Commit
•
5027a7a
1
Parent(s):
808d1dc
Update README.md
Browse files
README.md
CHANGED
|
@@ -30,6 +30,10 @@ So, the recipe. I added solardoc by Nyx to frostwind at a 0.15 weight, and the g
|
|
| 30 |
- value: 0.45
|
| 31 |
|
| 32 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
### Tentative Dozen or So Test Conclusion
|
| 34 |
|
| 35 |
This model seems to have better prose, less GPT-ish language and no degredation in coherency from the last version whilst retaining coherency from FrostWind (plus medical lora). I'm very pleased with this now, it's exactly what I wanted, basically Nyx's Frostmaid but smarter.
|
|
|
|
| 30 |
- value: 0.45
|
| 31 |
|
| 32 |
|
| 33 |
+
### Format Notes
|
| 34 |
+
|
| 35 |
+
Solar is desgined for 4k context, but Nyx reports that his merge works to 8k. Given this has a slerp gradient back into that, I'm not sure which applies here. Alpaca instruct formatting.
|
| 36 |
+
|
| 37 |
### Tentative Dozen or So Test Conclusion
|
| 38 |
|
| 39 |
This model seems to have better prose, less GPT-ish language and no degredation in coherency from the last version whilst retaining coherency from FrostWind (plus medical lora). I'm very pleased with this now, it's exactly what I wanted, basically Nyx's Frostmaid but smarter.
|