add model (epoch 3 rev3 batch512 lr6e-43)
Browse files- config.json +8 -1
- flax_model.msgpack +3 -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": 768,
|
| 15 |
"n_head": 12,
|
|
|
|
| 16 |
"n_layer": 12,
|
| 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,
|
|
@@ -27,5 +32,7 @@
|
|
| 27 |
"max_length": 50
|
| 28 |
}
|
| 29 |
},
|
|
|
|
|
|
|
| 30 |
"vocab_size": 51200
|
| 31 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "heegyu/ajoublue-gpt2-base",
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
|
|
|
| 14 |
"n_ctx": 1024,
|
| 15 |
"n_embd": 768,
|
| 16 |
"n_head": 12,
|
| 17 |
+
"n_inner": null,
|
| 18 |
"n_layer": 12,
|
| 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,
|
|
|
|
| 32 |
"max_length": 50
|
| 33 |
}
|
| 34 |
},
|
| 35 |
+
"transformers_version": "4.25.1",
|
| 36 |
+
"use_cache": true,
|
| 37 |
"vocab_size": 51200
|
| 38 |
+
}
|
flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:259ac32bcec9b45ea994de09f4115738326e366b8abf45144e35fe0f23d01c95
|
| 3 |
+
size 500661016
|