new version, now with more data

config.json

@@ -20,7 +20,6 @@
   "encoder_layerdrop": 0.05,
   "encoder_layers": 12,
   "eos_token_id": 2,
-  "forced_bos_token_id": 128028,
   "gradient_checkpointing": false,
   "init_std": 0.02,
   "is_encoder_decoder": true,
@@ -32,7 +31,7 @@
   "pad_token_id": 1,
   "scale_embedding": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.24.0",
+  "transformers_version": "4.26.1",
   "use_cache": true,
-  "vocab_size": 128112
+  "vocab_size": 128113
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1c8ae0171f992187869f7f6979a8762112705b6caa0404548a13cf039f8a5f1
-size 1935795713
+oid sha256:20e37f1f5345586165b1a8c5c93fd81894233c54739b13d4fb1660ccd9f906cd
+size 1944194627

special_tokens_map.json

@@ -103,6 +103,7 @@
   ],
   "bos_token": "<s>",
   "eos_token": "</s>",
+  "mask_token": "<mask>",
   "pad_token": "<pad>",
   "sep_token": "</s>",
   "unk_token": "<unk>"