marianna13
commited on
Commit
•
f37b9fb
1
Parent(s):
14ddb96
Upload tokenizer
Browse files- README.md +3 -3
- added_tokens.json +40 -0
- merges.txt +0 -0
- special_tokens_map.json +7 -1
- tokenizer.json +0 -0
- vocab.json +0 -0
README.md
CHANGED
@@ -1,11 +1,11 @@
|
|
1 |
---
|
2 |
-
|
|
|
3 |
license: mit
|
|
|
4 |
datasets:
|
5 |
- liuhaotian/LLaVA-Instruct-150K
|
6 |
- liuhaotian/LLaVA-Pretrain
|
7 |
-
language:
|
8 |
-
- en
|
9 |
---
|
10 |
|
11 |
# Model Card for LLaVa-Phi-2-3B
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
license: mit
|
5 |
+
library_name: transformers
|
6 |
datasets:
|
7 |
- liuhaotian/LLaVA-Instruct-150K
|
8 |
- liuhaotian/LLaVA-Pretrain
|
|
|
|
|
9 |
---
|
10 |
|
11 |
# Model Card for LLaVa-Phi-2-3B
|
added_tokens.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"\t\t": 50294,
|
3 |
+
"\t\t\t": 50293,
|
4 |
+
"\t\t\t\t": 50292,
|
5 |
+
"\t\t\t\t\t": 50291,
|
6 |
+
"\t\t\t\t\t\t": 50290,
|
7 |
+
"\t\t\t\t\t\t\t": 50289,
|
8 |
+
"\t\t\t\t\t\t\t\t": 50288,
|
9 |
+
"\t\t\t\t\t\t\t\t\t": 50287,
|
10 |
+
" ": 50286,
|
11 |
+
" ": 50285,
|
12 |
+
" ": 50284,
|
13 |
+
" ": 50283,
|
14 |
+
" ": 50282,
|
15 |
+
" ": 50281,
|
16 |
+
" ": 50280,
|
17 |
+
" ": 50279,
|
18 |
+
" ": 50278,
|
19 |
+
" ": 50277,
|
20 |
+
" ": 50276,
|
21 |
+
" ": 50275,
|
22 |
+
" ": 50274,
|
23 |
+
" ": 50273,
|
24 |
+
" ": 50272,
|
25 |
+
" ": 50271,
|
26 |
+
" ": 50270,
|
27 |
+
" ": 50269,
|
28 |
+
" ": 50268,
|
29 |
+
" ": 50267,
|
30 |
+
" ": 50266,
|
31 |
+
" ": 50265,
|
32 |
+
" ": 50264,
|
33 |
+
" ": 50263,
|
34 |
+
" ": 50262,
|
35 |
+
" ": 50261,
|
36 |
+
" ": 50260,
|
37 |
+
" ": 50259,
|
38 |
+
" ": 50258,
|
39 |
+
" ": 50257
|
40 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
CHANGED
@@ -13,7 +13,13 @@
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
"unk_token": {
|
18 |
"content": "<|endoftext|>",
|
19 |
"lstrip": false,
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
"unk_token": {
|
24 |
"content": "<|endoftext|>",
|
25 |
"lstrip": false,
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|