Edit model card
    quantization_options = [
        "Q4_K_M", "Q4_K_S", "IQ4_NL", "IQ4_XS", "Q5_K_M", 
        "Q5_K_S", "Q6_K", "Q8_0", "IQ3_M", "IQ3_S", "IQ3_XS", "IQ3_XXS"
    ]

GGUF-Imatrix quantizations for Test157t/Copium-Cola-9B.

All credits belong to the author.

If you liked these, check out the work with FantasiaFoundry's GGUF-IQ-Imatrix-Quantization-Script.

What does "Imatrix" mean?

It stands for Importance Matrix, a technique used to improve the quality of quantized models.
[1]
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 and lead to better quality preservation, especially when the calibration data is diverse.
[2]

For --imatrix data, included imatrix.dat was used.

Using llama.cpp-b2343:

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.

If you want any specific quantization to be added, feel free to ask.

Original model information:

image/png

This model was merged using the passthrough 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: ChaoticNeutrals/Eris_7B
        layer_range: [0, 20]
  - sources:
      - model: ChaoticNeutrals/Eris_7B
        layer_range: [12, 32]
merge_method: passthrough
dtype: float16
Downloads last month
131
GGUF
Model size
8.99B params
Architecture
llama

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Examples
Inference API (serverless) has been turned off for this model.

Collection including Lewdiculous/Copium-Cola-9B-GGUF-IQ-Imatrix