Hugging Face's logo

BenjaminTT
/
NLPGroupProject-Finetune-Funnel-Transformer

Multiple Choice
Transformers
Safetensors
funnel
Generated from Trainer
Inference Endpoints
Model card Files Community
BenjaminTT commited on
Commit
fbd64cf
•
1 Parent(s): d61ed51

Training in progress, step 500

Browse files
Files changed (7) hide show
  1. config.json +40 -0
  2. model.safetensors +3 -0
  3. special_tokens_map.json +51 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +75 -0
  6. training_args.bin +3 -0
  7. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "funnel-transformer/intermediate-base",
3
+ "activation_dropout": 0.0,
4
+ "architectures": [
5
+ "FunnelForMultipleChoice"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "attention_type": "relative_shift",
9
+ "block_repeats": [
10
+ 1,
11
+ 1,
12
+ 1
13
+ ],
14
+ "block_sizes": [
15
+ 6,
16
+ 6,
17
+ 6
18
+ ],
19
+ "d_head": 64,
20
+ "d_inner": 3072,
21
+ "d_model": 768,
22
+ "hidden_act": "gelu_new",
23
+ "hidden_dropout": 0.1,
24
+ "initializer_range": 0.1,
25
+ "initializer_std": null,
26
+ "layer_norm_eps": 1e-09,
27
+ "max_position_embeddings": 512,
28
+ "model_type": "funnel",
29
+ "n_head": 12,
30
+ "num_decoder_layers": 2,
31
+ "pool_q_only": true,
32
+ "pooling_type": "mean",
33
+ "rel_attn_type": "factorized",
34
+ "separate_cls": true,
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.40.0",
37
+ "truncate_seq": true,
38
+ "type_vocab_size": 3,
39
+ "vocab_size": 30522
40
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f18d6108da8506a08d9900361827d5d0011e5dec63169930c9ca8bd232ed7f3
3
+ size 649194004
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
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": "</s>",
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 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "96": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "97": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "100": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "101": {
36
+ "content": "<cls>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "102": {
44
+ "content": "<sep>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "103": {
52
+ "content": "<mask>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ },
60
+ "bos_token": "<s>",
61
+ "clean_text": true,
62
+ "clean_up_tokenization_spaces": true,
63
+ "cls_token": "<cls>",
64
+ "do_lower_case": true,
65
+ "eos_token": "</s>",
66
+ "mask_token": "<mask>",
67
+ "model_max_length": 512,
68
+ "pad_token": "<pad>",
69
+ "sep_token": "<sep>",
70
+ "strip_accents": null,
71
+ "tokenize_chinese_chars": true,
72
+ "tokenizer_class": "FunnelTokenizer",
73
+ "unk_token": "<unk>",
74
+ "wordpieces_prefix": "##"
75
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8c0866477666e334770cb9bdf95668105c9c0711d0dbf5b0128c1eaf53fb14f
3
+ size 5048
vocab.txt ADDED
The diff for this file is too large to render. See raw diff