rippertnt commited on
Commit
a76ff7f
1 Parent(s): c3e7e86

Upload 9 files

Browse files
config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "circulus/canvers-en2ko-v1",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.0,
11
+ "author": "[email protected]",
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": "NEGATIVE",
34
+ "1": "POSITIVE"
35
+ },
36
+ "init_std": 0.02,
37
+ "is_encoder_decoder": true,
38
+ "kobart_version": 2.0,
39
+ "label2id": {
40
+ "NEGATIVE": 0,
41
+ "POSITIVE": 1
42
+ },
43
+ "max_position_embeddings": 1026,
44
+ "model_type": "bart",
45
+ "normalize_before": false,
46
+ "normalize_embedding": true,
47
+ "num_hidden_layers": 6,
48
+ "pad_token_id": 3,
49
+ "scale_embedding": false,
50
+ "static_position_embeddings": false,
51
+ "tokenizer_class": "PreTrainedTokenizerFast",
52
+ "torch_dtype": "float32",
53
+ "transformers_version": "4.29.1",
54
+ "use_cache": true,
55
+ "vocab_size": 30000
56
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "decoder_start_token_id": 1,
5
+ "eos_token_id": 1,
6
+ "forced_eos_token_id": 1,
7
+ "pad_token_id": 3,
8
+ "transformers_version": "4.29.1"
9
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af02416fe9f6f94b194da6af0a32e61a5b0be96c2620cbec3db55a38bccb5d7f
3
+ size 991032261
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:823e47f39beb764f23e0d2536973d4dc477872327437a56a115d3526cea45e26
3
+ size 495648413
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8b1f9c678fd4a7e7d0daa1971457175d1255173b9f660e2ff786c9bfc52b5fc
3
+ size 14575
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b88de5103dbb2dbbf6a6973647d1b560cbfcdc6494d539465aa84605f20d7ea1
3
+ size 557
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a98d4d519a3aad6cfd1046f8bfc3193a136a056ecb73a617972e7ba27670c13
3
+ size 627
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b775df66f6d69e3119023fdb469db1413a107cfd60f0ba42098fbea7a6372b8
3
+ size 4027