yusufcelebi commited on
Commit
ae0652e
·
verified ·
1 Parent(s): bde163c

Upload model.safetensors & tokenizer (2025-08-14T11:49:37.371869Z)

Browse files
.gitattributes ADDED
@@ -0,0 +1 @@
 
 
1
+ model.safetensors filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "mean",
12
+ "cls_token_id": 2,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "embedding_dropout": 0.0,
16
+ "eos_token_id": 50282,
17
+ "global_attn_every_n_layers": 3,
18
+ "global_rope_theta": 160000.0,
19
+ "gradient_checkpointing": false,
20
+ "hidden_activation": "gelu",
21
+ "hidden_size": 768,
22
+ "initializer_cutoff_factor": 2.0,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 1152,
25
+ "layer_norm_eps": 1e-05,
26
+ "local_attention": 128,
27
+ "local_rope_theta": 10000.0,
28
+ "mask_token_id": 4,
29
+ "max_position_embeddings": 8192,
30
+ "mlp_bias": false,
31
+ "mlp_dropout": 0.0,
32
+ "model_type": "modernbert",
33
+ "norm_bias": false,
34
+ "norm_eps": 1e-05,
35
+ "num_attention_heads": 12,
36
+ "num_hidden_layers": 22,
37
+ "pad_token_id": 0,
38
+ "position_embedding_type": "absolute",
39
+ "repad_logits_with_grad": false,
40
+ "sep_token_id": 3,
41
+ "sparse_pred_ignore_index": -100,
42
+ "sparse_prediction": false,
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.55.0",
45
+ "unk_token_id": 1,
46
+ "vocab_size": 32000
47
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de1e2bd523bda35b7ca8e3806a6dc912f093af47ef0c9939ee3102421098443d
3
+ size 539643640
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "max_len": 8192,
51
+ "max_length": 8192,
52
+ "model_input_names": [
53
+ "input_ids",
54
+ "attention_mask"
55
+ ],
56
+ "model_max_length": 8192,
57
+ "never_split": null,
58
+ "pad_to_multiple_of": null,
59
+ "pad_token": "[PAD]",
60
+ "pad_token_type_id": 0,
61
+ "padding_side": "right",
62
+ "sep_token": "[SEP]",
63
+ "stride": 0,
64
+ "strip_accents": false,
65
+ "tokenize_chinese_chars": true,
66
+ "tokenizer_class": "PreTrainedTokenizerFast",
67
+ "truncation_side": "right",
68
+ "truncation_strategy": "longest_first",
69
+ "unk_token": "[UNK]"
70
+ }
training_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "teacher_id": "BAAI/bge-m3",
3
+ "student_base": "newmindai/modernbert-base-tr-uncased-allnli-stsb",
4
+ "dataset": "parsak/msmarco-tr",
5
+ "max_len": 128,
6
+ "batch_size": 128,
7
+ "epochs": 1,
8
+ "lr": 2e-05,
9
+ "warmup_ratio": 0.06,
10
+ "weight_decay": 0.01,
11
+ "neg_limit": 30,
12
+ "val_frac": 0.1,
13
+ "val_eval_q": 200,
14
+ "alpha_rank": 0.7,
15
+ "beta_kd": 0.3,
16
+ "kd_align_w": 0.5,
17
+ "kd_list_w": 0.5,
18
+ "temperature": 0.1,
19
+ "use_in_batch_negs": true,
20
+ "timestamp": "2025-08-14T11:41:21.768368Z"
21
+ }