Upload T5-Arabic-Base model

README.md

@@ -0,0 +1,21 @@
+---
+language: Arabic
+language: English
+datasets:
+- mc4
+license: apache-2.0
+---
+
+## Arabic T5 Base Model
+
+A customized T5 Model for Arabic and English Task. It could be used as an alternative for `google/mt5-base` model, as it's much smaller and only targets Arabic and English based tasks.
+
+### About T5
+
+```
+T5 is an encoder-decoder model pre-trained on a multi-task mixture of unsupervised and supervised tasks and for which each task is converted into a text-to-text format.
+
+The T5 model was presented in Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer by Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Peter J. Liu.
+```
+
+[Read More](https://ai.googleblog.com/2020/02/exploring-transfer-learning-with-t5.html)

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "bakrianoo/t5-arabic-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "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": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "transformers_version": "4.9.0.dev0",
+  "use_cache": true,
+  "vocab_size": 35000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:344ba7fd68e376e592efcea6deb8b3d97ea1f040723d2b29f8198a370beb8aa5
+size 1008087001

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b1638b19c09773fb382835ebed2a612ba15aceff181dd79703365aad4ae6821
+size 847294

tokenizer_config.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}