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

@@ -4,13 +4,12 @@
   "add_bias_logits": false,
   "add_final_layer_norm": false,
   "architectures": [
-    "BartModel",
-    "BartForConditionalGeneration",
-    "BartForSequenceClassification"
+    "BartModel"
   ],
   "attention_dropout": 0.1,
   "bos_token_id": 0,
   "classif_dropout": 0.1,
+  "classifier_dropout": 0.0,
   "d_model": 1024,
   "decoder_attention_heads": 16,
   "decoder_ffn_dim": 4096,
@@ -24,6 +23,8 @@
   "encoder_layerdrop": 0.0,
   "encoder_layers": 12,
   "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -38,20 +39,20 @@
   },
   "max_position_embeddings": 1024,
   "model_type": "bart",
+  "no_repeat_ngram_size": 3,
   "normalize_before": false,
+  "num_beams": 4,
   "num_hidden_layers": 12,
   "pad_token_id": 1,
   "scale_embedding": false,
-  "num_beams": 4,
-  "no_repeat_ngram_size": 3,
   "task_specific_params": {
-  	"summarization": {
-   	  "length_penalty": 1.0,
+    "summarization": {
+      "length_penalty": 1.0,
       "max_length": 128,
       "min_length": 12,
       "num_beams": 4
     },
-    "summarization_cnn": {      
+    "summarization_cnn": {
       "length_penalty": 2.0,
       "max_length": 142,
       "min_length": 56,
@@ -64,5 +65,7 @@
       "num_beams": 6
     }
   },
+  "transformers_version": "4.7.0.dev0",
+  "use_cache": true,
   "vocab_size": 50265
 }