avelezarce
commited on
Upload 3 files
Browse files- gf-20L-95M-i4096_config.json +24 -0
- gf-20L-95M-i4096_generation_config.json +5 -0
- training_args.bin +3 -0
gf-20L-95M-i4096_config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"BertForMaskedLM"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.02,
|
6 |
+
"classifier_dropout": null,
|
7 |
+
"hidden_act": "relu",
|
8 |
+
"hidden_dropout_prob": 0.02,
|
9 |
+
"hidden_size": 896,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 1792,
|
12 |
+
"layer_norm_eps": 1e-12,
|
13 |
+
"max_position_embeddings": 4096,
|
14 |
+
"model_type": "bert",
|
15 |
+
"num_attention_heads": 14,
|
16 |
+
"num_hidden_layers": 20,
|
17 |
+
"pad_token_id": 0,
|
18 |
+
"position_embedding_type": "absolute",
|
19 |
+
"torch_dtype": "float32",
|
20 |
+
"transformers_version": "4.37.1",
|
21 |
+
"type_vocab_size": 2,
|
22 |
+
"use_cache": true,
|
23 |
+
"vocab_size": 20275
|
24 |
+
}
|
gf-20L-95M-i4096_generation_config.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"pad_token_id": 0,
|
4 |
+
"transformers_version": "4.37.1"
|
5 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5afed602918d6f0c4916c1b9335bcdb619bca2c6fd6c7e0dd2a86d195264b8cc
|
3 |
+
size 5048
|