First version of the model

README.md

@@ -1,3 +1,17 @@
 ---
+language:
+- sl
+
 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.
+
+## Corpora
+The following corpora were used for training the model:
+* Gigafida 2.0
+* Kas 1.0
+* Janes 1.0 (only Janes-news, Janes-forum, Janes-blog, Janes-wiki subcorpora)
+* Slovenian parliamentary corpus siParl 2.0
+* slWaC

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 1024,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "gradient_checkpointing": false,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 8,
+  "num_heads": 6,
+  "num_layers": 8,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2470ebb115fdfb61504459a4e1f4924759cc59cbd438b0a25b2c5258daa2f8c2
+size 307402757

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79e3205b5a25b7a3b6fa48ea60d1c71d3b0f7adbaeb1d58949b04f8454946465
+size 797053