Upload tokenizer
Browse files- chat_template.jinja +4 -0
- cl100k_base.tiktoken +0 -0
- special_tokens_map.json +11 -0
- tokenizer_config.json +24 -0
chat_template.jinja
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{ bos_token }}{% for message in messages %}{{'<|' + message['role'] + '|>' + '
|
| 2 |
+
' + message['content'] + '<|end|>
|
| 3 |
+
' }}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>
|
| 4 |
+
' }}{% else %}{{ eos_token }}{% endif %}
|
cl100k_base.tiktoken
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": {
|
| 4 |
+
"content": "<|end|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
"pad_token": "<|endoftext|>"
|
| 11 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_commit_hash": "188b876e997ee4055df01afe46274c14c400fe40",
|
| 3 |
+
"_from_auto": true,
|
| 4 |
+
"added_tokens_decoder": {},
|
| 5 |
+
"auto_map": {
|
| 6 |
+
"AutoTokenizer": [
|
| 7 |
+
"tokenization_phi3_small.Phi3SmallTokenizer",
|
| 8 |
+
null
|
| 9 |
+
]
|
| 10 |
+
},
|
| 11 |
+
"bos_token": "<|endoftext|>",
|
| 12 |
+
"cache_dir": null,
|
| 13 |
+
"clean_up_tokenization_spaces": true,
|
| 14 |
+
"eos_token": "<|end|>",
|
| 15 |
+
"extra_special_tokens": {},
|
| 16 |
+
"model_max_length": 8192,
|
| 17 |
+
"pad_token": "<|endoftext|>",
|
| 18 |
+
"padding_side": "left",
|
| 19 |
+
"revision": "main",
|
| 20 |
+
"split_special_tokens": false,
|
| 21 |
+
"token": null,
|
| 22 |
+
"tokenizer_class": "Phi3SmallTokenizer",
|
| 23 |
+
"trust_remote_code": true
|
| 24 |
+
}
|