Commit
·
3f5a101
1
Parent(s):
c724cb4
Upload tiny models for NystromformerForMaskedLM
Browse files- config.json +27 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +15 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +24 -0
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"NystromformerForMaskedLM"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"bos_token_id": 2,
|
7 |
+
"conv_kernel_size": 65,
|
8 |
+
"eos_token_id": 3,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 32,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 37,
|
14 |
+
"inv_coeff_init_option": false,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 512,
|
17 |
+
"model_type": "nystromformer",
|
18 |
+
"num_attention_heads": 4,
|
19 |
+
"num_hidden_layers": 5,
|
20 |
+
"num_landmarks": 64,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"segment_means_seq_len": 64,
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.28.0.dev0",
|
25 |
+
"type_vocab_size": 16,
|
26 |
+
"vocab_size": 30000
|
27 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b83c89dff414d2a92e5047494f0a8848ce6b9ce7a473717ad9c18e51903b689a
|
3 |
+
size 4209361
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"eos_token": "[SEP]",
|
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": "[SEP]",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39ee5d0cd20ab9616138d90a6d9c811ed41aba04a95d515bee6d4d5cd42ef0a6
|
3 |
+
size 761089
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"cls_token": "[CLS]",
|
5 |
+
"do_lower_case": true,
|
6 |
+
"eos_token": "[SEP]",
|
7 |
+
"keep_accents": false,
|
8 |
+
"mask_token": {
|
9 |
+
"__type": "AddedToken",
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": true,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"model_max_length": 512,
|
17 |
+
"pad_token": "<pad>",
|
18 |
+
"remove_space": true,
|
19 |
+
"sep_token": "[SEP]",
|
20 |
+
"sp_model_kwargs": {},
|
21 |
+
"special_tokens_map_file": "C:\\Users\\prana/.cache\\huggingface\\transformers\\d225353999b4547543d7b66be9304faa64950fec7fb25e2d220dd84ee3f8b991.15ed5b79b197b4fcc5f3f80b2ee89a5a3ad708dbd076575cd22cffd9e1a56284",
|
22 |
+
"tokenizer_class": "AlbertTokenizer",
|
23 |
+
"unk_token": "<unk>"
|
24 |
+
}
|