Text Classification
Transformers
Safetensors
laya
mmbert
system-one
calibrated-decisions
rlcd
classification
routing
guardrails
moderation
commercial-use
Instructions to use hackoffice/laya-multilingual with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hackoffice/laya-multilingual with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="hackoffice/laya-multilingual")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("hackoffice/laya-multilingual", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer/tokenizer_config.json from hackoffice/laya-multilingual: direct link, hf CLI and curl.
- Browser
- Download file 502 Bytes
-
https://huggingface.co/hackoffice/laya-multilingual/resolve/main/tokenizer/tokenizer_config.json
- Command line
-
hf download hf://hackoffice/laya-multilingual/tokenizer/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/hackoffice/laya-multilingual/resolve/main/tokenizer/tokenizer_config.json
502 Bytes
| { | |
| "bos_token": "<bos>", | |
| "clean_up_tokenization_spaces": false, | |
| "cls_token": "<bos>", | |
| "eos_token": "<eos>", | |
| "extra_special_tokens": [ | |
| "<start_of_turn>", | |
| "<end_of_turn>" | |
| ], | |
| "mask_token": "<mask>", | |
| "model_input_names": [ | |
| "input_ids", | |
| "attention_mask" | |
| ], | |
| "model_max_length": 8192, | |
| "pad_token": "<pad>", | |
| "padding_side": "right", | |
| "sep_token": "<eos>", | |
| "spaces_between_special_tokens": false, | |
| "tokenizer_class": "PreTrainedTokenizerFast", | |
| "unk_token": "<unk>" | |
| } |