Vishvak Murahari
commited on
Commit
·
a7c3c30
1
Parent(s):
003b788
init commit
Browse files- config.json +34 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RobertaSequenceClassificationMuxed"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"binary_hadamard_epsilon": 0,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"demuxing_variant": "index",
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gaussian_hadamard_norm": 20,
|
| 11 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_dropout_prob": 0.1,
|
| 14 |
+
"hidden_size": 768,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 3072,
|
| 17 |
+
"layer_norm_eps": 1e-05,
|
| 18 |
+
"learn_muxing": 0,
|
| 19 |
+
"max_position_embeddings": 514,
|
| 20 |
+
"model_type": "roberta",
|
| 21 |
+
"muxing_variant": "gaussian_hadamard",
|
| 22 |
+
"num_attention_heads": 12,
|
| 23 |
+
"num_hidden_layers": 12,
|
| 24 |
+
"num_instances": 2,
|
| 25 |
+
"pad_token_id": 1,
|
| 26 |
+
"position_embedding_type": "absolute",
|
| 27 |
+
"retrieval_loss_coeff": 1,
|
| 28 |
+
"retrieval_percentage": 1,
|
| 29 |
+
"task_loss_coeff": 0,
|
| 30 |
+
"transformers_version": "4.4.2",
|
| 31 |
+
"type_vocab_size": 1,
|
| 32 |
+
"use_cache": true,
|
| 33 |
+
"vocab_size": 50265
|
| 34 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:474ef56cde07947642e60da55580a29e83942ab5751be8a8f63773575d22fe0b
|
| 3 |
+
size 662751831
|