This version is solely for scientific purposes, of course.

Nymeria is the balanced version, doesn't force nsfw. Nymeria-Maid has more Stheno's weights, leans more on nsfw and is more submissive.

All quants made using imatrix option with dataset provided by bartowski here

SillyTavern

Text Completion presets

temp 0.9
top_k 30
top_p 0.75
min_p 0.2
rep_pen 1.1
smooth_factor 0.25
smooth_curve 1

Advanced Formatting

Context & Instruct preset by Virt-io

Instruct Mode: Enabled

merge

This is a merge of pre-trained language models created using mergekit.

This model was merged using the slerp merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:



slices:
  - sources:
      - model: Sao10K/L3-8B-Stheno-v3.2
        layer_range: [0, 32]
      - model: princeton-nlp/Llama-3-Instruct-8B-SimPO
        layer_range: [0, 32]
merge_method: slerp
base_model: Sao10K/L3-8B-Stheno-v3.2
parameters:
  t:
    - filter: self_attn
      value: [0.2, 0.4, 0.4, 0.6]
    - filter: mlp
      value: [0.8, 0.6, 0.6, 0.4]
    - value: 0.4
dtype: bfloat16

Original model information:

Model: Sao10K/L3-8B-Stheno-v3.2

Stheno-v3.2-Zeta

Changes compared to v3.1
- Included a mix of SFW and NSFW Storywriting Data, thanks to Gryphe
- Included More Instruct / Assistant-Style Data
- Further cleaned up Roleplaying Samples from c2 Logs -> A few terrible, really bad samples escaped heavy filtering. Manual pass fixed it.
- Hyperparameter tinkering for training, resulting in lower loss levels.

Testing Notes - Compared to v3.1
- Handles SFW / NSFW seperately better. Not as overly excessive with NSFW now. Kinda balanced.
- Better at Storywriting / Narration.
- Better at Assistant-type Tasks.
- Better Multi-Turn Coherency -> Reduced Issues?
- Slightly less creative? A worthy tradeoff. Still creative.
- Better prompt / instruction adherence.

Want to support my work ? My Ko-fi page: https://ko-fi.com/tannedbum