Initialized

README.md

@@ -0,0 +1,32 @@
+---
+language: fa
+license: apache-2.0
+---
+
+# ALBERT-Persian
+
+A Lite BERT for Self-supervised Learning of Language Representations for the Persian Language
+
+> میتونی بهش بگی برت_کوچولو
+
+> Call it little_berty
+
+
+### BibTeX entry and citation info
+
+Please cite in your publication as the following:
+
+```bibtex
+@misc{ALBERTPersian,
+  author = {Mehrdad Farahani},
+  title = {ALBERT-Persian: A Lite BERT for Self-supervised Learning of Language Representations for the Persian Language},
+  year = {2021},
+  publisher = {GitHub},
+  journal = {GitHub repository},
+  howpublished = {\url{https://github.com/m3hrdadfi/albert-persian}},
+}
+```
+
+
+## Questions?
+Post a Github issue on the [ALBERT-Persian](https://github.com/m3hrdadfi/albert-persian) repo.

config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "AlbertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.2.2",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d68f3f623302e00bea37f6cdc4b6c01cb28fbd936367319c2a6ad2a6dd7a6f5
+size 44903266

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+    "bos_token": "[CLS]",
+    "eos_token": "[SEP]",
+    "unk_token": "<unk>",
+    "sep_token": "[SEP]",
+    "pad_token": "<pad>",
+    "cls_token": "[CLS]",
+    "mask_token": "[MASK]"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:903319b1a4a7e58e49383764d33897a7f49784510247d68438e4f3bff25b01f1
+size 857476

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6ec5b99be35daa07eeb205f5cfb6589706a3a11f8c2050d954b435cc74a4cd8
+size 60415224

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+    "do_lower_case": false,
+    "remove_space": true,
+    "keep_accents": false,
+    "bos_token": "[CLS]",
+    "eos_token": "[SEP]",
+    "unk_token": "<unk>",
+    "sep_token": "[SEP]",
+    "pad_token": "<pad>",
+    "cls_token": "[CLS]",
+    "mask_token": "[MASK]",
+    "special_tokens_map_file": null
+}