Commit
•
113b76d
1
Parent(s):
e17cd57
Update README.md
Browse files
README.md
CHANGED
|
@@ -4,16 +4,35 @@ language:
|
|
| 4 |
- en
|
| 5 |
library_name: peft
|
| 6 |
---
|
|
|
|
|
|
|
| 7 |
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
|
|
|
| 11 |
### Used Datasets
|
| 12 |
-
- Orca
|
| 13 |
-
-
|
| 14 |
-
- No other dataset was used except for the dataset mentioned above
|
| 15 |
- No benchmark test set or the training set are used
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
-
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
- en
|
| 5 |
library_name: peft
|
| 6 |
---
|
| 7 |
+
# **Introduction**
|
| 8 |
+
This is a sft version of QWEN/QWEN-72B Model, and llamafied for leaderboard submission
|
| 9 |
|
| 10 |
+
## Details
|
| 11 |
+
### Used Librarys
|
| 12 |
+
- torch
|
| 13 |
+
- peft
|
| 14 |
### Used Datasets
|
| 15 |
+
- Open-Orca/SlimOrca
|
| 16 |
+
- No other dataset was used
|
|
|
|
| 17 |
- No benchmark test set or the training set are used
|
| 18 |
+
- TBU: data contamination test results (with https://github.com/swj0419/detect-pretrain-code-contamination)
|
| 19 |
+
### Used Environments
|
| 20 |
+
- AMD MI250 & MoAI platform
|
| 21 |
+
- Please visit https://moreh.io/product for more information about MoAI platform
|
| 22 |
+
- Or, contact us directly [contact@moreh.io](mailto:contact@moreh.io)
|
| 23 |
+
|
| 24 |
+
## License
|
| 25 |
+
TBU
|
| 26 |
+
|
| 27 |
+
## How to use
|
| 28 |
|
| 29 |
+
```python
|
| 30 |
+
# pip install transformers==4.35.2
|
| 31 |
+
import torch
|
| 32 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 33 |
|
| 34 |
+
tokenizer = AutoTokenizer.from_pretrained("moreh/MoMo-70B-LoRA-V1.4")
|
| 35 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 36 |
+
"moreh/MoMo-70B-LoRA-V1.4"
|
| 37 |
+
)
|
| 38 |
+
```
|