Quantization made by Richard Erkhov.

franken-Beagle-11B - GGUF

Model creator: https://huggingface.co/vicgalle/
Original model: https://huggingface.co/vicgalle/franken-Beagle-11B/

Name	Quant method	Size
franken-Beagle-11B.Q2_K.gguf	Q2_K	3.73GB
franken-Beagle-11B.IQ3_XS.gguf	IQ3_XS	4.14GB
franken-Beagle-11B.IQ3_S.gguf	IQ3_S	4.37GB
franken-Beagle-11B.Q3_K_S.gguf	Q3_K_S	4.34GB
franken-Beagle-11B.IQ3_M.gguf	IQ3_M	4.51GB
franken-Beagle-11B.Q3_K.gguf	Q3_K	4.84GB
franken-Beagle-11B.Q3_K_M.gguf	Q3_K_M	4.84GB
franken-Beagle-11B.Q3_K_L.gguf	Q3_K_L	5.26GB
franken-Beagle-11B.IQ4_XS.gguf	IQ4_XS	5.43GB
franken-Beagle-11B.Q4_0.gguf	Q4_0	5.66GB
franken-Beagle-11B.IQ4_NL.gguf	IQ4_NL	5.72GB
franken-Beagle-11B.Q4_K_S.gguf	Q4_K_S	5.7GB
franken-Beagle-11B.Q4_K.gguf	Q4_K	6.02GB
franken-Beagle-11B.Q4_K_M.gguf	Q4_K_M	6.02GB
franken-Beagle-11B.Q4_1.gguf	Q4_1	6.27GB
franken-Beagle-11B.Q5_0.gguf	Q5_0	6.89GB
franken-Beagle-11B.Q5_K_S.gguf	Q5_K_S	6.89GB
franken-Beagle-11B.Q5_K.gguf	Q5_K	7.08GB
franken-Beagle-11B.Q5_K_M.gguf	Q5_K_M	7.08GB
franken-Beagle-11B.Q5_1.gguf	Q5_1	7.51GB
franken-Beagle-11B.Q6_K.gguf	Q6_K	8.2GB
franken-Beagle-11B.Q8_0.gguf	Q8_0	10.62GB

Original model description:

base_model: - mlabonne/NeuralBeagle14-7B tags: - mergekit - merge license: apache-2.0

franken-Beagle-11B

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

mlabonne/NeuralBeagle14-7B

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
    - model: mlabonne/NeuralBeagle14-7B
      layer_range: [0, 24]
  - sources:
    - model: mlabonne/NeuralBeagle14-7B
      layer_range: [8, 32]
merge_method: passthrough
dtype: bfloat16