bert-marker-type / config.json
permutans's picture
Upload folder using huggingface_hub
dbfd94d verified
raw
history blame
3.33 kB
{
"architectures": [
"ModernBertForSequenceClassification"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 50281,
"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,
"eos_token_id": 50282,
"global_attn_every_n_layers": 3,
"gradient_checkpointing": false,
"hidden_activation": "gelu",
"hidden_size": 768,
"id2label": {
"0": "abstraction",
"1": "agonistic",
"2": "agonistic_framing",
"3": "analytical_distance",
"4": "concrete",
"5": "concrete_situational",
"6": "direct_address",
"7": "formulaic",
"8": "formulaic_phrases",
"9": "hedging",
"10": "hedging_qualification",
"11": "literate_feature",
"12": "logical_connective",
"13": "logical_connectives",
"14": "oral_feature",
"15": "parallelism",
"16": "parataxis",
"17": "passive",
"18": "passive_agentless",
"19": "passive_constructions",
"20": "performance_markers",
"21": "repetition",
"22": "sound_patterns",
"23": "subordination",
"24": "textual_apparatus"
},
"initializer_cutoff_factor": 2.0,
"initializer_range": 0.02,
"intermediate_size": 1152,
"label2id": {
"abstraction": 0,
"agonistic": 1,
"agonistic_framing": 2,
"analytical_distance": 3,
"concrete": 4,
"concrete_situational": 5,
"direct_address": 6,
"formulaic": 7,
"formulaic_phrases": 8,
"hedging": 9,
"hedging_qualification": 10,
"literate_feature": 11,
"logical_connective": 12,
"logical_connectives": 13,
"oral_feature": 14,
"parallelism": 15,
"parataxis": 16,
"passive": 17,
"passive_agentless": 18,
"passive_constructions": 19,
"performance_markers": 20,
"repetition": 21,
"sound_patterns": 22,
"subordination": 23,
"textual_apparatus": 24
},
"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",
"repad_logits_with_grad": false,
"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,
"tie_word_embeddings": true,
"transformers_version": "5.0.0",
"vocab_size": 50368
}