update mask token embeddings

.ipynb_checkpoints/config-checkpoint.json

@@ -0,0 +1,74 @@
+{
+  "_name_or_path": "bart-base",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartModel"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "length_penalty": 1.0,
+      "max_length": 128,
+      "min_length": 12,
+      "num_beams": 4
+    },
+    "summarization_cnn": {
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "num_beams": 4
+    },
+    "summarization_xsum": {
+      "length_penalty": 1.0,
+      "max_length": 62,
+      "min_length": 11,
+      "num_beams": 6
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50265
+}

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "bart-base",
   "activation_dropout": 0.1,
   "activation_function": "gelu",
   "add_bias_logits": false,
@@ -66,7 +67,8 @@
       "num_beams": 6
     }
   },
-  "transformers_version": "4.7.0.dev0",
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.0.dev0",
   "use_cache": true,
   "vocab_size": 50265
 }

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3164d4f102798fb6f9cca23d2b952d5251d2011195183f42725809a9479e798
+oid sha256:53dd33667e5835469e2f7e32b51baf2356464ece3b80e3453a4febb83aa79752
 size 557690804

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c393f632913cdc64c13fcd1b039a74f17dd83cc3029c556802c0f2f8792b46f9
-size 557941479
+oid sha256:6e4fdb5e04114696ec4f7cc0cb5fc2a22a826f1c9eea234ca550b5390341a2fd
+size 557771387

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e9ad2cdde27cb028e63c63624bad056157121964fe7110237e27ab30e5b3ae8
-size 557956240
+oid sha256:7ed6459d5365fb22f77ab71e7b27b1ff13fde4752d5600b449a1c1ad782bd286
+size 557950280