Quantization made by Richard Erkhov.

Github

Discord

Request more models

mergekit-model_stock-xtxndeh - GGUF

• Model creator: https://huggingface.co/Hjgugugjhuhjggg/
• Original model: https://huggingface.co/Hjgugugjhuhjggg/mergekit-model_stock-xtxndeh/

Name	Quant method	Size
mergekit-model_stock-xtxndeh.Q2_K.gguf	Q2_K	0.7GB
mergekit-model_stock-xtxndeh.IQ3_XS.gguf	IQ3_XS	0.77GB
mergekit-model_stock-xtxndeh.IQ3_S.gguf	IQ3_S	0.8GB
mergekit-model_stock-xtxndeh.Q3_K_S.gguf	Q3_K_S	0.8GB
mergekit-model_stock-xtxndeh.IQ3_M.gguf	IQ3_M	0.82GB
mergekit-model_stock-xtxndeh.Q3_K.gguf	Q3_K	0.86GB
mergekit-model_stock-xtxndeh.Q3_K_M.gguf	Q3_K_M	0.86GB
mergekit-model_stock-xtxndeh.Q3_K_L.gguf	Q3_K_L	0.91GB
mergekit-model_stock-xtxndeh.IQ4_XS.gguf	IQ4_XS	0.96GB
mergekit-model_stock-xtxndeh.Q4_0.gguf	Q4_0	0.99GB
mergekit-model_stock-xtxndeh.IQ4_NL.gguf	IQ4_NL	1.0GB
mergekit-model_stock-xtxndeh.Q4_K_S.gguf	Q4_K_S	1.0GB
mergekit-model_stock-xtxndeh.Q4_K.gguf	Q4_K	1.04GB
mergekit-model_stock-xtxndeh.Q4_K_M.gguf	Q4_K_M	1.04GB
mergekit-model_stock-xtxndeh.Q4_1.gguf	Q4_1	1.08GB
mergekit-model_stock-xtxndeh.Q5_0.gguf	Q5_0	1.17GB
mergekit-model_stock-xtxndeh.Q5_K_S.gguf	Q5_K_S	1.17GB
mergekit-model_stock-xtxndeh.Q5_K.gguf	Q5_K	1.2GB
mergekit-model_stock-xtxndeh.Q5_K_M.gguf	Q5_K_M	1.2GB
mergekit-model_stock-xtxndeh.Q5_1.gguf	Q5_1	1.26GB
mergekit-model_stock-xtxndeh.Q6_K.gguf	Q6_K	1.36GB
mergekit-model_stock-xtxndeh.Q8_0.gguf	Q8_0	1.76GB

Original model description:

base_model:

• Qwen/Qwen2.5-1.5B
• Qwen/Qwen2.5-Math-1.5B-Instruct
• Qwen/Qwen2.5-1.5B-Instruct
• Qwen/Qwen2.5-Math-1.5B
• Qwen/Qwen2.5-Coder-1.5B
• Qwen/Qwen2.5-Coder-1.5B-Instruct 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-Coder-1.5B-Instruct as a base.

Models Merged

The following models were included in the merge:

• Qwen/Qwen2.5-1.5B
• Qwen/Qwen2.5-Math-1.5B-Instruct
• Qwen/Qwen2.5-1.5B-Instruct
• Qwen/Qwen2.5-Math-1.5B
• Qwen/Qwen2.5-Coder-1.5B

Configuration

The following YAML configuration was used to produce this model:

merge_method: model_stock
base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct

models:
  - model: Qwen/Qwen2.5-1.5B
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
  - model: Qwen/Qwen2.5-Math-1.5B
  - model: Qwen/Qwen2.5-1.5B-Instruct
  - model: Qwen/Qwen2.5-Coder-1.5B

parameters:
  density: 0.5
  weight: 1.0
  int8_mask: true