---
base_model:
- NousResearch/Meta-Llama-3-8B-Instruct
- Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B
library_name: peft
tags:
- mergekit
- peft

---
# Umbral-Mind-r128-LoRA

This is a LoRA extracted from a language model. It was extracted using [mergekit](https://github.com/arcee-ai/mergekit).

## LoRA Details

This LoRA adapter was extracted from [Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B](https://huggingface.co/Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B) and uses [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct) as a base.

### Parameters

The following command was used to extract this LoRA adapter:

```sh
/usr/local/bin/mergekit-extract-lora --out-path=loras/Umbral-Mind-r128-LoRA --model=Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B --base-model=NousResearch/Meta-Llama-3-8B-Instruct --no-lazy-unpickle --max-rank=128 --gpu-rich -v --embed-lora --skip-undecomposable
```