Upload model

config.json

@@ -1,56 +1,56 @@
-{
-  "_name_or_path": "zizi",
-  "activation_dropout": 0.0,
-  "activation_function": "swish",
-  "add_bias_logits": false,
-  "add_final_layer_norm": false,
-  "architectures": [
-    "MarianMTModel"
-  ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 0,
-  "classif_dropout": 0.0,
-  "classifier_dropout": 0.0,
-  "d_model": 256,
-  "decoder_attention_heads": 4,
-  "decoder_ffn_dim": 1024,
-  "decoder_layerdrop": 0.0,
-  "decoder_layers": 4,
-  "decoder_start_token_id": 29066,
-  "decoder_vocab_size": 29067,
-  "dropout": 0.1,
-  "encoder_attention_heads": 4,
-  "encoder_ffn_dim": 1024,
-  "encoder_layerdrop": 0.0,
-  "encoder_layers": 4,
-  "eos_token_id": 0,
-  "extra_pos_embeddings": 29067,
-  "forced_eos_token_id": 0,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2"
-  },
-  "init_std": 0.02,
-  "is_encoder_decoder": true,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2
-  },
-  "max_length": null,
-  "max_position_embeddings": 512,
-  "model_type": "marian",
-  "normalize_before": false,
-  "normalize_embedding": false,
-  "num_beams": null,
-  "num_hidden_layers": 4,
-  "pad_token_id": 29066,
-  "scale_embedding": true,
-  "share_encoder_decoder_embeddings": true,
-  "static_position_embeddings": true,
-  "torch_dtype": "float32",
-  "transformers_version": "4.46.3",
-  "use_cache": true,
-  "vocab_size": 29067
-}
+{
+  "_name_or_path": "Moleys/yiyi",
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 256,
+  "decoder_attention_heads": 4,
+  "decoder_ffn_dim": 1024,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 4,
+  "decoder_start_token_id": 29066,
+  "decoder_vocab_size": 29067,
+  "dropout": 0.1,
+  "encoder_attention_heads": 4,
+  "encoder_ffn_dim": 1024,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 4,
+  "eos_token_id": 0,
+  "extra_pos_embeddings": 29067,
+  "forced_eos_token_id": 0,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": null,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": null,
+  "num_hidden_layers": 4,
+  "pad_token_id": 29066,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "use_cache": true,
+  "vocab_size": 29067
+}

generation_config.json

@@ -12,5 +12,5 @@
   "max_length": 512,
   "num_beams": 6,
   "pad_token_id": 29066,
-  "transformers_version": "4.47.1"
+  "transformers_version": "4.48.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1346ebba926634b1580769868ee192fcd25193b7dbbcbd9072cc6b23bd01e338
+oid sha256:d6f9d3448a7947b8ff2c8ed96600951eab32b9ff3d7d2ca5681a3737a8a7c543
 size 59391260