library_name: transformers
license: other
language:
- en
tags:
- gguf
- quantized
- roleplay
- imatrix
- mistral
- merge
inference: false
base_model:
- Epiculous/Fett-uccine-Long-Noodle-7B-120k-Context
- Epiculous/Mika-7B
This repository hosts GGUF-Imatrix quantizations for Test157t/Mika-Longtext-7b.
Could work better for longer context sizes. Maybe.
What does "Imatrix" mean?
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.
Steps:
Base⇢ GGUF(F16)⇢ Imatrix-Data(F16)⇢ GGUF(Imatrix-Quants)
Quants:
quantization_options = [
"Q4_K_M", "IQ4_XS", "Q5_K_M", "Q5_K_S", "Q6_K",
"Q8_0", "IQ3_M", "IQ3_S", "IQ3_XXS"
]
If you want anything that's not here or another model, feel free to request.
Original model information:
This model was merged using the SLERP merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
slices:
- sources:
- model: Epiculous/Fett-uccine-Long-Noodle-7B-120k-Context
layer_range: [0, 32]
- model: Epiculous/Mika-7B
layer_range: [0, 32]
merge_method: slerp
base_model: Epiculous/Fett-uccine-Long-Noodle-7B-120k-Context
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: bfloat16