "single_word": false,
1100
+ "special": false,
1101
+ "id": 121
1102
+ },
1103
+ "122": {
1104
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1105
+ "lstrip": false,
1106
+ "normalized": false,
1107
+ "rstrip": false,
1108
+ "single_word": false,
1109
+ "special": false,
1110
+ "id": 122
1111
+ },
1112
+ "123": {
1113
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1114
+ "lstrip": false,
1115
+ "normalized": false,
1116
+ "rstrip": false,
1117
+ "single_word": false,
1118
+ "special": false,
1119
+ "id": 123
1120
+ },
1121
+ "124": {
1122
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1123
+ "lstrip": false,
1124
+ "normalized": false,
1125
+ "rstrip": false,
1126
+ "single_word": false,
1127
+ "special": false,
1128
+ "id": 124
1129
+ },
1130
+ "125": {
1131
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1132
+ "lstrip": false,
1133
+ "normalized": false,
1134
+ "rstrip": false,
1135
+ "single_word": false,
1136
+ "special": false,
1137
+ "id": 125
1138
+ },
1139
+ "126": {
1140
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": false,
1146
+ "id": 126
1147
+ },
1148
+ "127": {
1149
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1150
+ "lstrip": false,
1151
+ "normalized": false,
1152
+ "rstrip": false,
1153
+ "single_word": false,
1154
+ "special": false,
1155
+ "id": 127
1156
+ },
1157
+ "128": {
1158
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1159
+ "lstrip": false,
1160
+ "normalized": false,
1161
+ "rstrip": false,
1162
+ "single_word": false,
1163
+ "special": false,
1164
+ "id": 128
1165
+ },
1166
+ "129": {
1167
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1168
+ "lstrip": false,
1169
+ "normalized": false,
1170
+ "rstrip": false,
1171
+ "single_word": false,
1172
+ "special": false,
1173
+ "id": 129
1174
+ },
1175
+ "130": {
1176
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1177
+ "lstrip": false,
1178
+ "normalized": false,
1179
+ "rstrip": false,
1180
+ "single_word": false,
1181
+ "special": false,
1182
+ "id": 130
1183
+ },
1184
+ "131": {
1185
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1186
+ "lstrip": false,
1187
+ "normalized": false,
1188
+ "rstrip": false,
1189
+ "single_word": false,
1190
+ "special": false,
1191
+ "id": 131
1192
+ },
1193
+ "132": {
1194
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1195
+ "lstrip": false,
1196
+ "normalized": false,
1197
+ "rstrip": false,
1198
+ "single_word": false,
1199
+ "special": false,
1200
+ "id": 132
1201
+ },
1202
+ "133": {
1203
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1204
+ "lstrip": false,
1205
+ "normalized": false,
1206
+ "rstrip": false,
1207
+ "single_word": false,
1208
+ "special": false,
1209
+ "id": 133
1210
+ },
1211
+ "134": {
1212
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": false,
1218
+ "id": 134
1219
+ },
1220
+ "135": {
1221
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1222
+ "lstrip": false,
1223
+ "normalized": false,
1224
+ "rstrip": false,
1225
+ "single_word": false,
1226
+ "special": false,
1227
+ "id": 135
1228
+ },
1229
+ "136": {
1230
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1231
+ "lstrip": false,
1232
+ "normalized": false,
1233
+ "rstrip": false,
1234
