PeteBleackley's picture
End of training
9f5c6cd verified
{
"architectures": [
"DisamBertSingleSense"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoModel": "DisamBertSingleSense.DisamBertSingleSense"
},
"bos_token_id": null,
"classifier_activation": "gelu",
"classifier_bias": false,
"classifier_dropout": 0.0,
"classifier_pooling": "mean",
"cls_token_id": 50281,
"decoder_bias": true,
"deterministic_flash_attn": false,
"dtype": "float32",
"embedding_dropout": 0.0,
"end_token": 50369,
"eos_token_id": null,
"global_attn_every_n_layers": 3,
"gradient_checkpointing": false,
"hidden_activation": "gelu",
"hidden_size": 768,
"init_basemodel": false,
"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,
"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": 50283,
"position_embedding_type": "absolute",
"rope_parameters": {
"full_attention": {
"rope_theta": 160000.0,
"rope_type": "default"
},
"sliding_attention": {
"rope_theta": 10000.0,
"rope_type": "default"
}
},
"sep_token_id": 50282,
"sparse_pred_ignore_index": -100,
"sparse_prediction": false,
"start_token": 50368,
"tie_word_embeddings": true,
"transformers_version": "5.2.0",
"use_cache": false,
"vocab_size": 50370
}