Upload tokenizer
Browse files- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +9 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|startoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"pad_token": "<|pad|>",
|
| 5 |
+
"unk_token": "<|unk|>"
|
| 6 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|startoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 5 |
+
"pad_token": "<|pad|>",
|
| 6 |
+
"special_tokens_map_file": "geclm/tokenizers/split_digits/all_data_concatenated/special_tokens_map.json",
|
| 7 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 8 |
+
"unk_token": "<|unk|>"
|
| 9 |
+
}
|