etri-xainlp
commited on
Commit
•
c50bb39
1
Parent(s):
f01d5db
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,25 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
---
|
4 |
+
|
5 |
+
# etri-xainlp/llama2-13b-sft-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 |
+
**Base Model** [meta-llama/Llama-13b-hf](https://huggingface.co/meta-llama/Llama-2-13b-hf)
|
18 |
+
|
19 |
+
**Training Dataset**
|
20 |
+
|
21 |
+
- fully sft: 6500k instruction-following set
|
22 |
+
|
23 |
+
- dpo+lora: 90k user preference set
|
24 |
+
|
25 |
+
- We use A100 GPU 80GB * 8, when training.
|