Quantization made by Richard Erkhov.

Llama-Agent-Merge - GGUF

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

Name	Quant method	Size
Llama-Agent-Merge.Q2_K.gguf	Q2_K	1.27GB
Llama-Agent-Merge.Q3_K_S.gguf	Q3_K_S	1.44GB
Llama-Agent-Merge.Q3_K.gguf	Q3_K	1.57GB
Llama-Agent-Merge.Q3_K_M.gguf	Q3_K_M	1.57GB
Llama-Agent-Merge.Q3_K_L.gguf	Q3_K_L	1.69GB
Llama-Agent-Merge.IQ4_XS.gguf	IQ4_XS	1.71GB
Llama-Agent-Merge.Q4_0.gguf	Q4_0	1.79GB
Llama-Agent-Merge.IQ4_NL.gguf	IQ4_NL	1.79GB
Llama-Agent-Merge.Q4_K_S.gguf	Q4_K_S	1.8GB
Llama-Agent-Merge.Q4_K.gguf	Q4_K	1.88GB
Llama-Agent-Merge.Q4_K_M.gguf	Q4_K_M	1.88GB
Llama-Agent-Merge.Q4_1.gguf	Q4_1	1.95GB
Llama-Agent-Merge.Q5_0.gguf	Q5_0	2.11GB
Llama-Agent-Merge.Q5_K_S.gguf	Q5_K_S	2.11GB
Llama-Agent-Merge.Q5_K.gguf	Q5_K	2.16GB
Llama-Agent-Merge.Q5_K_M.gguf	Q5_K_M	2.16GB
Llama-Agent-Merge.Q5_1.gguf	Q5_1	2.28GB
Llama-Agent-Merge.Q6_K.gguf	Q6_K	2.46GB
Llama-Agent-Merge.Q8_0.gguf	Q8_0	3.19GB

Original model description:

base_model:

Bllossom/llama-3.2-Korean-Bllossom-3B
CarrotAI/Llama-3.2-Rabbit-Ko-3B-Instruct
EpistemeAI/Llama-3.2-3B-Agent007
Saxo/Linkbricks-Llama3.2-Korean-cpt-3b
RyanYr/llama32-3b-it_CoT-it_SFT 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 Model Stock merge method using EpistemeAI/Llama-3.2-3B-Agent007 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

merge_method: model_stock
base_model: EpistemeAI/Llama-3.2-3B-Agent007
dtype: float16
parameters:
    filter_wise: false
    weight: 1
    density: 0.42
    gamma: 0.03
models:
  - model: EpistemeAI/Llama-3.2-3B-Agent007
    layer_range: [0, 28]
  - model: Bllossom/llama-3.2-Korean-Bllossom-3B
    layer_range: [0, 28]
  - model: CarrotAI/Llama-3.2-Rabbit-Ko-3B-Instruct
    layer_range: [0, 28]
  - model: Saxo/Linkbricks-Llama3.2-Korean-cpt-3b
    layer_range: [0, 28]
  - model: RyanYr/llama32-3b-it_CoT-it_SFT
    layer_range: [0, 28]