nebhailema commited on
Commit
700a03f
·
verified ·
1 Parent(s): a970ba1

Add new MultiVectorEncoder model

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
1_Dense/config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "in_features": 384,
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:c3fb956b030c64ea42faa260fe1c61eab3c09af7c1c1f6a5915ac847925c7df3
3
+ size 196696
2_MultiVectorMask/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "skiplist_words": [
3
+ "!",
4
+ "\"",
5
+ "#",
6
+ "$",
7
+ "%",
8
+ "&",
9
+ "'",
10
+ "(",
11
+ ")",
12
+ "*",
13
+ "+",
14
+ ",",
15
+ "-",
16
+ ".",
17
+ "/",
18
+ ":",
19
+ ";",
20
+ "<",
21
+ "=",
22
+ ">",
23
+ "?",
24
+ "@",
25
+ "[",
26
+ "\\",
27
+ "]",
28
+ "^",
29
+ "_",
30
+ "`",
31
+ "{",
32
+ "|",
33
+ "}",
34
+ "~"
35
+ ],
36
+ "skiplist_tasks": [
37
+ "document"
38
+ ],
39
+ "keep_only_token_ids": null
40
+ }
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 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 384,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 1536,
16
+ "is_decoder": false,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "bert",
20
+ "num_attention_heads": 12,
21
+ "num_hidden_layers": 12,
22
+ "pad_token_id": 1,
23
+ "position_embedding_type": "absolute",
24
+ "tie_word_embeddings": true,
25
+ "tokenizer_class": "XLMRobertaTokenizer",
26
+ "transformers_version": "5.21.0",
27
+ "type_vocab_size": 2,
28
+ "use_cache": false,
29
+ "vocab_size": 250037
30
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "pytorch": "2.11.0+cu130",
4
+ "sentence_transformers": "6.2.0",
5
+ "transformers": "5.21.0"
6
+ },
7
+ "default_prompt_name": null,
8
+ "model_type": "MultiVectorEncoder",
9
+ "prompts": {
10
+ "document": "passage: ",
11
+ "query": "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 sha256:360021f296442573c73307b76821be3f66c5a0c9d4d708e6ae2241f775527f24
3
+ size 470637416
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.base.modules.normalize.Normalize"
25
+ }
26
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "query_length": 32,
11
+ "document_length": 180
12
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:274d243b6040a7b4f57a3b67d952c81e6a113e70fc7fdaea09a200a9ce64f43b
3
+ size 17082988
tokenizer_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<s>",
5
+ "clean_up_tokenization_spaces": true,
6
+ "cls_token": "<s>",
7
+ "eos_token": "</s>",
8
+ "is_local": true,
9
+ "local_files_only": false,
10
+ "mask_token": "<mask>",
11
+ "max_length": 180,
12
+ "model_max_length": 180,
13
+ "pad_to_multiple_of": null,
14
+ "pad_token": "<pad>",
15
+ "pad_token_type_id": 0,
16
+ "padding_side": "right",
17
+ "sep_token": "</s>",
18
+ "sp_model_kwargs": {},
19
+ "stride": 0,
20
+ "tokenizer_class": "XLMRobertaTokenizer",
21
+ "truncation_side": "right",
22
+ "truncation_strategy": "longest_first",
23
+ "unk_token": "<unk>"
24
+ }