Upload 6 files
Browse files- .gitattributes +9 -24
- README.md +6 -1
- config.json +46 -0
- flax_model.msgpack +3 -0
- pytorch_model.bin +3 -0
- tokenizer.json +0 -0
.gitattributes
CHANGED
@@ -1,32 +1,17 @@
|
|
1 |
-
*.
|
2 |
-
*.
|
3 |
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
-
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
5 |
-
*.ftz filter=lfs diff=lfs merge=lfs -text
|
6 |
-
*.gz filter=lfs diff=lfs merge=lfs -text
|
7 |
*.h5 filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
*.joblib filter=lfs diff=lfs merge=lfs -text
|
9 |
-
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
10 |
-
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
11 |
*.model filter=lfs diff=lfs merge=lfs -text
|
12 |
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
13 |
-
*.npy filter=lfs diff=lfs merge=lfs -text
|
14 |
-
*.npz filter=lfs diff=lfs merge=lfs -text
|
15 |
-
*.onnx filter=lfs diff=lfs merge=lfs -text
|
16 |
-
*.ot filter=lfs diff=lfs merge=lfs -text
|
17 |
-
*.parquet filter=lfs diff=lfs merge=lfs -text
|
18 |
*.pb filter=lfs diff=lfs merge=lfs -text
|
19 |
-
*.pickle filter=lfs diff=lfs merge=lfs -text
|
20 |
-
*.pkl filter=lfs diff=lfs merge=lfs -text
|
21 |
*.pt filter=lfs diff=lfs merge=lfs -text
|
22 |
*.pth filter=lfs diff=lfs merge=lfs -text
|
23 |
-
*.
|
24 |
-
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
25 |
-
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
26 |
-
*.tflite filter=lfs diff=lfs merge=lfs -text
|
27 |
-
*.tgz filter=lfs diff=lfs merge=lfs -text
|
28 |
-
*.wasm filter=lfs diff=lfs merge=lfs -text
|
29 |
-
*.xz filter=lfs diff=lfs merge=lfs -text
|
30 |
-
*.zip filter=lfs diff=lfs merge=lfs -text
|
31 |
-
*.zst filter=lfs diff=lfs merge=lfs -text
|
32 |
-
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
1 |
+
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
3 |
*.bin filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
4 |
*.h5 filter=lfs diff=lfs merge=lfs -text
|
5 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
10 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
11 |
*.joblib filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
12 |
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
14 |
*.pb filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
15 |
*.pt filter=lfs diff=lfs merge=lfs -text
|
16 |
*.pth filter=lfs diff=lfs merge=lfs -text
|
17 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
README.md
CHANGED
@@ -1,3 +1,8 @@
|
|
1 |
---
|
2 |
-
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
1 |
---
|
2 |
+
language: ko
|
3 |
+
tags:
|
4 |
+
- gpt2
|
5 |
+
license: cc-by-nc-sa-4.0
|
6 |
---
|
7 |
+
|
8 |
+
For more details: https://github.com/SKT-AI/KoGPT2
|
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_num_labels": 1,
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 1,
|
11 |
+
"gradient_checkpointing": false,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"label2id": {
|
17 |
+
"LABEL_0": 0
|
18 |
+
},
|
19 |
+
"layer_norm_epsilon": 1e-05,
|
20 |
+
"model_type": "gpt2",
|
21 |
+
"n_ctx": 1024,
|
22 |
+
"n_embd": 768,
|
23 |
+
"n_head": 12,
|
24 |
+
"n_inner": null,
|
25 |
+
"n_layer": 12,
|
26 |
+
"n_positions": 1024,
|
27 |
+
"pad_token_id": 3,
|
28 |
+
"resid_pdrop": 0.1,
|
29 |
+
"summary_activation": null,
|
30 |
+
"summary_first_dropout": 0.1,
|
31 |
+
"summary_proj_to_labels": true,
|
32 |
+
"summary_type": "cls_index",
|
33 |
+
"summary_use_proj": true,
|
34 |
+
"task_specific_params": {
|
35 |
+
"text-generation": {
|
36 |
+
"do_sample": true,
|
37 |
+
"max_length": 50
|
38 |
+
}
|
39 |
+
},
|
40 |
+
"transformers_version": "4.3.3",
|
41 |
+
"use_cache": true,
|
42 |
+
"vocab_size": 51200,
|
43 |
+
"author": "Heewon Jeon(madjakarta@gmail.com)",
|
44 |
+
"created_date": "2021-04-28",
|
45 |
+
"license": "CC-BY-NC-SA 4.0"
|
46 |
+
}
|
flax_model.msgpack
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11d8f69e03937dda286303dcca8947eae4509a702abd68e4584e9f003655b392
|
3 |
+
size 500661016
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d86ba64e06d505e2d1be295772dc1159a5aa18824afde5cb28fd48c23544ca4
|
3 |
+
size 513302779
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|