MorrisPark
commited on
Commit
β’
fc43cca
1
Parent(s):
468a7db
first
Browse files- config.json +45 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "MorrisPark/twc12-bart-pretrain",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"architectures": [
|
6 |
+
"BartForConditionalGeneration"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.1,
|
9 |
+
"bos_token_id": 2,
|
10 |
+
"classifier_dropout": 0.1,
|
11 |
+
"d_model": 512,
|
12 |
+
"decoder_attention_heads": 8,
|
13 |
+
"decoder_ffn_dim": 2048,
|
14 |
+
"decoder_layerdrop": 0.0,
|
15 |
+
"decoder_layers": 6,
|
16 |
+
"decoder_start_token_id": 2,
|
17 |
+
"dropout": 0.1,
|
18 |
+
"encoder_attention_heads": 8,
|
19 |
+
"encoder_ffn_dim": 2048,
|
20 |
+
"encoder_layerdrop": 0.0,
|
21 |
+
"encoder_layers": 6,
|
22 |
+
"eos_token_id": 3,
|
23 |
+
"forced_eos_token_id": 3,
|
24 |
+
"id2label": {
|
25 |
+
"0": "LABEL_0",
|
26 |
+
"1": "LABEL_1",
|
27 |
+
"2": "LABEL_2"
|
28 |
+
},
|
29 |
+
"init_std": 0.02,
|
30 |
+
"is_encoder_decoder": true,
|
31 |
+
"label2id": {
|
32 |
+
"LABEL_0": 0,
|
33 |
+
"LABEL_1": 1,
|
34 |
+
"LABEL_2": 2
|
35 |
+
},
|
36 |
+
"max_position_embeddings": 512,
|
37 |
+
"model_type": "bart",
|
38 |
+
"num_hidden_layers": 6,
|
39 |
+
"pad_token_id": 0,
|
40 |
+
"scale_embedding": false,
|
41 |
+
"torch_dtype": "float32",
|
42 |
+
"transformers_version": "4.14.1",
|
43 |
+
"use_cache": false,
|
44 |
+
"vocab_size": 4000
|
45 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5cd00b7560fadac8c9808edd0fa4731d6010631bde2a71bfb0f615ed9da640f
|
3 |
+
size 186974109
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "[BOS]", "eos_token": "[EOS]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[BOS]", "mask_token": "[MASK]", "additional_special_tokens": ["#@μ£Όμ#", "#@μ΄λͺ¨ν°μ½#", "#@μ΄λ¦#", "#@URL#", "#@μμ#", "#@κΈ°ν#", "#@μ λ²#", "#@κ³μ #", "#@url#", "#@λ²νΈ#", "#@κΈμ΅#", "#@μ μ#", "#@μ₯μ#", "#@μμ€ν
#μ¬μ§#", "#@μμ€ν
#λμμ#", "#@μμ€ν
#κΈ°ν#", "#@μμ€ν
#κ²μ#", "#@μμ€ν
#μ§λ#", "#@μμ€ν
#μμ #", "#@μμ€ν
#νμΌ#", "#@μμ€ν
#μ‘κΈ#", "#@μμ€ν
#"]}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "[BOS]", "eos_token": "[EOS]", "cls_token": "[BOS]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "mask_token": "[MASK]", "additional_special_tokens": ["#@μ£Όμ#", "#@μ΄λͺ¨ν°μ½#", "#@μ΄λ¦#", "#@URL#", "#@μμ#", "#@κΈ°ν#", "#@μ λ²#", "#@κ³μ #", "#@url#", "#@λ²νΈ#", "#@κΈμ΅#", "#@μ μ#", "#@μ₯μ#", "#@μμ€ν
#μ¬μ§#", "#@μμ€ν
#λμμ#", "#@μμ€ν
#κΈ°ν#", "#@μμ€ν
#κ²μ#", "#@μμ€ν
#μ§λ#", "#@μμ€ν
#μμ #", "#@μμ€ν
#νμΌ#", "#@μμ€ν
#μ‘κΈ#", "#@μμ€ν
#"], "tokenizer_class": "PreTrainedTokenizerFast"}
|