IHaBiS/

Nethena-MLewd-Xwin-23B-exl2

main : 3.75bpw h8
b3.75h8 : 3.75bpw h8
b4h6 : 4bpw h6
b4h8 : 4bpw h8

I checked that main branch runs on 24G GPU (tested on Runpod 3090 server)
Maybe I'll test 3.8bpw or 3.9bpw next time (Not sure about it)

Undi doing chemistry again.

Layer of Xwin-Mlewd was added in a different way than I do before, result seem good, but I'm a VRAMlet so I can only run the Q2 at 2k context for now.

Need to see if it really work good or I was just lucky with my prompt.

OG model : NeverSleep/Nethena-13B

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Response:

LimaRP is always kicking in and thus, this can be used to have more control on the size of the output.

Thanks Ikari.