Model Stock: All we need is just a few fine-tuned models
Paper • 2403.19522 • Published • 14
This is a merge of pre-trained language models created using mergekit.
This model was merged using the Model Stock merge method using DreadPoor/Suavemente-8B-Model_Stock as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: tannedbum/L3-Nymeria-v2-8B+surya-narayanan/formal_logic
- model: tannedbum/L3-Nymeria-v2-8B+surya-narayanan/health
- model: tannedbum/L3-Nymeria-v2-8B+vincentyandex/lora_llama3_chunked_novel_bs128
- model: tannedbum/L3-Nymeria-v2-8B+kik41/lora-type-narrative-llama-3-8b-v2
- model: tannedbum/L3-Nymeria-v2-8B+surya-narayanan/sociology
- model: tannedbum/L3-Nymeria-v2-8B+surya-narayanan/professional_psychology
- model: tannedbum/L3-Nymeria-v2-8B+ResplendentAI/Smarts_Llama3
- model: tannedbum/L3-Nymeria-v2-8B+Azazelle/Llama3-RP-Lora
- model: tannedbum/L3-Nymeria-v2-8B+DreadPoor/OpenBioLLM-8B-r64-LoRA
- model: tannedbum/L3-Nymeria-v2-8B+Azazelle/Llama-3-8B-Abomination-LORA
- model: tannedbum/L3-Nymeria-v2-8B+kik41/lora-type-descriptive-llama-3-8b-v2
- model: tannedbum/L3-Nymeria-v2-8B+kik41/lora-length-long-llama-3-8b-v2
- model: tannedbum/L3-Nymeria-v2-8B+surya-narayanan/anatomy
- model: tannedbum/L3-Nymeria-v2-8B+surya-narayanan/human_sexuality
merge_method: model_stock
base_model: DreadPoor/Suavemente-8B-Model_Stock
dtype: float32