ankush-003
commited on
Commit
•
774c09a
1
Parent(s):
60b2d86
ankush-003/bart-nosqli
Browse files- config.json +18 -14
- generation_config.json +0 -3
- pytorch_model.bin +2 -2
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,15 +1,15 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "facebook/bart-large
|
3 |
-
"
|
4 |
-
"activation_dropout": 0.0,
|
5 |
"activation_function": "gelu",
|
|
|
6 |
"add_final_layer_norm": false,
|
7 |
"architectures": [
|
8 |
"BartForConditionalGeneration"
|
9 |
],
|
10 |
-
"attention_dropout": 0.
|
11 |
"bos_token_id": 0,
|
12 |
-
"classif_dropout": 0.
|
13 |
"classifier_dropout": 0.0,
|
14 |
"d_model": 1024,
|
15 |
"decoder_attention_heads": 16,
|
@@ -24,7 +24,6 @@
|
|
24 |
"encoder_layerdrop": 0.0,
|
25 |
"encoder_layers": 12,
|
26 |
"eos_token_id": 2,
|
27 |
-
"force_bos_token_to_be_generated": true,
|
28 |
"forced_bos_token_id": 0,
|
29 |
"forced_eos_token_id": 2,
|
30 |
"gradient_checkpointing": false,
|
@@ -40,31 +39,36 @@
|
|
40 |
"LABEL_1": 1,
|
41 |
"LABEL_2": 2
|
42 |
},
|
43 |
-
"length_penalty": 2.0,
|
44 |
-
"max_length": 142,
|
45 |
"max_position_embeddings": 1024,
|
46 |
-
"min_length": 56,
|
47 |
"model_type": "bart",
|
48 |
"no_repeat_ngram_size": 3,
|
49 |
"normalize_before": false,
|
50 |
"num_beams": 4,
|
51 |
"num_hidden_layers": 12,
|
52 |
-
"output_past": true,
|
53 |
"pad_token_id": 1,
|
54 |
-
"prefix": " ",
|
55 |
"scale_embedding": false,
|
56 |
"task_specific_params": {
|
57 |
"summarization": {
|
58 |
-
"
|
|
|
|
|
|
|
|
|
|
|
59 |
"length_penalty": 2.0,
|
60 |
"max_length": 142,
|
61 |
"min_length": 56,
|
62 |
-
"no_repeat_ngram_size": 3,
|
63 |
"num_beams": 4
|
|
|
|
|
|
|
|
|
|
|
|
|
64 |
}
|
65 |
},
|
66 |
"torch_dtype": "float32",
|
67 |
"transformers_version": "4.31.0",
|
68 |
"use_cache": true,
|
69 |
-
"vocab_size":
|
70 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "facebook/bart-large",
|
3 |
+
"activation_dropout": 0.1,
|
|
|
4 |
"activation_function": "gelu",
|
5 |
+
"add_bias_logits": false,
|
6 |
"add_final_layer_norm": false,
|
7 |
"architectures": [
|
8 |
"BartForConditionalGeneration"
|
9 |
],
|
10 |
+
"attention_dropout": 0.1,
|
11 |
"bos_token_id": 0,
|
12 |
+
"classif_dropout": 0.1,
|
13 |
"classifier_dropout": 0.0,
|
14 |
"d_model": 1024,
|
15 |
"decoder_attention_heads": 16,
|
|
|
24 |
"encoder_layerdrop": 0.0,
|
25 |
"encoder_layers": 12,
|
26 |
"eos_token_id": 2,
|
|
|
27 |
"forced_bos_token_id": 0,
|
28 |
"forced_eos_token_id": 2,
|
29 |
"gradient_checkpointing": false,
|
|
|
39 |
"LABEL_1": 1,
|
40 |
"LABEL_2": 2
|
41 |
},
|
|
|
|
|
42 |
"max_position_embeddings": 1024,
|
|
|
43 |
"model_type": "bart",
|
44 |
"no_repeat_ngram_size": 3,
|
45 |
"normalize_before": false,
|
46 |
"num_beams": 4,
|
47 |
"num_hidden_layers": 12,
|
|
|
48 |
"pad_token_id": 1,
|
|
|
49 |
"scale_embedding": false,
|
50 |
"task_specific_params": {
|
51 |
"summarization": {
|
52 |
+
"length_penalty": 1.0,
|
53 |
+
"max_length": 128,
|
54 |
+
"min_length": 12,
|
55 |
+
"num_beams": 4
|
56 |
+
},
|
57 |
+
"summarization_cnn": {
|
58 |
"length_penalty": 2.0,
|
59 |
"max_length": 142,
|
60 |
"min_length": 56,
|
|
|
61 |
"num_beams": 4
|
62 |
+
},
|
63 |
+
"summarization_xsum": {
|
64 |
+
"length_penalty": 1.0,
|
65 |
+
"max_length": 62,
|
66 |
+
"min_length": 11,
|
67 |
+
"num_beams": 6
|
68 |
}
|
69 |
},
|
70 |
"torch_dtype": "float32",
|
71 |
"transformers_version": "4.31.0",
|
72 |
"use_cache": true,
|
73 |
+
"vocab_size": 50265
|
74 |
}
|
generation_config.json
CHANGED
@@ -6,9 +6,6 @@
|
|
6 |
"eos_token_id": 2,
|
7 |
"forced_bos_token_id": 0,
|
8 |
"forced_eos_token_id": 2,
|
9 |
-
"length_penalty": 2.0,
|
10 |
-
"max_length": 142,
|
11 |
-
"min_length": 56,
|
12 |
"no_repeat_ngram_size": 3,
|
13 |
"num_beams": 4,
|
14 |
"pad_token_id": 1,
|
|
|
6 |
"eos_token_id": 2,
|
7 |
"forced_bos_token_id": 0,
|
8 |
"forced_eos_token_id": 2,
|
|
|
|
|
|
|
9 |
"no_repeat_ngram_size": 3,
|
10 |
"num_beams": 4,
|
11 |
"pad_token_id": 1,
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc8f38235b112ad1fcb671822f481ce29e0c0945b4e2454d921fdbee8cd4cbd0
|
3 |
+
size 1625541389
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3899
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4a7640d841219d7e93f73e2ed35f131f29abd007f0dd20ebe92814275a443ad
|
3 |
size 3899
|