Upload tokenizer
Browse files- cl100k_base.tiktoken +0 -0
- special_tokens_map.json +5 -0
- tokenizer_config.json +13 -0
cl100k_base.tiktoken
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"pad_token": "<|endoftext|>"
|
| 5 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_commit_hash": "f5527db8a43fc9a4bf17c5b754251e1efe1d4ad3",
|
| 3 |
+
"_from_auto": true,
|
| 4 |
+
"added_tokens_decoder": {},
|
| 5 |
+
"bos_token": "<|endoftext|>",
|
| 6 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
|
| 7 |
+
"clean_up_tokenization_spaces": true,
|
| 8 |
+
"eos_token": "<|endoftext|>",
|
| 9 |
+
"model_max_length": 8192,
|
| 10 |
+
"pad_token": "<|endoftext|>",
|
| 11 |
+
"tokenizer_class": "Phi3SmallTokenizer",
|
| 12 |
+
"trust_remote_code": true
|
| 13 |
+
}
|