Upload tokenizer

README.md

@@ -1,15 +1,15 @@
 ---
-license: apache-2.0
-pipeline_tag: text-generation
 language:
 - ta
+license: apache-2.0
 tags:
 - pretrained
+datasets:
+- Hemanth-thunder/tamil-madlad-400
+pipeline_tag: text-generation
 inference:
   parameters:
     temperature: 0.7
-datasets:
-- Hemanth-thunder/tamil-madlad-400
 ---
 # Model Card for Tamil-Mistral-7B-v0.1
 

special_tokens_map.json

@@ -13,13 +13,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "pad_token": "</s>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 200,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

tokenizer_config.json

@@ -1,6 +1,7 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
+  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",