Hugging Face's logo

ProximaAI
/
urnova-95m

Fill-Mask
Transformers
Safetensors
Urdu
modernbert
urdu
encoder
masked-language-modeling
long-context
8k-context
urblimp
zero-shot
benchmark
Model card Files
xet
 Community
mahwizzzz commited on
Commit
dc9c7e6
·
verified ·
1 Parent(s): 2532bb0

ziwham

Browse files
Files changed (7) hide show
  1. config.json +46 -0
  2. model.safetensors +3 -0
  3. native-export-parity.json +8 -0
  4. special_tokens_map.json +51 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +55 -0
  7. urnova_identity.json +5 -0
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForMaskedLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 2,
8
+ "classifier_activation": "gelu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "cls",
12
+ "cls_token_id": 2,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "dtype": "float32",
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 3,
18
+ "global_attn_every_n_layers": 3,
19
+ "global_rope_theta": 160000.0,
20
+ "hidden_activation": "gelu",
21
+ "hidden_size": 640,
22
+ "initializer_cutoff_factor": 2.0,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 960,
25
+ "local_attention": 128,
26
+ "local_rope_theta": 10000.0,
27
+ "mask_token_id": 4,
28
+ "max_position_embeddings": 8192,
29
+ "mlp_bias": false,
30
+ "mlp_dropout": 0.0,
31
+ "model_type": "modernbert",
32
+ "norm_bias": false,
33
+ "norm_eps": 1e-05,
34
+ "num_attention_heads": 10,
35
+ "num_hidden_layers": 18,
36
+ "pad_token_id": 0,
37
+ "repad_logits_with_grad": false,
38
+ "sep_token_id": 3,
39
+ "sparse_pred_ignore_index": -100,
40
+ "sparse_prediction": true,
41
+ "tokenizer_identity_sha256": "7dbaf80b50202ab56ec3e8d1b169bba4fda88751b9076c30692b6c0a78e2cef0",
42
+ "tokenizer_manifest_identity_sha256": "f5be87232500f26ccd626fa352c53217651f8031a840f23d824dfb1a838c6b30",
43
+ "transformers_version": "4.57.6",
44
+ "unk_token_id": 1,
45
+ "vocab_size": 50048
46
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7eb0123482c3299b952572b4a0d3fd6961057a15698fc238348bdb929097ba3b
3
+ size 380745552
native-export-parity.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "atol": 2e-05,
3
+ "max_absolute_error": 8.106231689453125e-06,
4
+ "max_relative_error": 0.08237548172473907,
5
+ "passed": true,
6
+ "rtol": 0.0002,
7
+ "token_count": 16
8
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "[CLS]",
47
+ "eos_token": "[SEP]",
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 8192,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "tokenizer_class": "PreTrainedTokenizerFast",
54
+ "unk_token": "[UNK]"
55
+ }
urnova_identity.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "tokenizer_identity_sha256": "7dbaf80b50202ab56ec3e8d1b169bba4fda88751b9076c30692b6c0a78e2cef0",
3
+ "tokenizer_manifest_identity_sha256": "f5be87232500f26ccd626fa352c53217651f8031a840f23d824dfb1a838c6b30",
4
+ "tokenizer_manifest_sha256": "61815333a6199cd1e54470d384f726e49781a4e9127c8dda5a250599197ba1a5"
5
+ }