Isaak Carter Augustus
commited on
Commit
•
9dd132d
1
Parent(s):
be10e90
Upload tokenizer
Browse files- added_tokens.json +20 -0
- special_tokens_map.json +42 -0
- tokenizer.model +3 -0
- tokenizer_config.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|assistant|>": 32775,
|
3 |
+
"<|available_functions|>": 32770,
|
4 |
+
"<|context|>": 32783,
|
5 |
+
"<|current_states|>": 32782,
|
6 |
+
"<|endoftext|>": 32769,
|
7 |
+
"<|function_call|>": 32776,
|
8 |
+
"<|function_response|>": 32777,
|
9 |
+
"<|gökdeniz|>": 32772,
|
10 |
+
"<|home_state|>": 32781,
|
11 |
+
"<|im_end|>": 32785,
|
12 |
+
"<|im_start|>": 32784,
|
13 |
+
"<|image|>": 32778,
|
14 |
+
"<|josie|>": 32774,
|
15 |
+
"<|long_term_memory|>": 32779,
|
16 |
+
"<|short_term_memory|>": 32780,
|
17 |
+
"<|startoftext|>": 32768,
|
18 |
+
"<|system|>": 32771,
|
19 |
+
"<|user|>": 32773
|
20 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|available_functions|>",
|
4 |
+
"<|system|>",
|
5 |
+
"<|gökdeniz|>",
|
6 |
+
"<|user|>",
|
7 |
+
"<|josie|>",
|
8 |
+
"<|assistant|>",
|
9 |
+
"<|function_call|>",
|
10 |
+
"<|function_response|>",
|
11 |
+
"<|image|>",
|
12 |
+
"<|long_term_memory|>",
|
13 |
+
"<|short_term_memory|>",
|
14 |
+
"<|home_state|>",
|
15 |
+
"<|current_states|>",
|
16 |
+
"<|context|>",
|
17 |
+
"<|im_start|>",
|
18 |
+
"<|im_end|>"
|
19 |
+
],
|
20 |
+
"bos_token": {
|
21 |
+
"content": "<|startoftext|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
},
|
27 |
+
"eos_token": {
|
28 |
+
"content": "<|endoftext|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
},
|
34 |
+
"pad_token": "[control_768]",
|
35 |
+
"unk_token": {
|
36 |
+
"content": "<unk>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false
|
41 |
+
}
|
42 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
|
3 |
+
size 587404
|
tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|