dranger003

/

miquliz-120b-v2.0-iMat.GGUF

Like 11

GGUF importance matrix (imatrix) quants for https://huggingface.co/wolfram/miquliz-120b-v2.0
The importance matrix was trained for 100K tokens (200 batches of 512 tokens) using wiki.train.raw.

Using IQ2_XXS it seems to fit 100/141 layers using 2K context on a 24GB card.

140

32768

[INST] {prompt} [/INST]
{response}