Thanks to @mradermacher for his excellent quants! You can find his GGUFs for this repo
here.
This is a merge of pre-trained language models created using
mergekit. š
Works pretty good. Also seems to be happy when ROPEing up to 8K. Uncensored, told me how to build a nuke.
This model was merged using the passthrough merge method. Taking models and smashing em all together š
1slices:
2 - sources:
3 - model: Sao10K/Fimbulvetr-11B-v2
4 layer_range: [0, 40]
5 - sources:
6 - model: Undi95/Mistral-11B-CC-Air-RP
7 layer_range: [8, 48]
8merge_method: passthrough
9dtype: bfloat16
10
11š
12
### Instruction:
<Prompt>
### Input:
<Insert Context Here>
### Response:
Less silly models are in the works. I'm still figuring things out right now, so don't judge the bazillions of readme edits and other goofiness.
