Nexesenex's picture
Create README.md
6a2bafc verified
|
raw
history blame
305 Bytes

Requantization of a Q5_K_M quant of a trending 70b model without better quant/fp16 available, this through a Q8_0 intermediary step.

Model has a theta of 1,000,000, and not 10,000, like Llama 2 models usually have.

So, no Alpha or Rope Base Frequency up to its base 32k context, if it works as intended.