MrRobotoAI/R3

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 MrRobotoAI/R2 as a base.

Models Merged

The following models were included in the merge:

• MrRobotoAI/R2 + ResplendentAI/NoWarning_Llama3
• MrRobotoAI/R2 + ResplendentAI/Theory_of_Mind_Llama3
• MrRobotoAI/R2 + athirdpath/BigMistral-11b-GLUE_LORA
• MrRobotoAI/R2 + kik41/lora-type-descriptive-llama-3-8b-v2
• MrRobotoAI/R2 + tdolega/rag-tge_Llama-3-8B_LoRA
• MrRobotoAI/R2 + DreadPoor/Everything-COT-8B-r128-LoRA
• MrRobotoAI/R2 + Blackroot/Llama-3-LongStory-LORA
• MrRobotoAI/R2 + automorphic/LORA_20231221_042843_philosophy
• MrRobotoAI/R2 + kik41/lora-sarcasm-more-llama-3-8b-v2
• MrRobotoAI/R2 + vaitech/open-hermes-erotic-story-finetune
• MrRobotoAI/R2 + vincentyandex/lora_llama3_chunked_novel_bs128
• MrRobotoAI/R2 + kik41/lora-type-narrative-llama-3-8b-v2
• MrRobotoAI/R2 + vaitech/open-hermes-sd-finetune

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: MrRobotoAI/R2+tdolega/rag-tge_Llama-3-8B_LoRA
  - model: MrRobotoAI/R2+Blackroot/Llama-3-LongStory-LORA
  - model: MrRobotoAI/R2+automorphic/LORA_20231221_042843_philosophy
  - model: MrRobotoAI/R2+ResplendentAI/NoWarning_Llama3
  - model: MrRobotoAI/R2+ResplendentAI/Theory_of_Mind_Llama3
  - model: MrRobotoAI/R2+vaitech/open-hermes-erotic-story-finetune
  - model: MrRobotoAI/R2+vaitech/open-hermes-sd-finetune
  - model: MrRobotoAI/R2+vincentyandex/lora_llama3_chunked_novel_bs128
  - model: MrRobotoAI/R2+athirdpath/BigMistral-11b-GLUE_LORA
  - model: MrRobotoAI/R2+DreadPoor/Everything-COT-8B-r128-LoRA
  - model: MrRobotoAI/R2+kik41/lora-type-descriptive-llama-3-8b-v2
  - model: MrRobotoAI/R2+kik41/lora-type-narrative-llama-3-8b-v2
  - model: MrRobotoAI/R2+kik41/lora-sarcasm-more-llama-3-8b-v2
merge_method: model_stock
base_model: MrRobotoAI/R2
normalize: true
dtype: float16