NLTM

MKB_NIOS_hindi_sanskrit_5/added_tokens.json

@@ -1,16 +0,0 @@
-{
-  "</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,
-  "<s>": 64000
-}

MKB_NIOS_hindi_sanskrit_5/config.json

@@ -1,36 +0,0 @@
-{
-  "_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": "4.20.1",
-  "use_cache": true,
-  "vocab_size": 64014
-}

MKB_NIOS_hindi_sanskrit_5/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a21d3296e8659cbb6d10ca1fefd86abccb5b8f470b112c964dc730bb322a225e
-size 976412337

MKB_NIOS_hindi_sanskrit_5/special_tokens_map.json

@@ -1,31 +0,0 @@
-{
-  "additional_special_tokens": [
-    "<s>",
-    "</s>",
-    "<2as>",
-    "<2bn>",
-    "<2en>",
-    "<2gu>",
-    "<2hi>",
-    "<2kn>",
-    "<2ml>",
-    "<2mr>",
-    "<2or>",
-    "<2pa>",
-    "<2ta>",
-    "<2te>"
-  ],
-  "bos_token": "[CLS]",
-  "cls_token": "[CLS]",
-  "eos_token": "[SEP]",
-  "mask_token": {
-    "content": "[MASK]",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<pad>",
-  "sep_token": "[SEP]",
-  "unk_token": "<unk>"
-}

MKB_NIOS_hindi_sanskrit_5/spiece.model

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9d924c4e4e0d7a073e8289c20e29cd27657629064f2571fb18ab82008cf79a72
-size 1898704

MKB_NIOS_hindi_sanskrit_5/tokenizer_config.json

@@ -1,25 +0,0 @@
-{
-  "bos_token": "[CLS]",
-  "cls_token": "[CLS]",
-  "do_lower_case": false,
-  "eos_token": "[SEP]",
-  "keep_accents": true,
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "[MASK]",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "name_or_path": "ai4bharat/IndicBART",
-  "pad_token": "<pad>",
-  "remove_space": true,
-  "sep_token": "[SEP]",
-  "sp_model_kwargs": {},
-  "special_tokens_map_file": "albert-indicunified64k/special_tokens_map.json",
-  "tokenizer_class": "AlbertTokenizer",
-  "tokenizer_file": null,
-  "unk_token": "<unk>",
-  "use_fast": false
-}

MKB_NIOS_hindi_sanskrit_5/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:518285c971d6f874d7889b31092801dd7e198f2b4d3cae342b61683869a66e9c
-size 3375

app.py

@@ -4,7 +4,7 @@ from transformers import pipeline
 import indicnlp
 from indicnlp.transliterate.unicode_transliterate import UnicodeIndicTransliterator
 
-model_checkpoint = './MKB_NIOS_hindi_sanskrit_5'
+model_checkpoint = './hindi_sanskrit'
 translator = pipeline('translation', model=model_checkpoint, decoder_start_token='<2sa>')
 
 st.title('NLTM')