Upload tokenizer
Browse files- README.md +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -13
README.md
CHANGED
|
@@ -1,3 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# BPE Tokenizer for Nepali LLM
|
| 2 |
|
| 3 |
This repository contains a Byte Pair Encoding (BPE) tokenizer trained using the Hugging Face `transformers` package on the Nepali LLM dataset. The tokenizer has been optimized for handling Nepali text and is intended for use in language modeling and other natural language processing tasks.
|
|
|
|
| 1 |
+
---
|
| 2 |
+
{}
|
| 3 |
+
---
|
| 4 |
# BPE Tokenizer for Nepali LLM
|
| 5 |
|
| 6 |
This repository contains a Byte Pair Encoding (BPE) tokenizer trained using the Hugging Face `transformers` package on the Nepali LLM dataset. The tokenizer has been optimized for handling Nepali text and is intended for use in language modeling and other natural language processing tasks.
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,47 +1,47 @@
|
|
| 1 |
{
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
-
"
|
| 4 |
-
"content": "<|
|
| 5 |
"lstrip": false,
|
| 6 |
"normalized": false,
|
| 7 |
"rstrip": false,
|
| 8 |
"single_word": false,
|
| 9 |
"special": true
|
| 10 |
},
|
| 11 |
-
"
|
| 12 |
-
"content": "<|
|
| 13 |
"lstrip": false,
|
| 14 |
"normalized": false,
|
| 15 |
"rstrip": false,
|
| 16 |
"single_word": false,
|
| 17 |
"special": true
|
| 18 |
},
|
| 19 |
-
"
|
| 20 |
-
"content": "<|
|
| 21 |
"lstrip": false,
|
| 22 |
"normalized": false,
|
| 23 |
"rstrip": false,
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
| 26 |
},
|
| 27 |
-
"
|
| 28 |
-
"content": "<|
|
| 29 |
"lstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"rstrip": false,
|
| 32 |
"single_word": false,
|
| 33 |
"special": true
|
| 34 |
},
|
| 35 |
-
"
|
| 36 |
-
"content": "<|
|
| 37 |
"lstrip": false,
|
| 38 |
"normalized": false,
|
| 39 |
"rstrip": false,
|
| 40 |
"single_word": false,
|
| 41 |
"special": true
|
| 42 |
},
|
| 43 |
-
"
|
| 44 |
-
"content": "
|
| 45 |
"lstrip": false,
|
| 46 |
"normalized": false,
|
| 47 |
"rstrip": false,
|
|
@@ -49,7 +49,8 @@
|
|
| 49 |
"special": true
|
| 50 |
}
|
| 51 |
},
|
| 52 |
-
"clean_up_tokenization_spaces":
|
|
|
|
| 53 |
"model_max_length": 1000000000000000019884624838656,
|
| 54 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 55 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
+
"50000": {
|
| 4 |
+
"content": "<|begin_of_text|>",
|
| 5 |
"lstrip": false,
|
| 6 |
"normalized": false,
|
| 7 |
"rstrip": false,
|
| 8 |
"single_word": false,
|
| 9 |
"special": true
|
| 10 |
},
|
| 11 |
+
"50001": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
"lstrip": false,
|
| 14 |
"normalized": false,
|
| 15 |
"rstrip": false,
|
| 16 |
"single_word": false,
|
| 17 |
"special": true
|
| 18 |
},
|
| 19 |
+
"50002": {
|
| 20 |
+
"content": "<|start_header_id|>",
|
| 21 |
"lstrip": false,
|
| 22 |
"normalized": false,
|
| 23 |
"rstrip": false,
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
| 26 |
},
|
| 27 |
+
"50003": {
|
| 28 |
+
"content": "<|end_header_id|>",
|
| 29 |
"lstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"rstrip": false,
|
| 32 |
"single_word": false,
|
| 33 |
"special": true
|
| 34 |
},
|
| 35 |
+
"50004": {
|
| 36 |
+
"content": "<|eot_id|>",
|
| 37 |
"lstrip": false,
|
| 38 |
"normalized": false,
|
| 39 |
"rstrip": false,
|
| 40 |
"single_word": false,
|
| 41 |
"special": true
|
| 42 |
},
|
| 43 |
+
"50005": {
|
| 44 |
+
"content": "\n\n",
|
| 45 |
"lstrip": false,
|
| 46 |
"normalized": false,
|
| 47 |
"rstrip": false,
|
|
|
|
| 49 |
"special": true
|
| 50 |
}
|
| 51 |
},
|
| 52 |
+
"clean_up_tokenization_spaces": false,
|
| 53 |
+
"extra_special_tokens": {},
|
| 54 |
"model_max_length": 1000000000000000019884624838656,
|
| 55 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 56 |
}
|