Quantization made by Richard Erkhov.

Qwen2.5-1.5B-Matrix - GGUF

Model creator: https://huggingface.co/bunnycore/
Original model: https://huggingface.co/bunnycore/Qwen2.5-1.5B-Matrix/

Name	Quant method	Size
Qwen2.5-1.5B-Matrix.Q2_K.gguf	Q2_K	0.7GB
Qwen2.5-1.5B-Matrix.Q3_K_S.gguf	Q3_K_S	0.8GB
Qwen2.5-1.5B-Matrix.Q3_K.gguf	Q3_K	0.86GB
Qwen2.5-1.5B-Matrix.Q3_K_M.gguf	Q3_K_M	0.86GB
Qwen2.5-1.5B-Matrix.Q3_K_L.gguf	Q3_K_L	0.91GB
Qwen2.5-1.5B-Matrix.IQ4_XS.gguf	IQ4_XS	0.96GB
Qwen2.5-1.5B-Matrix.Q4_0.gguf	Q4_0	0.99GB
Qwen2.5-1.5B-Matrix.IQ4_NL.gguf	IQ4_NL	1.0GB
Qwen2.5-1.5B-Matrix.Q4_K_S.gguf	Q4_K_S	1.0GB
Qwen2.5-1.5B-Matrix.Q4_K.gguf	Q4_K	1.04GB
Qwen2.5-1.5B-Matrix.Q4_K_M.gguf	Q4_K_M	1.04GB
Qwen2.5-1.5B-Matrix.Q4_1.gguf	Q4_1	1.08GB
Qwen2.5-1.5B-Matrix.Q5_0.gguf	Q5_0	1.17GB
Qwen2.5-1.5B-Matrix.Q5_K_S.gguf	Q5_K_S	1.17GB
Qwen2.5-1.5B-Matrix.Q5_K.gguf	Q5_K	1.2GB
Qwen2.5-1.5B-Matrix.Q5_K_M.gguf	Q5_K_M	1.2GB
Qwen2.5-1.5B-Matrix.Q5_1.gguf	Q5_1	1.26GB
Qwen2.5-1.5B-Matrix.Q6_K.gguf	Q6_K	1.36GB
Qwen2.5-1.5B-Matrix.Q8_0.gguf	Q8_0	1.76GB

Original model description:

base_model:

Qwen/Qwen2.5-Math-1.5B-Instruct
Qwen/Qwen2.5-1.5B-Instruct
Qwen/Qwen2.5-Coder-1.5B-Instruct
Goekdeniz-Guelmez/Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1 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 Qwen/Qwen2.5-1.5B-Instruct 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: Qwen/Qwen2.5-Coder-1.5B-Instruct
  - model: Qwen/Qwen2.5-1.5B-Instruct
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
  - model: Goekdeniz-Guelmez/Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1
merge_method: model_stock
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16