RichardErkhov/mergekit-community_-_mergekit-task_arithmetic-fyizkfk-8bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

mergekit-task_arithmetic-fyizkfk - bnb 8bits

• Model creator: https://huggingface.co/mergekit-community/
• Original model: https://huggingface.co/mergekit-community/mergekit-task_arithmetic-fyizkfk/

Original model description:

base_model:

• xMaulana/FinMatcha-3B-Instruct
• PurpleAILAB/Llama-3.2-3B-Instruct-uncensored-LoRA library_name: transformers tags:
• mergekit
• merge

---

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the task arithmetic merge method using xMaulana/FinMatcha-3B-Instruct + PurpleAILAB/Llama-3.2-3B-Instruct-uncensored-LoRA as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: xMaulana/FinMatcha-3B-Instruct+PurpleAILAB/Llama-3.2-3B-Instruct-uncensored-LoRA
dtype: bfloat16
merge_method: task_arithmetic
parameters:
  normalize: false
slices:
- sources:
  - layer_range: [0, 28]
    model: xMaulana/FinMatcha-3B-Instruct+PurpleAILAB/Llama-3.2-3B-Instruct-uncensored-LoRA
    parameters:
      weight: 1.0