+ "single_word": false,
1235
+ "special": false,
1236
+ "id": 136
1237
+ },
1238
+ "137": {
1239
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1240
+ "lstrip": false,
1241
+ "normalized": false,
1242
+ "rstrip": false,
1243
+ "single_word": false,
1244
+ "special": false,
1245
+ "id": 137
1246
+ },
1247
+ "138": {
1248
+ "content": "▁▁",
1249
+ "lstrip": false,
1250
+ "normalized": false,
1251
+ "rstrip": false,
1252
+ "single_word": false,
1253
+ "special": false,
1254
+ "id": 138
1255
+ },
1256
+ "139": {
1257
+ "content": "▁▁▁",
1258
+ "lstrip": false,
1259
+ "normalized": false,
1260
+ "rstrip": false,
1261
+ "single_word": false,
1262
+ "special": false,
1263
+ "id": 139
1264
+ },
1265
+ "140": {
1266
+ "content": "▁▁▁▁",
1267
+ "lstrip": false,
1268
+ "normalized": false,
1269
+ "rstrip": false,
1270
+ "single_word": false,
1271
+ "special": false,
1272
+ "id": 140
1273
+ },
1274
+ "141": {
1275
+ "content": "▁▁▁▁▁",
1276
+ "lstrip": false,
1277
+ "normalized": false,
1278
+ "rstrip": false,
1279
+ "single_word": false,
1280
+ "special": false,
1281
+ "id": 141
1282
+ },
1283
+ "142": {
1284
+ "content": "▁▁▁▁▁▁",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": false,
1290
+ "id": 142
1291
+ },
1292
+ "143": {
1293
+ "content": "▁▁▁▁▁▁▁",
1294
+ "lstrip": false,
1295
+ "normalized": false,
1296
+ "rstrip": false,
1297
+ "single_word": false,
1298
+ "special": false,
1299
+ "id": 143
1300
+ },
1301
+ "144": {
1302
+ "content": "▁▁▁▁▁▁▁▁",
1303
+ "lstrip": false,
1304
+ "normalized": false,
1305
+ "rstrip": false,
1306
+ "single_word": false,
1307
+ "special": false,
1308
+ "id": 144
1309
+ },
1310
+ "145": {
1311
+ "content": "▁▁▁▁▁▁▁▁▁",
1312
+ "lstrip": false,
1313
+ "normalized": false,
1314
+ "rstrip": false,
1315
+ "single_word": false,
1316
+ "special": false,
1317
+ "id": 145
1318
+ },
1319
+ "146": {
1320
+ "content": "▁▁▁▁▁▁▁▁▁▁",
1321
+ "lstrip": false,
1322
+ "normalized": false,
1323
+ "rstrip": false,
1324
+ "single_word": false,
1325
+ "special": false,
1326
+ "id": 146
1327
+ },
1328
+ "147": {
1329
+ "content": "▁▁▁▁▁▁▁▁▁▁▁",
1330
+ "lstrip": false,
1331
+ "normalized": false,
1332
+ "rstrip": false,
1333
+ "single_word": false,
1334
+ "special": false,
1335
+ "id": 147
1336
+ },
1337
+ "148": {
1338
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
1339
+ "lstrip": false,
1340
+ "normalized": false,
1341
+ "rstrip": false,
1342
+ "single_word": false,
1343
+ "special": false,
1344
+ "id": 148
1345
+ },
1346
+ "149": {
1347
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
1348
+ "lstrip": false,
1349
+ "normalized": false,
1350
+ "rstrip": false,
1351
+ "single_word": false,
1352
+ "special": false,
1353
+ "id": 149
1354
+ },
1355
+ "150": {
1356
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": false,
1362
+ "id": 150
1363
+ },
1364
+ "151": {
1365
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1366
+ "lstrip": false,
1367
+ "normalized": false,
1368
+ "rstrip": false,
1369
+ "single_word": false,
1370
+ "special": false,
1371
+ "id": 151
1372
+ },
1373
+ "152": {
1374
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1375
+ "lstrip": false,
1376
+ "normalized": false,
1377
+ "rstrip": false,
1378
