Upload tokenizer

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+model.SRC filter=lfs diff=lfs merge=lfs -text
+model.TGT filter=lfs diff=lfs merge=lfs -text

model.SRC

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cedc5cbcc740369b76201942a0f096fec7287fee039b55bdb956f301235b914
+size 759425

model.TGT

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac9257c8e76b8b607705b959cc3d075656ea33032f7a974e467b8941df6e98d4
+size 3256903

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,53 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "auto_map": {
+    "AutoTokenizer": [
+      "ai4bharat/indictrans2-en-indic-dist-200M--tokenization_indictrans.IndicTransTokenizer",
+      null
+    ]
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 256,
+  "pad_token": "<pad>",
+  "src_vocab_file": "/root/.cache/huggingface/hub/models--ai4bharat--indictrans2-en-indic-dist-200M/snapshots/cfd37e5675971641e606255e75a8e56b3e453b50/dict.SRC.json",
+  "tgt_vocab_file": "/root/.cache/huggingface/hub/models--ai4bharat--indictrans2-en-indic-dist-200M/snapshots/cfd37e5675971641e606255e75a8e56b3e453b50/dict.SRC.json",
+  "tokenizer_class": "IndicTransTokenizer",
+  "unk_token": "<unk>"
+}