L3.1-Athena-l2-8B

merge

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

Merge Details

Merge Method

This model was merged using the Model Stock merge method using meta-llama/Llama-3.1-8B as a base.

Models Merged

The following models were included in the merge:

• NousResearch/DeepHermes-3-Llama-3-8B-Preview
• AtlaAI/Selene-1-Mini-Llama-3.1-8B
• normster/RealGuardrails-Llama3.1-8B-SFT
• DavidAU/L3.1-RP-Hero-BigTalker-8B + kik41/lora-length-long-llama-3-8b-v2
• mergekit-community/L3.1-Athena-d-8B
• mergekit-community/L3.1-Athena-i-8B + kik41/lora-length-long-llama-3-8b-v2
• Skywork/Skywork-Critic-Llama-3.1-8B
• kromeurus/L3.1-Clouded-Uchtave-v0.1-8B + kik41/lora-type-descriptive-llama-3-8b-v2
• mergekit-community/L3.1-Athena-c-8B + vincentyandex/lora_llama3_chunked_novel_bs128
• MathGenie/MathCoder2-Llama-3-8B
• DavidAU/L3.1-Dark-Planet-SpinFire-Uncensored-8B
• Skywork/Skywork-o1-Open-Llama-3.1-8B
• mergekit-community/L3.1-Athena-j-8B + kik41/lora-type-descriptive-llama-3-8b-v2
• nothingiisreal/L3.1-8B-Celeste-V1.5 + vincentyandex/lora_llama3_chunked_novel_bs128

Configuration

The following YAML configuration was used to produce this model:

dtype: float32
out_dtype: bfloat16
merge_method: model_stock
base_model: meta-llama/Llama-3.1-8B
models:
  - model: AtlaAI/Selene-1-Mini-Llama-3.1-8B
  - model: DavidAU/L3.1-Dark-Planet-SpinFire-Uncensored-8B
  - model: DavidAU/L3.1-RP-Hero-BigTalker-8B+kik41/lora-length-long-llama-3-8b-v2
  - model: kromeurus/L3.1-Clouded-Uchtave-v0.1-8B+kik41/lora-type-descriptive-llama-3-8b-v2
  - model: MathGenie/MathCoder2-Llama-3-8B
  - model: mergekit-community/L3.1-Athena-c-8B+vincentyandex/lora_llama3_chunked_novel_bs128
  - model: mergekit-community/L3.1-Athena-d-8B
  - model: mergekit-community/L3.1-Athena-i-8B+kik41/lora-length-long-llama-3-8b-v2
  - model: mergekit-community/L3.1-Athena-j-8B+kik41/lora-type-descriptive-llama-3-8b-v2
  - model: meta-llama/Llama-3.1-8B
  - model: normster/RealGuardrails-Llama3.1-8B-SFT
  - model: nothingiisreal/L3.1-8B-Celeste-V1.5+vincentyandex/lora_llama3_chunked_novel_bs128
  - model: NousResearch/DeepHermes-3-Llama-3-8B-Preview
  - model: Skywork/Skywork-o1-Open-Llama-3.1-8B
  - model: Skywork/Skywork-Critic-Llama-3.1-8B