This repo contains GGUF quants of
Llama-3-Luminurse-v0.2-OAS-8B. 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.
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.
The combined restrictions of both the cc-by-nc-4.0 and llama3 licenses apply to this model and its derivatives. If one restricts where the other does not, then the restriction applies.
This model was merged using the
task arithmetic merge method using
NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS as a base.
1base_model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS
2slices:
3- sources:
4 - model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS
5 layer_range: [0,32]
6 - model: grimjim/llama-3-aaditya-OpenBioLLM-8B
7 layer_range: [0,32]
8 parameters:
9 weight: 0.2
10 - model: cgato/L3-TheSpice-8b-v0.8.3
11 layer_range: [0,32]
12 parameters:
13 weight: 0.04
14merge_method: task_arithmetic
15dtype: bfloat16
16
