add flax model
Browse files- .gitattributes +1 -0
- config.json +9 -6
- flax_model.msgpack +3 -0
.gitattributes
CHANGED
@@ -6,3 +6,4 @@
|
|
6 |
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
7 |
*.ot filter=lfs diff=lfs merge=lfs -text
|
8 |
*.onnx filter=lfs diff=lfs merge=lfs -text
|
|
|
|
6 |
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
7 |
*.ot filter=lfs diff=lfs merge=lfs -text
|
8 |
*.onnx filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
config.json
CHANGED
@@ -4,13 +4,12 @@
|
|
4 |
"add_bias_logits": false,
|
5 |
"add_final_layer_norm": false,
|
6 |
"architectures": [
|
7 |
-
"BartModel"
|
8 |
-
"BartForConditionalGeneration",
|
9 |
-
"BartForSequenceClassification"
|
10 |
],
|
11 |
"attention_dropout": 0.1,
|
12 |
"bos_token_id": 0,
|
13 |
"classif_dropout": 0.1,
|
|
|
14 |
"d_model": 768,
|
15 |
"decoder_attention_heads": 12,
|
16 |
"decoder_ffn_dim": 3072,
|
@@ -24,6 +23,8 @@
|
|
24 |
"encoder_layerdrop": 0.0,
|
25 |
"encoder_layers": 6,
|
26 |
"eos_token_id": 2,
|
|
|
|
|
27 |
"id2label": {
|
28 |
"0": "LABEL_0",
|
29 |
"1": "LABEL_1",
|
@@ -38,13 +39,13 @@
|
|
38 |
},
|
39 |
"max_position_embeddings": 1024,
|
40 |
"model_type": "bart",
|
|
|
41 |
"normalize_before": false,
|
42 |
"normalize_embedding": true,
|
|
|
43 |
"num_hidden_layers": 6,
|
44 |
"pad_token_id": 1,
|
45 |
"scale_embedding": false,
|
46 |
-
"num_beams": 4,
|
47 |
-
"no_repeat_ngram_size": 3,
|
48 |
"task_specific_params": {
|
49 |
"summarization": {
|
50 |
"length_penalty": 1.0,
|
@@ -52,7 +53,7 @@
|
|
52 |
"min_length": 12,
|
53 |
"num_beams": 4
|
54 |
},
|
55 |
-
"summarization_cnn": {
|
56 |
"length_penalty": 2.0,
|
57 |
"max_length": 142,
|
58 |
"min_length": 56,
|
@@ -65,5 +66,7 @@
|
|
65 |
"num_beams": 6
|
66 |
}
|
67 |
},
|
|
|
|
|
68 |
"vocab_size": 50265
|
69 |
}
|
|
|
4 |
"add_bias_logits": false,
|
5 |
"add_final_layer_norm": false,
|
6 |
"architectures": [
|
7 |
+
"BartModel"
|
|
|
|
|
8 |
],
|
9 |
"attention_dropout": 0.1,
|
10 |
"bos_token_id": 0,
|
11 |
"classif_dropout": 0.1,
|
12 |
+
"classifier_dropout": 0.0,
|
13 |
"d_model": 768,
|
14 |
"decoder_attention_heads": 12,
|
15 |
"decoder_ffn_dim": 3072,
|
|
|
23 |
"encoder_layerdrop": 0.0,
|
24 |
"encoder_layers": 6,
|
25 |
"eos_token_id": 2,
|
26 |
+
"forced_eos_token_id": 2,
|
27 |
+
"gradient_checkpointing": false,
|
28 |
"id2label": {
|
29 |
"0": "LABEL_0",
|
30 |
"1": "LABEL_1",
|
|
|
39 |
},
|
40 |
"max_position_embeddings": 1024,
|
41 |
"model_type": "bart",
|
42 |
+
"no_repeat_ngram_size": 3,
|
43 |
"normalize_before": false,
|
44 |
"normalize_embedding": true,
|
45 |
+
"num_beams": 4,
|
46 |
"num_hidden_layers": 6,
|
47 |
"pad_token_id": 1,
|
48 |
"scale_embedding": false,
|
|
|
|
|
49 |
"task_specific_params": {
|
50 |
"summarization": {
|
51 |
"length_penalty": 1.0,
|
|
|
53 |
"min_length": 12,
|
54 |
"num_beams": 4
|
55 |
},
|
56 |
+
"summarization_cnn": {
|
57 |
"length_penalty": 2.0,
|
58 |
"max_length": 142,
|
59 |
"min_length": 56,
|
|
|
66 |
"num_beams": 6
|
67 |
}
|
68 |
},
|
69 |
+
"transformers_version": "4.7.0.dev0",
|
70 |
+
"use_cache": true,
|
71 |
"vocab_size": 50265
|
72 |
}
|
flax_model.msgpack
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3164d4f102798fb6f9cca23d2b952d5251d2011195183f42725809a9479e798
|
3 |
+
size 557690804
|