DreadPoor/WIP-Acacia-8B-Model_Stock

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 Epiculous/NovaSpark + ResplendentAI/Theory_of_Mind_Llama3 as a base.

Models Merged

The following models were included in the merge:

• cgato/L3-TheSpice-8b-v0.8.3 + kloodia/lora-8b-physic
• allenai/Llama-3.1-Tulu-3-8B-SFT + Azazelle/L3-Daybreak-8b-lora
• Replete-AI/L3-Pneuma-8B + grimjim/Llama-3-Instruct-abliteration-LoRA-8B
• Sao10K/L3-8B-Stheno-v3.2 + ResplendentAI/Smarts_Llama3
• NeverSleep/Lumimaid-v0.2-8B + kloodia/lora-8b-bio

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: cgato/L3-TheSpice-8b-v0.8.3+kloodia/lora-8b-physic
  - model: Replete-AI/L3-Pneuma-8B+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
  - model: Sao10K/L3-8B-Stheno-v3.2+ResplendentAI/Smarts_Llama3 
  - model: NeverSleep/Lumimaid-v0.2-8B+kloodia/lora-8b-bio
  - model: allenai/Llama-3.1-Tulu-3-8B-SFT+Azazelle/L3-Daybreak-8b-lora
merge_method: model_stock
base_model: Epiculous/NovaSpark+ResplendentAI/Theory_of_Mind_Llama3
normalize: false
int8_mask: true
dtype: bfloat16