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

@@ -8,52 +8,40 @@
   "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,
   "decoder_layerdrop": 0.0,
   "decoder_layers": 12,
-  "do_sample": false,
+  "decoder_start_token_id": 2,
   "dropout": 0.1,
-  "early_stopping": false,
   "encoder_attention_heads": 16,
   "encoder_ffn_dim": 4096,
   "encoder_layerdrop": 0.0,
   "encoder_layers": 12,
   "eos_token_id": 2,
-  "finetuning_task": null,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
   "id2label": {
     "0": "contradiction",
     "1": "neutral",
     "2": "entailment"
   },
   "init_std": 0.02,
-  "is_decoder": false,
   "is_encoder_decoder": true,
   "label2id": {
     "contradiction": 0,
     "entailment": 2,
     "neutral": 1
   },
-  "length_penalty": 1.0,
-  "max_length": 20,
   "max_position_embeddings": 1024,
-  "min_length": 0,
   "model_type": "bart",
-  "no_repeat_ngram_size": 0,
-  "num_beams": 1,
   "num_hidden_layers": 12,
-  "num_return_sequences": 1,
-  "output_attentions": false,
-  "output_hidden_states": false,
   "output_past": false,
   "pad_token_id": 1,
-  "pruned_heads": {},
-  "repetition_penalty": 1.0,
-  "temperature": 1.0,
-  "top_k": 50,
-  "top_p": 1.0,
-  "torchscript": false,
-  "use_bfloat16": false,
+  "scale_embedding": false,
+  "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 sha256:4cea25662c8c2d19f61ec3f271d41fad7d83b2b4218e5e2a8926744f053f6b46
+size 1629394629