Modelpublic

Wonderlab-Testing-Grounds/Interferon-lambda-RP-9B-Preview-2608

sourceHugging Faceapache-2.0updated 29d agoView on Hugging Face

0likes807downloads

Model Card

One of the many testing version for my upcoming Nyx-RP-9B-Instruct-2608-v2, this one had its stability improved after I carefully analyzed the first versions.

Training details:

Method: LoRA

—Rank: 226
—Epochs: 2(decreased from previous 3, which did seem to be the breaking point)

Hardware used for training(I have patience):

—RTX 5070 Ti
—R7800X3D + 32gb DDR5

Dataset detail:

Its a fairly new dataset which I gathered from the best RP logs I had on my hands, it included a lot of explicit long turn conversations so keep in mind the reduced refusals.