Update README.md
Browse filesUpdated the readme with prompt formatting suggestions
README.md
CHANGED
|
@@ -5,4 +5,6 @@ datasets:
|
|
| 5 |
language:
|
| 6 |
- en
|
| 7 |
---
|
| 8 |
-
This is an EXL2 quantized model in 3bpw of [jebcarter/Psyfighter-13B](https://huggingface.co/jebcarter/Psyfighter-13B) using [PIPPA](https://huggingface.co/datasets/jasonkstevens/pippa-llama2-chat/blob/refs%2Fconvert%2Fparquet/default/train/0000.parquet) as the calibration dataset.
|
|
|
|
|
|
|
|
|
| 5 |
language:
|
| 6 |
- en
|
| 7 |
---
|
| 8 |
+
This is an EXL2 quantized model in 3bpw of [jebcarter/Psyfighter-13B](https://huggingface.co/jebcarter/Psyfighter-13B) using [PIPPA](https://huggingface.co/datasets/jasonkstevens/pippa-llama2-chat/blob/refs%2Fconvert%2Fparquet/default/train/0000.parquet) as the calibration dataset.
|
| 9 |
+
|
| 10 |
+
Alpaca and ChatML prompt templates seem to work fine with this model.
|