xlmindic-base-multiscript tokenizer, model weights (in Pytorch, TF and Flax) and tags

README.md

@@ -1 +1,28 @@
-Hello World.
+---
+language:
+- as
+- bn
+- gu
+- hi
+- mr
+- ne
+- or
+- pa
+- si
+license: apache-2.0
+datasets:
+- oscar
+tags:
+- multilingual
+- albert
+- masked-language-modeling
+- sentence-order-prediction
+- fill-mask
+- nlp
+---
+
+# XLMIndic Base Uniscript
+
+Pretrained ALBERT model on the OSCAR corpus on the languages Assamese, Bengali, Gujarati, Hindi, Marathi, 
+Nepali, Oriya, Panjabi and Sinhala. Like ALBERT it was pretrained using as masked language modeling (MLM)
+and a sentence order prediction (SOP) objective.

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": ".",
+  "architectures": [
+    "AlbertForPreTraining"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "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",
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.15.0",
+  "type_vocab_size": 2,
+  "vocab_size": 50000
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2eccf3d75be315786c970ea4989f5f88474472a086c334c5ea74a8212567a1f
+size 57576476

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15d1fb119c9905f277d12f0beb7e829d1fc93e8316127314a69ab96bfa4089f2
+size 57591810

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": false}}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:214c9308d6ff921b9fab019e628c17ab57c95b0d01904ae298e7a2205abf9ef6
+size 1526052

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a3a6919ab5f5183bd6f72883fda7045c23806352d21e35f5e08bcf387ffc57a
+size 83696976

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": false, "__type": "AddedToken"}, "sp_model_kwargs": {}, "model_max_length": 512, "tokenizer_class": "AlbertTokenizer"}