[!CAUTION] ⚠️ Warning: This model can produce narratives and RP that contain violent and graphic erotic content. Adjust your system prompt accordingly, and use Mistral Tekken chat template.
🐌 Ślimaki 24B v1
This merge has zero refusals (confirmed), no ablation needed.
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Methods
This model was merged using the following merge method:
Note: This merge was heavily inspired by Maginum Cydoms
Recommended Settings
In particular temp 1 and topnsigma 1.25 seems to help a lot with improving quality but sometimes you need to reswipe.
Some models are more sensitive to Rep Pen settings, 1.12 is another, you may need to adjust higher for smaller models (like 1.4 if overcooked) or lower for smarter ones.
Not sure about adaptive_p that is a newer setting added to kobold
(bolded kobold non-defaults)
- Temp 1.0
- TopNSigma 1.25
- Min-P 0.1
- Repetition Penalty 1.08
- Top-P 1.0
- Top-K 100
- Top-A 0
- Typical Sampling 1
- Tail-Free Sampling 1
- Presence Penalty 0
- Sampler Seed -1
- Rp.Range 360
- Rp.Slope 0.7
- Smoothing Factor 0
- Smoothing Curve 1
- DynaTemp 0
- Mirostat Mode OFF ("2" enhances creativity but also errors)
- Mirostat Tau 5
- Mirostat Eta 0.1
- DRY Multiplier 0.8
- DRY Base 1.75
- DRY A.Len 2
- DRY L.Len 320
- XTC Threshold 0.1
- XTC Probability 0.08 (The "Anti-Cliche" Shield)
- DynaTemp ON (The "Poor Man's Fading Mirostat")
- Minimum Temperature 0.65
- Maximum Temperature 1.35
- Temperature 1.0
- DynaTemp-Range 0.35
- DynaTemp-Exponent 1