AbacusResearch/haLLawa4-7b

haLLawa4-7b

haLLawa4-7b is a merge of the following models using mergekit:

• —mlabonne/Monarch-7B
• —paulml/OGNO-7B
• —AbacusResearch/haLLAwa3

🧩 Configuration

\```yaml models:

• —model: eren23/ogno-monarch-jaskier-merge-7b # No parameters necessary for base model
• —model: mlabonne/Monarch-7B #Emphasize the beginning of Vicuna format models parameters: weight: 0.5 density: 0.59
• —model: paulml/OGNO-7B parameters: weight: 0.2 density: 0.55 # Vicuna format
• —model: AbacusResearch/haLLAwa3 parameters: weight: 0.3 density: 0.55

mergemethod: dareties basemodel: eren23/ogno-monarch-jaskier-merge-7b parameters: int8mask: true dtype: bfloat16 random_seed: 0 \```

Open LLM Leaderboard Evaluation Results

Detailed results can be found here