vasudevgupta
commited on
Commit
•
a859513
1
Parent(s):
b719ccb
add wts
Browse files- config.json +29 -0
- pytorch_model.bin +3 -0
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"BigBirdForPreTraining"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"attention_type": "block_sparse",
|
7 |
+
"block_size": 64,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu_fast",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-12,
|
16 |
+
"max_position_embeddings": 4096,
|
17 |
+
"model_type": "big_bird",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"num_random_blocks": 3,
|
21 |
+
"pad_token_id": 1,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"rescale_embeddings": false,
|
24 |
+
"transformers_version": "4.4.0.dev0",
|
25 |
+
"type_vocab_size": 2,
|
26 |
+
"use_bias": true,
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 50358
|
29 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7fd790b10c3bf11969200e4379fbcc5d457a569b14b3d7c63e70c028fdc14a4a
|
3 |
+
size 512568261
|