Upload model
Browse files- README.md +48 -0
- config.json +50 -0
- generation_config.json +7 -0
- tf_model.h5 +3 -0
README.md
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-sa-4.0
|
3 |
+
base_model: skt/kogpt2-base-v2
|
4 |
+
tags:
|
5 |
+
- generated_from_keras_callback
|
6 |
+
model-index:
|
7 |
+
- name: Tiabet-TFkoGPT-complete_story-epoch-3
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
12 |
+
probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# Tiabet-TFkoGPT-complete_story-epoch-3
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [skt/kogpt2-base-v2](https://huggingface.co/skt/kogpt2-base-v2) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- optimizer: None
|
38 |
+
- training_precision: float32
|
39 |
+
|
40 |
+
### Training results
|
41 |
+
|
42 |
+
|
43 |
+
|
44 |
+
### Framework versions
|
45 |
+
|
46 |
+
- Transformers 4.34.0
|
47 |
+
- TensorFlow 2.13.0
|
48 |
+
- Tokenizers 0.14.1
|
config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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([email protected])",
|
10 |
+
"bos_token_id": 0,
|
11 |
+
"created_date": "2021-04-28",
|
12 |
+
"embd_pdrop": 0.1,
|
13 |
+
"eos_token_id": 1,
|
14 |
+
"gradient_checkpointing": false,
|
15 |
+
"id2label": {
|
16 |
+
"0": "LABEL_0"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"label2id": {
|
20 |
+
"LABEL_0": 0
|
21 |
+
},
|
22 |
+
"layer_norm_epsilon": 1e-05,
|
23 |
+
"license": "CC-BY-NC-SA 4.0",
|
24 |
+
"model_type": "gpt2",
|
25 |
+
"n_ctx": 1024,
|
26 |
+
"n_embd": 768,
|
27 |
+
"n_head": 12,
|
28 |
+
"n_inner": null,
|
29 |
+
"n_layer": 12,
|
30 |
+
"n_positions": 1024,
|
31 |
+
"pad_token_id": 3,
|
32 |
+
"reorder_and_upcast_attn": false,
|
33 |
+
"resid_pdrop": 0.1,
|
34 |
+
"scale_attn_by_inverse_layer_idx": false,
|
35 |
+
"scale_attn_weights": true,
|
36 |
+
"summary_activation": null,
|
37 |
+
"summary_first_dropout": 0.1,
|
38 |
+
"summary_proj_to_labels": true,
|
39 |
+
"summary_type": "cls_index",
|
40 |
+
"summary_use_proj": true,
|
41 |
+
"task_specific_params": {
|
42 |
+
"text-generation": {
|
43 |
+
"do_sample": true,
|
44 |
+
"max_length": 50
|
45 |
+
}
|
46 |
+
},
|
47 |
+
"transformers_version": "4.34.0",
|
48 |
+
"use_cache": true,
|
49 |
+
"vocab_size": 51201
|
50 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 3,
|
6 |
+
"transformers_version": "4.34.0"
|
7 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f6e2ad1009983635878a6db25102ecac93c727abe44477ff93ffe145c2627d6
|
3 |
+
size 500835520
|