Upload DebertaForMaskedLM
Browse files- config.json +32 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "babylm-strict-small-mlsm",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DebertaForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 3072,
|
| 12 |
+
"layer_norm_eps": 1e-07,
|
| 13 |
+
"max_position_embeddings": 512,
|
| 14 |
+
"max_relative_positions": -1,
|
| 15 |
+
"model_type": "deberta",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 12,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"pooler_dropout": 0,
|
| 20 |
+
"pooler_hidden_act": "gelu",
|
| 21 |
+
"pooler_hidden_size": 768,
|
| 22 |
+
"pos_att_type": [
|
| 23 |
+
"c2p",
|
| 24 |
+
"p2c"
|
| 25 |
+
],
|
| 26 |
+
"position_biased_input": false,
|
| 27 |
+
"relative_attention": true,
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.27.1",
|
| 30 |
+
"type_vocab_size": 0,
|
| 31 |
+
"vocab_size": 27500
|
| 32 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a5f221274d8381b93f0ebfe1e12c4055d44860d526e772a5ebcd681f20077f3
|
| 3 |
+
size 487022261
|