Update tokenizer_config.json
Browse files- tokenizer_config.json +1 -2
tokenizer_config.json
CHANGED
|
@@ -1,10 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"add_prefix_space": false,
|
| 3 |
"bos_token": "<|endoftext|>",
|
|
|
|
| 4 |
"eos_token": "<|endoftext|>",
|
| 5 |
"model_max_length": 2048,
|
| 6 |
-
"name_or_path": "../train/ipt-125m/hf-model/",
|
| 7 |
-
"special_tokens_map_file": "/home/jovyan/nfs/nlandro/hf_hub/models--EleutherAI--gpt-neox-20b/snapshots/4e49eadb5d14bd22f314ec3f45b69a87b88c7691/special_tokens_map.json",
|
| 8 |
"tokenizer_class": "GPTNeoXTokenizer",
|
| 9 |
"unk_token": "<|endoftext|>"
|
| 10 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"add_prefix_space": false,
|
| 3 |
"bos_token": "<|endoftext|>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
"eos_token": "<|endoftext|>",
|
| 6 |
"model_max_length": 2048,
|
|
|
|
|
|
|
| 7 |
"tokenizer_class": "GPTNeoXTokenizer",
|
| 8 |
"unk_token": "<|endoftext|>"
|
| 9 |
}
|