CoolFace
Modelpublic

Linkup-Platform/linkup-sparseup-embed-v1

sourceHugging Faceapache-2.0updated 4d agoView on Hugging Face
51likes2kdownloads
config.json90 linesDownload Raw Back to root
1{2  "architectures": [3    "SpladeModel"4  ],5  "attention_bias": false,6  "attention_dropout": 0.0,7  "auto_map": {8    "AutoConfig": "modeling_splade.SpladeConfig",9    "AutoModel": "modeling_splade.SpladeModel"10  },11  "bos_token_id": 50281,12  "classifier_activation": "gelu",13  "classifier_bias": false,14  "classifier_dropout": 0.0,15  "classifier_pooling": "mean",16  "cls_token_id": 50281,17  "decoder_bias": true,18  "deterministic_flash_attn": false,19  "doc_max_length": 512,20  "document_prefix": "[D] ",21  "dtype": "float32",22  "embedding_dropout": 0.0,23  "eos_token_id": 50282,24  "global_attn_every_n_layers": 3,25  "gradient_checkpointing": false,26  "hidden_activation": "gelu",27  "hidden_size": 768,28  "initializer_cutoff_factor": 2.0,29  "initializer_range": 0.02,30  "intermediate_size": 1152,31  "layer_norm_eps": 1e-05,32  "layer_types": [33    "full_attention",34    "sliding_attention",35    "sliding_attention",36    "full_attention",37    "sliding_attention",38    "sliding_attention",39    "full_attention",40    "sliding_attention",41    "sliding_attention",42    "full_attention",43    "sliding_attention",44    "sliding_attention",45    "full_attention",46    "sliding_attention",47    "sliding_attention",48    "full_attention",49    "sliding_attention",50    "sliding_attention",51    "full_attention",52    "sliding_attention",53    "sliding_attention",54    "full_attention"55  ],56  "local_attention": 128,57  "logit_shift": 15,58  "max_position_embeddings": 8192,59  "mlp_bias": false,60  "mlp_dropout": 0.0,61  "model_type": "modernbert",62  "norm_bias": false,63  "norm_eps": 1e-05,64  "num_attention_heads": 12,65  "num_hidden_layers": 22,66  "pad_token_id": 50283,67  "position_embedding_type": "absolute",68  "position_top_k": 12,69  "query_max_length": 128,70  "query_prefix": "[Q] ",71  "repad_logits_with_grad": false,72  "rope_parameters": {73    "full_attention": {74      "rope_theta": 160000.0,75      "rope_type": "default"76    },77    "sliding_attention": {78      "rope_theta": 10000.0,79      "rope_type": "default"80    }81  },82  "sep_token_id": 50282,83  "sparse_pred_ignore_index": -100,84  "sparse_prediction": false,85  "tie_word_embeddings": false,86  "transformers_version": "5.3.0",87  "vocab_fold": "case_space",88  "vocab_size": 5037089}90