8bpw/h8 exl2 quantization of
NeverSleep/Llama-3-Lumimaid-8B-v0.1 using default exllamav2 calibration dataset.
Llama3 trained on our RP datasets, we tried to have a balance between the ERP and the RP, not too horny, but just enough.
We also added some non-RP dataset, making the model less dumb overall. It should look like a 40%/60% ratio for Non-RP/RP+ERP data.
This model includes the new Luminae dataset from Ikari.
If you consider trying this model please give us some feedback either on the Community tab on hf or on our
Discord Server .
This repo contains FP16 files of Lumimaid-8B-v0.1.
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
{output}<|eot_id|>Undi: If you want to support us, you can
here .
