franknoh commited on
Commit
3dce9c6
·
verified ·
1 Parent(s): d7ad2df

Upload 5 files

Browse files
.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
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForMaskedLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.1,
7
+ "bos_token_id": 1,
8
+ "classifier_activation": "gelu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 1,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "embedding_dropout": 0,
16
+ "eos_token_id": 2,
17
+ "global_attn_every_n_layers": 3,
18
+ "global_rope_theta": 160000,
19
+ "gradient_checkpointing": false,
20
+ "hidden_activation": "gelu",
21
+ "hidden_size": 768,
22
+ "initializer_cutoff_factor": 2,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 1152,
25
+ "layer_norm_eps": 0.00001,
26
+ "local_attention": 128,
27
+ "local_rope_theta": 10000,
28
+ "max_position_embeddings": 8192,
29
+ "mlp_bias": false,
30
+ "mlp_dropout": 0,
31
+ "model_type": "modernbert",
32
+ "norm_bias": false,
33
+ "norm_eps": 0.00001,
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 22,
36
+ "pad_token_id": 0,
37
+ "position_embedding_type": "absolute",
38
+ "reference_compile": null,
39
+ "sep_token_id": 2,
40
+ "sparse_pred_ignore_index": -100,
41
+ "sparse_prediction": false,
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.55.2",
44
+ "vocab_size": 131072
45
+ }
flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:065e767d2b6b0711cc76e7dd9621c97d17c40f30813c28acfd6f51d422136d2d
3
+ size 846871982
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd11e5269f05ad61a5f875333c655e04b716e06cf96c5f7be8136d8f7d843753
3
+ size 846880496
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8235dce74efa76b2f99d47f81e48518714393a5b34fb9f7c8de681810995e90a
3
+ size 17078372
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff