Commit
•
a97b432
1
Parent(s):
00f3a72
Update README.md
Browse files
README.md
CHANGED
|
@@ -16,10 +16,14 @@ tags:
|
|
| 16 |
|
| 17 |
Similar 50/50 merge like the other Magnum-Instruct, but using model variants that have had extra dpo/orpo training on top of them beforehand. Can't say if it's better or not comparatively speaking to just using the original models yet, but it seamed fine enough during my limited testing and worth the upload for now as an alternative.
|
| 18 |
|
| 19 |
-
**Edit:** After going back messing about with the various merges I've done, both Instant-RP-Noodles and the regular Magnum-Instruct, I think this one is still my favorite.
|
| 20 |
|
| 21 |
Big thanks to the MistralAI and Anthracite/SillyTilly teams for the original models used, plus nbeerbower for the extra training done as well!
|
| 22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
GGUF quants provided by mradermacher:
|
| 24 |
|
| 25 |
https://huggingface.co/mradermacher/Magnum-Instruct-DPO-12B-GGUF
|
|
|
|
| 16 |
|
| 17 |
Similar 50/50 merge like the other Magnum-Instruct, but using model variants that have had extra dpo/orpo training on top of them beforehand. Can't say if it's better or not comparatively speaking to just using the original models yet, but it seamed fine enough during my limited testing and worth the upload for now as an alternative.
|
| 18 |
|
| 19 |
+
**Edit:** After going back and messing about with the various merges I've done, both Instant-RP-Noodles and the regular Magnum-Instruct, I think this one is still my favorite.
|
| 20 |
|
| 21 |
Big thanks to the MistralAI and Anthracite/SillyTilly teams for the original models used, plus nbeerbower for the extra training done as well!
|
| 22 |
|
| 23 |
+
EXL2 quant using Fullmoon-Light:
|
| 24 |
+
|
| 25 |
+
https://huggingface.co/ParasiticRogue/Magnum-Instruct-DPO-12B-exl2-8.0
|
| 26 |
+
|
| 27 |
GGUF quants provided by mradermacher:
|
| 28 |
|
| 29 |
https://huggingface.co/mradermacher/Magnum-Instruct-DPO-12B-GGUF
|