+ "single_word": false,
1379
+ "special": false,
1380
+ "id": 152
1381
+ },
1382
+ "153": {
1383
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1384
+ "lstrip": false,
1385
+ "normalized": false,
1386
+ "rstrip": false,
1387
+ "single_word": false,
1388
+ "special": false,
1389
+ "id": 153
1390
+ },
1391
+ "154": {
1392
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1393
+ "lstrip": false,
1394
+ "normalized": false,
1395
+ "rstrip": false,
1396
+ "single_word": false,
1397
+ "special": false,
1398
+ "id": 154
1399
+ },
1400
+ "155": {
1401
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1402
+ "lstrip": false,
1403
+ "normalized": false,
1404
+ "rstrip": false,
1405
+ "single_word": false,
1406
+ "special": false,
1407
+ "id": 155
1408
+ },
1409
+ "156": {
1410
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1411
+ "lstrip": false,
1412
+ "normalized": false,
1413
+ "rstrip": false,
1414
+ "single_word": false,
1415
+ "special": false,
1416
+ "id": 156
1417
+ },
1418
+ "157": {
1419
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1420
+ "lstrip": false,
1421
+ "normalized": false,
1422
+ "rstrip": false,
1423
+ "single_word": false,
1424
+ "special": false,
1425
+ "id": 157
1426
+ },
1427
+ "158": {
1428
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": false,
1434
+ "id": 158
1435
+ },
1436
+ "159": {
1437
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1438
+ "lstrip": false,
1439
+ "normalized": false,
1440
+ "rstrip": false,
1441
+ "single_word": false,
1442
+ "special": false,
1443
+ "id": 159
1444
+ },
1445
+ "160": {
1446
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1447
+ "lstrip": false,
1448
+ "normalized": false,
1449
+ "rstrip": false,
1450
+ "single_word": false,
1451
+ "special": false,
1452
+ "id": 160
1453
+ },
1454
+ "161": {
1455
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1456
+ "lstrip": false,
1457
+ "normalized": false,
1458
+ "rstrip": false,
1459
+ "single_word": false,
1460
+ "special": false,
1461
+ "id": 161
1462
+ },
1463
+ "162": {
1464
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1465
+ "lstrip": false,
1466
+ "normalized": false,
1467
+ "rstrip": false,
1468
+ "single_word": false,
1469
+ "special": false,
1470
+ "id": 162
1471
+ },
1472
+ "163": {
1473
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1474
+ "lstrip": false,
1475
+ "normalized": false,
1476
+ "rstrip": false,
1477
+ "single_word": false,
1478
+ "special": false,
1479
+ "id": 163
1480
+ },
1481
+ "164": {
1482
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1483
+ "lstrip": false,
1484
+ "normalized": false,
1485
+ "rstrip": false,
1486
+ "single_word": false,
1487
+ "special": false,
1488
+ "id": 164
1489
+ },
1490
+ "165": {
1491
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1492
+ "lstrip": false,
1493
+ "normalized": false,
1494
+ "rstrip": false,
1495
+ "single_word": false,
1496
+ "special": false,
1497
+ "id": 165
1498
+ },
1499
+ "166": {
1500
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": false,
1506
+ "id": 166
1507
+ },
1508
+ "167": {
1509
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1510
+ "lstrip": false,
1511
+ "normalized": false,
1512
+ "rstrip": false,
1513
