Instructions to use yuchenxie/ArlowGPT-Tokenizer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use yuchenxie/ArlowGPT-Tokenizer with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("yuchenxie/ArlowGPT-Tokenizer", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "tokenizer_class": "PreTrainedTokenizerFast", | |
| "name_or_path": "tokenizer.json", | |
| "model_max_length": 131072, | |
| "errors": "replace", | |
| "add_bos_token": false, | |
| "add_prefix_space": false, | |
| "clean_up_tokenization_spaces": false, | |
| "additional_special_tokens": [ | |
| "<|mask|>" | |
| ], | |
| "bos_token": "<|startoftext|>", | |
| "eos_token": "<|endoftext|>", | |
| "unk_token": "<|unk|>", | |
| "pad_token": "<|pad|>", | |
| "chat_template": "{%- if messages[0]['role'] == 'system' %}\n<|im_start|>system\nYou are ArlowGPT made by Yuchen Xie. You are a helpful assistant in which you respond to users query without neglecting.\n<|im_end|>\n{%- else %}\n<|im_start|>system\nYou are ArlowGPT made by Yuchen Xie. You are a helpful assistant in which you respond to users query without neglecting.\n<|im_end|>\n{%- endif %}\n\n{%- for message in messages %}\n {%- if message.role == 'user' %}\n<|im_start|>user\n{{ message.content }}\n<|im_end|>\n {%- elif message.role == 'assistant' %}\n<|im_start|>assistant\n{{ message.content }}\n<|im_end|>\n {%- endif %}\n{%- endfor %}" | |
| } | |