ragzilla / config.json
nickswami's picture
Ragzilla model and card
8f825d4 verified
Raw History Blame Contribute Delete
3.69 kB
{
"architectures": [
"OpenjevScorer"
],
"auto_map": {
"AutoConfig": "modeling_openjev.OpenjevScorerConfig",
"AutoModel": "modeling_openjev.OpenjevScorer"
},
"base_config": {
"_name_or_path": "/home/nicks/rz4/runs/ragzilla4-raw/trunk",
"architectures": [
"ModernBertModel"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 50281,
"chunk_size_feed_forward": 0,
"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": "bfloat16",
"embedding_dropout": 0.0,
"eos_token_id": 50282,
"global_attn_every_n_layers": 3,
"gradient_checkpointing": false,
"hidden_activation": "gelu",
"hidden_size": 1024,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_cutoff_factor": 2.0,
"initializer_range": 0.02,
"intermediate_size": 2624,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"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",
"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": 16,
"num_hidden_layers": 28,
"output_attentions": false,
"output_hidden_states": false,
"pad_token_id": 50283,
"position_embedding_type": "absolute",
"problem_type": null,
"return_dict": true,
"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": "5.22.1",
"vocab_size": 50368
},
"dtype": "bfloat16",
"head": "mlp",
"kind_targets": {
"relevant": "subset"
},
"layout": "packed",
"max_chars": 4000,
"model_type": "openjev_scorer",
"operating_points": {
"calibration": {
"relevant": {
"dataset": "/home/nicks/rz4/data/ragzilla4",
"questions": 81796,
"split": "calibration",
"with_relevant": 62164
}
},
"default": "rho_99",
"kinds": {
"relevant": {
"rho_95": 0.4896734040655392,
"rho_98": 0.2484192153441876,
"rho_99": 0.14100515246531517,
"tau_95": 0.0873944913234316,
"tau_98": 0.037584883025427944,
"tau_99": 0.019544395931894377
}
},
"survival": "any",
"targets": [
0.95,
0.98,
0.99
]
},
"sequence_tokens": 8192,
"temperatures": {
"relevant": 0.4066069798285397
},
"transformers_version": "5.22.1"
}