Raj-Sanjay-Shah
commited on
Commit
•
6204000
1
Parent(s):
cb6f231
Upload model
Browse files- config.json +28 -0
- model.safetensors +3 -0
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "phueb/BabyBERTa-1",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 3,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 4,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 256,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 1024,
|
16 |
+
"layer_norm_eps": 1e-05,
|
17 |
+
"max_position_embeddings": 130,
|
18 |
+
"model_type": "roberta",
|
19 |
+
"num_attention_heads": 8,
|
20 |
+
"num_hidden_layers": 8,
|
21 |
+
"pad_token_id": 1,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.35.2",
|
25 |
+
"type_vocab_size": 2,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 8192
|
28 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:784f11ef8bf10a5dd9e0608bb5f6589965f901dfc037bdda33493e95b716b6a7
|
3 |
+
size 34076160
|