Llama-Phi-3_DoRA / README.md
Ba2han's picture
Update README.md
af6f5e9 verified
|
raw
history blame
607 Bytes
---
datasets:
- Sao10K/Claude-3-Opus-Instruct-15K
- abacusai/SystemChat-1.1
- Ba2han/DollyLlama-5k
language:
- en
license: mit
---
**We have Llama-3 at home!**
Highest PHI-3-Mini MMLU and Winogrande on the board!
The model has been trained on filtered versions of tagged datasets, as well as a few thousand more examples generated with llama-3-70B.
Use **Zephyr template** with any system message. Default system message should be:
You are a smart, friendly and helpful assistant.
![image/png](https://cdn-uploads.huggingface.co/production/uploads/6324eabf05bd8a54c6eb1650/pJZxrxB1keWNr2Uqw7fkv.png)