Update README.md
Browse files
README.md
CHANGED
|
@@ -50,6 +50,11 @@ QwQ-32B-ArliAI-RpR-v1 is the first release in the RpR series. It is a 32-billion
|
|
| 50 |
* **Learning Rate**: 0.000005
|
| 51 |
* **Gradient accumulation**: 32
|
| 52 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
### How to use reasoning models correctly in ST
|
| 54 |
|
| 55 |
<img src="RpR-ST-Settings.png" alt="Important settings in ST for reasoning models" width="600" />
|
|
|
|
| 50 |
* **Learning Rate**: 0.000005
|
| 51 |
* **Gradient accumulation**: 32
|
| 52 |
|
| 53 |
+
### Quantization
|
| 54 |
+
|
| 55 |
+
* **BF16**: https://huggingface.co/ArliAI/QwQ-32B-ArliAI-RpR-v1
|
| 56 |
+
* **GGUF**: https://huggingface.co/ArliAI/QwQ-32B-ArliAI-RpR-v1-GGUF
|
| 57 |
+
|
| 58 |
### How to use reasoning models correctly in ST
|
| 59 |
|
| 60 |
<img src="RpR-ST-Settings.png" alt="Important settings in ST for reasoning models" width="600" />
|