Upload M2M100ForConditionalGeneration

config.json

@@ -1,35 +1,35 @@
-{
-  "_name_or_path": "../models/nllb-deu-frr-v3-cp6",
-  "activation_dropout": 0.0,
-  "activation_function": "relu",
-  "architectures": [
-    "M2M100ForConditionalGeneration"
-  ],
-  "attention_dropout": 0.1,
-  "bos_token_id": 0,
-  "d_model": 1024,
-  "decoder_attention_heads": 16,
-  "decoder_ffn_dim": 4096,
-  "decoder_layerdrop": 0,
-  "decoder_layers": 12,
-  "decoder_start_token_id": 2,
-  "dropout": 0.1,
-  "encoder_attention_heads": 16,
-  "encoder_ffn_dim": 4096,
-  "encoder_layerdrop": 0,
-  "encoder_layers": 12,
-  "eos_token_id": 2,
-  "init_std": 0.02,
-  "is_encoder_decoder": true,
-  "max_length": 200,
-  "max_position_embeddings": 1024,
-  "model_type": "m2m_100",
-  "num_hidden_layers": 12,
-  "pad_token_id": 1,
-  "scale_embedding": true,
-  "tokenizer_class": "NllbTokenizer",
-  "torch_dtype": "float32",
-  "transformers_version": "4.33.0",
-  "use_cache": true,
-  "vocab_size": 256205
-}
+{
+  "_name_or_path": "models/nllb-deu-frr-v5-cp5",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "M2M100ForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_length": 200,
+  "max_position_embeddings": 1024,
+  "model_type": "m2m_100",
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "tokenizer_class": "NllbTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.0",
+  "use_cache": true,
+  "vocab_size": 256205
+}

generation_config.json

@@ -1,9 +1,9 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 0,
-  "decoder_start_token_id": 2,
-  "eos_token_id": 2,
-  "max_length": 200,
-  "pad_token_id": 1,
-  "transformers_version": "4.33.0"
-}
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "max_length": 200,
+  "pad_token_id": 1,
+  "transformers_version": "4.33.0"
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cee6bc164493ae8609c80fc3be302b6d8072d9b387aaef62490395b7f3d17cf
+oid sha256:3dd4d525a128b2b45e67bd3b28e5d33d47b0e507b636eeae128e5318413b3d37
 size 2460465086