Upload M2M100ForConditionalGeneration

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "jla25/results",
+  "_name_or_path": "jla25/squareV3",
   "activation_dropout": 0.0,
   "activation_function": "relu",
   "architectures": [
@@ -14,7 +14,7 @@
   "decoder_layers": 12,
   "decoder_start_token_id": 2,
   "dropout": 0.1,
-  "early_stopping": true,
+  "early_stopping": null,
   "encoder_attention_heads": 16,
   "encoder_ffn_dim": 4096,
   "encoder_layerdrop": 0.05,
@@ -23,15 +23,15 @@
   "gradient_checkpointing": false,
   "init_std": 0.02,
   "is_encoder_decoder": true,
-  "max_length": 200,
+  "max_length": null,
   "max_position_embeddings": 1024,
   "model_type": "m2m_100",
-  "num_beams": 5,
+  "num_beams": null,
   "num_hidden_layers": 12,
   "pad_token_id": 1,
   "scale_embedding": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.44.2",
+  "transformers_version": "4.46.2",
   "use_cache": true,
   "vocab_size": 128112
 }

generation_config.json

@@ -7,5 +7,5 @@
   "max_length": 200,
   "num_beams": 5,
   "pad_token_id": 1,
-  "transformers_version": "4.44.2"
+  "transformers_version": "4.46.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:187896e69ba282c13ca8b8568794eda2ca9c957649277314e080fb30e7ca7a9e
+oid sha256:191a33fcd9d7fb92438de5a21f78df5fe9a8fa9b1d5d4972fd93eb6d0af39a96
 size 1935681888