calneymgp's picture
feat: braza-embedding-ptbr-v1 — 474K B2B PT-BR, 36 autoresearch iters, ASSIN2 0.8082, SICK-BR 0.8513
bb33fec verified
{
"architectures": [
"ModernBertModel"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 179934,
"classifier_activation": "silu",
"classifier_bias": false,
"classifier_dropout": 0.0,
"classifier_pooling": "mean",
"cls_token_id": 179934,
"decoder_bias": true,
"deterministic_flash_attn": false,
"dtype": "bfloat16",
"embedding_dropout": 0.0,
"eos_token_id": 179938,
"global_attn_every_n_layers": 3,
"gradient_checkpointing": false,
"hidden_activation": "silu",
"hidden_size": 384,
"initializer_cutoff_factor": 2.0,
"initializer_range": 0.02,
"intermediate_size": 1536,
"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"
],
"local_attention": 128,
"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": 12,
"pad_token_id": 179935,
"position_embedding_type": "absolute",
"repad_logits_with_grad": false,
"rope_parameters": {
"full_attention": {
"rope_theta": 150000.0,
"rope_type": "default"
},
"sliding_attention": {
"rope_theta": 160000.0,
"rope_type": "default"
}
},
"sep_token_id": 179938,
"sparse_pred_ignore_index": -100,
"sparse_prediction": false,
"tie_word_embeddings": true,
"transformers_version": "5.7.0",
"vocab_size": 180000
}