+ "single_word": false,
1514
+ "special": false,
1515
+ "id": 167
1516
+ },
1517
+ "168": {
1518
+ "content": "<table>",
1519
+ "lstrip": false,
1520
+ "normalized": false,
1521
+ "rstrip": false,
1522
+ "single_word": false,
1523
+ "special": false,
1524
+ "id": 168
1525
+ },
1526
+ "169": {
1527
+ "content": "<caption>",
1528
+ "lstrip": false,
1529
+ "normalized": false,
1530
+ "rstrip": false,
1531
+ "single_word": false,
1532
+ "special": false,
1533
+ "id": 169
1534
+ },
1535
+ "170": {
1536
+ "content": "<thead>",
1537
+ "lstrip": false,
1538
+ "normalized": false,
1539
+ "rstrip": false,
1540
+ "single_word": false,
1541
+ "special": false,
1542
+ "id": 170
1543
+ },
1544
+ "171": {
1545
+ "content": "<tbody>",
1546
+ "lstrip": false,
1547
+ "normalized": false,
1548
+ "rstrip": false,
1549
+ "single_word": false,
1550
+ "special": false,
1551
+ "id": 171
1552
+ },
1553
+ "172": {
1554
+ "content": "<tfoot>",
1555
+ "lstrip": false,
1556
+ "normalized": false,
1557
+ "rstrip": false,
1558
+ "single_word": false,
1559
+ "special": false,
1560
+ "id": 172
1561
+ },
1562
+ "173": {
1563
+ "content": "<tr>",
1564
+ "lstrip": false,
1565
+ "normalized": false,
1566
+ "rstrip": false,
1567
+ "single_word": false,
1568
+ "special": false,
1569
+ "id": 173
1570
+ },
1571
+ "174": {
1572
+ "content": "<th>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": false,
1578
+ "id": 174
1579
+ },
1580
+ "175": {
1581
+ "content": "<td>",
1582
+ "lstrip": false,
1583
+ "normalized": false,
1584
+ "rstrip": false,
1585
+ "single_word": false,
1586
+ "special": false,
1587
+ "id": 175
1588
+ },
1589
+ "176": {
1590
+ "content": "</table>",
1591
+ "lstrip": false,
1592
+ "normalized": false,
1593
+ "rstrip": false,
1594
+ "single_word": false,
1595
+ "special": false,
1596
+ "id": 176
1597
+ },
1598
+ "177": {
1599
+ "content": "</caption>",
1600
+ "lstrip": false,
1601
+ "normalized": false,
1602
+ "rstrip": false,
1603
+ "single_word": false,
1604
+ "special": false,
1605
+ "id": 177
1606
+ },
1607
+ "178": {
1608
+ "content": "</thead>",
1609
+ "lstrip": false,
1610
+ "normalized": false,
1611
+ "rstrip": false,
1612
+ "single_word": false,
1613
+ "special": false,
1614
+ "id": 178
1615
+ },
1616
+ "179": {
1617
+ "content": "</tbody>",
1618
+ "lstrip": false,
1619
+ "normalized": false,
1620
+ "rstrip": false,
1621
+ "single_word": false,
1622
+ "special": false,
1623
+ "id": 179
1624
+ },
1625
+ "180": {
1626
+ "content": "</tfoot>",
1627
+ "lstrip": false,
1628
+ "normalized": false,
1629
+ "rstrip": false,
1630
+ "single_word": false,
1631
+ "special": false,
1632
+ "id": 180
1633
+ },
1634
+ "181": {
1635
+ "content": "</tr>",
1636
+ "lstrip": false,
1637
+ "normalized": false,
1638
+ "rstrip": false,
1639
+ "single_word": false,
1640
+ "special": false,
1641
+ "id": 181
1642
+ },
1643
+ "182": {
1644
+ "content": "</th>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": false,
1650
+ "id": 182
1651
+ },
1652
+ "183": {
1653
+ "content": "</td>",
1654
+ "lstrip": false,
1655
+ "normalized": false,
1656
+ "rstrip": false,
1657
+ "single_word": false,
1658
+ "special": false,
1659
+ "id": 183
1660
+ },
1661
+ "184": {
1662
+ "content": "<h1>",
1663
+ "lstrip": false,
