add model
Browse files- config.json +4 -5
- pytorch_model.bin +2 -2
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
@@ -8,15 +8,14 @@
|
|
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",
|
15 |
"n_ctx": 1024,
|
16 |
-
"n_embd":
|
17 |
-
"n_head":
|
18 |
"n_inner": null,
|
19 |
-
"n_layer":
|
20 |
"n_positions": 1024,
|
21 |
"reorder_and_upcast_attn": false,
|
22 |
"resid_pdrop": 0.1,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "microsoft/DialoGPT-large",
|
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",
|
14 |
"n_ctx": 1024,
|
15 |
+
"n_embd": 1280,
|
16 |
+
"n_head": 20,
|
17 |
"n_inner": null,
|
18 |
+
"n_layer": 36,
|
19 |
"n_positions": 1024,
|
20 |
"reorder_and_upcast_attn": false,
|
21 |
"resid_pdrop": 0.1,
|
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:b23e9eab2b440e18612a2ab19505a7bf128c346a441804c21bcedd1076fca4ac
|
3 |
+
size 3134045897
|