zubenelgenubi-124m / tokenizer_config.json
farpluto's picture
Upload 124M GPT trained from scratch with SmolLM distillation
ca40472 verified
raw
history blame contribute delete
405 Bytes
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": "<|im_start|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"extra_special_tokens": [
"<|im_start|>",
"<|im_end|>"
],
"is_local": false,
"model_max_length": 2048,
"pad_token": "<|im_end|>",
"tokenizer_class": "TokenizersBackend",
"unk_token": "<|endoftext|>",
"vocab_size": 49152
}