nisten
/

franqwenstein-35b

Model card Files Files and versions Community

nisten commited on Oct 3

Commit

901351a

•

1 Parent(s): ae0847e

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -15,7 +15,7 @@ It should train very very well as over half the layers are from the base model.
 By default you still get the safety guard of Qwen but also nearly full system-prompt obedience of the AGI finetune, so you can tune the inference for however you wanna be responsible of using it.
-Thank you [Hive Digital Technologies](https://x.com/HIVEDigitalTech) for sticking providing the compute and sticking with us as a sponsor for [AlignmentLab](https://alignmentlab.ai/). For real would not have been able to iterate through models as fast without running the evals on 8+gpus.
 Prompt Template:

 By default you still get the safety guard of Qwen but also nearly full system-prompt obedience of the AGI finetune, so you can tune the inference for however you wanna be responsible of using it.
+Thank you [Hive Digital Technologies](https://x.com/HIVEDigitalTech) for providing the compute and sticking with us as a sponsor for [AlignmentLab](https://alignmentlab.ai/). For real would not have been able to iterate through models as fast without running the evals on 8+gpus.
 Prompt Template: