initial commit

config.json

@@ -0,0 +1,38 @@
+{
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "gradient_checkpointing": false,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_position_embeddings": 1024,
+  "model_type": "mvp",
+  "no_repeat_ngram_size": 3,
+  "num_beams": 5,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.2",
+  "use_cache": true,
+  "use_prompt": true,
+  "prompt_length": 100,
+  "prompt_mid_dim": 800,
+  "vocab_size": 50267
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25c77afff527293d6dbc7ac066efc216de6ad5f9faec0b70eb5f721f46e14bbb
+size 1872844515

tokenizer_config.json

@@ -0,0 +1 @@
+{"model_max_length": 1024}