djuna_-_TEST-L3.1-8B-dare_linear-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

TEST-L3.1-8B-dare_linear - GGUF

• Model creator: https://huggingface.co/djuna/
• Original model: https://huggingface.co/djuna/TEST-L3.1-8B-dare_linear/

Original model description:

base_model:

• HiroseKoichi/Llama-3-8B-Stroganoff-4.0
• ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.2 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 linear DARE merge method using ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.2 as a base.

Models Merged

The following models were included in the merge:

• HiroseKoichi/Llama-3-8B-Stroganoff-4.0

Configuration

The following YAML configuration was used to produce this model:

dtype: bfloat16
tokenizer_source: base
merge_method: dare_linear
base_model: ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.2
models:
  - model: HiroseKoichi/Llama-3-8B-Stroganoff-4.0
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: up_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - value: 0
  - model: ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.2
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: up_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - value: 1