Hugging Face's logo

jangedoo
/
all-MiniLM-L6-v2-nepali

Sentence Similarity
sentence-transformers
TensorBoard
Safetensors
English
Nepali
bert
feature-extraction
Generated from Trainer
dataset_size:850049
loss:MultipleNegativesSymmetricRankingLoss
loss:MSELoss
Eval Results
text-embeddings-inference
Inference Endpoints
Model card Files Metrics Community
jangedoo commited on
Commit
e7821f2
•
1 Parent(s): fd3e3dc

Training in progress, step 100

Browse files
Files changed (11) hide show
  1. config.json +26 -0
  2. model.safetensors +3 -0
  3. runs/Aug18_21-36-37_6bab8749950a/events.out.tfevents.1724017009.6bab8749950a.248.0 +3 -0
  4. runs/Aug18_21-37-21_6bab8749950a/events.out.tfevents.1724017044.6bab8749950a.248.1 +3 -0
  5. runs/Aug18_21-38-20_6bab8749950a/events.out.tfevents.1724017105.6bab8749950a.248.2 +3 -0
  6. runs/Aug18_21-47-55_6bab8749950a/events.out.tfevents.1724017691.6bab8749950a.248.3 +3 -0
  7. special_tokens_map.json +37 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +64 -0
  10. training_args.bin +3 -0
  11. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sentence-transformers/all-MiniLM-L6-v2",
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 384,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 1536,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 6,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.42.4",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeeed220391cd3ee4d199eb6ce5b121ee8a37b64ce838504130e8434fe40f66f
3
+ size 90864192
runs/Aug18_21-36-37_6bab8749950a/events.out.tfevents.1724017009.6bab8749950a.248.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1de137f232269a2a9cc4a33cafe1a1ee6c199c7fe27e0b14b29c54c7a46e2ee3
3
+ size 4576
runs/Aug18_21-37-21_6bab8749950a/events.out.tfevents.1724017044.6bab8749950a.248.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b36b82c1ae4e19be7fd1480cd35615141d8afa5989dc2af97fe71611d5fbe7c4
3
+ size 4576
runs/Aug18_21-38-20_6bab8749950a/events.out.tfevents.1724017105.6bab8749950a.248.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61d5422eb11c42a026999933b946a3bcc65652c43f17a9c3881ccc99bfb193bd
3
+ size 6096
runs/Aug18_21-47-55_6bab8749950a/events.out.tfevents.1724017691.6bab8749950a.248.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43cca48261900e49157962ecc63c577a61e9a9643c3aa89189432e732c4d3987
3
+ size 5798
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "max_length": 128,
50
+ "model_max_length": 256,
51
+ "never_split": null,
52
+ "pad_to_multiple_of": null,
53
+ "pad_token": "[PAD]",
54
+ "pad_token_type_id": 0,
55
+ "padding_side": "right",
56
+ "sep_token": "[SEP]",
57
+ "stride": 0,
58
+ "strip_accents": null,
59
+ "tokenize_chinese_chars": true,
60
+ "tokenizer_class": "BertTokenizer",
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "longest_first",
63
+ "unk_token": "[UNK]"
64
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6885d0026ef7385d63dca2c9042ff34aa0601c072fc22cb0d3a5bbd3174f8543
3
+ size 5432
vocab.txt ADDED
The diff for this file is too large to render. See raw diff