wangrui
commited on
Commit
•
3f4ffb6
1
Parent(s):
8189b37
facebook nougat 0.1.0
Browse files- .gitattributes +1 -0
- config.json +33 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +4 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/fsx-llm/lblecher/checkpoints/nougat/small/20230426_125023",
|
3 |
+
"align_long_axis": false,
|
4 |
+
"architectures": [
|
5 |
+
"NougatModel"
|
6 |
+
],
|
7 |
+
"decoder_layer": 4,
|
8 |
+
"embed_dim": 128,
|
9 |
+
"encoder_layer": [
|
10 |
+
2,
|
11 |
+
2,
|
12 |
+
14,
|
13 |
+
2
|
14 |
+
],
|
15 |
+
"hidden_dimension": 1024,
|
16 |
+
"input_size": [
|
17 |
+
896,
|
18 |
+
672
|
19 |
+
],
|
20 |
+
"max_length": 3584,
|
21 |
+
"max_position_embeddings": 3584,
|
22 |
+
"model_type": "nougat",
|
23 |
+
"num_heads": [
|
24 |
+
4,
|
25 |
+
8,
|
26 |
+
16,
|
27 |
+
32
|
28 |
+
],
|
29 |
+
"patch_size": 4,
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.25.1",
|
32 |
+
"window_size": 7
|
33 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bfca8831ad5e81fcd96b66f207934f2aaac4e8996449619515c58267c5e03686
|
3 |
+
size 1002629505
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "<pad>",
|
5 |
+
"unk_token": "<unk>"
|
6 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model_max_length": 1000000000000000019884624838656,
|
3 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
4 |
+
}
|