Instructions to use eitanturok/llama-tokenizer-tool with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use eitanturok/llama-tokenizer-tool with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("eitanturok/llama-tokenizer-tool", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from eitanturok/llama-tokenizer-tool: direct link, hf CLI and curl.
- Browser
- Download file 1.64 kB
-
https://huggingface.co/eitanturok/llama-tokenizer-tool/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://eitanturok/llama-tokenizer-tool/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/eitanturok/llama-tokenizer-tool/resolve/main/tokenizer_config.json
1.64 kB
| { | |
| "add_bos_token": true, | |
| "add_eos_token": false, | |
| "added_tokens_decoder": { | |
| "0": { | |
| "content": "<unk>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "1": { | |
| "content": "<s>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "2": { | |
| "content": "</s>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| } | |
| }, | |
| "bos_token": "<s>", | |
| "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = '<<SYS>>' + messages[0]['content'].strip() + '<</SYS>>' %}{% else %}{% set loop_messages = messages %}{% set system_message = '' %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{% set content = system_message + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% elif message['role'] == 'tool' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}", | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "</s>", | |
| "legacy": false, | |
| "model_max_length": 1000000000000000019884624838656, | |
| "pad_token": null, | |
| "padding_side": "right", | |
| "sp_model_kwargs": {}, | |
| "tokenizer_class": "LlamaTokenizer", | |
| "unk_token": "<unk>", | |
| "use_default_system_prompt": false | |
| } | |