Hugging Face's logo

ai4data
/
devdata-search-granite-97m-multilingual-cmnrl

Feature Extraction
sentence-transformers
Safetensors
modernbert
retrieval
devdata-search
text-embeddings-inference
Model card Files
xet
 Community
avsolatorio commited on
Commit
035f7de
·
verified ·
1 Parent(s): 33ff0e9

Add new SentenceTransformer model

Browse files
Files changed (10) hide show
  1. .gitattributes +1 -0
  2. 1_Pooling/config.json +5 -0
  3. README.md +0 -0
  4. config.json +68 -0
  5. config_sentence_transformers.json +14 -0
  6. model.safetensors +3 -0
  7. modules.json +20 -0
  8. sentence_bert_config.json +10 -0
  9. tokenizer.json +3 -0
  10. tokenizer_config.json +25 -0
.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_Pooling/config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "embedding_dimension": 384,
3
+ "pooling_mode": "cls",
4
+ "include_prompt": false
5
+ }
README.md ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertModel"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 179934,
8
+ "classifier_activation": "silu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "cls",
12
+ "cls_token_id": 179934,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "dtype": "bfloat16",
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 179938,
18
+ "global_attn_every_n_layers": 3,
19
+ "gradient_checkpointing": false,
20
+ "hidden_activation": "silu",
21
+ "hidden_size": 384,
22
+ "initializer_cutoff_factor": 2.0,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 1536,
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
+ ],
40
+ "local_attention": 128,
41
+ "max_position_embeddings": 32768,
42
+ "mlp_bias": false,
43
+ "mlp_dropout": 0.0,
44
+ "model_type": "modernbert",
45
+ "norm_bias": false,
46
+ "norm_eps": 1e-05,
47
+ "num_attention_heads": 12,
48
+ "num_hidden_layers": 12,
49
+ "pad_token_id": 179935,
50
+ "position_embedding_type": "absolute",
51
+ "repad_logits_with_grad": false,
52
+ "rope_parameters": {
53
+ "full_attention": {
54
+ "rope_theta": 150000.0,
55
+ "rope_type": "default"
56
+ },
57
+ "sliding_attention": {
58
+ "rope_theta": 160000.0,
59
+ "rope_type": "default"
60
+ }
61
+ },
62
+ "sep_token_id": 179938,
63
+ "sparse_pred_ignore_index": -100,
64
+ "sparse_prediction": false,
65
+ "tie_word_embeddings": true,
66
+ "transformers_version": "5.12.0",
67
+ "vocab_size": 180000
68
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "pytorch": "2.12.0+cu130",
4
+ "sentence_transformers": "5.5.1",
5
+ "transformers": "5.12.0"
6
+ },
7
+ "default_prompt_name": null,
8
+ "model_type": "SentenceTransformer",
9
+ "prompts": {
10
+ "document": "",
11
+ "query": ""
12
+ },
13
+ "similarity_fn_name": "cosine"
14
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4ee53f43a726a2b913cb3bd99b02fd11fb3d2d42b01c6eb3ce77a829e233fa4
3
+ size 194889568
modules.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_Pooling",
12
+ "type": "sentence_transformers.sentence_transformer.modules.pooling.Pooling"
13
+ },
14
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Normalize",
18
+ "type": "sentence_transformers.sentence_transformer.modules.normalize.Normalize"
19
+ }
20
+ ]
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
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df82a441eb293660b0d1f44303bed3abe8ca33a13866eab0ce37451adcc767ff
3
+ size 25301669
tokenizer_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<|startoftext|>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "cls_token": "<|startoftext|>",
6
+ "eos_token": "<|return|>",
7
+ "is_local": true,
8
+ "local_files_only": false,
9
+ "mask_token": "[MASK]",
10
+ "max_length": 32768,
11
+ "model_input_names": [
12
+ "input_ids",
13
+ "attention_mask"
14
+ ],
15
+ "model_max_length": 512,
16
+ "pad_to_multiple_of": null,
17
+ "pad_token": "<|endoftext|>",
18
+ "pad_token_type_id": 0,
19
+ "padding_side": "right",
20
+ "sep_token": "<|return|>",
21
+ "stride": 0,
22
+ "tokenizer_class": "TokenizersBackend",
23
+ "truncation_side": "right",
24
+ "truncation_strategy": "longest_first"
25
+ }