Upload M2M100ForConditionalGeneration

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "facebook/nllb-200-distilled-600M",
+  "_name_or_path": "facebook/nllb-200-1.3B",
   "activation_dropout": 0.0,
   "activation_function": "relu",
   "architectures": [
@@ -9,27 +9,26 @@
   "bos_token_id": 0,
   "d_model": 1024,
   "decoder_attention_heads": 16,
-  "decoder_ffn_dim": 4096,
+  "decoder_ffn_dim": 8192,
   "decoder_layerdrop": 0,
-  "decoder_layers": 12,
+  "decoder_layers": 24,
   "decoder_start_token_id": 2,
   "dropout": 0.1,
   "encoder_attention_heads": 16,
-  "encoder_ffn_dim": 4096,
+  "encoder_ffn_dim": 8192,
   "encoder_layerdrop": 0,
-  "encoder_layers": 12,
+  "encoder_layers": 24,
   "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,
+  "num_hidden_layers": 24,
   "pad_token_id": 1,
   "scale_embedding": true,
-  "tokenizer_class": "NllbTokenizer",
   "torch_dtype": "float32",
-  "transformers_version": "4.41.2",
+  "transformers_version": "4.33.0",
   "use_cache": true,
   "vocab_size": 256204
 }

generation_config.json

@@ -5,5 +5,5 @@
   "eos_token_id": 2,
   "max_length": 200,
   "pad_token_id": 1,
-  "transformers_version": "4.41.2"
+  "transformers_version": "4.33.0"
 }

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17a264b4c60492bd808b9b9756236c726da602103166518dc699cb04aac73cf2
+size 5482895247