Commit
·
4cd3dd9
1
Parent(s):
d7d412e
Upload config.json
Browse files- config.json +3 -5
config.json
CHANGED
|
@@ -1,9 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "tolga-ozturk/mGPT-nsp",
|
| 3 |
"_num_labels": 2,
|
| 4 |
"activation_function": "gelu_new",
|
| 5 |
"architectures": [
|
| 6 |
-
"
|
| 7 |
],
|
| 8 |
"attn_pdrop": 0.1,
|
| 9 |
"bos_token_id": 1,
|
|
@@ -12,12 +11,12 @@
|
|
| 12 |
"gradient_checkpointing": false,
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
"layer_norm_epsilon": 1e-05,
|
| 15 |
-
"model_type": "
|
| 16 |
"n_ctx": 1024,
|
| 17 |
"n_embd": 1024,
|
| 18 |
"n_head": 16,
|
| 19 |
"n_inner": 4096,
|
| 20 |
-
"n_layer":
|
| 21 |
"n_positions": 1024,
|
| 22 |
"reorder_and_upcast_attn": false,
|
| 23 |
"resid_pdrop": 0.1,
|
|
@@ -28,7 +27,6 @@
|
|
| 28 |
"summary_proj_to_labels": true,
|
| 29 |
"summary_type": "cls_index",
|
| 30 |
"summary_use_proj": true,
|
| 31 |
-
"torch_dtype": "float32",
|
| 32 |
"transformers_version": "4.18.0",
|
| 33 |
"use_cache": true,
|
| 34 |
"vocab_size": 250100
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"_num_labels": 2,
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
],
|
| 7 |
"attn_pdrop": 0.1,
|
| 8 |
"bos_token_id": 1,
|
|
|
|
| 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": 1024,
|
| 17 |
"n_head": 16,
|
| 18 |
"n_inner": 4096,
|
| 19 |
+
"n_layer": 24,
|
| 20 |
"n_positions": 1024,
|
| 21 |
"reorder_and_upcast_attn": false,
|
| 22 |
"resid_pdrop": 0.1,
|
|
|
|
| 27 |
"summary_proj_to_labels": true,
|
| 28 |
"summary_type": "cls_index",
|
| 29 |
"summary_use_proj": true,
|
|
|
|
| 30 |
"transformers_version": "4.18.0",
|
| 31 |
"use_cache": true,
|
| 32 |
"vocab_size": 250100
|