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

@@ -10,6 +10,7 @@
   "attention_dropout": 0.0,
   "bos_token_id": 0,
   "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
   "d_model": 1024,
   "decoder_attention_heads": 16,
   "decoder_ffn_dim": 4096,
@@ -17,6 +18,7 @@
   "decoder_layers": 3,
   "decoder_start_token_id": 2,
   "dropout": 0.1,
+  "early_stopping": true,
   "encoder_attention_heads": 16,
   "encoder_ffn_dim": 4096,
   "encoder_layerdrop": 0.0,
@@ -24,6 +26,8 @@
   "eos_token_id": 2,
   "extra_pos_embeddings": 2,
   "force_bos_token_to_be_generated": false,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -38,6 +42,7 @@
   },
   "max_position_embeddings": 1024,
   "model_type": "bart",
+  "no_repeat_ngram_size": 3,
   "normalize_before": false,
   "normalize_embedding": true,
   "num_hidden_layers": 12,
@@ -46,8 +51,6 @@
   "prefix": " ",
   "scale_embedding": false,
   "static_position_embeddings": false,
-  "no_repeat_ngram_size": 3,
-  "early_stopping": true,
   "task_specific_params": {
     "summarization_cnn": {
       "length_penalty": 2.0,
@@ -56,11 +59,13 @@
       "num_beams": 4
     },
     "summarization_xsum": {
-        "length_penalty": 0.6,
-        "max_length": 62,
-        "num_beams": 6,
-        "min_length": 11
+      "length_penalty": 0.6,
+      "max_length": 62,
+      "min_length": 11,
+      "num_beams": 6
     }
   },
+  "transformers_version": "4.7.0.dev0",
+  "use_cache": true,
   "vocab_size": 50265
 }

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0667987e49467192e9ca74f36962905e8910e7d68276b5745326ec77ed3e6b71
+size 510353120