Sohan Anisetty
commited on
Commit
•
dc57090
1
Parent(s):
07667e4
initial commit
Browse files- config.json +53 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/coc/scratch/sanisetty3/DLM/OFA-tiny-vqa=finetune",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"add_type_embedding": true,
|
6 |
+
"architectures": [
|
7 |
+
"OFAModelForVQA"
|
8 |
+
],
|
9 |
+
"attention_dropout": 0.0,
|
10 |
+
"attn_scale_factor": 2.0,
|
11 |
+
"bos_token_id": 0,
|
12 |
+
"classifier_dropout": 0.0,
|
13 |
+
"code_image_size": 128,
|
14 |
+
"code_layernorm_embedding": true,
|
15 |
+
"d_model": 256,
|
16 |
+
"decoder_attention_heads": 4,
|
17 |
+
"decoder_drop_path_rate": 0.0,
|
18 |
+
"decoder_ffn_dim": 1024,
|
19 |
+
"decoder_layerdrop": 0.0,
|
20 |
+
"decoder_layers": 4,
|
21 |
+
"decoder_normalize_before": true,
|
22 |
+
"decoder_start_token_id": 0,
|
23 |
+
"dropout": 0.1,
|
24 |
+
"encoder_attention_heads": 4,
|
25 |
+
"encoder_drop_path_rate": 0.0,
|
26 |
+
"encoder_ffn_dim": 1024,
|
27 |
+
"encoder_layerdrop": 0.0,
|
28 |
+
"encoder_layers": 4,
|
29 |
+
"encoder_normalize_before": true,
|
30 |
+
"entangle_position_embedding": false,
|
31 |
+
"eos_token_id": 2,
|
32 |
+
"forced_eos_token_id": 2,
|
33 |
+
"image_bucket_size": 42,
|
34 |
+
"init_std": 0.02,
|
35 |
+
"is_encoder_decoder": true,
|
36 |
+
"layernorm_embedding": true,
|
37 |
+
"max_position_embeddings": 1024,
|
38 |
+
"model_type": "ofa",
|
39 |
+
"normformer": true,
|
40 |
+
"num_hidden_layers": 4,
|
41 |
+
"pad_token_id": 1,
|
42 |
+
"patch_layernorm_embedding": true,
|
43 |
+
"resnet_drop_path_rate": 0.0,
|
44 |
+
"resnet_model_path": null,
|
45 |
+
"resnet_type": "resnet50",
|
46 |
+
"scale_embedding": false,
|
47 |
+
"share_decoder_input_output_embed": true,
|
48 |
+
"token_bucket_size": 256,
|
49 |
+
"torch_dtype": "float32",
|
50 |
+
"transformers_version": "4.26.1",
|
51 |
+
"use_cache": false,
|
52 |
+
"vocab_size": 59457
|
53 |
+
}
|
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 sha256:392ede7e9a3325bb2c17387d26816d17dfd9c198ea0e084a2cb316e9eca5c398
|
3 |
+
size 200877241
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|