Initial commit

README.md

@@ -0,0 +1,11 @@
+Converted for Tensorflow
+
+```
+!pip install transformers sentencepiece
+from transformers import TFAutoModel, AutoTokenizer
+name = "ai4bharat/indic-bert"
+model = TFAutoModel.from_pretrained(name, from_pt=True)
+tokenizer = AutoTokenizer.from_pretrained(name)
+model.save_pretrained("local-indic-bert")
+tokenizer.save_pretrained("local-indic-bert")
+```

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "ai4bharat/indic-bert",
+  "architectures": [
+    "AlbertModel"
+  ],
+  "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",
+  "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": "4.11.3",
+  "type_vocab_size": 2,
+  "vocab_size": 200000
+}

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 sha256:3a1173c2b6e144a02c001e289a05b5dbefddf247c50d4dcf42633158b2968fcb
+size 5646064

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9823391ce840af12149de02fdce23954e911e351f0e2bd635aefc03e97b0fcc0
+size 133811376

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "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": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "special_tokens_map_file": null, "name_or_path": "ai4bharat/indic-bert", "sp_model_kwargs": {}, "tokenizer_class": "AlbertTokenizer"}