Files
gpt-sw3-126m-exercise-scena…/tokenizer_config.json
ModelHub XC 7cbf69a626 初始化项目,由ModelHub XC社区提供模型
Model: lorinet3/gpt-sw3-126m-exercise-scenario-generator
Source: Original Platform
2026-08-18 00:51:16 +08:00

203 lines
4.3 KiB
JSON

{
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"603": {
"content": "--",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64000": {
"content": "free_writing",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64001": {
"content": "matching_pairs",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64002": {
"content": "reorder_tokens",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64003": {
"content": "fill_in_the_blanks",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64004": {
"content": "general_vocab",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64005": {
"content": "morphology_focus",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64006": {
"content": "synonym_focus",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64007": {
"content": "antonym_focus",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64008": {
"content": "definition_only",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64009": {
"content": "[LESSON]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64010": {
"content": "[PRACTICE_TEXT]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64011": {
"content": "[EXERCISE_VARIATIONS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64012": {
"content": "[A1]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64013": {
"content": "[A2]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64014": {
"content": "[B1]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64015": {
"content": "[B2]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"--",
"free_writing",
"matching_pairs",
"reorder_tokens",
"fill_in_the_blanks",
"general_vocab",
"morphology_focus",
"synonym_focus",
"antonym_focus",
"definition_only",
"[LESSON]",
"[PRACTICE_TEXT]",
"[EXERCISE_VARIATIONS]",
"[A1]",
"[A2]",
"[B1]",
"[B2]"
],
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"do_lower_case": false,
"eos_token": "<|endoftext|>",
"extra_special_tokens": {},
"keep_accents": false,
"model_max_length": 4096,
"pad_token": "<pad>",
"remove_space": false,
"sp_model_kwargs": {},
"tokenizer_class": "GPTSw3Tokenizer",
"unk_token": "<unk>"
}