L3-8B-Lunar-Stheno

L3-8B-Lunaris-v1 is definitely a significant improvement over L3-8B-Stheno-v3.2 in terms of situational awareness and prose, but it's not without issues: the response length can sometimes be very long, causing it to go on a rant; it tends to not take direct action, saying that it will do something but never actually doing it; and its performance outside of roleplay took a hit.

This merge fixes all of those issues, and I'm genuinely impressed with the results. While I did use a SLERP merge to create this model, there was no blending of the models; all I did was replace L3-8B-Stheno-v3.2's weights with L3-8B-Lunaris-v1's.

Quantization Formats

GGUF

• Static:
  • https://huggingface.co/HiroseKoichi/L3-8B-Lunar-Stheno-GGUF
  • https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-GGUF
• Imatrix:
  • https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF

Details

• License: llama3
• Instruct Format: llama-3
• Context Size: 8K

Models Used

• L3-8B-Stheno-v3.2
• L3-8B-Lunaris-v1

Merge Config

models:
    - model: Sao10K/L3-8B-Stheno-v3.2
    - model: Sao10K/L3-8B-Lunaris-v1
merge_method: slerp
base_model: Sao10K/L3-8B-Stheno-v3.2
parameters:
  t:
    - filter: self_attn
      value: 0
    - filter: mlp
      value: 1
    - value: 0
dtype: bfloat16