Initial commit for MahaAlBERT model trained on L3Cube-MahaMono Corpus

added_tokens.json

@@ -0,0 +1 @@
+{"<pad>": 32000}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "l3cube-pune/marathi-albert",
+  "architectures": [
+    "AlbertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.1",
+  "type_vocab_size": 2,
+  "vocab_size": 32001
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b4a694e962a7b2fd9ae33d659ea421324991d3e47bce639606a6082fa365f6b
+size 45934350

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac082d4350fd4cf7bd47c220d25bac43d402a19471029e8ffcffa64037c557cd
+size 1191645

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "remove_space": true, "keep_accents": true, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "max_len": 512, "model_type": "albert", "special_tokens_map_file": null, "name_or_path": "l3cube-pune/marathi-albert", "tokenizer_class": "AlbertTokenizer"}