yanjunbing
commited on
Commit
•
1acf534
1
Parent(s):
2c8f69b
First model version
Browse files- config.json +20 -0
- pytorch_model.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"attention_probs_dropout_prob": 0.1,
|
| 3 |
+
"easynlp_version": "0.0.3",
|
| 4 |
+
"gradient_checkpointing": false,
|
| 5 |
+
"hidden_act": "gelu_new",
|
| 6 |
+
"hidden_dropout_prob": 0.1,
|
| 7 |
+
"hidden_size": 2048,
|
| 8 |
+
"initializer_range": 0.2,
|
| 9 |
+
"intermediate_size": 8192,
|
| 10 |
+
"layer_norm_eps": 1e-12,
|
| 11 |
+
"max_position_embeddings": 512,
|
| 12 |
+
"model_type": "megatron-bert",
|
| 13 |
+
"num_attention_heads": 8,
|
| 14 |
+
"num_hidden_layers": 24,
|
| 15 |
+
"pad_token_id": 0,
|
| 16 |
+
"position_embedding_type": "absolute",
|
| 17 |
+
"type_vocab_size": 2,
|
| 18 |
+
"use_cache": false,
|
| 19 |
+
"vocab_size": 21248
|
| 20 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39d82c6b76b6639776667c9fdbffa8d03c8ad51b64ecbefca426c024bb91b8d6
|
| 3 |
+
size 5203851423
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|