TehVenom

/

Pygmalion-7b-4bit-Q4_1-GGML

like 19

We're still working on figuring out GGML quantization, it seems like the Pygmalion team has used a non-standard format.

Thank you in advance sir, ahh that explains why it's so hard to see this model that works on llamaccp.
There's no rush, you're doing a god's work ;)

Cracked it 😁
Will finish uploading a working conversion in a few, look back later.

It's up!
Second model also available at:
https://huggingface.co/TehVenom/Metharme-7b-4bit-Q4_1-GGML

damn, thats fast af. Super thanks for this sir!