etri-xainlp
commited on
Commit
•
c0027e7
1
Parent(s):
f397f9d
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,27 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
---
|
4 |
+
|
5 |
+
# etri-xainlp/SOLAR-10.7B-merge-dpo
|
6 |
+
|
7 |
+
## Model Details
|
8 |
+
|
9 |
+
**Model Developers** ETRI xainlp team
|
10 |
+
|
11 |
+
**Input** text only.
|
12 |
+
|
13 |
+
**Output** text only.
|
14 |
+
|
15 |
+
**Model Architecture**
|
16 |
+
|
17 |
+
We used MergeKit to merge Model heavytail/kullm-solar into Model upstage/SOLAR-10.7B-Instruct-v1.0 as the base.
|
18 |
+
|
19 |
+
**Base Model** [upstage/SOLAR-10.7B-Instruct-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0)
|
20 |
+
|
21 |
+
**Merge Model [heavytail/kullm-solar](https://huggingface.co/heavytail/kullm-solar)
|
22 |
+
|
23 |
+
**Training Dataset**
|
24 |
+
|
25 |
+
- dpo+lora: 90k user preference set
|
26 |
+
|
27 |
+
- We use A100 GPU 80GB * 1, when training.
|