đ Rose-20B
Rose-20B is an experimental Frankenmerge model, which combines the strengths of multiple models and is suitable for various role - play scenarios.
đ Quick Start
The recommended format to use is Alpaca.
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
Feel free to share any other prompts that works. This model is very robust.
⨠Features
- This is a Frankenmerge model, combining [Thorns - 13B](https://huggingface.co/CalderaAI/13B - Thorns - l2) by CalderaAI and [Noromaid - 13 - v0.1.1](https://huggingface.co/NeverSleep/Noromaid - 13b - v0.1.1) by NeverSleep (IkariDev and Undi).
- It should be very good at any role - play scenarios.
- It has potential as a base model for finetune experiments to create Pygmalion - 20B.
- There is potential for experimentation with merging with other 20B Frankenmerge models.
đĻ Installation
No installation steps are provided in the original README.
đ Documentation
Other Formats
- [GGUF](https://huggingface.co/TheBloke/Rose - 20B - GGUF)
- [GPTQ](https://huggingface.co/TheBloke/Rose - 20B - GPTQ)
- [AWQ](https://huggingface.co/TheBloke/Rose - 20B - AWQ)
- [exl2](https://huggingface.co/royallab/Rose - 20B - exl2)
Model Details
A Frankenmerge with [Thorns - 13B](https://huggingface.co/CalderaAI/13B - Thorns - l2) by CalderaAI and [Noromaid - 13 - v0.1.1](https://huggingface.co/NeverSleep/Noromaid - 13b - v0.1.1) by NeverSleep (IkariDev and Undi). This recipe was proposed by Trappu and the layer distribution recipe was made by Undi. I thank them for sharing their knowledge with me.
The recommended format to use is Alpaca.
Justification for its Existence
Potential base model for finetune experiments using our dataset to create Pygmalion - 20B. Due to the already high capabilities, adding our dataset will mesh well with how the model performs.
Potential experimentation with merging with other 20B Frankenmerge models.
Model Recipe
slices:
- sources:
- model: Thorns - 13B
layer_range: [0, 16]
- sources:
- model: Noromaid - 13B
layer_range: [8, 24]
- sources:
- model: Thorns - 13B
layer_range: [17, 32]
- sources:
- model: Noromaid - 13B
layer_range: [25, 40]
merge_method: passthrough
dtype: float16
Again, credits to Undi for the recipe.
Reception
The model was given to a handful of members in the PygmalionAI Discord community for testing. A strong majority really enjoyed the model with only a couple giving the model a passing grade. Since our community has high standards for role - playing models, I was surprised at the positive reception.
Contact
Send a message to tav (tav) on Discord if you want to talk about the model to me. I'm always open to receive comments.
đ§ Technical Details
No technical details are provided in the original README.
đ License
The license of this model is llama2.
â ī¸ Important Note
This model uses significantly more VRAM due to the KV cache increase resulting in more VRAM required for the context window.
%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