1664
+ "normalized": false,
1665
+ "rstrip": false,
1666
+ "single_word": false,
1667
+ "special": false,
1668
+ "id": 184
1669
+ },
1670
+ "185": {
1671
+ "content": "<h2>",
1672
+ "lstrip": false,
1673
+ "normalized": false,
1674
+ "rstrip": false,
1675
+ "single_word": false,
1676
+ "special": false,
1677
+ "id": 185
1678
+ },
1679
+ "186": {
1680
+ "content": "<h3>",
1681
+ "lstrip": false,
1682
+ "normalized": false,
1683
+ "rstrip": false,
1684
+ "single_word": false,
1685
+ "special": false,
1686
+ "id": 186
1687
+ },
1688
+ "187": {
1689
+ "content": "<h4>",
1690
+ "lstrip": false,
1691
+ "normalized": false,
1692
+ "rstrip": false,
1693
+ "single_word": false,
1694
+ "special": false,
1695
+ "id": 187
1696
+ },
1697
+ "188": {
1698
+ "content": "<h5>",
1699
+ "lstrip": false,
1700
+ "normalized": false,
1701
+ "rstrip": false,
1702
+ "single_word": false,
1703
+ "special": false,
1704
+ "id": 188
1705
+ },
1706
+ "189": {
1707
+ "content": "<h6>",
1708
+ "lstrip": false,
1709
+ "normalized": false,
1710
+ "rstrip": false,
1711
+ "single_word": false,
1712
+ "special": false,
1713
+ "id": 189
1714
+ },
1715
+ "190": {
1716
+ "content": "<blockquote>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": false,
1722
+ "id": 190
1723
+ },
1724
+ "191": {
1725
+ "content": "</h1>",
1726
+ "lstrip": false,
1727
+ "normalized": false,
1728
+ "rstrip": false,
1729
+ "single_word": false,
1730
+ "special": false,
1731
+ "id": 191
1732
+ },
1733
+ "192": {
1734
+ "content": "</h2>",
1735
+ "lstrip": false,
1736
+ "normalized": false,
1737
+ "rstrip": false,
1738
+ "single_word": false,
1739
+ "special": false,
1740
+ "id": 192
1741
+ },
1742
+ "193": {
1743
+ "content": "</h3>",
1744
+ "lstrip": false,
1745
+ "normalized": false,
1746
+ "rstrip": false,
1747
+ "single_word": false,
1748
+ "special": false,
1749
+ "id": 193
1750
+ },
1751
+ "194": {
1752
+ "content": "</h4>",
1753
+ "lstrip": false,
1754
+ "normalized": false,
1755
+ "rstrip": false,
1756
+ "single_word": false,
1757
+ "special": false,
1758
+ "id": 194
1759
+ },
1760
+ "195": {
1761
+ "content": "</h5>",
1762
+ "lstrip": false,
1763
+ "normalized": false,
1764
+ "rstrip": false,
1765
+ "single_word": false,
1766
+ "special": false,
1767
+ "id": 195
1768
+ },
1769
+ "196": {
1770
+ "content": "</h6>",
1771
+ "lstrip": false,
1772
+ "normalized": false,
1773
+ "rstrip": false,
1774
+ "single_word": false,
1775
+ "special": false,
1776
+ "id": 196
1777
+ },
1778
+ "197": {
1779
+ "content": "</blockquote>",
1780
+ "lstrip": false,
1781
+ "normalized": false,
1782
+ "rstrip": false,
1783
+ "single_word": false,
1784
+ "special": false,
1785
+ "id": 197
1786
+ },
1787
+ "198": {
1788
+ "content": "<strong>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": false,
1794
+ "id": 198
1795
+ },
1796
+ "199": {
1797
+ "content": "<em>",
1798
+ "lstrip": false,
1799
+ "normalized": false,
1800
+ "rstrip": false,
1801
+ "single_word": false,
1802
+ "special": false,
1803
+ "id": 199
1804
+ },
1805
+ "200": {
1806
+ "content": "<b>",
1807
+ "lstrip": false,
1808
+ "normalized": false,
1809
+ "rstrip": false,
1810
+ "single_word": false,
1811
+ "special": false,
1812
+ "id": 200
1813
+ },
1814
+ "201": {
