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

README.md

@@ -1,10 +1,10 @@
 ---
-language: english
+language: en
 tags:
 - summarization
 license: apache-2.0
 datasets:
-- cnndm
+- cnn_dailymail
 - xsum
 thumbnail: https://huggingface.co/front/thumbnails/distilbart_medium.png
 ---
@@ -24,5 +24,6 @@ This checkpoint should be loaded into `BartForConditionalGeneration.from_pretrai
 | bart-large-xsum (baseline) |         406 |                   229 |      1    |     21.85 |     36.50 |
 | distilbart-xsum-12-6       |         306 |                   137 |      1.68 |     22.12 |     36.99 |
 | bart-large-cnn (baseline)  |         406 |                   381 |      1    |     21.06 |     30.63 |
+| distilbart-12-3-cnn        |         255 |                   214 |      1.78 |     20.57 |     30.00 |
 | distilbart-12-6-cnn        |         306 |                   307 |      1.24 |     21.26 |     30.59 |
-| distilbart-6-6-cnn         |         230 |                   182 |      1.69 |     20.17 |     29.70 |
+| distilbart-6-6-cnn         |         230 |                   182 |      2.09 |     20.17 |     29.70 |

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,
@@ -24,6 +25,10 @@
   "encoder_layers": 12,
   "eos_token_id": 2,
   "extra_pos_embeddings": 2,
+  "force_bos_token_to_be_generated": true,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -64,5 +69,7 @@
       "num_beams": 4
     }
   },
+  "transformers_version": "4.7.0.dev0",
+  "use_cache": true,
   "vocab_size": 50264
 }