Added model

hindi_sanskrit/added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 64000, "</s>": 64001, "<2as>": 64002, "<2bn>": 64003, "<2en>": 64004, "<2gu>": 64005, "<2hi>": 64006, "<2kn>": 64007, "<2ml>": 64008, "<2mr>": 64009, "<2or>": 64010, "<2pa>": 64011, "<2ta>": 64012, "<2te>": 64013}

hindi_sanskrit/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "ai4bharat/IndicBART",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "architectures": [
+    "MBartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 64000,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 64001,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_position_embeddings": 1024,
+  "model_type": "mbart",
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "scale_embedding": false,
+  "tokenizer_class": "AlbertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.19.4",
+  "use_cache": true,
+  "vocab_size": 64014
+}

hindi_sanskrit/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}, "additional_special_tokens": ["<s>", "</s>", "<2as>", "<2bn>", "<2en>", "<2gu>", "<2hi>", "<2kn>", "<2ml>", "<2mr>", "<2or>", "<2pa>", "<2ta>", "<2te>"]}

hindi_sanskrit/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": {}, "use_fast": false, "special_tokens_map_file": "albert-indicunified64k/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "ai4bharat/IndicBART", "tokenizer_class": "AlbertTokenizer"}