hyunwoo3235
commited on
Commit
•
52dd57c
1
Parent(s):
33b0a9c
Upload 7 files
Browse files423k steps 2k batch size
- config.json +24 -0
- flax_model.msgpack +3 -0
- model.safetensors +3 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +9 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"attention_probs_dropout_prob": 0.1,
|
3 |
+
"hidden_act": "gelu",
|
4 |
+
"hidden_dropout_prob": 0.1,
|
5 |
+
"hidden_size": 1536,
|
6 |
+
"initializer_range": 0.02,
|
7 |
+
"intermediate_size": 6144,
|
8 |
+
"layer_norm_eps": 1e-07,
|
9 |
+
"max_position_embeddings": 512,
|
10 |
+
"max_relative_positions": -1,
|
11 |
+
"model_type": "deberta-v2",
|
12 |
+
"norm_rel_ebd": "layer_norm",
|
13 |
+
"num_attention_heads": 24,
|
14 |
+
"num_hidden_layers": 24,
|
15 |
+
"pad_token_id": 0,
|
16 |
+
"pos_att_type": "p2c|c2p",
|
17 |
+
"position_biased_input": false,
|
18 |
+
"position_buckets": 256,
|
19 |
+
"relative_attention": true,
|
20 |
+
"share_att_key": true,
|
21 |
+
"torch_dtype": "bfloat16",
|
22 |
+
"type_vocab_size": 0,
|
23 |
+
"vocab_size": 64100
|
24 |
+
}
|
flax_model.msgpack
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2ed56448afe2134db90f66401256f8f0bb4dbfb3d45604cd891241c8decc8e5
|
3 |
+
size 1563159073
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d65553757b0b712e3441f36ea81146716928a0bbd011de048b26399380100cda
|
3 |
+
size 1563198122
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0e89def70fb4fe94159cde4736ae65abae2a315a5089ccd0265f941ea0fbf8e
|
3 |
+
size 1563280385
|
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"eos_token": "[SEP]",
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"sep_token": "[SEP]",
|
8 |
+
"unk_token": "[UNK]"
|
9 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_lower_case": false,
|
5 |
+
"eos_token": "[SEP]",
|
6 |
+
"mask_token": "[MASK]",
|
7 |
+
"model_max_length": 1000000000000000019884624838656,
|
8 |
+
"name_or_path": "debertav2",
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"special_tokens_map_file": null,
|
12 |
+
"split_by_punct": false,
|
13 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
14 |
+
"unk_token": "[UNK]"
|
15 |
+
}
|