Commit
·
25d3c1b
1
Parent(s):
0f38a01
Upload 4 files
Browse files- merges.txt +0 -0
- special_tokens_map.json +5 -1
- tokenizer_config.json +9 -0
- vocab.json +0 -0
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
CHANGED
|
@@ -1,5 +1,9 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": "<|endoftext|>",
|
| 3 |
"eos_token": "<|endoftext|>",
|
| 4 |
"unk_token": "<|endoftext|>"
|
| 5 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>"
|
| 5 |
+
],
|
| 6 |
"bos_token": "<|endoftext|>",
|
| 7 |
"eos_token": "<|endoftext|>",
|
| 8 |
"unk_token": "<|endoftext|>"
|
| 9 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 5 |
+
"clean_up_tokenization_spaces": true,
|
| 6 |
+
"eos_token": "<|endoftext|>",
|
| 7 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 8 |
+
"unk_token": "<|endoftext|>"
|
| 9 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|