Upload MarianForCausalLM

config.json

@@ -1,42 +1,42 @@
-{
-  "_name_or_path": "Helsinki-NLP/opus-mt-tc-big-en-ko",
-  "activation_dropout": 0.0,
-  "activation_function": "relu",
-  "architectures": [
-    "MarianForCausalLM"
-  ],
-  "attention_dropout": 0.0,
-  "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": 6,
-  "decoder_start_token_id": 32000,
-  "decoder_vocab_size": 32001,
-  "dropout": 0.1,
-  "encoder_attention_heads": 16,
-  "encoder_ffn_dim": 4096,
-  "encoder_layerdrop": 0.0,
-  "encoder_layers": 6,
-  "eos_token_id": 2,
-  "forced_eos_token_id": null,
-  "init_std": 0.02,
-  "is_decoder": true,
-  "is_encoder_decoder": false,
-  "max_length": null,
-  "max_position_embeddings": 1024,
-  "model_type": "marian",
-  "normalize_embedding": false,
-  "num_beams": null,
-  "num_hidden_layers": 6,
-  "pad_token_id": 32000,
-  "scale_embedding": true,
-  "share_encoder_decoder_embeddings": true,
-  "static_position_embeddings": true,
-  "torch_dtype": "float16",
-  "transformers_version": "4.45.1",
-  "use_cache": true,
-  "vocab_size": 32001
-}
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-tc-big-en-ko",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "MarianForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "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": 6,
+  "decoder_start_token_id": 32000,
+  "decoder_vocab_size": 32001,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "forced_eos_token_id": null,
+  "init_std": 0.02,
+  "is_decoder": true,
+  "is_encoder_decoder": false,
+  "max_length": null,
+  "max_position_embeddings": 1024,
+  "model_type": "marian",
+  "normalize_embedding": false,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "pad_token_id": 32000,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.1",
+  "use_cache": true,
+  "vocab_size": 32001
+}

generation_config.json

@@ -1,16 +1,16 @@
-{
-  "bad_words_ids": [
-    [
-      32000
-    ]
-  ],
-  "bos_token_id": 0,
-  "decoder_start_token_id": 32000,
-  "eos_token_id": 2,
-  "forced_eos_token_id": 2,
-  "max_length": 512,
-  "num_beams": 4,
-  "pad_token_id": 32000,
-  "renormalize_logits": true,
-  "transformers_version": "4.45.1"
-}
+{
+  "bad_words_ids": [
+    [
+      32000
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 32000,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 32000,
+  "renormalize_logits": true,
+  "transformers_version": "4.45.1"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88bf4c1f4b4dccb35fa2acfe6a4a39e3d3b5f49efb5ab3247fe734e2f641e38b
-size 275512400
+oid sha256:11978e10c79c4273df5897b527d5397e561ff2f296ee7664fed98cd628ee8552
+size 550999184