Hugging Face's logo

anaghaj111
/
codebert-base-code-embed-mrl-langchain-langgraph

Sentence Similarity
sentence-transformers
Safetensors
English
roberta
feature-extraction
dense
Generated from Trainer
dataset_size:180
loss:MatryoshkaLoss
loss:MultipleNegativesRankingLoss
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
 Community
anaghaj111 commited on
Commit
603f647
·
verified ·
1 Parent(s): aeb55ce

Add new SentenceTransformer model

Browse files
Files changed (8) hide show
  1. README.md +0 -0
  2. config.json +1 -4
  3. config_sentence_transformers.json +3 -3
  4. merges.txt +0 -0
  5. model.safetensors +2 -2
  6. special_tokens_map.json +51 -0
  7. tokenizer_config.json +50 -3
  8. vocab.json +0 -0
README.md CHANGED
The diff for this file is too large to render. See raw diff
 
config.json CHANGED
@@ -1,5 +1,4 @@
1
  {
2
- "add_cross_attention": false,
3
  "architectures": [
4
  "RobertaModel"
5
  ],
@@ -13,7 +12,6 @@
13
  "hidden_size": 768,
14
  "initializer_range": 0.02,
15
  "intermediate_size": 3072,
16
- "is_decoder": false,
17
  "layer_norm_eps": 1e-05,
18
  "max_position_embeddings": 514,
19
  "model_type": "roberta",
@@ -22,8 +20,7 @@
22
  "output_past": true,
23
  "pad_token_id": 1,
24
  "position_embedding_type": "absolute",
25
- "tie_word_embeddings": true,
26
- "transformers_version": "5.0.0",
27
  "type_vocab_size": 1,
28
  "use_cache": true,
29
  "vocab_size": 50265
 
1
  {
 
2
  "architectures": [
3
  "RobertaModel"
4
  ],
 
12
  "hidden_size": 768,
13
  "initializer_range": 0.02,
14
  "intermediate_size": 3072,
 
15
  "layer_norm_eps": 1e-05,
16
  "max_position_embeddings": 514,
17
  "model_type": "roberta",
 
20
  "output_past": true,
21
  "pad_token_id": 1,
22
  "position_embedding_type": "absolute",
23
+ "transformers_version": "4.57.3",
 
24
  "type_vocab_size": 1,
25
  "use_cache": true,
26
  "vocab_size": 50265
config_sentence_transformers.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "model_type": "SentenceTransformer",
3
  "__version__": {
4
- "sentence_transformers": "5.2.1",
5
- "transformers": "5.0.0",
6
- "pytorch": "2.10.0"
7
  },
8
  "prompts": {
9
  "query": "",
 
1
  {
2
  "model_type": "SentenceTransformer",
3
  "__version__": {
4
+ "sentence_transformers": "5.2.2",
5
+ "transformers": "4.57.3",
6
+ "pytorch": "2.9.1"
7
  },
8
  "prompts": {
9
  "query": "",
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:180fd754acf3876c3ede6d2ba40e6ba3eaecee1115d82481953408051451d3ca
3
- size 498604880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e336af50d5161e6c2a23fc2b76178dbe1279e6e07b1ba260d9c192956fd1d839
3
+ size 498604904
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
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": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer_config.json CHANGED
@@ -1,18 +1,65 @@
1
  {
2
  "add_prefix_space": false,
3
- "backend": "tokenizers",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  "bos_token": "<s>",
5
  "clean_up_tokenization_spaces": false,
6
  "cls_token": "<s>",
7
  "eos_token": "</s>",
8
  "errors": "replace",
9
- "is_local": false,
10
  "mask_token": "<mask>",
 
11
  "model_max_length": 512,
12
- "model_specific_special_tokens": {},
13
  "pad_token": "<pad>",
 
 
14
  "sep_token": "</s>",
 
15
  "tokenizer_class": "RobertaTokenizer",
16
  "trim_offsets": true,
 
 
17
  "unk_token": "<unk>"
18
  }
 
1
  {
2
  "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
  "bos_token": "<s>",
46
  "clean_up_tokenization_spaces": false,
47
  "cls_token": "<s>",
48
  "eos_token": "</s>",
49
  "errors": "replace",
50
+ "extra_special_tokens": {},
51
  "mask_token": "<mask>",
52
+ "max_length": 512,
53
  "model_max_length": 512,
54
+ "pad_to_multiple_of": null,
55
  "pad_token": "<pad>",
56
+ "pad_token_type_id": 0,
57
+ "padding_side": "right",
58
  "sep_token": "</s>",
59
+ "stride": 0,
60
  "tokenizer_class": "RobertaTokenizer",
61
  "trim_offsets": true,
62
+ "truncation_side": "right",
63
+ "truncation_strategy": "longest_first",
64
  "unk_token": "<unk>"
65
  }
vocab.json ADDED
The diff for this file is too large to render. See raw diff