add flax model

.gitattributes

@@ -6,3 +6,4 @@
 *.tar.gz filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text

config.json

@@ -10,11 +10,13 @@
   "attention_dropout": 0.1,
   "bos_token_id": 0,
   "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
   "d_model": 1024,
   "decoder_attention_heads": 16,
   "decoder_ffn_dim": 4096,
   "decoder_layerdrop": 0.0,
   "decoder_layers": 3,
+  "decoder_start_token_id": 2,
   "dropout": 0.1,
   "encoder_attention_heads": 16,
   "encoder_ffn_dim": 4096,
@@ -24,6 +26,8 @@
   "extra_pos_embeddings": 2,
   "finetuning_task": "mnli",
   "force_bos_token_to_be_generated": false,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
   "id2label": {
     "0": "contradiction",
     "1": "neutral",
@@ -46,5 +50,7 @@
   "scale_embedding": false,
   "static_position_embeddings": false,
   "total_flos": 176191632140147712,
+  "transformers_version": "4.7.0.dev0",
+  "use_cache": true,
   "vocab_size": 50265
 }