Pedro13543/experimental_merge_no2

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 vicgalle/Humanish-Roleplay-Llama-3.1-8B as a base.

Models Merged

The following models were included in the merge:

• Undi95/Meta-Llama-3.1-8B-Claude
• Sao10K/Llama-3.1-8B-Stheno-v3.4
• Nitral-AI/Poppy_Porpoise-0.72-L3-8B
• Undi95/Llama3-Unholy-8B-OAS
• Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
• Solshine/reflection-llama-3.1-8B-Solshine-Full
• TheDrummer/Llama-3SOME-8B-v2
• deepseek-ai/DeepSeek-R1-Distill-Llama-8B
• bluuwhale/L3-SthenoMaidBlackroot-8B-V1
• Sao10K/L3-8B-Niitama-v1
• mergekit-community/hopefully_humanish-rp-nsfw-test-v-retry
• vicgalle/Roleplay-Hermes-3-Llama-3.1-8B
• Skywork/Skywork-o1-Open-Llama-3.1-8B
• SicariusSicariiStuff/Impish_Mind_8B
• ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.3

Configuration

The following YAML configuration was used to produce this model:

models:
  # Pivot model
  - model: vicgalle/Humanish-Roleplay-Llama-3.1-8B   
  # Target models
  - model: ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.3
  - model: Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
  - model: Undi95/Llama3-Unholy-8B-OAS
  - model : Undi95/Meta-Llama-3.1-8B-Claude
  - model : deepseek-ai/DeepSeek-R1-Distill-Llama-8B
  - model: vicgalle/Roleplay-Hermes-3-Llama-3.1-8B
  - model: TheDrummer/Llama-3SOME-8B-v2
  - model: Skywork/Skywork-o1-Open-Llama-3.1-8B
  - model: Solshine/reflection-llama-3.1-8B-Solshine-Full
  - model: bluuwhale/L3-SthenoMaidBlackroot-8B-V1
  - model : Sao10K/Llama-3.1-8B-Stheno-v3.4
  - model: Nitral-AI/Poppy_Porpoise-0.72-L3-8B
  - model: mergekit-community/hopefully_humanish-rp-nsfw-test-v-retry
  - model: Sao10K/L3-8B-Niitama-v1
  - model: SicariusSicariiStuff/Impish_Mind_8B
merge_method: sce
base_model: vicgalle/Humanish-Roleplay-Llama-3.1-8B 
parameters:
  select_topk: 1.0
dtype: bfloat16