ibokajordan/mbart_final_RAG2

README.md

@@ -49,7 +49,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.52.2
-- Pytorch 2.6.0+cu124
-- Datasets 2.14.4
-- Tokenizers 0.21.1
+- Transformers 4.48.3
+- Pytorch 2.5.1+cu124
+- Datasets 3.6.0
+- Tokenizers 0.21.0

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "facebook/mbart-large-50-many-to-many-mmt",
   "_num_labels": 3,
   "activation_dropout": 0.0,
   "activation_function": "relu",
@@ -51,7 +52,7 @@
   "static_position_embeddings": false,
   "tokenizer_class": "MBart50Tokenizer",
   "torch_dtype": "float32",
-  "transformers_version": "4.52.2",
+  "transformers_version": "4.48.3",
   "use_cache": true,
   "vocab_size": 250054
 }

generation_config.json

@@ -4,9 +4,10 @@
   "decoder_start_token_id": 2,
   "early_stopping": true,
   "eos_token_id": 2,
+  "forced_bos_token_id": 250023,
   "forced_eos_token_id": 2,
   "max_length": 200,
   "num_beams": 5,
   "pad_token_id": 1,
-  "transformers_version": "4.52.2"
+  "transformers_version": "4.48.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4253c08105fff31ac19733528c2497e4be5711fdbf7c54a07f5bc37e10fb3a6b
+oid sha256:92ce936cb513ad8469618bcc8346495188c81f8bd4bd3b55979f945f33acf927
 size 2444578688

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c78bf7827358e64760b0fc79f4f3fddf2c6626cbde209a362cf3b1b881013f2a
+oid sha256:0e19ec7524391598dd260bdd47a0797825ffe78a27bd52b61940690ef01192a3
 size 5304