Upload tokenizer
Browse files- cl100k_base.tiktoken +0 -0
- special_tokens_map.json +5 -0
- tokenizer_config.json +19 -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 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_commit_hash": "69caae1f2acea34b26f535fecb1f2abb9a304695",
|
3 |
+
"_from_auto": true,
|
4 |
+
"added_tokens_decoder": {},
|
5 |
+
"auto_map": {
|
6 |
+
"AutoTokenizer": [
|
7 |
+
"tokenization_phi3_small.Phi3SmallTokenizer",
|
8 |
+
"tokenization_phi3_small.Phi3SmallTokenizer"
|
9 |
+
]
|
10 |
+
},
|
11 |
+
"bos_token": "<|endoftext|>",
|
12 |
+
"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 %}",
|
13 |
+
"clean_up_tokenization_spaces": true,
|
14 |
+
"eos_token": "<|endoftext|>",
|
15 |
+
"model_max_length": 8192,
|
16 |
+
"pad_token": "<|endoftext|>",
|
17 |
+
"tokenizer_class": "Phi3SmallTokenizer",
|
18 |
+
"trust_remote_code": true
|
19 |
+
}
|