Hugging Face's logo

nimishph
/
anvesa-code-1b

Feature Extraction
ONNX
modernbert
code-search
retrieval
anvesa
text-embeddings-inference
Model card Files
xet
 Community
nimishph commited on
Commit
8d855d8
·
verified ·
1 Parent(s): a64c65f

anvesa-code-1b: ONNX fp32

Browse files
Files changed (6) hide show
  1. .gitattributes +1 -0
  2. config.json +85 -0
  3. model.onnx +3 -0
  4. model.onnx_data +3 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +24 -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
+ model.onnx_data filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertModel"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 50281,
8
+ "causal_mask": false,
9
+ "classifier_activation": "gelu",
10
+ "classifier_bias": false,
11
+ "classifier_dropout": 0.0,
12
+ "classifier_pooling": "mean",
13
+ "cls_token_id": 50281,
14
+ "decoder_bias": true,
15
+ "deterministic_flash_attn": false,
16
+ "dtype": "float32",
17
+ "embedding_dropout": 0.0,
18
+ "eos_token_id": 50282,
19
+ "global_attn_every_n_layers": 3,
20
+ "gradient_checkpointing": false,
21
+ "hidden_activation": "gelu",
22
+ "hidden_size": 1792,
23
+ "initializer_cutoff_factor": 2.0,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 3840,
26
+ "is_causal": false,
27
+ "layer_norm_eps": 1e-05,
28
+ "layer_types": [
29
+ "full_attention",
30
+ "sliding_attention",
31
+ "sliding_attention",
32
+ "full_attention",
33
+ "sliding_attention",
34
+ "sliding_attention",
35
+ "full_attention",
36
+ "sliding_attention",
37
+ "sliding_attention",
38
+ "full_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "full_attention",
42
+ "sliding_attention",
43
+ "sliding_attention",
44
+ "full_attention",
45
+ "sliding_attention",
46
+ "sliding_attention",
47
+ "full_attention",
48
+ "sliding_attention",
49
+ "sliding_attention",
50
+ "full_attention",
51
+ "sliding_attention",
52
+ "sliding_attention",
53
+ "full_attention",
54
+ "sliding_attention",
55
+ "sliding_attention",
56
+ "full_attention"
57
+ ],
58
+ "local_attention": 128,
59
+ "max_position_embeddings": 7999,
60
+ "mlp_bias": false,
61
+ "mlp_dropout": 0.0,
62
+ "model_type": "modernbert",
63
+ "norm_bias": false,
64
+ "norm_eps": 1e-05,
65
+ "num_attention_heads": 28,
66
+ "num_hidden_layers": 28,
67
+ "pad_token_id": 50283,
68
+ "position_embedding_type": "sans_pos",
69
+ "rope_parameters": {
70
+ "full_attention": {
71
+ "rope_theta": 160000.0,
72
+ "rope_type": "default"
73
+ },
74
+ "sliding_attention": {
75
+ "rope_theta": 160000.0,
76
+ "rope_type": "default"
77
+ }
78
+ },
79
+ "sep_token_id": 50282,
80
+ "sparse_pred_ignore_index": -100,
81
+ "sparse_prediction": false,
82
+ "tie_word_embeddings": true,
83
+ "transformers_version": "5.20.2",
84
+ "vocab_size": 50368
85
+ }
model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df33320b7ea9a50823b04f5b189fa4077f72fa530274a36e9634d1e4e1cdeae1
3
+ size 1034044
model.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bf8038ac17358a505091b27816beac37a32e64cf3d928212b36a634ef775805
3
+ size 4112202752
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "is_local": true,
6
+ "local_files_only": false,
7
+ "mask_token": "[MASK]",
8
+ "max_length": 256,
9
+ "model_input_names": [
10
+ "input_ids",
11
+ "attention_mask"
12
+ ],
13
+ "model_max_length": 8192,
14
+ "pad_to_multiple_of": null,
15
+ "pad_token": "[PAD]",
16
+ "pad_token_type_id": 0,
17
+ "padding_side": "right",
18
+ "sep_token": "[SEP]",
19
+ "stride": 0,
20
+ "tokenizer_class": "TokenizersBackend",
21
+ "truncation_side": "right",
22
+ "truncation_strategy": "longest_first",
23
+ "unk_token": "[UNK]"
24
+ }