library_name: transformers
license: cc-by-4.0
language:
- en
tags:
- gguf
- quantized
- roleplay
- imatrix
- mistral
- merge
inference: false
This repository hosts GGUF-IQ-Imatrix quantizations for grimjim/kukulemon-7B.
- ChatML/Alpaca.
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.
My waifu image for this card:
Original model information:
kukulemon-7B
A merger of two similar models with strong reasoning, hopefully resulting in "dense" encoding of said reasoning, was merged with a model targeting roleplay.
I've tested with ChatML prompts with temperature=1.1 and minP=0.03. The model itself supports Alpaca format prompts. The model claims a context length of 32K, but I've only tested to 8K to date.
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
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: grimjim/kuno-kunoichi-v1-DPO-v2-SLERP-7B
layer_range: [0, 32]
- model: KatyTheCutie/LemonadeRP-4.5.3
layer_range: [0, 32]
# or, the equivalent models: syntax:
# models:
merge_method: slerp
base_model: KatyTheCutie/LemonadeRP-4.5.3
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 # fallback for rest of tensors
dtype: float16