IQ2-GGUF quants of Sao10K/WinterGoddess-1.4x-70B-L2

Unlike regular GGUF quants this uses important matrix similar to Quip# to keep the quant from degrading too much even at 2bpw allowing you to run larger models on less powerful machines.

NOTE: Currently you will need experimental branches of Koboldcpp or Ooba for this to work.

Models: IQ2-XS, IQ2-XXS

Regular GGUF Quants: Here

### Instruction:
<Prompt>

### Response:

OR

### Instruction:
<Prompt>

### Input:
<Insert Context Here>

### Response:

Kooten on discord