Upload 3 files
Browse files- config.json +30 -0
- pytorch_model.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"attention_probs_dropout_prob": 0.1,
|
| 3 |
+
"do_lower_case": "false",
|
| 4 |
+
"embedding_size": 384,
|
| 5 |
+
"hidden_act": "gelu",
|
| 6 |
+
"hidden_dropout_prob": 0.1,
|
| 7 |
+
"hidden_size": 512,
|
| 8 |
+
"initializer_range": 0.02,
|
| 9 |
+
"intermediate_size": 2048,
|
| 10 |
+
"layer_norm_eps": 1e-12,
|
| 11 |
+
"max_position_embeddings": 512,
|
| 12 |
+
"max_seq_length": 512,
|
| 13 |
+
"model_size": "mid",
|
| 14 |
+
"model_type": "electra",
|
| 15 |
+
"num_attention_heads": 8,
|
| 16 |
+
"num_hidden_layers": 12,
|
| 17 |
+
"num_train_steps": 1000000,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"position_embedding_type": "absolute",
|
| 20 |
+
"summary_activation": "gelu",
|
| 21 |
+
"summary_last_dropout": 0.1,
|
| 22 |
+
"summary_type": "first",
|
| 23 |
+
"summary_use_proj": true,
|
| 24 |
+
"train_batch_size": 256,
|
| 25 |
+
"transformers_version": "4.6.1",
|
| 26 |
+
"type_vocab_size": 2,
|
| 27 |
+
"vocab_file": "vocab.txt",
|
| 28 |
+
"vocab_size": 31620
|
| 29 |
+
}
|
| 30 |
+
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:475236af7ab4975f36ad637878add475789b568c217834eaf8bce20611a992ab
|
| 3 |
+
size 202599785
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|