Upload model
Browse files- config.json +46 -0
- model.safetensors +3 -0
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/user1-system11/Documents/research-shradha/deploy-spt-code/spt-code/outputs/pre_train_20241125_001741/models",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"architectures": [
|
6 |
+
"BartModel"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.0,
|
9 |
+
"bos_token_id": 1,
|
10 |
+
"classifier_dropout": 0.0,
|
11 |
+
"d_model": 768,
|
12 |
+
"decoder_attention_heads": 12,
|
13 |
+
"decoder_ffn_dim": 3072,
|
14 |
+
"decoder_layerdrop": 0.0,
|
15 |
+
"decoder_layers": 12,
|
16 |
+
"decoder_start_token_id": 1,
|
17 |
+
"dropout": 0.1,
|
18 |
+
"encoder_attention_heads": 12,
|
19 |
+
"encoder_ffn_dim": 3072,
|
20 |
+
"encoder_layerdrop": 0.0,
|
21 |
+
"encoder_layers": 12,
|
22 |
+
"eos_token_id": 2,
|
23 |
+
"forced_eos_token_id": 2,
|
24 |
+
"id2label": {
|
25 |
+
"0": "LABEL_0",
|
26 |
+
"1": "LABEL_1"
|
27 |
+
},
|
28 |
+
"init_std": 0.02,
|
29 |
+
"is_encoder_decoder": true,
|
30 |
+
"label2id": {
|
31 |
+
"LABEL_0": 0,
|
32 |
+
"LABEL_1": 1
|
33 |
+
},
|
34 |
+
"max_length": 256,
|
35 |
+
"max_position_embeddings": 1024,
|
36 |
+
"min_length": 1,
|
37 |
+
"model_type": "bart",
|
38 |
+
"num_beams": 5,
|
39 |
+
"num_hidden_layers": 12,
|
40 |
+
"pad_token_id": 0,
|
41 |
+
"scale_embedding": false,
|
42 |
+
"torch_dtype": "float32",
|
43 |
+
"transformers_version": "4.36.2",
|
44 |
+
"use_cache": true,
|
45 |
+
"vocab_size": 80059
|
46 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4694f8359821883d4f640ef860983a45dab5733adc51c7d28376e7f0a73b676f
|
3 |
+
size 1046216384
|