pashaprokaz
commited on
Commit
•
01856af
1
Parent(s):
f741fc8
Trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- added_tokens.json +5 -0
- merges.txt +0 -0
- special_tokens_map.json +16 -0
- tokenizer.json +0 -0
- tokenizer_config.json +36 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 151643,
|
3 |
+
"<|im_end|>": 151645,
|
4 |
+
"<|im_start|>": 151644
|
5 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": {
|
3 |
+
"content": "<|im_end|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"pad_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
}
|
16 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"151643": {
|
4 |
+
"content": "<|endoftext|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"151644": {
|
12 |
+
"content": "<|im_start|>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"151645": {
|
20 |
+
"content": "<|im_end|>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
}
|
27 |
+
},
|
28 |
+
"bos_token": null,
|
29 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if message['from'] == 'human' %}{{'<|user|>\n' + message['value'] + '<|end|>\n'}}{% elif message['from'] == 'gpt' %}{{'<|assistant|>\n' + message['value'] + '<|end|>\n'}}{% else %}{{'<|' + message['from'] + '|>\n' + message['value'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% endif %}",
|
30 |
+
"clean_up_tokenization_spaces": true,
|
31 |
+
"eos_token": "<|im_end|>",
|
32 |
+
"model_max_length": 1000000000000000019884624838656,
|
33 |
+
"pad_token": "<|endoftext|>",
|
34 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
35 |
+
"unk_token": null
|
36 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|