Download tokenizer_config.json from VDC-team/VDrontGPT10m-Base: direct link, hf CLI and curl.
- Browser
- Download file 609 Bytes
-
https://huggingface.co/VDC-team/VDrontGPT10m-Base/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://VDC-team/VDrontGPT10m-Base/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/VDC-team/VDrontGPT10m-Base/resolve/main/tokenizer_config.json
609 Bytes
| { | |
| "add_prefix_space": false, | |
| "added_tokens_decoder": { | |
| "50256": { | |
| "content": "<|endoftext|>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| } | |
| }, | |
| "bos_token": "<|endoftext|>", | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "<|endoftext|>", | |
| "max_length": 128, | |
| "model_max_length": 1024, | |
| "pad_token": "<|endoftext|>", | |
| "stride": 0, | |
| "tokenizer_class": "GPT2Tokenizer", | |
| "truncation_side": "right", | |
| "truncation_strategy": "longest_first", | |
| "unk_token": "<|endoftext|>" | |
| } | |