Commit
·
130b107
1
Parent(s):
2e9e482
Upload 3 files
Browse files- special_tokens_map.json +5 -0
- tokenizer.json +0 -0
- tokenizer_config.json +9 -0
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"unk_token": "<|endoftext|>"
|
5 |
+
}
|
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 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"eos_token": "<|endoftext|>",
|
5 |
+
"name_or_path": "EleutherAI/gpt-neox-20b",
|
6 |
+
"special_tokens_map_file": "/root/.cache/huggingface/transformers/d9026dc928c47ac2a72d46fea7db959acc4bacac2176bf32be5c331604b77d32.3ae9ae72462581d20e36bc528e9c47bb30cd671bb21add40ca0b24a0be9fac22",
|
7 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
8 |
+
"unk_token": "<|endoftext|>"
|
9 |
+
}
|