AraEuroBert-2.1B / config.json
Omartificial-Intelligence-Space's picture
upload 12 files
091a9e6 verified
{
"_name_or_path": "EuroBERT/EuroBERT-2.1B",
"architectures": [
"EuroBertModel"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "EuroBERT/EuroBERT-2.1B--configuration_eurobert.EuroBertConfig",
"AutoModel": "EuroBERT/EuroBERT-2.1B--modeling_eurobert.EuroBertModel",
"AutoModelForMaskedLM": "EuroBERT/EuroBERT-2.1B--modeling_eurobert.EuroBertForMaskedLM",
"AutoModelForPreTraining": "EuroBERT/EuroBERT-2.1B--modeling_eurobert.EuroBertPreTrainedModel",
"AutoModelForSequenceClassification": "EuroBERT/EuroBERT-2.1B--modeling_eurobert.EuroBertForSequenceClassification"
},
"bos_token": "<|begin_of_text|>",
"bos_token_id": 128000,
"clf_pooling": "late",
"eos_token": "<|end_of_text|>",
"eos_token_id": 128001,
"head_dim": 128,
"hidden_act": "silu",
"hidden_dropout": 0.0,
"hidden_size": 2304,
"initializer_range": 0.02,
"intermediate_size": 6144,
"mask_token": "<|mask|>",
"mask_token_id": 128002,
"max_position_embeddings": 8192,
"mlp_bias": false,
"model_type": "eurobert",
"num_attention_heads": 18,
"num_hidden_layers": 32,
"num_key_value_heads": 6,
"pad_token": "<|end_of_text|>",
"pad_token_id": 128001,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 250000,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.49.0",
"use_cache": false,
"vocab_size": 128256
}