ali-elganzory/Baguettotron-longsft_16k
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: ali-elganzory/Baguettotron-longsft_16k
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-22 03:17:25 +08:00
commit 6cb3fe09be
8 changed files with 327716 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

454
tokenizer_config.json Normal file
View File

@@ -0,0 +1,454 @@
{
"added_tokens_decoder": {
"0": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<|begin_of_text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<|end_of_text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65491": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65492": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65493": {
"content": "<think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65494": {
"content": "</think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65495": {
"content": "source_1",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65496": {
"content": "source_2",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65497": {
"content": "source_3",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65498": {
"content": "source_4",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65499": {
"content": "source_5",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65500": {
"content": "source_6",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65501": {
"content": "source_7",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65502": {
"content": "source_8",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65503": {
"content": "source_9",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65504": {
"content": "source_10",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65505": {
"content": "<ref",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65506": {
"content": "</ref>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65507": {
"content": "→",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65508": {
"content": "↺",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65509": {
"content": "※",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65510": {
"content": "?maybe?",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65511": {
"content": "●",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65512": {
"content": "◐",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65513": {
"content": "○",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65514": {
"content": "⚠",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65515": {
"content": "☐",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65516": {
"content": "☑",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65517": {
"content": "✓",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65518": {
"content": "⟨H≈0.1⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65519": {
"content": "⟨H≈0.2⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65520": {
"content": "⟨H≈0.3⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65521": {
"content": "⟨H≈0.4⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65522": {
"content": "⟨H≈0.5⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65523": {
"content": "⟨H≈0.6⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65524": {
"content": "⟨H≈0.7⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65525": {
"content": "⟨H≈0.8⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65526": {
"content": "⟨H≈0.9⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65527": {
"content": "⟨H≈1.0⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65528": {
"content": "⟨H≈1.1⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65529": {
"content": "⟨H≈1.2⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65530": {
"content": "⟨H≈1.3⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65531": {
"content": "⟨H≈1.4⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65532": {
"content": "⟨H≈1.5⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65533": {
"content": "⟨H≈1.6⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65534": {
"content": "⟨H≈1.7⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65535": {
"content": "⟨H≈1.8⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<think>",
"</think>",
"source_1",
"source_2",
"source_3",
"source_4",
"source_5",
"source_6",
"source_7",
"source_8",
"source_9",
"source_10",
"<ref",
"</ref>",
"→",
"↺",
"※",
"?maybe?",
"●",
"◐",
"○",
"⚠",
"☐",
"☑",
"✓",
"⟨H≈0.1⟩",
"⟨H≈0.2⟩",
"⟨H≈0.3⟩",
"⟨H≈0.4⟩",
"⟨H≈0.5⟩",
"⟨H≈0.6⟩",
"⟨H≈0.7⟩",
"⟨H≈0.8⟩",
"⟨H≈0.9⟩",
"⟨H≈1.0⟩",
"⟨H≈1.1⟩",
"⟨H≈1.2⟩",
"⟨H≈1.3⟩",
"⟨H≈1.4⟩",
"⟨H≈1.5⟩",
"⟨H≈1.6⟩",
"⟨H≈1.7⟩",
"⟨H≈1.8⟩"
],
"bos_token": "<|begin_of_text|>",
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>\n' }}{% endif %}{% endfor %}",
"clean_up_tokenization_spaces": true,
"eos_token": "<|im_end|>",
"extra_special_tokens": {},
"model_max_length": 1000000000000000019884624838656,
"pad_token": "[PAD]",
"padding_side": "right",
"split_special_tokens": false,
"tokenizer_class": "PreTrainedTokenizer",
"unk_token": "[UNK]"
}