Hugging Face's logo

SuperbEmphasis
/
The-Omega-Directive-12B-EVISCERATED-FT-Stage2

Safetensors
mistral
Model card Files Community

ALMOST... There...

Using mergekit, I removed the 5 "least" used layers. This caused significant issues. However fine tuning has helped significantly. Still some issues. But things are almost usable.

I am occasionally getting odd text at the end of responses... but WAY better.... I think 1 more round of fine tuning...

Downloads last month
11
Safetensors
Model size
10.6B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for SuperbEmphasis/The-Omega-Directive-12B-EVISCERATED-FT-Stage2

Base model

SuperbEmphasis/The-Omega-Directive-12B-EVISCERATED
Finetuned
SuperbEmphasis/The-Omega-Directive-12B-EVISCERATED-FT
Finetuned
(1)
this model
Quantizations
1 model

Dataset used to train SuperbEmphasis/The-Omega-Directive-12B-EVISCERATED-FT-Stage2