kyujinpy commited on
Commit
d50c04b
1 Parent(s): a0acc89

Upload 2 files

Browse files
Files changed (3) hide show
  1. .gitattributes +1 -0
  2. README.md +49 -0
  3. sakura.png +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ sakura.png filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,3 +1,52 @@
1
  ---
 
 
 
 
 
2
  license: cc-by-nc-sa-4.0
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ language:
3
+ - en
4
+ datasets:
5
+ - argilla/distilabel-math-preference-dpo
6
+ pipeline_tag: text-generation
7
  license: cc-by-nc-sa-4.0
8
  ---
9
+
10
+ # **Sakura-SOLAR-Instruct-DPO-v2**
11
+ <img src='./sakura.png' width=512>
12
+
13
+ ## Model Details
14
+
15
+ **Model Developers** Kyujin Han (kyujinpy)
16
+
17
+ **Method**
18
+ Using DPO method.
19
+ With [argilla/distilabel-math-preference-dpo](https://huggingface.co/datasets/argilla/distilabel-math-preference-dpo).
20
+
21
+ I will share the information about my model. (training and code)
22
+ Please see: ⭐[Sakura-SOLAR(will update)]().
23
+
24
+ # **Model Benchmark**
25
+
26
+ ## Open leaderboard
27
+ - Follow up as [link](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
28
+
29
+ | Model | Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
30
+ | --- | --- | --- | --- | --- | --- | --- | --- |
31
+ | akura-SOLAR-Instruct-DPO-v2 | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
32
+ | Sakura-SOLAR-Instruct-DPO-v1 | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
33
+ | [kyujinpy/Sakura-SOLAR-Instruct](https://huggingface.co/kyujinpy/Sakura-SOLAR-Instruct) | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
34
+
35
+
36
+ # Implementation Code
37
+ ```python
38
+ ### KO-Platypus
39
+ from transformers import AutoModelForCausalLM, AutoTokenizer
40
+ import torch
41
+
42
+ repo = "kyujinpy/Sakura-SOLAR-Instruct-DPO-v2"
43
+ OpenOrca = AutoModelForCausalLM.from_pretrained(
44
+ repo,
45
+ return_dict=True,
46
+ torch_dtype=torch.float16,
47
+ device_map='auto'
48
+ )
49
+ OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo)
50
+ ```
51
+
52
+ ---
sakura.png ADDED

Git LFS Details

  • SHA256: 5a066cccad8d305c4ea9bc00d720c7c487853b2eb4d50c9f879742ecfdb56396
  • Pointer size: 132 Bytes
  • Size of remote file: 1.35 MB