The mergekit-community/nsfw-w-deepseek-r1-retry model is a merged language model created using the Model Stock method, based on mergekit-community/nsfw_merge_test_vFFS. It combines stepenZEN/DeepSeek-R1-Distill-Llama-8B-Abliterated with various Llama-3 LoRAs, including Azazelle/Llama-3-LongStory-LORA, moetezsa/Llama3_instruct_on_wikibio, and Azazelle/Llama-3-LimaRP-Instruct-LoRA-8B. This 8B parameter model is designed to integrate diverse capabilities from its constituent models, likely focusing on instruction following and narrative generation, given the Llama-3 LoRA components.
Loading preview...
Overview
This model, nsfw-w-deepseek-r1-retry, is a merged language model developed by mergekit-community. It leverages the Model Stock merge method, as described in the Model Stock paper, building upon mergekit-community/nsfw_merge_test_vFFS as its base.
Key Capabilities
The model integrates components from several specialized LoRAs with stepenZEN/DeepSeek-R1-Distill-Llama-8B-Abliterated. This merge aims to combine:
- Long-form narrative generation: Incorporating
Azazelle/Llama-3-LongStory-LORAsuggests an emphasis on extended text generation. - Instruction following: The inclusion of
moetezsa/Llama3_instruct_on_wikibioandAzazelle/Llama-3-LimaRP-Instruct-LoRA-8Bindicates a focus on robust instruction-tuned capabilities and role-play scenarios.
Good for
This model is particularly well-suited for applications requiring:
- Generating detailed and coherent long-form text.
- Following complex instructions in conversational or creative contexts.
- Engaging in role-playing or interactive narrative generation, benefiting from the combined strengths of its Llama-3 based LoRA components.
Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.