Upload M2M100ForConditionalGeneration

config.json

@@ -1,59 +1,35 @@
 {
-  "_name_or_path": "facebook/mbart-large-50-many-to-many-mmt",
-  "_num_labels": 3,
+  "_name_or_path": "facebook/nllb-200-distilled-600M",
   "activation_dropout": 0.0,
   "activation_function": "relu",
-  "add_bias_logits": false,
-  "add_final_layer_norm": true,
   "architectures": [
-    "MBartForConditionalGeneration"
+    "M2M100ForConditionalGeneration"
   ],
-  "attention_dropout": 0.0,
+  "attention_dropout": 0.1,
   "bos_token_id": 0,
-  "classif_dropout": 0.0,
-  "classifier_dropout": 0.0,
   "d_model": 1024,
   "decoder_attention_heads": 16,
   "decoder_ffn_dim": 4096,
-  "decoder_layerdrop": 0.0,
+  "decoder_layerdrop": 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_layerdrop": 0,
   "encoder_layers": 12,
   "eos_token_id": 2,
-  "forced_bos_token_id": 250001,
-  "forced_eos_token_id": 2,
-  "gradient_checkpointing": false,
-  "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": 200,
   "max_position_embeddings": 1024,
-  "model_type": "mbart",
-  "normalize_before": true,
-  "normalize_embedding": true,
-  "num_beams": 5,
+  "model_type": "m2m_100",
   "num_hidden_layers": 12,
-  "output_past": true,
   "pad_token_id": 1,
   "scale_embedding": true,
-  "static_position_embeddings": false,
-  "tokenizer_class": "MBart50Tokenizer",
+  "tokenizer_class": "NllbTokenizer",
   "torch_dtype": "float32",
   "transformers_version": "4.38.2",
   "use_cache": true,
-  "vocab_size": 250054
+  "vocab_size": 256206
 }

generation_config.json

@@ -2,11 +2,8 @@
   "_from_model_config": true,
   "bos_token_id": 0,
   "decoder_start_token_id": 2,
-  "early_stopping": true,
   "eos_token_id": 2,
-  "forced_eos_token_id": 2,
   "max_length": 200,
-  "num_beams": 5,
   "pad_token_id": 1,
   "transformers_version": "4.38.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10ef2c7b94d92f301d64ed29825ed05cb5374f347d8db7755de5474295e07ff7
-size 2444578688
+oid sha256:c26fea1b0788456e3e0d6dfd0165cacec798a0b6d957c9045a234826994dec41
+size 2460354912