Hugging Face's logo

johnnyboycurtis
/
ModernBERT-small-v2

Sentence Similarity
sentence-transformers
Safetensors
modernbert
feature-extraction
dense
Generated from Trainer
dataset_size:3375201
loss:MSELoss
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
Community
johnnyboycurtis commited on
Commit
3a7af12
·
verified ·
1 Parent(s): 996a984

Upload folder using huggingface_hub

Browse files
Files changed (15) hide show
  1. 1_Pooling/config.json +10 -0
  2. README.md +0 -0
  3. config.json +64 -0
  4. config_sentence_transformers.json +14 -0
  5. model.safetensors +3 -0
  6. modules.json +14 -0
  7. optimizer.pt +3 -0
  8. rng_state.pth +3 -0
  9. scaler.pt +3 -0
  10. scheduler.pt +3 -0
  11. sentence_bert_config.json +4 -0
  12. tokenizer.json +0 -0
  13. tokenizer_config.json +16 -0
  14. trainer_state.json +0 -0
  15. training_args.bin +3 -0
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 384,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
README.md CHANGED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertModel"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 50281,
8
+ "classifier_activation": "gelu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "cls",
12
+ "cls_token_id": 50281,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "dtype": "float32",
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 50282,
18
+ "global_attn_every_n_layers": 3,
19
+ "hidden_activation": "gelu",
20
+ "hidden_size": 384,
21
+ "initializer_cutoff_factor": 2.0,
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 768,
24
+ "layer_types": [
25
+ "full_attention",
26
+ "sliding_attention",
27
+ "sliding_attention",
28
+ "full_attention",
29
+ "sliding_attention",
30
+ "sliding_attention",
31
+ "full_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "full_attention",
35
+ "sliding_attention",
36
+ "sliding_attention"
37
+ ],
38
+ "local_attention": 128,
39
+ "max_position_embeddings": 1024,
40
+ "mlp_bias": false,
41
+ "mlp_dropout": 0.0,
42
+ "model_type": "modernbert",
43
+ "norm_bias": false,
44
+ "norm_eps": 1e-05,
45
+ "num_attention_heads": 6,
46
+ "num_hidden_layers": 12,
47
+ "pad_token_id": 50283,
48
+ "rope_parameters": {
49
+ "full_attention": {
50
+ "rope_theta": 160000.0,
51
+ "rope_type": "default"
52
+ },
53
+ "sliding_attention": {
54
+ "rope_theta": 10000.0,
55
+ "rope_type": "default"
56
+ }
57
+ },
58
+ "sep_token_id": 50282,
59
+ "sparse_pred_ignore_index": -100,
60
+ "sparse_prediction": false,
61
+ "tie_word_embeddings": true,
62
+ "transformers_version": "5.1.0",
63
+ "vocab_size": 50368
64
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_type": "SentenceTransformer",
3
+ "__version__": {
4
+ "sentence_transformers": "5.2.2",
5
+ "transformers": "5.1.0",
6
+ "pytorch": "2.7.1+cu128"
7
+ },
8
+ "prompts": {
9
+ "query": "",
10
+ "document": ""
11
+ },
12
+ "default_prompt_name": null,
13
+ "similarity_fn_name": "cosine"
14
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98d412f6207754b98a45308942cbdc6bf457063eb4490cf2f837c674da10c656
3
+ size 148189656
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ }
14
+ ]
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7066a060b4f5b7213739d87132630f0868fc3d4e85c5f148f651ffd7fe0397cd
3
+ size 296428043
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:135053a075b58178b50a915c4067e06918ddabe34a7915a978e459fdfa648c81
3
+ size 14645
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc97b1973eb956efd7e80046d23db9360d2e1af789c40ae4533579ff4abd3133
3
+ size 1383
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5f56c619e2d5fc31bef7a0aad9e94df4c2446f2888f64fb29d2d5ad3f6d233f
3
+ size 1465
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 1024,
3
+ "do_lower_case": false
4
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "is_local": true,
6
+ "mask_token": "[MASK]",
7
+ "model_input_names": [
8
+ "input_ids",
9
+ "attention_mask"
10
+ ],
11
+ "model_max_length": 8192,
12
+ "pad_token": "[PAD]",
13
+ "sep_token": "[SEP]",
14
+ "tokenizer_class": "TokenizersBackend",
15
+ "unk_token": "[UNK]"
16
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6afd6a2a601d64240a77c598b9a55481931ce2653300111e6a36ed83a9c58da4
3
+ size 5521