add model
Browse files- README.md +45 -1
- config.json +50 -0
- tf_model.h5 +3 -0
README.md
CHANGED
|
@@ -1,3 +1,47 @@
|
|
| 1 |
---
|
| 2 |
-
license:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
license: cc-by-nc-sa-4.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_keras_callback
|
| 5 |
+
model-index:
|
| 6 |
+
- name: kogpt2-chat
|
| 7 |
+
results: []
|
| 8 |
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
| 11 |
+
probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# kogpt2-chat
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [skt/kogpt2-base-v2](https://huggingface.co/skt/kogpt2-base-v2) on an unknown dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- optimizer: None
|
| 37 |
+
- training_precision: float32
|
| 38 |
+
|
| 39 |
+
### Training results
|
| 40 |
+
|
| 41 |
+
|
| 42 |
+
|
| 43 |
+
### Framework versions
|
| 44 |
+
|
| 45 |
+
- Transformers 4.21.2
|
| 46 |
+
- TensorFlow 2.8.2
|
| 47 |
+
- Tokenizers 0.12.1
|
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": "4.21.2",
|
| 48 |
+
"use_cache": true,
|
| 49 |
+
"vocab_size": 51200
|
| 50 |
+
}
|
tf_model.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6049201a1e933c81ee5e98ecf7b4b39a0b34b4e6453fe41ba2e6521e4322d93
|
| 3 |
+
size 500832360
|