RichardErkhov/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/

Name	Quant method	Size
TEST-L3.1-8B-dare_linear.Q2_K.gguf	Q2_K	2.96GB
TEST-L3.1-8B-dare_linear.IQ3_XS.gguf	IQ3_XS	3.28GB
TEST-L3.1-8B-dare_linear.IQ3_S.gguf	IQ3_S	3.43GB
TEST-L3.1-8B-dare_linear.Q3_K_S.gguf	Q3_K_S	3.41GB
TEST-L3.1-8B-dare_linear.IQ3_M.gguf	IQ3_M	3.52GB
TEST-L3.1-8B-dare_linear.Q3_K.gguf	Q3_K	3.74GB
TEST-L3.1-8B-dare_linear.Q3_K_M.gguf	Q3_K_M	3.74GB
TEST-L3.1-8B-dare_linear.Q3_K_L.gguf	Q3_K_L	4.03GB
TEST-L3.1-8B-dare_linear.IQ4_XS.gguf	IQ4_XS	4.18GB
TEST-L3.1-8B-dare_linear.Q4_0.gguf	Q4_0	4.34GB
TEST-L3.1-8B-dare_linear.IQ4_NL.gguf	IQ4_NL	4.38GB
TEST-L3.1-8B-dare_linear.Q4_K_S.gguf	Q4_K_S	4.37GB
TEST-L3.1-8B-dare_linear.Q4_K.gguf	Q4_K	4.58GB
TEST-L3.1-8B-dare_linear.Q4_K_M.gguf	Q4_K_M	4.58GB
TEST-L3.1-8B-dare_linear.Q4_1.gguf	Q4_1	4.78GB
TEST-L3.1-8B-dare_linear.Q5_0.gguf	Q5_0	5.21GB
TEST-L3.1-8B-dare_linear.Q5_K_S.gguf	Q5_K_S	5.21GB
TEST-L3.1-8B-dare_linear.Q5_K.gguf	Q5_K	5.34GB
TEST-L3.1-8B-dare_linear.Q5_K_M.gguf	Q5_K_M	5.34GB
TEST-L3.1-8B-dare_linear.Q5_1.gguf	Q5_1	5.65GB
TEST-L3.1-8B-dare_linear.Q6_K.gguf	Q6_K	6.14GB
TEST-L3.1-8B-dare_linear.Q8_0.gguf	Q8_0	7.95GB

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