Absolucy/

laserxtral-sota-GGUF

This is just, SOTA 2 and 3-bit quants for laserxtral. Not much more to it. Meow.

The importance matrix, which is generated from group_10_merged.txt, is included in this repo, as imatrix_laserxtral.dat.

UPDATE 2/11/2024: The models have been reuploaded, with a new importance matrix used (group_10_merged.txt rather than 20k_random_data.txt), which should in theory provide better performance. I'm not an expert, don't quote me on that.

Alpaca format

### Instruction:
...
### Input:
...
### Response:

If you use LM Studio, this repo has a model_config.json you can import which has that pre-configured.