--- library_name: transformers tags: - llama-factory license: llama3 datasets: - TheSkullery/Aether-Lite-V1.2 ---

8bpw/h8 exl2 quantization of [Steelskull/L3-Aethora-15B](https://huggingface.co/Steelskull/L3-Aethora-15B) using exllamav2 v0.1.4 and default calibration dataset. --- **ORIGINAL CARD:** L3-Aethora-15B Data Card

L3-Aethora-15B

The Skullery Presents L3-Aethora-15B.

Creator: Steelskull

Dataset: Aether-Lite-V1.2

Trained: 4 x A100 for 15 hours Using RsLora and DORA

About L3-Aethora-15B:

 L3 = Llama3 

L3-Aethora-15B was crafted through using the abilteration method to adjust model responses. The model's refusal is inhibited, focusing on yielding more compliant and facilitative dialogue interactions. It then underwent a modified DUS (Depth Up Scale) merge (originally used by @Elinas) by using passthrough merge to create a 15b model, with specific adjustments (zeroing) to 'o_proj' and 'down_proj', enhancing its efficiency and reducing perplexity. This created AbL3In-15b.

AbL3In-15b was then trained for 4 epochs using Rslora & DORA training methods on the Aether-Lite-V1.2 dataset, containing ~82000 high quality samples, designed to strike a fine balance between creativity, slop, and intelligence at about a 60/40 split

This model is trained on the L3 prompt format.

Quants:

  • Mradermacher/L3-Aethora-15B-GGUF
  • NikolayKozloff/L3-Aethora-15B-GGUF
  • Dataset Summary: (Filtered)

    Filtered Phrases: GPTslop, Claudism's

    Deduplication Stats:

    Starting row count: 85628, Final row count: 81960, Rows removed: 3668