Update config.json
Browse files- config.json +8 -0
config.json
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"activation_function": "gelu_new",
|
| 3 |
"architectures": [
|
| 4 |
"GPT2LMHeadModel"
|
|
@@ -13,9 +14,13 @@
|
|
| 13 |
"n_ctx": 1024,
|
| 14 |
"n_embd": 1024,
|
| 15 |
"n_head": 16,
|
|
|
|
| 16 |
"n_layer": 24,
|
| 17 |
"n_positions": 1024,
|
|
|
|
| 18 |
"resid_pdrop": 0.1,
|
|
|
|
|
|
|
| 19 |
"summary_activation": null,
|
| 20 |
"summary_first_dropout": 0.1,
|
| 21 |
"summary_proj_to_labels": true,
|
|
@@ -26,5 +31,8 @@
|
|
| 26 |
"max_length": 1000
|
| 27 |
}
|
| 28 |
},
|
|
|
|
|
|
|
|
|
|
| 29 |
"vocab_size": 50257
|
| 30 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "microsoft/DialoGPT-medium",
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
|
|
|
| 14 |
"n_ctx": 1024,
|
| 15 |
"n_embd": 1024,
|
| 16 |
"n_head": 16,
|
| 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,
|
| 26 |
"summary_proj_to_labels": true,
|
|
|
|
| 31 |
"max_length": 1000
|
| 32 |
}
|
| 33 |
},
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.16.2",
|
| 36 |
+
"use_cache": true,
|
| 37 |
"vocab_size": 50257
|
| 38 |
}
|