Edit model card

My current low-budget daily driver, so far.

Frostwindv2 + Sensualize v1.1 + ___ data on uncen Instruct Solar.

This is meant to be a verbose, smart Roleplaying model. I think I captured those two parts this time. Well, for my own cards and scenarios anyway, it passed with flying colours.

I recommend using min-p, I liked Universal-Light preset in SillyTavern.

Experimental.


Prompt Format: Alpaca

### Instruction:
<Prompt>

### Input:
<Insert Context Here>

### Response:

31-Jan-24 Update:

forgot to link GGUF quants here: https://huggingface.co/Sao10K/Fimbulvetr-10.7B-v1-GGUF

or thebloke already quantized them to gptq and others. lonestriker did exl2 quants so ty ty a lot.

anyway, I have a few solar-based ideas before I move to the new InternLM, Yi, Mixtral or back to 70B.

Downloads last month
3,417
Safetensors
Model size
10.7B params
Tensor type
FP16
·

Collection including Sao10K/Fimbulvetr-10.7B-v1