1024m commited on
Commit
ecb3612
·
verified ·
1 Parent(s): c5bbfde

Upload model trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (2) hide show
  1. config.json +123 -0
  2. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForSequenceClassification"
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": 50281,
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": 1024,
22
+ "id2label": {
23
+ "0": "NA",
24
+ "1": "Incomplete",
25
+ "2": "WNB",
26
+ "3": "SwapDividend",
27
+ "4": "Mult",
28
+ "5": "FlipChange",
29
+ "6": "Irrelevant",
30
+ "7": "Wrong_Fraction",
31
+ "8": "Additive",
32
+ "9": "Not_variable",
33
+ "10": "Adding_terms",
34
+ "11": "Inverse_operation",
35
+ "12": "Inversion",
36
+ "13": "Duplication",
37
+ "14": "Wrong_Operation",
38
+ "15": "Whole_numbers_larger",
39
+ "16": "Longer_is_bigger",
40
+ "17": "Ignores_zeroes",
41
+ "18": "Shorter_is_bigger",
42
+ "19": "Wrong_fraction",
43
+ "20": "Adding_across",
44
+ "21": "Denominator-only_change",
45
+ "22": "Incorrect_equivalent_fraction_addition",
46
+ "23": "Division",
47
+ "24": "Subtraction",
48
+ "25": "Unknowable",
49
+ "26": "Definition",
50
+ "27": "Interior",
51
+ "28": "Positive",
52
+ "29": "Tacking",
53
+ "30": "Wrong_term",
54
+ "31": "Firstterm",
55
+ "32": "Base_rate",
56
+ "33": "Multiplying_by_4",
57
+ "34": "Certainty",
58
+ "35": "Scale"
59
+ },
60
+ "initializer_cutoff_factor": 2.0,
61
+ "initializer_range": 0.02,
62
+ "intermediate_size": 2624,
63
+ "label2id": {
64
+ "Adding_across": 20,
65
+ "Adding_terms": 10,
66
+ "Additive": 8,
67
+ "Base_rate": 32,
68
+ "Certainty": 34,
69
+ "Definition": 26,
70
+ "Denominator-only_change": 21,
71
+ "Division": 23,
72
+ "Duplication": 13,
73
+ "Firstterm": 31,
74
+ "FlipChange": 5,
75
+ "Ignores_zeroes": 17,
76
+ "Incomplete": 1,
77
+ "Incorrect_equivalent_fraction_addition": 22,
78
+ "Interior": 27,
79
+ "Inverse_operation": 11,
80
+ "Inversion": 12,
81
+ "Irrelevant": 6,
82
+ "Longer_is_bigger": 16,
83
+ "Mult": 4,
84
+ "Multiplying_by_4": 33,
85
+ "NA": 0,
86
+ "Not_variable": 9,
87
+ "Positive": 28,
88
+ "Scale": 35,
89
+ "Shorter_is_bigger": 18,
90
+ "Subtraction": 24,
91
+ "SwapDividend": 3,
92
+ "Tacking": 29,
93
+ "Unknowable": 25,
94
+ "WNB": 2,
95
+ "Whole_numbers_larger": 15,
96
+ "Wrong_Fraction": 7,
97
+ "Wrong_Operation": 14,
98
+ "Wrong_fraction": 19,
99
+ "Wrong_term": 30
100
+ },
101
+ "layer_norm_eps": 1e-05,
102
+ "local_attention": 128,
103
+ "local_rope_theta": 10000.0,
104
+ "max_position_embeddings": 8192,
105
+ "mlp_bias": false,
106
+ "mlp_dropout": 0.0,
107
+ "model_type": "modernbert",
108
+ "norm_bias": false,
109
+ "norm_eps": 1e-05,
110
+ "num_attention_heads": 16,
111
+ "num_hidden_layers": 28,
112
+ "pad_token_id": 50283,
113
+ "position_embedding_type": "absolute",
114
+ "problem_type": "single_label_classification",
115
+ "repad_logits_with_grad": false,
116
+ "sep_token_id": 50282,
117
+ "sparse_pred_ignore_index": -100,
118
+ "sparse_prediction": false,
119
+ "torch_dtype": "bfloat16",
120
+ "transformers_version": "4.55.4",
121
+ "unsloth_version": "2025.10.1",
122
+ "vocab_size": 50368
123
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef60703823e7d14a67bc1b15f3e9b22b20c5f92b1d5e44c963b09a50e9f33aae
3
+ size 791754680