File size: 1,279 Bytes
fef9ff7 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 |
{
"_name_or_path": "logs/speed/llm-jp-modernbert-base-v4-ja-stage1-500k_msl8192-lr5e-5-bs384-ws24000-ms200000-mlm0.30-buf50000-20250314-0022/step_200000",
"architectures": [
"ModernBertForMaskedLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 5,
"classifier_activation": "gelu",
"classifier_bias": false,
"classifier_dropout": 0.0,
"classifier_pooling": "cls",
"cls_token_id": 5,
"decoder_bias": true,
"deterministic_flash_attn": false,
"embedding_dropout": 0.0,
"eos_token_id": 6,
"global_attn_every_n_layers": 3,
"global_rope_theta": 10000.0,
"hidden_activation": "gelu",
"hidden_size": 768,
"initializer_cutoff_factor": 2.0,
"initializer_range": 0.02,
"intermediate_size": 1152,
"local_attention": 128,
"local_rope_theta": 10000.0,
"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": 4,
"reference_compile": true,
"repad_logits_with_grad": false,
"sep_token_id": 6,
"sparse_pred_ignore_index": -100,
"sparse_prediction": false,
"torch_dtype": "float32",
"transformers_version": "4.48.0",
"vocab_size": 99574
}
|