Support:
My upload speeds have been cooked and unstable lately.
Realistically I'd need to move to get a better provider.
If you want and you are able to...
You can support my various endeavors here (Ko-fi).
I apologize for disrupting your experience.
In this repository you can find GGUF-IQ-Imatrix quants for ChaoticNeutrals/Nyanade_Stunna-Maid-7B-v0.2 and if needed you can get some basic SillyTavern presets here, if you have issues with repetitiveness or lack or variety in responses I recommend changing the Temperature to 1.15, MinP to 0.075, RepPen to 1.15 and RepPenRange to 1024.
Vision:
This is a #multimodal model that also has optional #vision capabilities.
Expand the relevant sections bellow and read the full card information if you also want to make use that functionality.Quant options:
Reading bellow you can also find quant option recommendations for some common GPU VRAM capacities.
"Unhinged RP with the spice of the previous 0.420 remixes, 32k context and vision capabilities."
Assuming a context size of 8192 for simplicity and 1GB of Operating System VRAM overhead with some safety margin to avoid overflowing buffers...
For 11-12GB VRAM:
A GPU with 11-12GB of VRAM capacity can comfortably use the Q6_K-imat quant option and run it at good speeds.
This is the same with or without using #vision capabilities.
For 8GB VRAM:
If not using #vision, for GPUs with 8GB of VRAM capacity the Q5_K_M-imat quant option will fit comfortably and should run at good speeds.
If you are also using #vision from this model opt for the Q4_K_M-imat quant option to avoid filling the buffers and potential slowdowns.
For 6GB VRAM:
If not using #vision, for GPUs with 6GB of VRAM capacity the IQ3_M-imat quant option should fit comfortably to run at good speeds.
If you are also using #vision from this model opt for the IQ3_XXS-imat quant option.
quantization_options = [
"IQ3_M", "IQ3_XXS",
"Q4_K_M", "Q4_K_S", "IQ4_XS", "IQ4_NL",
"Q5_K_M", "Q5_K_S",
"Q6_K",
"Q8_0"
]
Steps performed:
Base⇢ GGUF(F16)⇢ Imatrix-Data(F16)⇢ GGUF(Imatrix-Quants)
The latest of llama.cpp available at the time was used, with imatrix-with-rp-ex.txt as calibration data.
It stands for Importance Matrix, a technique used to improve the quality of quantized models. The Imatrix is calculated based on calibration data, and it helps determine the importance of different model activations during the quantization process. The idea is to preserve the most important information during quantization, which can help reduce the loss of model performance, especially when the calibration data is diverse. [1] [2]
For imatrix data generation, kalomaze's
groups_merged.txtwith additional roleplay chats was used, you can find it here for reference. This was just to add a bit more diversity to the data with the intended use case in mind.
To use the multimodal capabilities of this model, such as vision, you also need to load the specified mmproj file, you can get it here or as uploaded in the mmproj folder in the repository.
1: Make sure you are using the latest version of KoboldCpp.
2: Load the mmproj file by using the corresponding section in the interface:
2.1: For CLI users, you can load the mmproj file by adding the respective flag to your usual command:
--mmproj your-mmproj-file.gguf