pyrrho-v2-nano-g1 / config.json
yafitzdev's picture
Add files using upload-large-folder tool
d482f6b verified
Raw
History Blame
3.86 kB
{
"architectures": [
"ModernBertForSequenceClassification"
],
"attention_bias": false,
"attention_dropout": 0.0,
"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,
"eos_token_id": null,
"global_attn_every_n_layers": 3,
"global_rope_theta": 160000.0,
"gradient_checkpointing": false,
"hidden_activation": "gelu",
"hidden_size": 768,
"id2label": {
"0": "evidence_verdict.INSUFFICIENT",
"1": "evidence_verdict.DISPUTED",
"2": "evidence_verdict.SUFFICIENT",
"3": "failure_mode.none",
"4": "failure_mode.unresolved_conflict",
"5": "failure_mode.missing_or_incomplete_evidence",
"6": "failure_mode.wrong_scope_or_version",
"7": "failure_mode.ambiguous_request",
"8": "retrieval_intents.needs_lookup",
"9": "retrieval_intents.needs_temporal_resolution",
"10": "retrieval_intents.needs_comparison_or_set",
"11": "retrieval_intents.needs_broad_coverage",
"12": "evidence_kinds.needs_text",
"13": "evidence_kinds.needs_table_or_record",
"14": "evidence_kinds.needs_code_or_symbol",
"15": "evidence_kinds.needs_config_or_setting",
"16": "evidence_kinds.needs_log_or_run_result",
"17": "evidence_kinds.needs_document_layout"
},
"initializer_cutoff_factor": 2.0,
"initializer_range": 0.02,
"intermediate_size": 1152,
"label2id": {
"evidence_kinds.needs_code_or_symbol": 14,
"evidence_kinds.needs_config_or_setting": 15,
"evidence_kinds.needs_document_layout": 17,
"evidence_kinds.needs_log_or_run_result": 16,
"evidence_kinds.needs_table_or_record": 13,
"evidence_kinds.needs_text": 12,
"evidence_verdict.DISPUTED": 1,
"evidence_verdict.INSUFFICIENT": 0,
"evidence_verdict.SUFFICIENT": 2,
"failure_mode.ambiguous_request": 7,
"failure_mode.missing_or_incomplete_evidence": 5,
"failure_mode.none": 3,
"failure_mode.unresolved_conflict": 4,
"failure_mode.wrong_scope_or_version": 6,
"retrieval_intents.needs_broad_coverage": 11,
"retrieval_intents.needs_comparison_or_set": 10,
"retrieval_intents.needs_lookup": 8,
"retrieval_intents.needs_temporal_resolution": 9
},
"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,
"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": 50283,
"position_embedding_type": "absolute",
"problem_type": "multi_label_classification",
"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,
"transformers_version": "4.57.6",
"use_cache": false,
"vocab_size": 50368
}