ExLlamaV2 Quants
Collection
14 items
•
Updated
➡️ Exl2 version : 0.0.20
➡️ Cal. dataset : Default.
📄 Measurement.json file.
This model uses the Llama3 prompting format
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.
IkariDev: Visit my retro/neocities style website please kek