Upload folder using huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- Roleplay
|
| 5 |
+
- Solar
|
| 6 |
+
- Mistral
|
| 7 |
+
- Text Generation
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
### Premise
|
| 12 |
+
|
| 13 |
+
So this is a basic slerp merge between a smart model and a good prose model. Prose and smarts. What we all want in an uncensored RP model right? I feel like Solar has untapped potential, in any case.
|
| 14 |
+
|
| 15 |
+
Sao10K's Frostwind finetune is a key component of the mixture, its smarts are impressive. NyxKrage's Frostmaid experiment, which merges Frostwind with a frankenmerge of Noromaid and a mystery medical model, delivers quite impressive prose. His model creatively incorporates long-range context and instructions too, despite being slightly incoherent due to the fraken merging.
|
| 16 |
+
|
| 17 |
+
So those are the main ingredients. Thanks to Nyx for sorting out the pytorch files btw.
|
| 18 |
+
|
| 19 |
+
GGUF (Small selection of Imatrix and regular k-quants): https://huggingface.co/BlueNipples/DaringLotus-SnowLotus-10.7b-IQ-GGUF
|
| 20 |
+
|
| 21 |
+
### Recipe
|
| 22 |
+
|
| 23 |
+
So, the recipe. I added solardoc by Nyx to frostwind at a 0.15 weight, and the gradient SLERP'd Frostwind (+solardoc) into Frostmaid with these params:
|
| 24 |
+
|
| 25 |
+
- filter: self_attn
|
| 26 |
+
value: [0.9, 0.4, 0.1, 0, 0]
|
| 27 |
+
- filter: mlp
|
| 28 |
+
value: [0.05, 0.95]
|
| 29 |
+
- value: 0.45
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
### Tentative Dozen or So Test Conclusion
|
| 33 |
+
|
| 34 |
+
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.
|
| 35 |
+
|
| 36 |
+
Cheers to all the finetuners, mergers and developers without which open source models wouldn't be half of what they are.
|
| 37 |
+
|
| 38 |
+
Resources used:
|
| 39 |
+
|
| 40 |
+
https://huggingface.co/NyxKrage/FrostMaid-10.7B-TESTING-pt
|
| 41 |
+
|
| 42 |
+
https://huggingface.co/Sao10K/Frostwind-10.7B-v1
|
| 43 |
+
|
| 44 |
+
https://huggingface.co/NyxKrage/Solar-Doc-10.7B-Lora
|
| 45 |
+
|
| 46 |
+
https://github.com/cg123/mergekit/tree/main
|