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.
One of the benefits of using an Imatrix is that it can lead to better model performance, especially when the calibration data is diverse.
If you want any specific quantization to be added, feel free to ask.
All credits belong to the creator.
Base⇢ GGUF(F16)⇢ Imatrix-Data(F16)⇢ GGUF(Imatrix-Quants)
The new IQ3_S quant-option has shown to be better than the old Q3_K_S, so I added that instead of the later. Only supported in koboldcpp-1.59.1 or higher.
For --imatrix data, imatrix-Prodigy_7B-F16.dat was used.
This is a merge of pre-trained language models created using mergekit.
This model was merged using the SLERP merge method.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
slices:
- sources:
- model: ChaoticNeutrals/This_is_fine_7B
layer_range: [0, 32]
- model: macadeliccc/WestLake-7B-v2-laser-truthy-dpo
layer_range: [0, 32]
merge_method: slerp
base_model: macadeliccc/WestLake-7B-v2-laser-truthy-dpo
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16