mergekit-community/nsfw-test-again-yes-it-was-bad

merge

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

Merge Details

Merge Method

This model was merged using the SCE merge method using DreadPoor/Derivative-8B-Model_Stock + grimjim/Llama-3-Instruct-abliteration-LoRA-8B as a base.

Models Merged

The following models were included in the merge:

• v000000/Llama-3.1-8B-Stheno-v3.4-abliterated + surya-narayanan/human_sexuality
• v000000/Llama-3.1-8B-Stheno-v3.4-abliterated + Azazelle/Llama-3-8B-Abomination-LORA
• v000000/Llama-3.1-8B-Stheno-v3.4-abliterated + surya-narayanan/formal_logic
• v000000/Llama-3.1-8B-Stheno-v3.4-abliterated + surya-narayanan/health
• v000000/Llama-3.1-8B-Stheno-v3.4-abliterated + DreadPoor/Everything-COT-8B-r128-LoRA
• v000000/Llama-3.1-8B-Stheno-v3.4-abliterated + eeeebbb2/3aff0ea7-4262-4abb-97b1-1879f340d32e
• v000000/Llama-3.1-8B-Stheno-v3.4-abliterated + kik41/lora-length-long-llama-3-8b-v2
• v000000/Llama-3.1-8B-Stheno-v3.4-abliterated + surya-narayanan/anatomy
• v000000/Llama-3.1-8B-Stheno-v3.4-abliterated + ResplendentAI/Smarts_Llama3
• v000000/Llama-3.1-8B-Stheno-v3.4-abliterated + surya-narayanan/biology
• v000000/Llama-3.1-8B-Stheno-v3.4-abliterated + moetezsa/Llama3_instruct_on_wikibio
• v000000/Llama-3.1-8B-Stheno-v3.4-abliterated + kik41/lora-type-descriptive-llama-3-8b-v2
• v000000/Llama-3.1-8B-Stheno-v3.4-abliterated + surya-narayanan/professional_psychology

Configuration

The following YAML configuration was used to produce this model:

models:   
  - model: v000000/Llama-3.1-8B-Stheno-v3.4-abliterated+surya-narayanan/formal_logic  
  - model: v000000/Llama-3.1-8B-Stheno-v3.4-abliterated+surya-narayanan/health  
  - model: v000000/Llama-3.1-8B-Stheno-v3.4-abliterated+eeeebbb2/3aff0ea7-4262-4abb-97b1-1879f340d32e 
  - model: v000000/Llama-3.1-8B-Stheno-v3.4-abliterated+surya-narayanan/biology  
  - model: v000000/Llama-3.1-8B-Stheno-v3.4-abliterated+DreadPoor/Everything-COT-8B-r128-LoRA 
  - model: v000000/Llama-3.1-8B-Stheno-v3.4-abliterated+moetezsa/Llama3_instruct_on_wikibio  
  - model: v000000/Llama-3.1-8B-Stheno-v3.4-abliterated+surya-narayanan/professional_psychology   
  - model: v000000/Llama-3.1-8B-Stheno-v3.4-abliterated+ResplendentAI/Smarts_Llama3
  - model: v000000/Llama-3.1-8B-Stheno-v3.4-abliterated+Azazelle/Llama-3-8B-Abomination-LORA
  - model: v000000/Llama-3.1-8B-Stheno-v3.4-abliterated+kik41/lora-type-descriptive-llama-3-8b-v2  
  - model: v000000/Llama-3.1-8B-Stheno-v3.4-abliterated+kik41/lora-length-long-llama-3-8b-v2
  - model: v000000/Llama-3.1-8B-Stheno-v3.4-abliterated+surya-narayanan/anatomy
  - model: v000000/Llama-3.1-8B-Stheno-v3.4-abliterated+surya-narayanan/human_sexuality
merge_method: sce
base_model: DreadPoor/Derivative-8B-Model_Stock+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
dtype: bfloat16
parameters:
  select_topk: 0.5