Hugging Face's logo

tomaarsen
/
multivector-ModernBERT-base-msmarco-cached-contrastive-no-query-expansion

Feature Extraction
sentence-transformers
Safetensors
English
modernbert
multi-vector
colbert
late-interaction
Generated from Trainer
dataset_size:99000
loss:CachedMultiVectorMultipleNegativesRankingLoss
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
 Community
tomaarsen HF Staff commited on
Commit
6ae85e7
·
verified ·
1 Parent(s): a6c14d8

Add new MultiVectorEncoder model

Browse files
Files changed (12) hide show
  1. 1_Dense/config.json +8 -0
  2. 1_Dense/model.safetensors +3 -0
  3. 2_MultiVectorMask/config.json +4 -0
  4. 3_Normalize/config.json +4 -0
  5. README.md +0 -0
  6. config.json +78 -0
  7. config_sentence_transformers.json +14 -0
  8. model.safetensors +3 -0
  9. modules.json +26 -0
  10. sentence_bert_config.json +10 -0
  11. tokenizer.json +0 -0
  12. tokenizer_config.json +17 -0
1_Dense/config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "in_features": 768,
3
+ "out_features": 128,
4
+ "bias": false,
5
+ "activation_function": "torch.nn.modules.linear.Identity",
6
+ "module_input_name": "token_embeddings",
7
+ "module_output_name": "token_embeddings"
8
+ }
1_Dense/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ce6a3877a7f57ff4d7637547b94914cca53a443d0c515a957b7a1d19da7ee75
3
+ size 393304
2_MultiVectorMask/config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "skiplist_words": [],
3
+ "keep_only_token_ids": null
4
+ }
3_Normalize/config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "module_input_name": "token_embeddings",
3
+ "module_output_name": "token_embeddings"
4
+ }
README.md ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertModel"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": null,
8
+ "classifier_activation": "gelu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 50281,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "dtype": "float32",
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": null,
18
+ "global_attn_every_n_layers": 3,
19
+ "gradient_checkpointing": false,
20
+ "hidden_activation": "gelu",
21
+ "hidden_size": 768,
22
+ "initializer_cutoff_factor": 2.0,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 1152,
25
+ "layer_norm_eps": 1e-05,
26
+ "layer_types": [
27
+ "full_attention",
28
+ "sliding_attention",
29
+ "sliding_attention",
30
+ "full_attention",
31
+ "sliding_attention",
32
+ "sliding_attention",
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
+ ],
50
+ "local_attention": 128,
51
+ "max_position_embeddings": 8192,
52
+ "mlp_bias": false,
53
+ "mlp_dropout": 0.0,
54
+ "model_type": "modernbert",
55
+ "norm_bias": false,
56
+ "norm_eps": 1e-05,
57
+ "num_attention_heads": 12,
58
+ "num_hidden_layers": 22,
59
+ "pad_token_id": 50283,
60
+ "position_embedding_type": "absolute",
61
+ "rope_parameters": {
62
+ "full_attention": {
63
+ "rope_theta": 160000.0,
64
+ "rope_type": "default"
65
+ },
66
+ "sliding_attention": {
67
+ "rope_theta": 10000.0,
68
+ "rope_type": "default"
69
+ }
70
+ },
71
+ "sep_token_id": 50282,
72
+ "sparse_pred_ignore_index": -100,
73
+ "sparse_prediction": false,
74
+ "tie_word_embeddings": true,
75
+ "transformers_version": "5.13.1",
76
+ "use_cache": false,
77
+ "vocab_size": 50368
78
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "pytorch": "2.10.0+cu128",
4
+ "sentence_transformers": "5.7.0.dev0",
5
+ "transformers": "5.13.1"
6
+ },
7
+ "default_prompt_name": null,
8
+ "model_type": "MultiVectorEncoder",
9
+ "prompts": {
10
+ "document": "",
11
+ "query": ""
12
+ },
13
+ "similarity_fn_name": "maxsim"
14
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b99d041116c2b4a2f25c234158941cd9546e3057bd626dea3bc705c612c4a303
3
+ size 596070136
modules.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.base.modules.transformer.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Dense",
12
+ "type": "sentence_transformers.base.modules.dense.Dense"
13
+ },
14
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_MultiVectorMask",
18
+ "type": "sentence_transformers.multi_vector_encoder.modules.multi_vector_mask.MultiVectorMask"
19
+ },
20
+ {
21
+ "idx": 3,
22
+ "name": "3",
23
+ "path": "3_Normalize",
24
+ "type": "sentence_transformers.sentence_transformer.modules.normalize.Normalize"
25
+ }
26
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "transformer_task": "feature-extraction",
3
+ "modality_config": {
4
+ "text": {
5
+ "method": "forward",
6
+ "method_output_name": "last_hidden_state"
7
+ }
8
+ },
9
+ "module_output_name": "token_embeddings"
10
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "is_local": false,
6
+ "local_files_only": false,
7
+ "mask_token": "[MASK]",
8
+ "model_input_names": [
9
+ "input_ids",
10
+ "attention_mask"
11
+ ],
12
+ "model_max_length": 8192,
13
+ "pad_token": "[PAD]",
14
+ "sep_token": "[SEP]",
15
+ "tokenizer_class": "TokenizersBackend",
16
+ "unk_token": "[UNK]"
17
+ }