add flax model
Browse files- .gitattributes +1 -0
- config.json +9 -0
- 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
|
@@ -3,20 +3,27 @@
|
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "gelu",
|
| 5 |
"add_final_layer_norm": false,
|
|
|
|
|
|
|
|
|
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 0,
|
| 8 |
"classif_dropout": 0.0,
|
|
|
|
| 9 |
"d_model": 1024,
|
| 10 |
"decoder_attention_heads": 16,
|
| 11 |
"decoder_ffn_dim": 4096,
|
| 12 |
"decoder_layerdrop": 0.0,
|
| 13 |
"decoder_layers": 12,
|
|
|
|
| 14 |
"dropout": 0.1,
|
| 15 |
"encoder_attention_heads": 16,
|
| 16 |
"encoder_ffn_dim": 4096,
|
| 17 |
"encoder_layerdrop": 0.0,
|
| 18 |
"encoder_layers": 12,
|
| 19 |
"eos_token_id": 2,
|
|
|
|
|
|
|
| 20 |
"id2label": {
|
| 21 |
"0": "contradiction",
|
| 22 |
"1": "neutral",
|
|
@@ -36,5 +43,7 @@
|
|
| 36 |
"output_past": false,
|
| 37 |
"pad_token_id": 1,
|
| 38 |
"scale_embedding": false,
|
|
|
|
|
|
|
| 39 |
"vocab_size": 50265
|
| 40 |
}
|
|
|
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "gelu",
|
| 5 |
"add_final_layer_norm": false,
|
| 6 |
+
"architectures": [
|
| 7 |
+
"BartForSequenceClassification"
|
| 8 |
+
],
|
| 9 |
"attention_dropout": 0.0,
|
| 10 |
"bos_token_id": 0,
|
| 11 |
"classif_dropout": 0.0,
|
| 12 |
+
"classifier_dropout": 0.0,
|
| 13 |
"d_model": 1024,
|
| 14 |
"decoder_attention_heads": 16,
|
| 15 |
"decoder_ffn_dim": 4096,
|
| 16 |
"decoder_layerdrop": 0.0,
|
| 17 |
"decoder_layers": 12,
|
| 18 |
+
"decoder_start_token_id": 2,
|
| 19 |
"dropout": 0.1,
|
| 20 |
"encoder_attention_heads": 16,
|
| 21 |
"encoder_ffn_dim": 4096,
|
| 22 |
"encoder_layerdrop": 0.0,
|
| 23 |
"encoder_layers": 12,
|
| 24 |
"eos_token_id": 2,
|
| 25 |
+
"forced_eos_token_id": 2,
|
| 26 |
+
"gradient_checkpointing": false,
|
| 27 |
"id2label": {
|
| 28 |
"0": "contradiction",
|
| 29 |
"1": "neutral",
|
|
|
|
| 43 |
"output_past": false,
|
| 44 |
"pad_token_id": 1,
|
| 45 |
"scale_embedding": false,
|
| 46 |
+
"transformers_version": "4.7.0.dev0",
|
| 47 |
+
"use_cache": true,
|
| 48 |
"vocab_size": 50265
|
| 49 |
}
|
flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e07d1ae73ae1c1267fd174a3b21c73b0d77bad288f8ed17fb685f79c419a897
|
| 3 |
+
size 1629394629
|