cheonboy commited on
Commit
9d133d8
1 Parent(s): cf8cd60

Upload model

Browse files
Files changed (4) hide show
  1. README.md +46 -0
  2. config.json +50 -0
  3. generation_config.json +7 -0
  4. tf_model.h5 +3 -0
README.md ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_keras_callback
4
+ model-index:
5
+ - name: kogpt2_small50
6
+ results: []
7
+ ---
8
+
9
+ <!-- This model card has been generated automatically according to the information Keras had access to. You should
10
+ probably proofread and complete it, then remove this comment. -->
11
+
12
+ # kogpt2_small50
13
+
14
+ This model was trained from scratch on an unknown dataset.
15
+ It achieves the following results on the evaluation set:
16
+
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - optimizer: None
36
+ - training_precision: float32
37
+
38
+ ### Training results
39
+
40
+
41
+
42
+ ### Framework versions
43
+
44
+ - Transformers 4.26.1
45
+ - TensorFlow 2.10.0
46
+ - Tokenizers 0.13.2
config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "samlltalk_model_epoch50",
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
+ "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": "4.26.1",
48
+ "use_cache": true,
49
+ "vocab_size": 51200
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": "4.26.1"
7
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:212ea96591a3be7bf292f727ff4897e2d9703070f6927c815920a8c37f04c71f
3
+ size 500832336