Upload config.
Browse files- config.json +46 -0
config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ModernBertForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"classifier_activation": "gelu",
|
| 9 |
+
"classifier_bias": false,
|
| 10 |
+
"classifier_dropout": 0.0,
|
| 11 |
+
"classifier_pooling": "cls",
|
| 12 |
+
"cls_token_id": 6,
|
| 13 |
+
"decoder_bias": true,
|
| 14 |
+
"deterministic_flash_attn": false,
|
| 15 |
+
"embedding_dropout": 0.0,
|
| 16 |
+
"eos_token_id": 2,
|
| 17 |
+
"global_attn_every_n_layers": 3,
|
| 18 |
+
"global_rope_theta": 160000.0,
|
| 19 |
+
"gradient_checkpointing": false,
|
| 20 |
+
"hidden_activation": "gelu",
|
| 21 |
+
"hidden_size": 768,
|
| 22 |
+
"initializer_cutoff_factor": 2.0,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 3072,
|
| 25 |
+
"layer_norm_eps": 1e-05,
|
| 26 |
+
"local_attention": 128,
|
| 27 |
+
"local_rope_theta": 10000.0,
|
| 28 |
+
"max_position_embeddings": 8192,
|
| 29 |
+
"mlp_bias": false,
|
| 30 |
+
"mlp_dropout": 0.0,
|
| 31 |
+
"model_type": "modernbert",
|
| 32 |
+
"norm_bias": false,
|
| 33 |
+
"norm_eps": 1e-05,
|
| 34 |
+
"num_attention_heads": 12,
|
| 35 |
+
"num_hidden_layers": 25,
|
| 36 |
+
"pad_token_id": 3,
|
| 37 |
+
"position_embedding_type": "rope",
|
| 38 |
+
"reference_compile": false,
|
| 39 |
+
"repad_logits_with_grad": false,
|
| 40 |
+
"sep_token_id": 4,
|
| 41 |
+
"sparse_pred_ignore_index": -100,
|
| 42 |
+
"sparse_prediction": false,
|
| 43 |
+
"torch_dtype": "float32",
|
| 44 |
+
"transformers_version": "4.48.3",
|
| 45 |
+
"vocab_size": 102400
|
| 46 |
+
}
|