Download tokenizer_config.json from sovythos/Sovythos-303M-Base: direct link, hf CLI and curl.
- Browser
- Download file 2.23 kB
-
https://huggingface.co/sovythos/Sovythos-303M-Base/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://sovythos/Sovythos-303M-Base/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/sovythos/Sovythos-303M-Base/resolve/main/tokenizer_config.json
2.23 kB
| { | |
| "tokenizer_class": "PreTrainedTokenizerFast", | |
| "model_max_length": 2048, | |
| "clean_up_tokenization_spaces": false, | |
| "bos_token": "<|endoftext|>", | |
| "eos_token": "<|endoftext|>", | |
| "unk_token": "<|endoftext|>", | |
| "pad_token": "<|pad|>", | |
| "added_tokens_decoder": { | |
| "0": {"content": "<|endoftext|>", "special": true, "single_word": false, "lstrip": false, "rstrip": false, "normalized": false}, | |
| "1": {"content": "<|pad|>", "special": true, "single_word": false, "lstrip": false, "rstrip": false, "normalized": false}, | |
| "2": {"content": "<|user|>", "special": true, "single_word": false, "lstrip": false, "rstrip": false, "normalized": false}, | |
| "3": {"content": "<|assistant|>", "special": true, "single_word": false, "lstrip": false, "rstrip": false, "normalized": false}, | |
| "4": {"content": "<|system|>", "special": true, "single_word": false, "lstrip": false, "rstrip": false, "normalized": false}, | |
| "5": {"content": "<|code|>", "special": true, "single_word": false, "lstrip": false, "rstrip": false, "normalized": false}, | |
| "6": {"content": "<|/code|>", "special": true, "single_word": false, "lstrip": false, "rstrip": false, "normalized": false}, | |
| "7": {"content": "<|think|>", "special": true, "single_word": false, "lstrip": false, "rstrip": false, "normalized": false}, | |
| "8": {"content": "<|/think|>", "special": true, "single_word": false, "lstrip": false, "rstrip": false, "normalized": false}, | |
| "9": {"content": "<|egy|>", "special": true, "single_word": false, "lstrip": false, "rstrip": false, "normalized": false}, | |
| "10": {"content": "<|msa|>", "special": true, "single_word": false, "lstrip": false, "rstrip": false, "normalized": false}, | |
| "11": {"content": "<|en|>", "special": true, "single_word": false, "lstrip": false, "rstrip": false, "normalized": false} | |
| }, | |
| "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|system|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'user' %}{{ '<|user|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'assistant' %}{{ '<|assistant|>\n' + message['content'] + '<|endoftext|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% endif %}" | |
| } | |