Upload ModernBertForMaskedLM
Browse files- config.json +4 -4
- model.safetensors +3 -0
config.json
CHANGED
|
@@ -19,10 +19,10 @@
|
|
| 19 |
"global_rope_theta": 160000.0,
|
| 20 |
"gradient_checkpointing": false,
|
| 21 |
"hidden_activation": "gelu",
|
| 22 |
-
"hidden_size":
|
| 23 |
"initializer_cutoff_factor": 2.0,
|
| 24 |
"initializer_range": 0.02,
|
| 25 |
-
"intermediate_size":
|
| 26 |
"layer_norm_eps": 1e-05,
|
| 27 |
"local_attention": 128,
|
| 28 |
"local_rope_theta": 10000.0,
|
|
@@ -32,8 +32,8 @@
|
|
| 32 |
"model_type": "modernbert",
|
| 33 |
"norm_bias": false,
|
| 34 |
"norm_eps": 1e-05,
|
| 35 |
-
"num_attention_heads":
|
| 36 |
-
"num_hidden_layers":
|
| 37 |
"pad_token_id": 50283,
|
| 38 |
"position_embedding_type": "absolute",
|
| 39 |
"repad_logits_with_grad": false,
|
|
|
|
| 19 |
"global_rope_theta": 160000.0,
|
| 20 |
"gradient_checkpointing": false,
|
| 21 |
"hidden_activation": "gelu",
|
| 22 |
+
"hidden_size": 768,
|
| 23 |
"initializer_cutoff_factor": 2.0,
|
| 24 |
"initializer_range": 0.02,
|
| 25 |
+
"intermediate_size": 1152,
|
| 26 |
"layer_norm_eps": 1e-05,
|
| 27 |
"local_attention": 128,
|
| 28 |
"local_rope_theta": 10000.0,
|
|
|
|
| 32 |
"model_type": "modernbert",
|
| 33 |
"norm_bias": false,
|
| 34 |
"norm_eps": 1e-05,
|
| 35 |
+
"num_attention_heads": 12,
|
| 36 |
+
"num_hidden_layers": 22,
|
| 37 |
"pad_token_id": 50283,
|
| 38 |
"position_embedding_type": "absolute",
|
| 39 |
"repad_logits_with_grad": false,
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f0c864e9da0be2645cfbcbfa51e4868a6f7973e670d5a8a712b51b9d466ede7
|
| 3 |
+
size 598635032
|