Upload 3 files
Browse files- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +19 -0
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:656b66a920a54bc45e8e06dc587691ab3c0b2930b9ae56d5fa31e72db2f3bff3
|
3 |
+
size 1423961
|
tokenizer_config.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": false,
|
5 |
+
"additional_special_tokens": ["<|im_start|>", "<|im_end|>", "<fim_prefix>", "<fim_middle>", "<fim_suffix>", "<fim_pad>"],
|
6 |
+
"bos_token": "<|endoftext|>",
|
7 |
+
"clean_up_tokenization_spaces": false,
|
8 |
+
"eos_token": "<|im_end|>",
|
9 |
+
"legacy": false,
|
10 |
+
"model_max_length": 1000000000000000019884624838656,
|
11 |
+
"pad_token": "<fim_pad>",
|
12 |
+
"sp_model_kwargs": {},
|
13 |
+
"spaces_between_special_tokens": false,
|
14 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
15 |
+
"unk_token": "<unk>",
|
16 |
+
"use_default_system_prompt": false,
|
17 |
+
"add_prefix_space": true,
|
18 |
+
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
|
19 |
+
}
|