katarinayuan
commited on
Upload PrototypeContrastiveForMaskedLM
Browse files- config.json +41 -0
- pytorch_model.bin +3 -0
config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/xinyu402/projects/rrg-bengioy-ad/xinyu402/scZero_ckpts/240202_181731/checkpoint-40000",
|
3 |
+
"architectures": [
|
4 |
+
"PrototypeContrastiveForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.02,
|
7 |
+
"bert_objective": "plm",
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"contrastive_dropout": null,
|
10 |
+
"data_branch": "frac100",
|
11 |
+
"gradient_checkpointing": false,
|
12 |
+
"hidden_act": "relu",
|
13 |
+
"hidden_dropout_prob": 0.02,
|
14 |
+
"hidden_size": 256,
|
15 |
+
"initialize_decoder_as_identity": null,
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 512,
|
18 |
+
"layer_norm_eps": 1e-12,
|
19 |
+
"learnable_logits_scale": null,
|
20 |
+
"max_length": null,
|
21 |
+
"max_position_embeddings": 2048,
|
22 |
+
"min_position": null,
|
23 |
+
"model_type": "bert",
|
24 |
+
"moving_avg_ratio": 0.9,
|
25 |
+
"num_attention_heads": 4,
|
26 |
+
"num_hidden_layers": 6,
|
27 |
+
"output_hidden_states": true,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"position_embedding_type": "absolute",
|
30 |
+
"scale_grad_by_freq": true,
|
31 |
+
"tau": 0.01,
|
32 |
+
"tie_word_embeddings": 0,
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"total_logging_steps": 40,
|
35 |
+
"transformers_version": "4.32.1",
|
36 |
+
"truth_use_decoder": null,
|
37 |
+
"type_vocab_size": null,
|
38 |
+
"use_abspos_embed": true,
|
39 |
+
"use_cache": true,
|
40 |
+
"vocab_size": 25427
|
41 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b30ddf0aadfbcca32f1a92c3b77743091e433e4f4a38dcd77c87a89236c3e676
|
3 |
+
size 44049097
|