1815
+ "content": "<i>",
1816
+ "lstrip": false,
1817
+ "normalized": false,
1818
+ "rstrip": false,
1819
+ "single_word": false,
1820
+ "special": false,
1821
+ "id": 201
1822
+ },
1823
+ "202": {
1824
+ "content": "<u>",
1825
+ "lstrip": false,
1826
+ "normalized": false,
1827
+ "rstrip": false,
1828
+ "single_word": false,
1829
+ "special": false,
1830
+ "id": 202
1831
+ },
1832
+ "203": {
1833
+ "content": "<s>",
1834
+ "lstrip": false,
1835
+ "normalized": false,
1836
+ "rstrip": false,
1837
+ "single_word": false,
1838
+ "special": false,
1839
+ "id": 203
1840
+ },
1841
+ "204": {
1842
+ "content": "<sub>",
1843
+ "lstrip": false,
1844
+ "normalized": false,
1845
+ "rstrip": false,
1846
+ "single_word": false,
1847
+ "special": false,
1848
+ "id": 204
1849
+ },
1850
+ "205": {
1851
+ "content": "<sup>",
1852
+ "lstrip": false,
1853
+ "normalized": false,
1854
+ "rstrip": false,
1855
+ "single_word": false,
1856
+ "special": false,
1857
+ "id": 205
1858
+ },
1859
+ "206": {
1860
+ "content": "<code>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": false,
1866
+ "id": 206
1867
+ },
1868
+ "207": {
1869
+ "content": "</strong>",
1870
+ "lstrip": false,
1871
+ "normalized": false,
1872
+ "rstrip": false,
1873
+ "single_word": false,
1874
+ "special": false,
1875
+ "id": 207
1876
+ },
1877
+ "208": {
1878
+ "content": "</em>",
1879
+ "lstrip": false,
1880
+ "normalized": false,
1881
+ "rstrip": false,
1882
+ "single_word": false,
1883
+ "special": false,
1884
+ "id": 208
1885
+ },
1886
+ "209": {
1887
+ "content": "</b>",
1888
+ "lstrip": false,
1889
+ "normalized": false,
1890
+ "rstrip": false,
1891
+ "single_word": false,
1892
+ "special": false,
1893
+ "id": 209
1894
+ },
1895
+ "210": {
1896
+ "content": "</i>",
1897
+ "lstrip": false,
1898
+ "normalized": false,
1899
+ "rstrip": false,
1900
+ "single_word": false,
1901
+ "special": false,
1902
+ "id": 210
1903
+ },
1904
+ "211": {
1905
+ "content": "</u>",
1906
+ "lstrip": false,
1907
+ "normalized": false,
1908
+ "rstrip": false,
1909
+ "single_word": false,
1910
+ "special": false,
1911
+ "id": 211
1912
+ },
1913
+ "212": {
1914
+ "content": "</s>",
1915
+ "lstrip": false,
1916
+ "normalized": false,
1917
+ "rstrip": false,
1918
+ "single_word": false,
1919
+ "special": false,
1920
+ "id": 212
1921
+ },
1922
+ "213": {
1923
+ "content": "</sub>",
1924
+ "lstrip": false,
1925
+ "normalized": false,
1926
+ "rstrip": false,
1927
+ "single_word": false,
1928
+ "special": false,
1929
+ "id": 213
1930
+ },
1931
+ "214": {
1932
+ "content": "</sup>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": false,
1938
+ "id": 214
1939
+ },
1940
+ "215": {
1941
+ "content": "</code>",
1942
+ "lstrip": false,
1943
+ "normalized": false,
1944
+ "rstrip": false,
1945
+ "single_word": false,
1946
+ "special": false,
1947
+ "id": 215
1948
+ },
1949
+ "216": {
1950
+ "content": "<a>",
1951
+ "lstrip": false,
1952
+ "normalized": false,
1953
+ "rstrip": false,
1954
+ "single_word": false,
1955
+ "special": false,
1956
+ "id": 216
1957
+ },
1958
+ "217": {
1959
+ "content": "<html>",
1960
+ "lstrip": false,
1961
+ "normalized": false,
1962
+ "rstrip": false,
1963
+ "single_word": false,
1964
+ "special": false,
