---
base_model: grimjim/Llama-3-Luminurse-v0.2-OAS-8B
library_name: transformers
quanted_by: grimjim
pipeline_tag: text-generation
license: cc-by-nc-4.0
---
# grimjim/Llama-3-Luminurse-v0.2-OAS-8B-8bpw-exl2

This repo contains an exl2 quant of [Llama-3-Luminurse-v0.2-OAS-8B](https://huggingface.co/grimjim/Llama-3-Luminurse-v0.2-OAS-8B) at 8bpw. For suggested sampler settings, refer to the model card of the original repo.

This model is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

Luminurse is a merge based on Lumimaid, enhanced with a biomedical model, with a dash of TheSpice thrown in to improve formatting of text generation.

Built with Meta Llama 3.

## Merge Details
### Merge Method

This model was merged using the [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using [NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS](https://huggingface.co/NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS) as a base.

### Models Merged

The following models were included in the merge:
* [grimjim/llama-3-aaditya-OpenBioLLM-8B](https://huggingface.co/grimjim/llama-3-aaditya-OpenBioLLM-8B)
* [cgato/L3-TheSpice-8b-v0.8.3](https://huggingface.co/cgato/L3-TheSpice-8b-v0.8.3)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
base_model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS
slices:
- sources:
  - model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS
    layer_range: [0,32]
  - model: grimjim/llama-3-aaditya-OpenBioLLM-8B
    layer_range: [0,32]
    parameters:
      weight: 0.2
  - model: cgato/L3-TheSpice-8b-v0.8.3
    layer_range: [0,32]
    parameters:
      weight: 0.04
merge_method: task_arithmetic
dtype: bfloat16

```