First commit
Browse files- .gitattributes +1 -0
- config.json +33 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +3 -0
- spiece.model +3 -0
- spiece.vocab +0 -0
- tokenizer_config.json +2 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"AlbertForMaskedLM"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0,
|
6 |
+
"bos_token_id": 2,
|
7 |
+
"classifier_dropout_prob": 0.1,
|
8 |
+
"down_scale_factor": 1,
|
9 |
+
"embedding_size": 128,
|
10 |
+
"eos_token_id": 3,
|
11 |
+
"eos_token_ids": null,
|
12 |
+
"gap_size": 0,
|
13 |
+
"hidden_act": "gelu_new",
|
14 |
+
"hidden_dropout_prob": 0,
|
15 |
+
"hidden_size": 768,
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"inner_group_num": 1,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"layer_norm_eps": 1e-12,
|
20 |
+
"max_position_embeddings": 512,
|
21 |
+
"model_type": "albert",
|
22 |
+
"net_structure_type": 0,
|
23 |
+
"num_attention_heads": 12,
|
24 |
+
"num_hidden_groups": 1,
|
25 |
+
"num_hidden_layers": 12,
|
26 |
+
"num_memory_blocks": 0,
|
27 |
+
"output_past": true,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"position_embedding_type": "absolute",
|
30 |
+
"transformers_version": "4.24.0",
|
31 |
+
"type_vocab_size": 2,
|
32 |
+
"vocab_size": 128000
|
33 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b870512bcf35cbe48bbac113068fef4207784d03860c3d5c66e4cde0324b910e
|
3 |
+
size 163364287
|
special_tokens_map.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
2 |
+
|
3 |
+
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0989df2caa3d2e7ae3871b903708bb5192e8f25ad7423b56cb29e81f9385f98d
|
3 |
+
size 2409017
|
spiece.vocab
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
{"keep_accents": true, "do_lower_case": false}
|
2 |
+
|