Upload DistillationWrapper
Browse files- config.json +2 -2
- pytorch_model.bin +2 -2
config.json
CHANGED
|
@@ -8,7 +8,7 @@
|
|
| 8 |
"dtype": "float32",
|
| 9 |
"embedding_size": 128,
|
| 10 |
"expert_intermediate_size": 2624,
|
| 11 |
-
"group_depth":
|
| 12 |
"hidden_act": "gelu",
|
| 13 |
"hidden_dropout_prob": 0.1,
|
| 14 |
"hidden_size": 768,
|
|
@@ -23,7 +23,7 @@
|
|
| 23 |
"num_attention_heads": 12,
|
| 24 |
"num_expert_modules": 2,
|
| 25 |
"num_experts": 4,
|
| 26 |
-
"num_hidden_layers":
|
| 27 |
"pad_token_id": 0,
|
| 28 |
"router_jitter_noise": 0.01,
|
| 29 |
"top_k": 1,
|
|
|
|
| 8 |
"dtype": "float32",
|
| 9 |
"embedding_size": 128,
|
| 10 |
"expert_intermediate_size": 2624,
|
| 11 |
+
"group_depth": 2,
|
| 12 |
"hidden_act": "gelu",
|
| 13 |
"hidden_dropout_prob": 0.1,
|
| 14 |
"hidden_size": 768,
|
|
|
|
| 23 |
"num_attention_heads": 12,
|
| 24 |
"num_expert_modules": 2,
|
| 25 |
"num_experts": 4,
|
| 26 |
+
"num_hidden_layers": 14,
|
| 27 |
"pad_token_id": 0,
|
| 28 |
"router_jitter_noise": 0.01,
|
| 29 |
"top_k": 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:e89bcee781230900cba4bdf2299a71de8fa592e0bc1017e9a9e8afb1984ed811
|
| 3 |
+
size 402029570
|