Upload ModernALBERTForMaskedLM
Browse files- config.json +4 -4
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -11,9 +11,9 @@
|
|
| 11 |
"group_depth": 4,
|
| 12 |
"hidden_act": "gelu",
|
| 13 |
"hidden_dropout_prob": 0.1,
|
| 14 |
-
"hidden_size":
|
| 15 |
"initializer_range": 0.02,
|
| 16 |
-
"intermediate_size":
|
| 17 |
"layer_norm_eps": 1e-06,
|
| 18 |
"load_balancing_loss_coef": 0.01,
|
| 19 |
"lora_alpha": 32,
|
|
@@ -21,9 +21,9 @@
|
|
| 21 |
"max_position_embeddings": 8192,
|
| 22 |
"model_type": "ModernALBERT",
|
| 23 |
"num_attention_heads": 16,
|
| 24 |
-
"num_expert_modules":
|
| 25 |
"num_experts": 8,
|
| 26 |
-
"num_hidden_layers":
|
| 27 |
"pad_token_id": 0,
|
| 28 |
"router_jitter_noise": 0.01,
|
| 29 |
"top_k": 2,
|
|
|
|
| 11 |
"group_depth": 4,
|
| 12 |
"hidden_act": "gelu",
|
| 13 |
"hidden_dropout_prob": 0.1,
|
| 14 |
+
"hidden_size": 1024,
|
| 15 |
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 2624,
|
| 17 |
"layer_norm_eps": 1e-06,
|
| 18 |
"load_balancing_loss_coef": 0.01,
|
| 19 |
"lora_alpha": 32,
|
|
|
|
| 21 |
"max_position_embeddings": 8192,
|
| 22 |
"model_type": "ModernALBERT",
|
| 23 |
"num_attention_heads": 16,
|
| 24 |
+
"num_expert_modules": 4,
|
| 25 |
"num_experts": 8,
|
| 26 |
+
"num_hidden_layers": 16,
|
| 27 |
"pad_token_id": 0,
|
| 28 |
"router_jitter_noise": 0.01,
|
| 29 |
"top_k": 2,
|
model.safetensors
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 sha256:458984f64113322f4dfd46fd3e02f2a3795036e66b9776a3705e134d4476eb16
|
| 3 |
+
size 328420408
|