My GGUF-IQ-Imatrix quants for nbeerbower/llama-3-Stheno-Mahou-8B.
"A potential precious hidden gem, will you polish this rough diamond?"
This is a merge of two very interesting models, aimed at roleplaying usage.
Personal-support:
I apologize for disrupting your experience.
Currently I'm working on moving for a better internet provider.
If you want and you are able to...
You can spare some change over here (Ko-fi).Author-support:
You can support the author at their own page.
Quantization process:
For future reference, these quants have been done after the fixes from #6920 have been merged.
Imatrix data was generated from the FP16-GGUF and the final conversions used BF16-GGUF for the quantization process.
This was a bit more disk and compute intensive but hopefully avoided any losses during conversion.
If you noticed any issues let me know in the discussions.
General usage:
Use the latest version of KoboldCpp.
Remember that you can also use--flashattentionon KoboldCpp now even with non-RTX cards for reduced VRAM usage.
For 8GB VRAM GPUs, I recommend the Q4_K_M-imat quant for up to 12288 context sizes.
For 12GB VRAM GPUs, the Q5_K_M-imat quant will give you a great size/quality balance.Resources:
You can find out more about how each quant stacks up against each other and their types here and here, respectively.Presets:
Some compatible SillyTavern presets can be found here (Virt's Roleplay Presets), experiment with Llama-3 and ChatML.
This is a merge of pre-trained language models created using mergekit.
This model was merged using the Model Stock merge method using flammenai/Mahou-1.2-llama3-8B as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: flammenai/Mahou-1.1-llama3-8B
- model: Sao10K/L3-8B-Stheno-v3.1
merge_method: model_stock
base_model: flammenai/Mahou-1.2-llama3-8B
dtype: bfloat16