epoch 10 trained
Browse files- config.json +3 -2
- pytorch_model.bin +2 -2
- tokenizer.json +6 -1
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
@@ -17,6 +17,7 @@
|
|
17 |
"n_inner": null,
|
18 |
"n_layer": 24,
|
19 |
"n_positions": 1024,
|
|
|
20 |
"reorder_and_upcast_attn": false,
|
21 |
"resid_pdrop": 0.1,
|
22 |
"scale_attn_by_inverse_layer_idx": false,
|
@@ -33,7 +34,7 @@
|
|
33 |
}
|
34 |
},
|
35 |
"torch_dtype": "float32",
|
36 |
-
"transformers_version": "4.
|
37 |
"use_cache": true,
|
38 |
"vocab_size": 51200
|
39 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "heegyu/ajoublue-gpt2-medium",
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
|
|
17 |
"n_inner": null,
|
18 |
"n_layer": 24,
|
19 |
"n_positions": 1024,
|
20 |
+
"pad_token_id": 0,
|
21 |
"reorder_and_upcast_attn": false,
|
22 |
"resid_pdrop": 0.1,
|
23 |
"scale_attn_by_inverse_layer_idx": false,
|
|
|
34 |
}
|
35 |
},
|
36 |
"torch_dtype": "float32",
|
37 |
+
"transformers_version": "4.25.1",
|
38 |
"use_cache": true,
|
39 |
"vocab_size": 51200
|
40 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b58ed74521092bd85273aea7017fc476734a7a5505426472bc9bee5279273b05
|
3 |
+
size 1658140055
|
tokenizer.json
CHANGED
@@ -1,6 +1,11 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 1024,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|