README.md

metadata

base_model: []
library_name: peft
tags:
  - mergekit
  - peft

Umbral-Mind-r128-LoRA

This is a LoRA extracted from a language model. It was extracted using mergekit.

LoRA Details

This LoRA adapter was extracted from merge/f32-umbral and uses merge/f32-instruct as a base.

Parameters

The following command was used to extract this LoRA adapter:

/usr/local/bin/mergekit-extract-lora --out-path=loras/Umbral-Mind-r128-LoRA --model=merge/f32-umbral --base-model=merge/f32-instruct --no-lazy-unpickle --max-rank=128 --sv-epsilon=0 --cuda --multi-gpu -v