duyntnet/Open-StarLake-Swap-7B-imatrix-GGUF

Quantizations of https://huggingface.co/Aryanne/Open-StarLake-Swap-7B

Inference Clients/UIs

• llama.cpp
• KoboldCPP
• ollama
• text-generation-webui
• GPT4All
• jan

---

From original readme

This is a merge of pre-trained language models created using mergekit, but my branch was used here

Merge Details

Merge Method

This model was merged using the task_swapping merge method using senseable/WestLake-7B-v2 as a base.

Models Merged

The following models were included in the merge:

• berkeley-nest/Starling-LM-7B-alpha

• NousResearch/Nous-Hermes-2-Mistral-7B-DPO

• openchat/openchat-3.5-0106

Prompt Format:

I prefer using this way, which seems to work.

Example using Koboldcpp:

Start Seq.:

\nYour_name: 

End Seq.:

\nCharacter_name: 

In Memory

### Instruction:
Character description.

Generate a endless verbose(very descriptive) role-play conversation with Character_name.

### Response:
Your_name: how are you doing babe? *Your_name approaches Character_name and kisses her in the lips*
Character_name: I'm fine, it's been an weird day. *Character_name blushes and hugs Your_name with love*