Commit
·
5662062
1
Parent(s):
29e05f1
add model
Browse files- config.json +7 -5
- pytorch_model.bin +2 -2
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "gpt2-
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
|
@@ -12,11 +12,13 @@
|
|
| 12 |
"layer_norm_epsilon": 1e-05,
|
| 13 |
"model_type": "gpt2",
|
| 14 |
"n_ctx": 1024,
|
| 15 |
-
"n_embd":
|
| 16 |
-
"n_head":
|
| 17 |
"n_inner": null,
|
| 18 |
-
"n_layer":
|
| 19 |
"n_positions": 1024,
|
|
|
|
|
|
|
| 20 |
"reorder_and_upcast_attn": true,
|
| 21 |
"resid_pdrop": 0.1,
|
| 22 |
"scale_attn_by_inverse_layer_idx": true,
|
|
@@ -35,5 +37,5 @@
|
|
| 35 |
"torch_dtype": "float32",
|
| 36 |
"transformers_version": "4.19.0",
|
| 37 |
"use_cache": true,
|
| 38 |
-
"vocab_size":
|
| 39 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "gpt2-medium",
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
|
|
|
| 12 |
"layer_norm_epsilon": 1e-05,
|
| 13 |
"model_type": "gpt2",
|
| 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 |
+
"n_special": 0,
|
| 21 |
+
"predict_special_tokens": true,
|
| 22 |
"reorder_and_upcast_attn": true,
|
| 23 |
"resid_pdrop": 0.1,
|
| 24 |
"scale_attn_by_inverse_layer_idx": true,
|
|
|
|
| 37 |
"torch_dtype": "float32",
|
| 38 |
"transformers_version": "4.19.0",
|
| 39 |
"use_cache": true,
|
| 40 |
+
"vocab_size": 200000
|
| 41 |
}
|
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 sha256:95b904851b71c3ee2fb7642054a64529f53f7c23dfde8d3007adb8ffca3d48bb
|
| 3 |
+
size 2057909465
|