初始化项目,由ModelHub XC社区提供模型

Model: alakxender/dhivehi-gpt2-base
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-10 10:52:12 +08:00
commit b06778f831
29 changed files with 300910 additions and 0 deletions

32
tokenizer_config.json Normal file
View File

@@ -0,0 +1,32 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"50256": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"50257": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|endoftext|>",
"<|startoftext|>"
],
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"model_max_length": 1024,
"pad_token": "<|endoftext|>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}