MrRobotoAI/93a

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/Odin-v2-8b-NOVELIST-128K as a base.

Models Merged

The following models were included in the merge:

• MrRobotoAI/92 + jspr/llama3-instruct-wordcel-smutrom-8k_peft
• MrRobotoAI/92 + jspr/llama3-wordcel-smutrom-reorder_peft
• MrRobotoAI/92 + jspr/smut_llama_8b_smutromance_32k_peft
• MrRobotoAI/92 + jspr/llama3_8b_wordcel_8k_peft
• MrRobotoAI/92 + Blackroot/Llama-3-LongStory-LORA
• MrRobotoAI/92 + jspr/llama3-instruct-wordcel-smutrom_peft
• MrRobotoAI/92 + jspr/smut_llama_8b_smut_2k_romance_1k_peft
• MrRobotoAI/92 + jspr/llama3_8b_instruct_wordcel_peft
• MrRobotoAI/92 + arushimgupta/lora_save_7
• MrRobotoAI/92 + jspr/llama3-wordcel-smutrom_peft
• MrRobotoAI/92 + jspr/llama3-wordcel-peft

Configuration

The following YAML configuration was used to produce this model:

models:

  - model: MrRobotoAI/92+arushimgupta/lora_save_7
  - model: MrRobotoAI/92+jspr/smut_llama_8b_smutromance_32k_peft
  - model: MrRobotoAI/92+jspr/llama3-instruct-wordcel-smutrom-8k_peft
  - model: MrRobotoAI/92+jspr/llama3_8b_wordcel_8k_peft
  - model: MrRobotoAI/92+jspr/llama3-instruct-wordcel-smutrom_peft
  - model: MrRobotoAI/92+jspr/llama3_8b_instruct_wordcel_peft
  - model: MrRobotoAI/92+jspr/llama3-wordcel-smutrom-reorder_peft
  - model: MrRobotoAI/92+jspr/llama3-wordcel-smutrom_peft
  - model: MrRobotoAI/92+jspr/llama3-wordcel-peft
  - model: MrRobotoAI/92+jspr/smut_llama_8b_smutromance_32k_peft
  - model: MrRobotoAI/92+jspr/smut_llama_8b_smut_2k_romance_1k_peft
  - model: MrRobotoAI/92+Blackroot/Llama-3-LongStory-LORA
  - model: MrRobotoAI/Odin-v2-8b-NOVELIST-128K

merge_method: model_stock
base_model: MrRobotoAI/Odin-v2-8b-NOVELIST-128K
normalize: true
dtype: float16