You can deploy this model and start earning money today!

RichardErkhov/
Solshine_-_Qwen2.5-METACODER-22.1B-mergekit-model1-gguf

Name: Solshine_-_Qwen2.5-METACODER-22.1B-mergekit-model1-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Qwen2.5-METACODER-22.1B-mergekit-model1 - GGUF

Model creator: https://huggingface.co/Solshine/
Original model: https://huggingface.co/Solshine/Qwen2.5-METACODER-22.1B-mergekit-model1/

Name	Quant method	Size
Qwen2.5-METACODER-22.1B-mergekit-model1.Q2_K.gguf	Q2_K	7.73GB
Qwen2.5-METACODER-22.1B-mergekit-model1.Q3_K_S.gguf	Q3_K_S	9.04GB
Qwen2.5-METACODER-22.1B-mergekit-model1.Q3_K.gguf	Q3_K	10.0GB
Qwen2.5-METACODER-22.1B-mergekit-model1.Q3_K_M.gguf	Q3_K_M	10.0GB
Qwen2.5-METACODER-22.1B-mergekit-model1.Q3_K_L.gguf	Q3_K_L	10.82GB
Qwen2.5-METACODER-22.1B-mergekit-model1.IQ4_XS.gguf	IQ4_XS	11.21GB
Qwen2.5-METACODER-22.1B-mergekit-model1.Q4_0.gguf	Q4_0	11.7GB
Qwen2.5-METACODER-22.1B-mergekit-model1.IQ4_NL.gguf	IQ4_NL	11.81GB
Qwen2.5-METACODER-22.1B-mergekit-model1.Q4_K_S.gguf	Q4_K_S	11.79GB
Qwen2.5-METACODER-22.1B-mergekit-model1.Q4_K.gguf	Q4_K	12.45GB
Qwen2.5-METACODER-22.1B-mergekit-model1.Q4_K_M.gguf	Q4_K_M	12.45GB
Qwen2.5-METACODER-22.1B-mergekit-model1.Q4_1.gguf	Q4_1	12.95GB
Qwen2.5-METACODER-22.1B-mergekit-model1.Q5_0.gguf	Q5_0	14.2GB
Qwen2.5-METACODER-22.1B-mergekit-model1.Q5_K_S.gguf	Q5_K_S	14.2GB
Qwen2.5-METACODER-22.1B-mergekit-model1.Q5_K.gguf	Q5_K	14.59GB
Qwen2.5-METACODER-22.1B-mergekit-model1.Q5_K_M.gguf	Q5_K_M	14.59GB
Qwen2.5-METACODER-22.1B-mergekit-model1.Q5_1.gguf	Q5_1	15.46GB
Qwen2.5-METACODER-22.1B-mergekit-model1.Q6_K.gguf	Q6_K	16.87GB
Qwen2.5-METACODER-22.1B-mergekit-model1.Q8_0.gguf	Q8_0	21.84GB

Original model description:

base_model:

Qwen/Qwen2.5-Coder-7B-Instruct
Qwen/Qwen2.5-Math-7B-Instruct
Qwen/Qwen2.5-Coder-7B
Qwen/Qwen2.5-Math-7B library_name: transformers tags:
mergekit
merge license: other

Qwen2.5-METACODER 22.1B (mergekit-model1) by Solshine (Caleb DeLeeuw)

merge

This is an expirimental merge of pre-trained language models created using mergekit. No Fine-tuning, nor benchmarking, has been done with this model.

License

Hippocratic License 3.0 + Ecocide module, + Extractive Industries module, + Copyleft

https://firstdonoharm.dev/version/3/0/cl-eco-extr.txt

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

yaml

slices:
  - sources:
      - model: Qwen/Qwen2.5-Coder-7B-Instruct
        layer_range: [0, 16]
  - sources:
      - model: Qwen/Qwen2.5-Math-7B-Instruct
        layer_range: [3, 4]
  - sources:
      - model: Qwen/Qwen2.5-Coder-7B
        layer_range: [4, 20]
  - sources:
      - model: Qwen/Qwen2.5-Math-7B
        layer_range: [8, 24]
  - sources:
      - model: Qwen/Qwen2.5-Coder-7B
        layer_range: [10, 24]
  - sources:
      - model: Qwen/Qwen2.5-Coder-7B
        layer_range: [10, 14]
  - sources:
      - model: Qwen/Qwen2.5-Coder-7B-Instruct
        layer_range: [6, 26]
  - sources:
      - model: Qwen/Qwen2.5-Math-7B-Instruct
        layer_range: [25, 26]
  - sources:
      - model: Qwen/Qwen2.5-Coder-7B-Instruct
        layer_range: [26, 28]
merge_method: passthrough
dtype: float16

RichardErkhov/Solshine_-_Qwen2.5-METACODER-22.1B-mergekit-model1-gguf