Download tokenizer_config.json from mkd-ai-dev/keural-tokenizer: direct link, hf CLI and curl.
- Browser
- Download file 645 Bytes
-
https://huggingface.co/mkd-ai-dev/keural-tokenizer/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://mkd-ai-dev/keural-tokenizer/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/mkd-ai-dev/keural-tokenizer/resolve/main/tokenizer_config.json
645 Bytes
| { | |
| "architectures": [ | |
| "KeuralMoEForCausalLM" | |
| ], | |
| "model_type": "keural_moe", | |
| "vocab_size": 131072, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "pad_token_id": 0, | |
| "unk_token_id": 3, | |
| "tokenizer_class": "SentencePieceTokenizer", | |
| "sentencepiece_model_file": "keural_tokenizer.model", | |
| "special_tokens_map": { | |
| "pad_token": "<pad>", | |
| "bos_token": "<bos>", | |
| "eos_token": "<eos>", | |
| "unk_token": "<unk>" | |
| }, | |
| "normalization": "nfkc", | |
| "split_digits": true, | |
| "byte_fallback": true, | |
| "max_context_target": 1048576, | |
| "context_stages": [ | |
| 4096, | |
| 8192, | |
| 32768, | |
| 131072, | |
| 262144, | |
| 524288, | |
| 1048576 | |
| ] | |
| } |