Initial commit

config.json

@@ -0,0 +1,37 @@
+{
+  "architectures": [
+    "FSMTForConditionalGeneration"
+  ],
+  "model_type": "fsmt",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "attention_dropout": 0.1,
+  "d_model": 1024,
+  "dropout": 0.2,
+  "init_std": 0.02,
+  "max_position_embeddings": 1024,
+  "num_hidden_layers": 6,
+  "src_vocab_size": 31232,
+  "tgt_vocab_size": 31640,
+  "langs": [
+    "ru",
+    "en"
+  ],
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 8192,
+  "encoder_layerdrop": 0,
+  "encoder_layers": 6,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0,
+  "decoder_layers": 6,
+  "bos_token_id": 0,
+  "pad_token_id": 1,
+  "eos_token_id": 2,
+  "is_encoder_decoder": true,
+  "scale_embedding": true,
+  "tie_word_embeddings": false,
+  "num_beams": 5,
+  "early_stopping": false,
+  "length_penalty": 1.0
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c94dd6e36aa6e6cbed31effd4c7134fa839b9ec68eeaa54460cdbf58c4e43de8
+size 1668112133

tokenizer_config.json

@@ -0,0 +1,8 @@
+{
+  "langs": [
+    "ru",
+    "en"
+  ],
+  "model_max_length": 1024,
+  "do_lower_case": false
+}