model init
Browse files- config.json +66 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gogamza/kobart-base-v2",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"BartForSequenceClassification"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.0,
|
11 |
+
"author": "Heewon Jeon(madjakarta@gmail.com)",
|
12 |
+
"bos_token_id": 1,
|
13 |
+
"classif_dropout": 0.1,
|
14 |
+
"classifier_dropout": 0.1,
|
15 |
+
"d_model": 768,
|
16 |
+
"decoder_attention_heads": 16,
|
17 |
+
"decoder_ffn_dim": 3072,
|
18 |
+
"decoder_layerdrop": 0.0,
|
19 |
+
"decoder_layers": 6,
|
20 |
+
"decoder_start_token_id": 1,
|
21 |
+
"do_blenderbot_90_layernorm": false,
|
22 |
+
"dropout": 0.1,
|
23 |
+
"encoder_attention_heads": 16,
|
24 |
+
"encoder_ffn_dim": 3072,
|
25 |
+
"encoder_layerdrop": 0.0,
|
26 |
+
"encoder_layers": 6,
|
27 |
+
"eos_token_id": 1,
|
28 |
+
"extra_pos_embeddings": 2,
|
29 |
+
"force_bos_token_to_be_generated": false,
|
30 |
+
"forced_eos_token_id": 1,
|
31 |
+
"gradient_checkpointing": false,
|
32 |
+
"id2label": {
|
33 |
+
"0": "LABEL_0",
|
34 |
+
"1": "LABEL_1",
|
35 |
+
"2": "LABEL_2",
|
36 |
+
"3": "LABEL_3",
|
37 |
+
"4": "LABEL_4",
|
38 |
+
"5": "LABEL_5",
|
39 |
+
"6": "LABEL_6"
|
40 |
+
},
|
41 |
+
"init_std": 0.02,
|
42 |
+
"is_encoder_decoder": true,
|
43 |
+
"kobart_version": 2.0,
|
44 |
+
"label2id": {
|
45 |
+
"LABEL_0": 0,
|
46 |
+
"LABEL_1": 1,
|
47 |
+
"LABEL_2": 2,
|
48 |
+
"LABEL_3": 3,
|
49 |
+
"LABEL_4": 4,
|
50 |
+
"LABEL_5": 5,
|
51 |
+
"LABEL_6": 6
|
52 |
+
},
|
53 |
+
"max_position_embeddings": 1026,
|
54 |
+
"model_type": "bart",
|
55 |
+
"normalize_before": false,
|
56 |
+
"normalize_embedding": true,
|
57 |
+
"num_hidden_layers": 6,
|
58 |
+
"pad_token_id": 3,
|
59 |
+
"scale_embedding": false,
|
60 |
+
"static_position_embeddings": false,
|
61 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
62 |
+
"torch_dtype": "float32",
|
63 |
+
"transformers_version": "4.10.0",
|
64 |
+
"use_cache": true,
|
65 |
+
"vocab_size": 30000
|
66 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e38502de6eedae7e5428c2e75eb33ab9887ce6d576b279a5c8594c669f290b77
|
3 |
+
size 497927854
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "</s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<pad>", "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": "<mask>"}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"errors": "replace", "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "special_tokens_map_file": "/opt/ml/.cache/huggingface/transformers/a87d2ed77831bb40ce806a97c04126addf5ecc82b3e23ecf916b2a4acdb9c29a.c23d5e62137984cf842a885705037b25b156747d145406702932d5f5d5e7c88e", "tokenizer_file": "/opt/ml/.cache/huggingface/transformers/f94202e1dad4fcfcb282aff4c6865b6119e03c87c6fa9e5886abe93835c41ecd.dc2013f8bbecd755468e2c44397f53dc624be5451d0190744397caf61a20383f", "name_or_path": "gogamza/kobart-base-v2", "tokenizer_class": "BartTokenizer"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|