mSlideOn / config.json
Paulo de Moura
Use max_active_dims for pooled latent pruning
8c9066f
Raw History Blame Contribute Delete
3.64 kB
{
"architectures": [
"SlideOnModel"
],
"auto_map": {
"AutoConfig": "modeling_slideon.SlideOnConfig",
"AutoModel": "modeling_slideon.SlideOnModel"
},
"backbone_config": {
"architectures": [
"ModernBertModel"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 2,
"classifier_activation": "gelu",
"classifier_bias": false,
"classifier_dropout": 0.0,
"classifier_pooling": "mean",
"cls_token_id": 1,
"decoder_bias": true,
"deterministic_flash_attn": false,
"dtype": "float32",
"embedding_dropout": 0.0,
"eos_token_id": 1,
"global_attn_every_n_layers": 3,
"gradient_checkpointing": false,
"hidden_activation": "gelu",
"hidden_size": 768,
"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,
"mask_token_id": 4,
"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": 0,
"position_embedding_type": "sans_pos",
"repad_logits_with_grad": false,
"rope_parameters": {
"full_attention": {
"rope_theta": 160000,
"rope_type": "default"
},
"sliding_attention": {
"rope_theta": 160000,
"rope_type": "default"
}
},
"sep_token_id": 1,
"sparse_pred_ignore_index": -100,
"sparse_prediction": false,
"tie_word_embeddings": true,
"vocab_size": 256002
},
"base_model": "lightonai/mLateOn",
"base_model_revision": "edd378f99593c0ac8a15518b97ad89786b02685e",
"checkpoint_type": "retrieval",
"head_config": {
"d_lift": 768,
"d_model": 128,
"has_decoder": false,
"hidden_dim": 1536,
"n_latents": 32768
},
"inference": {
"document_length": 8192,
"document_max_active_dims": null,
"head_chunk_size": 2048,
"pooling": "max_relu",
"prompts": {
"document": "",
"query": ""
},
"query_length": 8192,
"query_max_active_dims": null,
"score": "dot",
"token_k": 32
},
"model_type": "slideon",
"projection_configs": [
{
"activation_function": "torch.nn.modules.linear.Identity",
"bias": false,
"in_features": 768,
"out_features": 1536,
"use_residual": true
},
{
"activation_function": "torch.nn.modules.linear.Identity",
"bias": false,
"in_features": 1536,
"out_features": 768,
"use_residual": true
},
{
"activation_function": "torch.nn.modules.linear.Identity",
"bias": false,
"in_features": 768,
"out_features": 128,
"use_residual": false
}
],
"sae_path": "lightonai/mSlideOn-SAE",
"skip_token_ids": [],
"tokenizer_settings": {
"document_prefix": "[D] ",
"query_prefix": "[Q] ",
"skiplist_words": []
},
"transformers_version": "5.3.0"
}