Hugging Face's logo

Symato
/
jina-embeddings-v3__trimm_vocab__bf16

Safetensors
xlm-roberta
custom_code
Model card Files Community
tiendung commited on
Commit
5eccdfc
•
1 Parent(s): 7f83098

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. config.json +67 -0
  2. model.safetensors +3 -0
  3. special_tokens_map.json +51 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +54 -0
config.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "jinaai/jina-embeddings-v3",
3
+ "architectures": [
4
+ "XLMRobertaLoRA"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "auto_map": {
8
+ "AutoConfig": "jinaai/xlm-roberta-flash-implementation--configuration_xlm_roberta.XLMRobertaFlashConfig",
9
+ "AutoModel": "jinaai/xlm-roberta-flash-implementation--modeling_lora.XLMRobertaLoRA",
10
+ "AutoModelForMaskedLM": "jinaai/xlm-roberta-flash-implementation--modeling_xlm_roberta.XLMRobertaForMaskedLM",
11
+ "AutoModelForPreTraining": "jinaai/xlm-roberta-flash-implementation--modeling_xlm_roberta.XLMRobertaForPreTraining"
12
+ },
13
+ "bos_token_id": 0,
14
+ "classifier_dropout": null,
15
+ "emb_pooler": null,
16
+ "eos_token_id": 2,
17
+ "hidden_act": "gelu",
18
+ "hidden_dropout_prob": 0.1,
19
+ "hidden_size": 1024,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 4096,
22
+ "layer_norm_eps": 1e-05,
23
+ "load_trained_adapters": true,
24
+ "lora_adaptations": [
25
+ "retrieval.query",
26
+ "retrieval.passage",
27
+ "separation",
28
+ "classification",
29
+ "text-matching"
30
+ ],
31
+ "lora_alpha": 1,
32
+ "lora_dropout_p": 0.0,
33
+ "lora_main_params_trainable": false,
34
+ "lora_rank": 4,
35
+ "matryoshka_dimensions": [
36
+ 32,
37
+ 64,
38
+ 128,
39
+ 256,
40
+ 512,
41
+ 768,
42
+ 1024
43
+ ],
44
+ "max_position_embeddings": 8194,
45
+ "model_type": "xlm-roberta",
46
+ "num_attention_heads": 16,
47
+ "num_hidden_layers": 24,
48
+ "output_past": true,
49
+ "pad_token_id": 1,
50
+ "position_embedding_type": "rotary",
51
+ "rotary_emb_base": 20000.0,
52
+ "task_instructions": {
53
+ "classification": "",
54
+ "retrieval.passage": "Represent the document for retrieval: ",
55
+ "retrieval.query": "Represent the query for retrieving evidence documents: ",
56
+ "separation": "",
57
+ "text-matching": ""
58
+ },
59
+ "torch_dtype": "bfloat16",
60
+ "transformers_version": "4.45.2",
61
+ "truncate_dim": null,
62
+ "type_vocab_size": 1,
63
+ "use_cache": true,
64
+ "use_flash_attn": true,
65
+ "use_reentrant": false,
66
+ "vocab_size": 46528
67
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebcf07309511d92fd3a622a6d9a410335bd3cc81b3e5df734b3c2af5dbf474c7
3
+ size 721692520
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "46466": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 8192,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "tokenizer_class": "XLMRobertaTokenizer",
53
+ "unk_token": "<unk>"
54
+ }