Text Classification
PEFT
Safetensors
Arabic
French
darija
arabic
moroccan-arabic
arabizi
nlp
lora
bertouch
Instructions to use MedAdil/BERTal with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use MedAdil/BERTal with PEFT:
from peft import PeftModel from transformers import AutoModelForSequenceClassification base_model = AutoModelForSequenceClassification.from_pretrained("AbderrahmanSkiredj1/BERTouch") model = PeftModel.from_pretrained(base_model, "MedAdil/BERTal") - Notebooks
- Google Colab
- Kaggle
| { | |
| "backend": "tokenizers", | |
| "clean_up_tokenization_spaces": true, | |
| "cls_token": "[CLS]", | |
| "do_basic_tokenize": true, | |
| "do_lower_case": false, | |
| "is_local": false, | |
| "mask_token": "[MASK]", | |
| "max_len": 512, | |
| "max_length": 128, | |
| "model_max_length": 512, | |
| "never_split": [ | |
| "[بريد]", | |
| "[مستخدم]", | |
| "[رابط]" | |
| ], | |
| "pad_to_multiple_of": null, | |
| "pad_token": "[PAD]", | |
| "pad_token_type_id": 0, | |
| "padding_side": "right", | |
| "sep_token": "[SEP]", | |
| "stride": 0, | |
| "strip_accents": null, | |
| "tokenize_chinese_chars": true, | |
| "tokenizer_class": "BertTokenizer", | |
| "truncation_side": "right", | |
| "truncation_strategy": "longest_first", | |
| "unk_token": "[UNK]", | |
| "use_fast": true | |
| } | |