MalawiUniST
commited on
Commit
•
ee0d80d
1
Parent(s):
7342232
First version
Browse files- config.json +29 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LongformerForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"attention_window": [
|
| 7 |
+
512
|
| 8 |
+
],
|
| 9 |
+
"bos_token_id": 0,
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_dropout_prob": 0.1,
|
| 14 |
+
"hidden_size": 768,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 3072,
|
| 17 |
+
"layer_norm_eps": 1e-12,
|
| 18 |
+
"max_position_embeddings": 514,
|
| 19 |
+
"model_type": "longformer",
|
| 20 |
+
"num_attention_heads": 2,
|
| 21 |
+
"num_hidden_layers": 1,
|
| 22 |
+
"pad_token_id": 1,
|
| 23 |
+
"position_embedding_type": "absolute",
|
| 24 |
+
"sep_token_id": 2,
|
| 25 |
+
"transformers_version": "4.5.0.dev0",
|
| 26 |
+
"type_vocab_size": 1,
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 52000
|
| 29 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b3608da2e2de2698c2afdd14a0953560f4fda082fe872d1a71d80e9fefb426c
|
| 3 |
+
size 199365336
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66de30f039414bcc8a53b86543b432a9873454d93c1de82344e9b315d8cc722f
|
| 3 |
+
size 2351
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|