Yobenboben/L3.3-Smog-70B

Smog

Tried out some obscure merge method. Turned out decent enough. The result is something averaged from three selected models, without any of them being too prevalent.

Distinct prose and (imo) best ERP out of the L3.3 models.

Settings:

Temp 1.05, minP 0.01

Quants:

https://huggingface.co/mradermacher/L3.3-Smog-70B-GGUF

https://huggingface.co/mradermacher/L3.3-Smog-70B-i1-GGUF

Merge Details

Merge Method

This model was merged using the Karcher Mean merge method.

Models Merged

The following models were included in the merge:

• zerofata/L3.3-GeneticLemonade-Unleashed-v2.1-70B
• Nohobby/L3.3-Prikol-70B-v0.5
• allura-org/Bigger-Body-70b

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: zerofata/L3.3-GeneticLemonade-Unleashed-v2.1-70B
  - model: allura-org/Bigger-Body-70b
  - model: Nohobby/L3.3-Prikol-70B-v0.5
merge_method: karcher
parameters:
  max_iter: 18
  tol: 1e-8
normalize: true
int8_mask: true
dtype: bfloat16