Text Classification
Laya
Safetensors
multilingual
mmbert
modernbert
decision-making
classification
routing
scoring
fp16
Instructions to use MigoXV/laya-multilingual with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Laya
How to use MigoXV/laya-multilingual with Laya:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Download config.json from MigoXV/laya-multilingual: direct link, hf CLI and curl.
- Browser
- Download file 2.92 kB
-
https://huggingface.co/MigoXV/laya-multilingual/resolve/main/config.json
- Command line
-
hf download hf://MigoXV/laya-multilingual/config.json
-
curl -L -o config.json https://huggingface.co/MigoXV/laya-multilingual/resolve/main/config.json
2.92 kB
| { | |
| "format_version": 1, | |
| "encoder": { | |
| "architectures": [ | |
| "ModernBertForMaskedLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 2, | |
| "classifier_activation": "gelu", | |
| "classifier_bias": false, | |
| "classifier_dropout": 0.0, | |
| "classifier_pooling": "mean", | |
| "cls_token_id": 1, | |
| "decoder_bias": true, | |
| "deterministic_flash_attn": false, | |
| "dtype": "float32", | |
| "embedding_dropout": 0.0, | |
| "eos_token_id": 1, | |
| "global_attn_every_n_layers": 3, | |
| "gradient_checkpointing": false, | |
| "hidden_activation": "gelu", | |
| "hidden_size": 768, | |
| "initializer_cutoff_factor": 2.0, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1152, | |
| "layer_norm_eps": 1e-05, | |
| "layer_types": [ | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention" | |
| ], | |
| "local_attention": 128, | |
| "mask_token_id": 4, | |
| "max_position_embeddings": 8192, | |
| "mlp_bias": false, | |
| "mlp_dropout": 0.0, | |
| "model_type": "modernbert", | |
| "norm_bias": false, | |
| "norm_eps": 1e-05, | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 22, | |
| "pad_token_id": 0, | |
| "position_embedding_type": "sans_pos", | |
| "repad_logits_with_grad": false, | |
| "rope_parameters": { | |
| "full_attention": { | |
| "rope_theta": 160000, | |
| "rope_type": "default" | |
| }, | |
| "sliding_attention": { | |
| "rope_theta": 160000, | |
| "rope_type": "default" | |
| } | |
| }, | |
| "sep_token_id": 1, | |
| "sparse_pred_ignore_index": -100, | |
| "sparse_prediction": false, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.0.0", | |
| "vocab_size": 256000 | |
| }, | |
| "decision_head": { | |
| "layers": 2, | |
| "num_actions": 2 | |
| }, | |
| "input_limits": { | |
| "max_len": 1024, | |
| "head_max_len": 256 | |
| }, | |
| "calibration": { | |
| "temperature": [ | |
| 1.0, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "temperature_by_options": {} | |
| }, | |
| "tokenizer": { | |
| "bos_token": "<bos>", | |
| "clean_up_tokenization_spaces": false, | |
| "cls_token": "<bos>", | |
| "eos_token": "<eos>", | |
| "extra_special_tokens": { | |
| "extra_0": "<start_of_turn>", | |
| "extra_1": "<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, | |
| "unk_token": "<unk>" | |
| } | |
| } | |