mradermacher

/

Llama-DNA-1.0-8B-Instruct-i1-GGUF

like 0

Hi could you be able to give me which inference data you used for extracting imatrix?

Unfortunately no, see the FAQ at https://huggingface.co/mradermacher/model_requests

Moreover will you be able to tell us what was the process of quantizing this model using imatrix?

We use llama-quantize - see its help output on how to specify an imatrix file. It's basically the same as without imatrix, except you specify an imatrix file.