Hugging Face's logo

gerbejon
/
longcoder-html-nodes-mc-classifier

Safetensors
longformer
Model card Files
xet
Community
gerbejon commited on
Commit
7ab6611
·
verified ·
1 Parent(s): c6d9deb

Training in progress, epoch 1

Browse files
Files changed (8) hide show
  1. config.json +68 -0
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +51 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +58 -0
  7. training_args.bin +3 -0
  8. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LongformerForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "attention_window": [
7
+ 1024,
8
+ 1024,
9
+ 1024,
10
+ 1024,
11
+ 1024,
12
+ 1024,
13
+ 1024,
14
+ 1024,
15
+ 1024,
16
+ 1024,
17
+ 1024,
18
+ 1024
19
+ ],
20
+ "bos_token_id": 0,
21
+ "classifier_dropout": null,
22
+ "eos_token_id": 2,
23
+ "gradient_checkpointing": false,
24
+ "hidden_act": "gelu",
25
+ "hidden_dropout_prob": 0.1,
26
+ "hidden_size": 768,
27
+ "id2label": {
28
+ "0": "0",
29
+ "1": "1",
30
+ "2": "2",
31
+ "3": "3",
32
+ "4": "4",
33
+ "5": "5",
34
+ "6": "6",
35
+ "7": "7",
36
+ "8": "multiple"
37
+ },
38
+ "initializer_range": 0.02,
39
+ "intermediate_size": 3072,
40
+ "is_decoder_only": true,
41
+ "label2id": {
42
+ "0": 0,
43
+ "1": 1,
44
+ "2": 2,
45
+ "3": 3,
46
+ "4": 4,
47
+ "5": 5,
48
+ "6": 6,
49
+ "7": 7,
50
+ "multiple": 8
51
+ },
52
+ "layer_norm_eps": 1e-05,
53
+ "max_position_embeddings": 4098,
54
+ "model_type": "longformer",
55
+ "num_attention_heads": 12,
56
+ "num_hidden_layers": 12,
57
+ "onnx_export": false,
58
+ "output_past": true,
59
+ "pad_token_id": 1,
60
+ "position_embedding_type": "absolute",
61
+ "problem_type": "single_label_classification",
62
+ "sep_token_id": 2,
63
+ "torch_dtype": "float32",
64
+ "transformers_version": "4.52.4",
65
+ "type_vocab_size": 10,
66
+ "use_cache": true,
67
+ "vocab_size": 51416
68
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:768c2d7e585c05c39eef382308b5a8c4da3ebab88ef9cf5b8c0a14efb82764ca
3
+ size 598263236
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
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 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 4096,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03fbd21935b4dfd469f2ce6f0a15c6216087db60a8dd5c7bfe113bd02a1ee74a
3
+ size 5713
vocab.json ADDED
The diff for this file is too large to render. See raw diff