Commit
·
751a8ba
1
Parent(s):
4f199ad
Retrain model
Browse files- config.json +4 -3
- pytorch_model.bin +2 -2
- training_args.bin +3 -0
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
@@ -8,7 +8,6 @@
|
|
8 |
"bos_token_id": 50256,
|
9 |
"embd_pdrop": 0.1,
|
10 |
"eos_token_id": 50256,
|
11 |
-
"gradient_checkpointing": false,
|
12 |
"initializer_range": 0.02,
|
13 |
"layer_norm_epsilon": 1e-05,
|
14 |
"model_type": "gpt2",
|
@@ -18,7 +17,9 @@
|
|
18 |
"n_inner": null,
|
19 |
"n_layer": 24,
|
20 |
"n_positions": 1024,
|
|
|
21 |
"resid_pdrop": 0.1,
|
|
|
22 |
"scale_attn_weights": true,
|
23 |
"summary_activation": null,
|
24 |
"summary_first_dropout": 0.1,
|
@@ -31,7 +32,7 @@
|
|
31 |
}
|
32 |
},
|
33 |
"torch_dtype": "float32",
|
34 |
-
"transformers_version": "4.
|
35 |
"use_cache": true,
|
36 |
"vocab_size": 50257
|
37 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "microsoft/DialoGPT-medium",
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
|
|
8 |
"bos_token_id": 50256,
|
9 |
"embd_pdrop": 0.1,
|
10 |
"eos_token_id": 50256,
|
|
|
11 |
"initializer_range": 0.02,
|
12 |
"layer_norm_epsilon": 1e-05,
|
13 |
"model_type": "gpt2",
|
|
|
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,
|
23 |
"scale_attn_weights": true,
|
24 |
"summary_activation": null,
|
25 |
"summary_first_dropout": 0.1,
|
|
|
32 |
}
|
33 |
},
|
34 |
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.12.0",
|
36 |
"use_cache": true,
|
37 |
"vocab_size": 50257
|
38 |
}
|
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 sha256:28e212af58364a2dfb8a790b7a9f5fbf30925185159394029bf43a3d3d07b243
|
3 |
+
size 1444581337
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d03349ac6933826c80971b9eb2582744858f835d60469deb0160e74961431e3
|
3 |
+
size 2799
|