Upload model trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- special_tokens_map.json +4 -28
- tokenizer.json +2 -2
- tokenizer_config.json +6 -13
special_tokens_map.json
CHANGED
@@ -1,30 +1,6 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"eos_token": {
|
10 |
-
"content": "<eos>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"pad_token": {
|
17 |
-
"content": "<pad>",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
-
"unk_token": {
|
24 |
-
"content": "<unk>",
|
25 |
-
"lstrip": false,
|
26 |
-
"normalized": false,
|
27 |
-
"rstrip": false,
|
28 |
-
"single_word": false
|
29 |
-
}
|
30 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "<bos>",
|
3 |
+
"eos_token": "<|im_end|>",
|
4 |
+
"pad_token": "<pad>",
|
5 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
}
|
tokenizer.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10c5ca6deab5bf8bd9023b0d8836ccf06f15eac5b217b9548a2626a7a022ee24
|
3 |
+
size 17525361
|
tokenizer_config.json
CHANGED
@@ -11,7 +11,7 @@
|
|
11 |
"special": true
|
12 |
},
|
13 |
"1": {
|
14 |
-
"content": "
|
15 |
"lstrip": false,
|
16 |
"normalized": false,
|
17 |
"rstrip": false,
|
@@ -851,7 +851,7 @@
|
|
851 |
"special": false
|
852 |
},
|
853 |
"106": {
|
854 |
-
"content": "
|
855 |
"lstrip": false,
|
856 |
"normalized": false,
|
857 |
"rstrip": false,
|
@@ -1996,18 +1996,11 @@
|
|
1996 |
}
|
1997 |
},
|
1998 |
"bos_token": "<bos>",
|
1999 |
-
"chat_template": "{
|
2000 |
"clean_up_tokenization_spaces": false,
|
2001 |
-
"eos_token": "
|
2002 |
-
"
|
2003 |
-
"model_max_length": 8192,
|
2004 |
-
"pad_to_multiple_of": null,
|
2005 |
"pad_token": "<pad>",
|
2006 |
-
"pad_token_type_id": 0,
|
2007 |
-
"padding_side": "right",
|
2008 |
-
"sp_model_kwargs": {},
|
2009 |
-
"spaces_between_special_tokens": false,
|
2010 |
"tokenizer_class": "GemmaTokenizer",
|
2011 |
-
"unk_token": "<unk>"
|
2012 |
-
"use_default_system_prompt": false
|
2013 |
}
|
|
|
11 |
"special": true
|
12 |
},
|
13 |
"1": {
|
14 |
+
"content": "<|im_end|>",
|
15 |
"lstrip": false,
|
16 |
"normalized": false,
|
17 |
"rstrip": false,
|
|
|
851 |
"special": false
|
852 |
},
|
853 |
"106": {
|
854 |
+
"content": "<|im_start|>",
|
855 |
"lstrip": false,
|
856 |
"normalized": false,
|
857 |
"rstrip": false,
|
|
|
1996 |
}
|
1997 |
},
|
1998 |
"bos_token": "<bos>",
|
1999 |
+
"chat_template": "{% if 'role' in messages[0] %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{'<|im_start|>user\n' + message['content'] + '<|im_end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|im_start|>assistant\n' + message['content'] + '<|im_end|>\n' }}{% else %}{{ '<|im_start|>system\n' + message['content'] + '<|im_end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}{% else %}{{ bos_token }}{% for message in messages %}{% if message['from'] == 'human' %}{{'<|im_start|>user\n' + message['value'] + '<|im_end|>\n'}}{% elif message['from'] == 'gpt' %}{{'<|im_start|>assistant\n' + message['value'] + '<|im_end|>\n' }}{% else %}{{ '<|im_start|>system\n' + message['value'] + '<|im_end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}{% endif %}",
|
2000 |
"clean_up_tokenization_spaces": false,
|
2001 |
+
"eos_token": "<|im_end|>",
|
2002 |
+
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
|
2003 |
"pad_token": "<pad>",
|
|
|
|
|
|
|
|
|
2004 |
"tokenizer_class": "GemmaTokenizer",
|
2005 |
+
"unk_token": "<unk>"
|
|
|
2006 |
}
|