Quantization made by Richard Erkhov.

[Github](https://github.com/RichardErkhov)

[Discord](https://discord.gg/pvy7H8DZMG)

[Request more models](https://github.com/RichardErkhov/quant_request)


MFANNv0.14.10 - bnb 4bits
- Model creator: https://huggingface.co/netcat420/
- Original model: https://huggingface.co/netcat420/MFANNv0.14.10/




Original model description:
---
base_model:
- netcat420/MFANNv0.14
- MaziyarPanahi/Llama-3-8B-Instruct-v0.4
- netcat420/MFANNv0.13
library_name: transformers
tags:
- mergekit
- merge

---
# MFANNv0.14.10

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

## Merge Details
### Merge Method

This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [MaziyarPanahi/Llama-3-8B-Instruct-v0.4](https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-v0.4) as a base.

### Models Merged

The following models were included in the merge:
* [netcat420/MFANNv0.14](https://huggingface.co/netcat420/MFANNv0.14)
* [netcat420/MFANNv0.13](https://huggingface.co/netcat420/MFANNv0.13)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: netcat420/MFANNv0.14
    parameters:
      density: [1, 0.7, 0.1] # density gradient
      weight: 1.0
  - model: netcat420/MFANNv0.13
    parameters:
      density: [1, 0.7, 0.1] # density gradient
      weight: 1.0
merge_method: ties
base_model: MaziyarPanahi/Llama-3-8B-Instruct-v0.4
parameters:
  normalize: true
  int8_mask: true
dtype: float16

```