maykcaldas commited on
Commit
430203e
·
1 Parent(s): fb57838
Files changed (2) hide show
  1. config.json +16 -17
  2. flax_model.msgpack +2 -2
config.json CHANGED
@@ -2,32 +2,31 @@
2
  "activation_dropout": 0.0,
3
  "activation_function": "relu",
4
  "architectures": [
5
- "BartForCausalLM"
6
  ],
7
  "attention_dropout": 0.0,
8
- "bos_token_id": 12,
9
  "classifier_dropout": 0.0,
10
- "d_model": 6,
11
- "decoder_attention_heads": 6,
12
- "decoder_ffn_dim": 6,
13
  "decoder_layerdrop": 0.0,
14
- "decoder_layers": 2,
15
  "decoder_start_token_id": 2,
16
  "dropout": 0.1,
17
- "encoder_attention_heads": 6,
18
- "encoder_ffn_dim": 6,
19
  "encoder_layerdrop": 0.0,
20
- "encoder_layers": 2,
21
- "eos_token_id": 4,
22
- "forced_eos_token_id": 4,
23
  "id2label": {
24
  "0": "LABEL_0",
25
  "1": "LABEL_1",
26
  "2": "LABEL_2"
27
  },
28
  "init_std": 0.02,
29
- "is_decoder": true,
30
- "is_encoder_decoder": false,
31
  "label2id": {
32
  "LABEL_0": 0,
33
  "LABEL_1": 1,
@@ -35,10 +34,10 @@
35
  },
36
  "max_position_embeddings": 1024,
37
  "model_type": "bart",
38
- "num_hidden_layers": 2,
39
- "pad_token_id": 24,
40
  "scale_embedding": false,
41
- "transformers_version": "4.21.1",
42
  "use_cache": true,
43
- "vocab_size": 28
44
  }
 
2
  "activation_dropout": 0.0,
3
  "activation_function": "relu",
4
  "architectures": [
5
+ "BartModel"
6
  ],
7
  "attention_dropout": 0.0,
8
+ "bos_token_id": 14,
9
  "classifier_dropout": 0.0,
10
+ "d_model": 1024,
11
+ "decoder_attention_heads": 4,
12
+ "decoder_ffn_dim": 1024,
13
  "decoder_layerdrop": 0.0,
14
+ "decoder_layers": 6,
15
  "decoder_start_token_id": 2,
16
  "dropout": 0.1,
17
+ "encoder_attention_heads": 4,
18
+ "encoder_ffn_dim": 1024,
19
  "encoder_layerdrop": 0.0,
20
+ "encoder_layers": 6,
21
+ "eos_token_id": 82,
22
+ "forced_eos_token_id": 82,
23
  "id2label": {
24
  "0": "LABEL_0",
25
  "1": "LABEL_1",
26
  "2": "LABEL_2"
27
  },
28
  "init_std": 0.02,
29
+ "is_encoder_decoder": true,
 
30
  "label2id": {
31
  "LABEL_0": 0,
32
  "LABEL_1": 1,
 
34
  },
35
  "max_position_embeddings": 1024,
36
  "model_type": "bart",
37
+ "num_hidden_layers": 6,
38
+ "pad_token_id": 18,
39
  "scale_embedding": false,
40
+ "transformers_version": "4.21.2",
41
  "use_cache": true,
42
+ "vocab_size": 84
43
  }
flax_model.msgpack CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a96d08ab5358bb1fc57cf9d911611b17c9e31fa80e3792feadeb0ecf02e3851b
3
- size 30672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f30905e2a787c470160818dc6924585c26cc59f06586ae8d6d889fbc8e24c60
3
+ size 412066738