Hugging Face's logo

youssef227
/
merge-my-models

Feature Extraction
Transformers
Safetensors
longformer
Merge
mergekit
lazymergekit
allenai/longformer-base-4096
gpt2
Inference Endpoints
Model card Files Community
youssef227 commited on
Commit
c0d0bef
•
1 Parent(s): ac99e3a

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. config.json +42 -34
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +15 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +57 -0
  7. vocab.json +0 -0
config.json CHANGED
@@ -1,35 +1,43 @@
1
  {
2
- "model_type": "longformer",
3
- "architectures": [
4
- "LongformerForMaskedLM"
5
- ],
6
- "hidden_size": 768,
7
- "num_attention_heads": 12,
8
- "num_hidden_layers": 12,
9
- "intermediate_size": 3072,
10
- "max_position_embeddings": 4096,
11
- "attention_window": [
12
- 512,
13
- 512,
14
- 512,
15
- 512,
16
- 512,
17
- 512,
18
- 512,
19
- 512,
20
- 512,
21
- 512,
22
- 512,
23
- 512
24
- ],
25
- "hidden_act": "gelu",
26
- "initializer_range": 0.02,
27
- "layer_norm_eps": 1e-12,
28
- "vocab_size": 50265,
29
- "type_vocab_size": 1,
30
- "pad_token_id": 1,
31
- "bos_token_id": 0,
32
- "eos_token_id": 2,
33
- "attention_probs_dropout_prob": 0.1,
34
- "hidden_dropout_prob": 0.1
35
- }
 
 
 
 
 
 
 
 
 
1
  {
2
+ "_name_or_path": "allenai/longformer-base-4096",
3
+ "architectures": [
4
+ "LongformerModel"
5
+ ],
6
+ "attention_mode": "longformer",
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "attention_window": [
9
+ 512,
10
+ 512,
11
+ 512,
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512
21
+ ],
22
+ "bos_token_id": 0,
23
+ "eos_token_id": 2,
24
+ "gradient_checkpointing": false,
25
+ "hidden_act": "gelu",
26
+ "hidden_dropout_prob": 0.1,
27
+ "hidden_size": 768,
28
+ "ignore_attention_mask": false,
29
+ "initializer_range": 0.02,
30
+ "intermediate_size": 3072,
31
+ "layer_norm_eps": 1e-05,
32
+ "max_position_embeddings": 4098,
33
+ "model_type": "longformer",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "onnx_export": false,
37
+ "pad_token_id": 1,
38
+ "sep_token_id": 2,
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.40.2",
41
+ "type_vocab_size": 1,
42
+ "vocab_size": 50265
43
+ }
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 sha256:2afcb28ace1859a0d5e0d0a09a707d29e3fdce12ce1cdcfe73a34f5f08c85ef6
3
+ size 594668880
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "LongformerTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff