Upload DEQBertForMaskedLM
Browse files- config.json +33 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "models/lucas-cont-part3/checkpoint-5000",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DEQBertForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"b_solver": "broyden",
|
| 8 |
+
"b_thres": 100,
|
| 9 |
+
"bos_token_id": 0,
|
| 10 |
+
"classifier_dropout": null,
|
| 11 |
+
"eos_token_id": 2,
|
| 12 |
+
"f_solver": "anderson",
|
| 13 |
+
"f_thres": 100,
|
| 14 |
+
"hidden_act": "gelu",
|
| 15 |
+
"hidden_dropout_prob": 0.1,
|
| 16 |
+
"hidden_size": 768,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"jac_loss_freq": 0.35,
|
| 20 |
+
"jac_loss_weight": 1.9,
|
| 21 |
+
"layer_norm_eps": 1e-05,
|
| 22 |
+
"max_position_embeddings": 514,
|
| 23 |
+
"model_type": "deqbert",
|
| 24 |
+
"num_attention_heads": 12,
|
| 25 |
+
"num_hidden_layers": 12,
|
| 26 |
+
"pad_token_id": 1,
|
| 27 |
+
"position_embedding_type": "absolute",
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.25.1",
|
| 30 |
+
"type_vocab_size": 1,
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 50265
|
| 33 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a64303bedaed6f23b6f24387cd560cc2828c7e6b9e5f6b1c0f5d7d5c585a9481
|
| 3 |
+
size 194023688
|