Update README.md
Browse files
README.md
CHANGED
|
@@ -26,6 +26,19 @@ It's a successful fine-tune that follows the ChatML template!
|
|
| 26 |
|
| 27 |
This model uses a context window of 8k. It was trained with the ChatML template.
|
| 28 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
## 🏆 Evaluation
|
| 30 |
|
| 31 |
### Nous
|
|
|
|
| 26 |
|
| 27 |
This model uses a context window of 8k. It was trained with the ChatML template.
|
| 28 |
|
| 29 |
+
## ⚡ Quantized models
|
| 30 |
+
|
| 31 |
+
Thanks to bartowski, solidrust, and LoneStriker for the quantized models.
|
| 32 |
+
|
| 33 |
+
* **GGUF**: https://huggingface.co/bartowski/OrpoLlama-3-8B-GGUF
|
| 34 |
+
* **AWQ**: https://huggingface.co/solidrust/OrpoLlama-3-8B-AWQ
|
| 35 |
+
* **EXL2**:
|
| 36 |
+
* https://huggingface.co/LoneStriker/OrpoLlama-3-8B-3.0bpw-h6-exl2
|
| 37 |
+
* https://huggingface.co/LoneStriker/OrpoLlama-3-8B-4.0bpw-h6-exl2
|
| 38 |
+
* https://huggingface.co/LoneStriker/OrpoLlama-3-8B-5.0bpw-h6-exl2
|
| 39 |
+
* https://huggingface.co/LoneStriker/OrpoLlama-3-8B-6.0bpw-h6-exl2
|
| 40 |
+
* https://huggingface.co/LoneStriker/OrpoLlama-3-8B-8.0bpw-h6-exl2
|
| 41 |
+
|
| 42 |
## 🏆 Evaluation
|
| 43 |
|
| 44 |
### Nous
|