Hugging Face's logo

ai4data
/
devdata-search-harrier-270m-cmnrl

Feature Extraction
sentence-transformers
Safetensors
gemma3_text
retrieval
devdata-search
text-embeddings-inference
Model card Files
xet
 Community
avsolatorio commited on
Commit
75a068d
·
verified ·
1 Parent(s): 8818d7f

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 +65 -0
  5. config_sentence_transformers.json +17 -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 +31 -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": 640,
3
+ "pooling_mode": "lasttoken",
4
+ "include_prompt": true
5
+ }
README.md ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_sliding_window_pattern": 1,
3
+ "architectures": [
4
+ "Gemma3TextModel"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "attn_logit_softcapping": null,
9
+ "bos_token_id": 2,
10
+ "dtype": "bfloat16",
11
+ "eos_token_id": 1,
12
+ "final_logit_softcapping": null,
13
+ "head_dim": 256,
14
+ "hidden_activation": "gelu_pytorch_tanh",
15
+ "hidden_size": 640,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 2048,
18
+ "layer_types": [
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention"
37
+ ],
38
+ "max_position_embeddings": 32768,
39
+ "model_type": "gemma3_text",
40
+ "num_attention_heads": 4,
41
+ "num_hidden_layers": 18,
42
+ "num_key_value_heads": 1,
43
+ "pad_token_id": 0,
44
+ "query_pre_attn_scalar": 256,
45
+ "rms_norm_eps": 1e-06,
46
+ "rope_parameters": {
47
+ "full_attention": {
48
+ "rope_theta": 1000000.0,
49
+ "rope_type": "default"
50
+ },
51
+ "rope_theta": null,
52
+ "rope_type": "default",
53
+ "sliding_attention": {
54
+ "rope_theta": 10000.0,
55
+ "rope_type": "default"
56
+ }
57
+ },
58
+ "sliding_window": 512,
59
+ "sliding_window_pattern": 1,
60
+ "tie_word_embeddings": true,
61
+ "transformers_version": "5.12.0",
62
+ "use_bidirectional_attention": false,
63
+ "use_cache": false,
64
+ "vocab_size": 262144
65
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "bitext_query": "Instruct: Retrieve parallel sentences\nQuery: ",
11
+ "document": "",
12
+ "query": "",
13
+ "sts_query": "Instruct: Retrieve semantically similar text\nQuery: ",
14
+ "web_search_query": "Instruct: Given a web search query, retrieve relevant passages that answer the query\nQuery: "
15
+ },
16
+ "similarity_fn_name": "cosine"
17
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef5c40c03964cb952ad12ade7d14a925ed6478c743489fdc0a7eb99c8a899240
3
+ size 536221640
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:d6c4c6c7ecda463434a6fafacc071da6de4a1c644d58d2c14de03520ecb8ff32
3
+ size 33385260
tokenizer_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "boi_token": "<start_of_image>",
4
+ "bos_token": "<bos>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eoi_token": "<end_of_image>",
7
+ "eos_token": "<eos>",
8
+ "image_token": "<image_soft_token>",
9
+ "is_local": true,
10
+ "local_files_only": false,
11
+ "mask_token": "<mask>",
12
+ "max_length": 512,
13
+ "model_max_length": 512,
14
+ "model_specific_special_tokens": {
15
+ "boi_token": "<start_of_image>",
16
+ "eoi_token": "<end_of_image>",
17
+ "image_token": "<image_soft_token>"
18
+ },
19
+ "pad_to_multiple_of": null,
20
+ "pad_token": "<pad>",
21
+ "pad_token_type_id": 0,
22
+ "padding_side": "right",
23
+ "sp_model_kwargs": null,
24
+ "spaces_between_special_tokens": false,
25
+ "stride": 0,
26
+ "tokenizer_class": "GemmaTokenizer",
27
+ "truncation_side": "right",
28
+ "truncation_strategy": "longest_first",
29
+ "unk_token": "<unk>",
30
+ "use_default_system_prompt": false
31
+ }