Downloads · 30 days
8
3% of all-time downloads
RichardErkhov/matchaaaaa_-_Honey-Yuzu-13B-gguf
matchaaaaa_-_Honey-Yuzu-13B-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
8
3% of all-time downloads
All-time downloads
235
Public
Repo size
141 GB
Likes
0
Public
Click a slice to open those files.
.gguf164 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Honey-Yuzu-13B - GGUF
| Name | Quant method | Size |
|---|---|---|
| Honey-Yuzu-13B.Q2_K.gguf | Q2_K | 4.33GB |
| Honey-Yuzu-13B.IQ3_XS.gguf | IQ3_XS | 4.81GB |
| Honey-Yuzu-13B.IQ3_S.gguf | IQ3_S | 5.07GB |
| Honey-Yuzu-13B.Q3_K_S.gguf | Q3_K_S | 5.04GB |
| Honey-Yuzu-13B.IQ3_M.gguf | IQ3_M | 5.24GB |
| Honey-Yuzu-13B.Q3_K.gguf | Q3_K | 5.62GB |
| Honey-Yuzu-13B.Q3_K_M.gguf | Q3_K_M | 5.62GB |
| Honey-Yuzu-13B.Q3_K_L.gguf | Q3_K_L | 6.11GB |
| Honey-Yuzu-13B.IQ4_XS.gguf | IQ4_XS | 6.3GB |
| Honey-Yuzu-13B.Q4_0.gguf | Q4_0 | 6.57GB |
| Honey-Yuzu-13B.IQ4_NL.gguf | IQ4_NL | 6.64GB |
| Honey-Yuzu-13B.Q4_K_S.gguf | Q4_K_S | 6.62GB |
| Honey-Yuzu-13B.Q4_K.gguf | Q4_K | 6.99GB |
| Honey-Yuzu-13B.Q4_K_M.gguf | Q4_K_M | 6.99GB |
| Honey-Yuzu-13B.Q4_1.gguf | Q4_1 | 7.29GB |
| Honey-Yuzu-13B.Q5_0.gguf | Q5_0 | 8.01GB |
| Honey-Yuzu-13B.Q5_K_S.gguf | Q5_K_S | 8.01GB |
| Honey-Yuzu-13B.Q5_K.gguf | Q5_K | 8.22GB |
| Honey-Yuzu-13B.Q5_K_M.gguf | Q5_K_M | 8.22GB |
| Honey-Yuzu-13B.Q5_1.gguf | Q5_1 | 8.73GB |
| Honey-Yuzu-13B.Q6_K.gguf | Q6_K | 9.53GB |
| Honey-Yuzu-13B.Q8_0.gguf | Q8_0 | 12.35GB |
base_model:

Thank you @Brooketh for the GGUFs!!
Meet Honey-Yuzu, a sweet lemony tea brewed by yours truly! A bit of Chunky-Lemon-Cookie-11B here for its great flavor, with a dash of 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.
Max Context Length: 8K/8192
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
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!
This is a merge of pre-trained language models created using mergekit.
This model was merged using the passthrough merge method.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
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
This was meant to be a simple RP-focused merge. I chose 2 well-performing RP models - Chunky-Lemon-Cookie-11B by FallenMerick and WestLake-7B-v2 by 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 by 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! :)