1965
+ "id": 217
1966
+ },
1967
+ "218": {
1968
+ "content": "<body>",
1969
+ "lstrip": false,
1970
+ "normalized": false,
1971
+ "rstrip": false,
1972
+ "single_word": false,
1973
+ "special": false,
1974
+ "id": 218
1975
+ },
1976
+ "219": {
1977
+ "content": "<img>",
1978
+ "lstrip": false,
1979
+ "normalized": false,
1980
+ "rstrip": false,
1981
+ "single_word": false,
1982
+ "special": false,
1983
+ "id": 219
1984
+ },
1985
+ "220": {
1986
+ "content": "<span>",
1987
+ "lstrip": false,
1988
+ "normalized": false,
1989
+ "rstrip": false,
1990
+ "single_word": false,
1991
+ "special": false,
1992
+ "id": 220
1993
+ },
1994
+ "221": {
1995
+ "content": "<bbox>",
1996
+ "lstrip": false,
1997
+ "normalized": false,
1998
+ "rstrip": false,
1999
+ "single_word": false,
2000
+ "special": false,
2001
+ "id": 221
2002
+ },
2003
+ "222": {
2004
+ "content": "<ul>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": false,
2010
+ "id": 222
2011
+ },
2012
+ "223": {
2013
+ "content": "<li>",
2014
+ "lstrip": false,
2015
+ "normalized": false,
2016
+ "rstrip": false,
2017
+ "single_word": false,
2018
+ "special": false,
2019
+ "id": 223
2020
+ },
2021
+ "224": {
2022
+ "content": "<div>",
2023
+ "lstrip": false,
2024
+ "normalized": false,
2025
+ "rstrip": false,
2026
+ "single_word": false,
2027
+ "special": false,
2028
+ "id": 224
2029
+ },
2030
+ "225": {
2031
+ "content": "<iframe>",
2032
+ "lstrip": false,
2033
+ "normalized": false,
2034
+ "rstrip": false,
2035
+ "single_word": false,
2036
+ "special": false,
2037
+ "id": 225
2038
+ },
2039
+ "226": {
2040
+ "content": "<footer>",
2041
+ "lstrip": false,
2042
+ "normalized": false,
2043
+ "rstrip": false,
2044
+ "single_word": false,
2045
+ "special": false,
2046
+ "id": 226
2047
+ },
2048
+ "227": {
2049
+ "content": "</a>",
2050
+ "lstrip": false,
2051
+ "normalized": false,
2052
+ "rstrip": false,
2053
+ "single_word": false,
2054
+ "special": false,
2055
+ "id": 227
2056
+ },
2057
+ "228": {
2058
+ "content": "</html>",
2059
+ "lstrip": false,
2060
+ "normalized": false,
2061
+ "rstrip": false,
2062
+ "single_word": false,
2063
+ "special": false,
2064
+ "id": 228
2065
+ },
2066
+ "229": {
2067
+ "content": "</body>",
2068
+ "lstrip": false,
2069
+ "normalized": false,
2070
+ "rstrip": false,
2071
+ "single_word": false,
2072
+ "special": false,
2073
+ "id": 229
2074
+ },
2075
+ "230": {
2076
+ "content": "</img>",
2077
+ "lstrip": false,
2078
+ "normalized": false,
2079
+ "rstrip": false,
2080
+ "single_word": false,
2081
+ "special": false,
2082
+ "id": 230
2083
+ },
2084
+ "231": {
2085
+ "content": "</span>",
2086
+ "lstrip": false,
2087
+ "normalized": false,
2088
+ "rstrip": false,
2089
+ "single_word": false,
2090
+ "special": false,
2091
+ "id": 231
2092
+ },
2093
+ "232": {
2094
+ "content": "</bbox>",
2095
+ "lstrip": false,
2096
+ "normalized": false,
2097
+ "rstrip": false,
2098
+ "single_word": false,
2099
+ "special": false,
2100
+ "id": 232
2101
+ },
2102
+ "233": {
2103
+ "content": "</ul>",
2104
+ "lstrip": false,
2105
+ "normalized": false,
2106
+ "rstrip": false,
2107
+ "single_word": false,
2108
+ "special": false,
2109
+ "id": 233
2110
+ },
2111
+ "234": {
2112
+ "content": "</li>",
2113
