add model

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "/data/suraj/wmt21-x-en-24-wide",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "M2M100ForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "d_model": 2048,
+  "decoder_attention_heads": 32,
+  "decoder_ffn_dim": 16384,
+  "decoder_layerdrop": 0,
+  "decoder_layers": 24,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 32,
+  "encoder_ffn_dim": 16384,
+  "encoder_layerdrop": 0,
+  "encoder_layers": 24,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 128001,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_length": 200,
+  "max_position_embeddings": 1024,
+  "model_type": "m2m_100",
+  "num_beams": 5,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.13.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128009
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e457a9180ca920d431d9a2511eeb477e559195f304e2b3ecc85f95be57c26024
+size 18773661472

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cad99b5428aa4802c265015a12dd8a18a43b9d53a3ae8cc123e7e25aba7ef4f
+size 2586236

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "additional_special_tokens": ["__en__", "__ha__", "__is__", "__ja__", "__cs__", "__ru__", "__zh__", "__de__"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"src_lang": null, "tgt_lang": "en", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "sp_model_kwargs": {}, "language_codes": "wmt21", "num_madeup_words": 0, "additional_special_tokens": ["__en__", "__ha__", "__is__", "__ja__", "__cs__", "__ru__", "__zh__", "__de__"], "tokenizer_class": "M2M100Tokenizer"}