--- base_model: - FallenMerick/Chunky-Lemon-Cookie-11B - Sao10K/Fimbulvetr-11B-v2.1-16K - senseable/WestLake-7B-v2 base_model_relation: merge library_name: transformers tags: - mergekit - merge - roleplay - text-generation-inference license: cc-by-4.0 --- ![cute](https://huggingface.co/matchaaaaa/Honey-Yuzu-13B/resolve/main/honey-yuzu-cute.png) **Thank you [@Brooketh](https://huggingface.co/brooketh) for the [GGUFs](https://huggingface.co/backyardai/Honey-Yuzu-13B-GGUF)!!** # Honey-Yuzu-13B Meet Honey-Yuzu, a sweet lemony tea brewed by yours truly! A bit of [Chunky-Lemon-Cookie-11B](https://huggingface.co/FallenMerick/Chunky-Lemon-Cookie-11B) here for its great flavor, with a dash of [WestLake-7B-v2](https://huggingface.co/senseable/WestLake-7B-v2) there to add some depth. I'm really proud of how it turned out, and I hope you like it too! It's not as verbose as Chaifighter, but it still writes very well. It boasts fantastic coherence and character understanding (in my opinion) for a 13B, and it's been my daily driver for a little bit. It's a solid RP model that should generally play nice with just about anything. **Native Context Length: 8K/8192** *(can be extended using RoPE, possibly past 16K)* ## Prompt Template: Alpaca ``` Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction: {prompt} ### Response: ``` ## Recommended Settings: Universal-Light Here are some settings ranges that tend to work for me. They aren't strict values, and there's a bit of leeway in them. Feel free to experiment a bit! * Temperature: **1.0** to **1.25** * Min-P: **0.05** to **0.1** * Repetition Penalty: **1.05** *to* **1.1** (high values aren't needed and usually degrade output) * Rep. Penalty Range: **256** *or* **512** * *(all other samplers disabled)* ## The Deets This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). ### Merge Method This model was merged using the passthrough merge method. ### Models Merged The following models were included in the merge: * [Chunky-Lemon-Cookie-11B](https://huggingface.co/FallenMerick/Chunky-Lemon-Cookie-11B) * [SanjiWatsuki/Kunoichi-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-7B) * [SanjiWatsuki/Silicon-Maid-7B](https://huggingface.co/SanjiWatsuki/Silicon-Maid-7B) * [KatyTheCutie/LemonadeRP-4.5.3](https://huggingface.co/KatyTheCutie/LemonadeRP-4.5.3) * [Fimbulvetr-11B-v2.1-16K](https://huggingface.co/Sao10K/Fimbulvetr-11B-v2.1-16K) * [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) * [senseable/WestLake-7B-v2](https://huggingface.co/senseable/WestLake-7B-v2) ### The Special Sauce The following YAML configuration was used to produce this model: ```yaml slices: # this is a quick float32 restack of BLC using the OG recipe - sources: - model: SanjiWatsuki/Kunoichi-7B layer_range: [0, 24] - sources: - model: SanjiWatsuki/Silicon-Maid-7B layer_range: [8, 24] - sources: - model: KatyTheCutie/LemonadeRP-4.5.3 layer_range: [24, 32] merge_method: passthrough dtype: float32 name: Big-Lemon-Cookie-11B --- models: # this is a remake of CLC with the newer Fimbul v2.1 version - model: Big-Lemon-Cookie-11B parameters: weight: 0.85 - model: Sao10K/Fimbulvetr-11B-v2.1-16K parameters: weight: 0.15 merge_method: linear dtype: float32 name: Chunky-Lemon-Cookie-11B --- slices: # 8 layers of WL for the splice - sources: - model: senseable/WestLake-7B-v2 layer_range: [8, 16] merge_method: passthrough dtype: float32 name: WL-splice --- slices: # 8 layers of CLC for the splice - sources: - model: Chunky-Lemon-Cookie-11B layer_range: [8, 16] merge_method: passthrough dtype: float32 name: CLC-splice --- models: # this is the splice, a gradient merge meant to gradually and smoothly interpolate between stacks of different models - model: WL-splice parameters: weight: [1, 1, 0.75, 0.625, 0.5, 0.375, 0.25, 0, 0] # 0.125 / 0.875 values removed here - "math gets screwy" - model: CLC-splice parameters: weight: [0, 0, 0.25, 0.375, 0.5, 0.625, 0.75, 1, 1] # 0.125 / 0.875 values removed here - "math gets screwy" merge_method: dare_linear # according to some paper, "DARE is all you need" base_model: WL-splice dtype: float32 name: splice --- slices: # putting it all together - sources: - model: senseable/WestLake-7B-v2 layer_range: [0, 16] - sources: - model: splice layer_range: [0, 8] - sources: - model: Chunky-Lemon-Cookie-11B layer_range: [16, 48] merge_method: passthrough dtype: float32 name: Honey-Yuzu-13B ``` ### The Thought Process This was meant to be a simple RP-focused merge. I chose 2 well-performing RP models - [Chunky-Lemon-Cookie-11B](https://huggingface.co/FallenMerick/Chunky-Lemon-Cookie-11B) by [FallenMerick](https://huggingface.co/FallenMerick) and [WestLake-7B-v2](https://huggingface.co/senseable/WestLake-7B-v2) by [senseable](https://huggingface.co/senseable) - and merge them using a more conventional configuration (okay, okay, a 56 layer 12.5B Mistral isn't that conventional but still) rather than trying something wild or crazy and pushing the limits. I was very pleased with the results, but I wanted to see what would happen if I remade CLC with [Fimbulvetr-11B-v2.1-16K](https://huggingface.co/Sao10K/Fimbulvetr-11B-v2.1-16K) by [Sao10K](https://huggingface.co/Sao10K). This resulted in equally nice (if not slightly better) outputs but greatly improved native context length. Have feedback? Comments? Questions? Don't hesitate to let me know! As always, have a wonderful day, and please be nice to yourself! :)