Quantization made by Richard Erkhov.

Llama-Ko-Merge - GGUF

Model creator: https://huggingface.co/Gunulhona/
Original model: https://huggingface.co/Gunulhona/Llama-Ko-Merge/

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

Original model description:

base_model:

Saxo/Linkbricks-Horizon-AI-Korean-llama3-sft-dpo-8b-base
tesser-ai/Tesser-Llama-3-Ko-8B
NousResearch/Hermes-3-Llama-3.1-8B
meta-llama/Meta-Llama-3.1-8B
maum-ai/Llama-3-MAAL-8B-Instruct-v0.1
Saxo/Linkbricks-Horizon-AI-Korean-llama-3.1-sft-dpo-8B 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 DARE TIES merge method using Saxo/Linkbricks-Horizon-AI-Korean-llama-3.1-sft-dpo-8B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
    - model: tesser-ai/Tesser-Llama-3-Ko-8B
      layer_range: [0, 32]
      parameters:
          density: 0.5
          weight: 0.45
    - model: maum-ai/Llama-3-MAAL-8B-Instruct-v0.1
      layer_range: [0, 32]
      parameters:
          density: 0.5
          weight: 0.45
    - model: meta-llama/Meta-Llama-3.1-8B
      layer_range: [0, 32]
      parameters:
          density: 0.5
          weight: 0.45
    - model: NousResearch/Hermes-3-Llama-3.1-8B
      layer_range: [0, 32]
      parameters:
          density: 0.5
          weight: 0.45
    - model: Saxo/Linkbricks-Horizon-AI-Korean-llama3-sft-dpo-8b-base
      layer_range: [0, 32]
      parameters:
          density: 0.5
          weight: 0.45
    - model: Saxo/Linkbricks-Horizon-AI-Korean-llama-3.1-sft-dpo-8B
      layer_range: [0, 32]
      parameters:
          density: 0.5
          weight: 0.45
merge_method: dare_ties
base_model: Saxo/Linkbricks-Horizon-AI-Korean-llama-3.1-sft-dpo-8B
dtype: bfloat16