liangyuxin
commited on
Commit
•
c3ebc0a
1
Parent(s):
1344be8
delete dir
Browse files- decoder/cog-pretrain.model +0 -3
- decoder/cog-pretrain.vocab +0 -0
- decoder/config.json +0 -16
- encoder/config.json +0 -25
- encoder/tokenizer.json +0 -0
- encoder/tokenizer_config.json +0 -3
decoder/cog-pretrain.model
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:6ea6f4164152bc58d23e24e48f7bf4187aad72a32e97ec4b3acc832fe183cbc2
|
| 3 |
-
size 1021864
|
|
|
|
|
|
|
|
|
|
|
|
decoder/cog-pretrain.vocab
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
decoder/config.json
DELETED
|
@@ -1,16 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"num_layers":32,
|
| 3 |
-
"vocab_size":50048,
|
| 4 |
-
"hidden_size":1600,
|
| 5 |
-
"num_attention_heads":25,
|
| 6 |
-
"embedding_dropout_prob":0.1,
|
| 7 |
-
"attention_dropout_prob":0.1,
|
| 8 |
-
"output_dropout_prob":0.1,
|
| 9 |
-
"max_sequence_length":512,
|
| 10 |
-
"max_memory_length":512,
|
| 11 |
-
"latent_size":256,
|
| 12 |
-
"checkpoint_activations":false,
|
| 13 |
-
"checkpoint_num_layers":1,
|
| 14 |
-
"parallel_output":true,
|
| 15 |
-
"relative_encoding":true
|
| 16 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
encoder/config.json
DELETED
|
@@ -1,25 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"BertForMaskedLM"
|
| 4 |
-
],
|
| 5 |
-
"attention_probs_dropout_prob": 0.1,
|
| 6 |
-
"directionality": "bidi",
|
| 7 |
-
"hidden_act": "gelu",
|
| 8 |
-
"hidden_dropout_prob": 0.1,
|
| 9 |
-
"hidden_size": 768,
|
| 10 |
-
"initializer_range": 0.02,
|
| 11 |
-
"intermediate_size": 3072,
|
| 12 |
-
"layer_norm_eps": 1e-12,
|
| 13 |
-
"max_position_embeddings": 512,
|
| 14 |
-
"model_type": "bert",
|
| 15 |
-
"num_attention_heads": 12,
|
| 16 |
-
"num_hidden_layers": 12,
|
| 17 |
-
"pad_token_id": 0,
|
| 18 |
-
"pooler_fc_size": 768,
|
| 19 |
-
"pooler_num_attention_heads": 12,
|
| 20 |
-
"pooler_num_fc_layers": 3,
|
| 21 |
-
"pooler_size_per_head": 128,
|
| 22 |
-
"pooler_type": "first_token_transform",
|
| 23 |
-
"type_vocab_size": 2,
|
| 24 |
-
"vocab_size": 21128
|
| 25 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
encoder/tokenizer.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
encoder/tokenizer_config.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"do_lower_case": false
|
| 3 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|