+ "lstrip": false,
2114
+ "normalized": false,
2115
+ "rstrip": false,
2116
+ "single_word": false,
2117
+ "special": false,
2118
+ "id": 234
2119
+ },
2120
+ "235": {
2121
+ "content": "</div>",
2122
+ "lstrip": false,
2123
+ "normalized": false,
2124
+ "rstrip": false,
2125
+ "single_word": false,
2126
+ "special": false,
2127
+ "id": 235
2128
+ },
2129
+ "236": {
2130
+ "content": "</iframe>",
2131
+ "lstrip": false,
2132
+ "normalized": false,
2133
+ "rstrip": false,
2134
+ "single_word": false,
2135
+ "special": false,
2136
+ "id": 236
2137
+ },
2138
+ "237": {
2139
+ "content": "</footer>",
2140
+ "lstrip": false,
2141
+ "normalized": false,
2142
+ "rstrip": false,
2143
+ "single_word": false,
2144
+ "special": false,
2145
+ "id": 237
2146
+ },
2147
+ "16382": {
2148
+ "content": "<start_of_image>",
2149
+ "lstrip": false,
2150
+ "normalized": false,
2151
+ "rstrip": false,
2152
+ "single_word": false,
2153
+ "special": true,
2154
+ "id": 16382
2155
+ },
2156
+ "16383": {
2157
+ "content": "<end_of_image>",
2158
+ "lstrip": false,
2159
+ "normalized": false,
2160
+ "rstrip": false,
2161
+ "single_word": false,
2162
+ "special": true,
2163
+ "id": 16383
2164
+ },
2165
+ "16384": {
2166
+ "content": "<image_soft_token>",
2167
+ "lstrip": false,
2168
+ "normalized": false,
2169
+ "rstrip": false,
2170
+ "single_word": false,
2171
+ "special": true,
2172
+ "id": 16384
2173
+ }
2174
+ },
2175
+ "boi_token": "<start_of_image>",
2176
+ "bos_token": "<bos>",
2177
+ "chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n {%- if messages[0]['content'] is string -%}\n {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n {%- else -%}\n {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n {%- endif -%}\n {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n {%- set first_user_prefix = \"\" -%}\n {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n {%- endif -%}\n {%- if (message['role'] == 'assistant') -%}\n {%- set role = \"model\" -%}\n {%- else -%}\n {%- set role = message['role'] -%}\n {%- endif -%}\n {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n {%- if message['content'] is string -%}\n {{ message['content'] | trim }}\n {%- elif message['content'] is iterable -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'image' -%}\n {{ '<start_of_image>' }}\n {%- elif item['type'] == 'text' -%}\n {{ item['text'] | trim }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ raise_exception(\"Invalid content type\") }}\n {%- endif -%}\n {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{'<start_of_turn>model\n'}}\n{%- endif -%}\n",
2178
+ "clean_up_tokenization_spaces": false,
2179
+ "eoi_token": "<end_of_image>",
2180
+ "eos_token": "<eos>",
2181
+ "extra_special_tokens": {
2182
+ "boi_token": "<start_of_image>",
2183
+ "eoi_token": "<end_of_image>",
2184
+ "image_token": "<image_soft_token>"
2185
+ },
2186
+ "image_token": "<image_soft_token>",
2187
+ "model_max_length": 16384,
2188
+ "pad_token": "<pad>",
2189
+ "processor_class": "Gemma3Processor",
2190
+ "sp_model_kwargs": null,
2191
+ "spaces_between_special_tokens": false,
2192
+ "tokenizer_class": "GemmaTokenizer",
2193
+ "unk_token": "<unk>",
2194
+ "use_default_system_prompt": false
2195
+ }