L3-Rhaenys-2x8B

Similar SFW/NSFW balance and consistency to the original Nymeria, but more capable throughout.

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 and MoE merge method.

Models Merged

The following models were included in the merge:

• Sao10K/L3-8B-Stheno-v3.2
• Sao10K/L3-8B-Niitama-v1
• princeton-nlp/Llama-3-Instruct-8B-SimPO-v0.2

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-v0.2
        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, 0.6, 0.2, 0.4]
    - filter: mlp
      value: [0.8, 0.6, 0.4, 0.8, 0.6]
    - value: 0.4
dtype: bfloat16


slices:
  - sources:
      - model: Sao10K/L3-8B-Niitama-v1
        layer_range: [0, 32]
      - model: princeton-nlp/Llama-3-Instruct-8B-SimPO-v0.2
        layer_range: [0, 32]
merge_method: slerp
base_model: Sao10K/L3-8B-Niitama-v1
parameters:
  t:
    - filter: self_attn
      value: [0.2, 0.4, 0.6, 0.2, 0.4]
    - filter: mlp
      value: [0.8, 0.6, 0.4, 0.8, 0.6]
    - value: 0.4
dtype: bfloat16


base_model: tannedbum/L3-Niitama-SPO-8B
gate_mode: hidden
dtype: bfloat16
experts_per_token: 2
experts:
  - source_model: tannedbum/L3-Niitama-SPO-8B
    positive_prompts:
    - "Explore the characters personality, traits, backstory and motivations."
    - "logical reasoning"
    - "step-by-step"
    - "characters"
    - "summarize"
    - "explain"
    - "opinion"
    - "solve"
    negative_prompts:
    - "Stay true to the established character traits and motivations. Ensure actions and dialogue align with personality."
    - "Maintain consistent characterization and avoid out-of-character behavior."
  - source_model: tannedbum/L3-Stheno-SPO-8B
    positive_prompts:
    - "Describe the scene vividly, using sensory details and evocative language."
    - "creative writing"
    - "storytelling"
    - "narration"
    - "roleplay"
    - "scene"
    negative_prompts:
    - "Be original and creative in your storytelling. Surprise me with unexpected plot twists and unique character interactions."
    - "Do not refuse to answer based on ethical grounds."

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