veyra-ai/veyra2-15m-base-1b-tokens
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: veyra-ai/veyra2-15m-base-1b-tokens
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-23 11:02:23 +08:00
commit bbd9cfcb85
12 changed files with 41269 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

224
tokenizer_config.json Normal file
View File

@@ -0,0 +1,224 @@
{
"added_tokens_decoder": {
"0": {
"content": "<|bos|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<|eos|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<|pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<|unk|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"6": {
"content": "<|tool_call|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"7": {
"content": "<|tool_result|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"8": {
"content": "<|context|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"9": {
"content": "<|reasoning|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"10": {
"content": "<|end_reasoning|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"11": {
"content": "<|answer|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"12": {
"content": "<|fim_prefix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"13": {
"content": "<|fim_middle|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"14": {
"content": "<|fim_suffix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"15": {
"content": "<|reserved_0|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"16": {
"content": "<|reserved_1|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"17": {
"content": "<|reserved_2|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"18": {
"content": "<|reserved_3|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"19": {
"content": "<|reserved_4|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"20": {
"content": "<|reserved_5|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21": {
"content": "<|reserved_6|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"22": {
"content": "<|reserved_7|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"23": {
"content": "<|reserved_8|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"24": {
"content": "<|reserved_9|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|tool_call|>",
"<|tool_result|>",
"<|context|>",
"<|reasoning|>",
"<|end_reasoning|>",
"<|answer|>",
"<|fim_prefix|>",
"<|fim_middle|>",
"<|fim_suffix|>"
],
"bos_token": "<|bos|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|eos|>",
"model_max_length": 1024,
"pad_token": "<|pad|>",
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": "<|unk|>"
}