Commit
·
5cf883a
1
Parent(s):
2972612
Training in progress epoch 0
Browse files- config.json +4 -1
- tf_model.h5 +1 -1
config.json
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"activation_function": "gelu_new",
|
| 3 |
"architectures": [
|
| 4 |
"GPT2LMHeadModel"
|
|
@@ -16,7 +17,9 @@
|
|
| 16 |
"n_inner": null,
|
| 17 |
"n_layer": 12,
|
| 18 |
"n_positions": 1024,
|
|
|
|
| 19 |
"resid_pdrop": 0.1,
|
|
|
|
| 20 |
"scale_attn_weights": true,
|
| 21 |
"summary_activation": null,
|
| 22 |
"summary_first_dropout": 0.1,
|
|
@@ -29,7 +32,7 @@
|
|
| 29 |
"max_length": 50
|
| 30 |
}
|
| 31 |
},
|
| 32 |
-
"transformers_version": "4.
|
| 33 |
"use_cache": true,
|
| 34 |
"vocab_size": 50257
|
| 35 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "gpt2",
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
|
|
|
| 17 |
"n_inner": null,
|
| 18 |
"n_layer": 12,
|
| 19 |
"n_positions": 1024,
|
| 20 |
+
"reorder_and_upcast_attn": false,
|
| 21 |
"resid_pdrop": 0.1,
|
| 22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 23 |
"scale_attn_weights": true,
|
| 24 |
"summary_activation": null,
|
| 25 |
"summary_first_dropout": 0.1,
|
|
|
|
| 32 |
"max_length": 50
|
| 33 |
}
|
| 34 |
},
|
| 35 |
+
"transformers_version": "4.13.0.dev0",
|
| 36 |
"use_cache": true,
|
| 37 |
"vocab_size": 50257
|
| 38 |
}
|
tf_model.h5
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 497934920
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f54ca63da52eca2d71a30f076e89e44838bac2b26396433dd48961623da7d325
|
| 3 |
size 497934920
|