This repository hosts GGUF-IQ-Imatrix quantizations for
Nitral-AI/Prima-LelantaclesV6.3-7b.
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.txt with added roleplay chats was used, you can find it
here.
1 quantization_options = [
2 "Q4_K_M", "IQ4_XS", "Q5_K_M", "Q5_K_S", "Q6_K",
3 "Q8_0", "IQ3_M", "IQ3_S", "IQ3_XXS"
4 ]
If you want anything that's not here or another model, feel free to request.
This model was merged using the SLERP merge method.
1slices:
2 - sources:
3 - model: Test157t/Prima-LelantaclesV6.1-7b
4 layer_range: [0, 32]
5 - model: Test157t/Eris-Floramix-7b
6 layer_range: [0, 32]
7merge_method: slerp
8base_model: Test157t/Prima-LelantaclesV6.1-7b
9parameters:
10 t:
11 - filter: self_attn
12 value: [0, 0.5, 0.3, 0.7, 1]
13 - filter: mlp
14 value: [1, 0.5, 0.7, 0.3, 0]
15 - value: 0.5
16dtype: bfloat16
