DreadPoor/VENN_1.2-8B-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 arcee-ai/Llama-3.1-SuperNova-Lite + DreadPoor/Everything-COT-8B-r128-LoRA as a base.

Models Merged

The following models were included in the merge:

• DreadPoor/Aurora_faustus-8B-LINEAR + kik41/lora-type-descriptive-llama-3-8b-v2
• DreadPoor/Dragon-8B-Model_Stock + kik41/lora-sarcasm-more-llama-3-8b-v2
• DreadPoor/Elusive1.2-8B-Model_Stock + kik41/lora-voice-active-llama-3-8b-v2
• DreadPoor/BaeZel-8B-LINEAR + kik41/lora-type-expository-llama-3-8b-v2
• DreadPoor/Alita99-8B-LINEAR + kik41/lora-formality-informal-llama-3-8b-v2

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: DreadPoor/Elusive1.2-8B-Model_Stock+kik41/lora-voice-active-llama-3-8b-v2
  - model: DreadPoor/Dragon-8B-Model_Stock+kik41/lora-sarcasm-more-llama-3-8b-v2 
  - model: DreadPoor/Alita99-8B-LINEAR+kik41/lora-formality-informal-llama-3-8b-v2 
  - model: DreadPoor/BaeZel-8B-LINEAR+kik41/lora-type-expository-llama-3-8b-v2 
  - model: DreadPoor/Aurora_faustus-8B-LINEAR+kik41/lora-type-descriptive-llama-3-8b-v2
merge_method: model_stock
base_model: arcee-ai/Llama-3.1-SuperNova-Lite+DreadPoor/Everything-COT-8B-r128-LoRA
normalize: false
int8_mask: true
dtype: bfloat16