Upload tokenizer
Browse files- README.md +6 -6
- merges.txt +0 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +0 -0
- vocab.json +0 -0
README.md
CHANGED
@@ -1,17 +1,17 @@
|
|
1 |
---
|
2 |
-
license: apache-2.0
|
3 |
base_model:
|
4 |
- werty1248/Mistral-Nemo-NT-Ko-12B-sft
|
5 |
-
language:
|
6 |
-
- en
|
7 |
-
- ko
|
8 |
-
- ja
|
9 |
-
- zh
|
10 |
datasets:
|
11 |
- zake7749/kyara-chinese-preference-rl-dpo-s0-30K
|
12 |
- sionic/ko-dpo-mix-7k-trl-style
|
13 |
- kuotient/orca-math-korean-dpo-pairs
|
14 |
- HuggingFaceH4/ultrafeedback_binarized
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
---
|
16 |
# Mistral-Nemo-NT-Ko-12B-dpo-test
|
17 |
|
|
|
1 |
---
|
|
|
2 |
base_model:
|
3 |
- werty1248/Mistral-Nemo-NT-Ko-12B-sft
|
|
|
|
|
|
|
|
|
|
|
4 |
datasets:
|
5 |
- zake7749/kyara-chinese-preference-rl-dpo-s0-30K
|
6 |
- sionic/ko-dpo-mix-7k-trl-style
|
7 |
- kuotient/orca-math-korean-dpo-pairs
|
8 |
- HuggingFaceH4/ultrafeedback_binarized
|
9 |
+
language:
|
10 |
+
- en
|
11 |
+
- ko
|
12 |
+
- ja
|
13 |
+
- zh
|
14 |
+
license: apache-2.0
|
15 |
---
|
16 |
# Mistral-Nemo-NT-Ko-12B-dpo-test
|
17 |
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
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 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|