Upload with huggingface_hub (#1)
Browse files- Upload with huggingface_hub (3884d0755302f661ca0d4493856b3805a3aa3294)
- config.json +53 -0
- generation_config.json +9 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "skt/kogpt2-base-v2",
|
3 |
+
"_num_labels": 1,
|
4 |
+
"activation_function": "gelu_new",
|
5 |
+
"architectures": [
|
6 |
+
"GPT2LMHeadModel"
|
7 |
+
],
|
8 |
+
"attn_pdrop": 0.1,
|
9 |
+
"author": "Heewon Jeon(madjakarta@gmail.com)",
|
10 |
+
"bos_token_id": 0,
|
11 |
+
"created_date": "2021-04-28",
|
12 |
+
"do_sample": true,
|
13 |
+
"embd_pdrop": 0.1,
|
14 |
+
"eos_token_id": 1,
|
15 |
+
"gradient_checkpointing": false,
|
16 |
+
"id2label": {
|
17 |
+
"0": "LABEL_0"
|
18 |
+
},
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"label2id": {
|
21 |
+
"LABEL_0": 0
|
22 |
+
},
|
23 |
+
"layer_norm_epsilon": 1e-05,
|
24 |
+
"license": "CC-BY-NC-SA 4.0",
|
25 |
+
"max_length": 50,
|
26 |
+
"model_type": "gpt2",
|
27 |
+
"n_ctx": 1024,
|
28 |
+
"n_embd": 768,
|
29 |
+
"n_head": 12,
|
30 |
+
"n_inner": null,
|
31 |
+
"n_layer": 12,
|
32 |
+
"n_positions": 1024,
|
33 |
+
"pad_token_id": 3,
|
34 |
+
"reorder_and_upcast_attn": false,
|
35 |
+
"resid_pdrop": 0.1,
|
36 |
+
"scale_attn_by_inverse_layer_idx": false,
|
37 |
+
"scale_attn_weights": true,
|
38 |
+
"summary_activation": null,
|
39 |
+
"summary_first_dropout": 0.1,
|
40 |
+
"summary_proj_to_labels": true,
|
41 |
+
"summary_type": "cls_index",
|
42 |
+
"summary_use_proj": true,
|
43 |
+
"task_specific_params": {
|
44 |
+
"text-generation": {
|
45 |
+
"do_sample": true,
|
46 |
+
"max_length": 50
|
47 |
+
}
|
48 |
+
},
|
49 |
+
"torch_dtype": "float32",
|
50 |
+
"transformers_version": "4.26.1",
|
51 |
+
"use_cache": true,
|
52 |
+
"vocab_size": 51200
|
53 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"do_sample": true,
|
5 |
+
"eos_token_id": 1,
|
6 |
+
"max_length": 50,
|
7 |
+
"pad_token_id": 3,
|
8 |
+
"transformers_version": "4.26.1"
|
9 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ffe6ee303513aa2b90c1ccce9c78e6d5f261f47148e2185dec591b81448ab4cd
|
3 |
+
size 513294909
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3e631a16569cc08a88827268ac271f69b43689ebd78d777438f32b4faa87de5
|
3 |
+
size 3451
|