updated with v2 model

README.md

@@ -7,6 +7,7 @@ license: cc-by-sa-4.0
 
 # t5-sl-small
 t5-sl-small model is a Slovene T5 model. It has 8 encoder and 8 decoder layers, in total about 60 million parameters.
+It was trained for 5 epochs on the following corpora:
 
 ## Corpora
 The following corpora were used for training the model:
@@ -15,3 +16,6 @@ The following corpora were used for training the model:
 * Janes 1.0 (only Janes-news, Janes-forum, Janes-blog, Janes-wiki subcorpora)
 * Slovenian parliamentary corpus siParl 2.0
 * slWaC
+
+## Changelog
+2022-07-21: updated with v2 of the model, the old one is still accesible at [cjvt/legacy-t5-sl-small](https://huggingface.co/cjvt/legacy-t5-sl-small).

config.json

@@ -22,7 +22,7 @@
   "relative_attention_num_buckets": 32,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.11.0.dev0",
+  "transformers_version": "4.9.1",
   "use_cache": true,
   "vocab_size": 32000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2470ebb115fdfb61504459a4e1f4924759cc59cbd438b0a25b2c5258daa2f8c2
+oid sha256:891fa1f9de9d243383fe075f4e8a044b3147a842d21d05f4e7a91db19eb820c0
 size 307402757