Quantization made by Richard Erkhov.

bophades-v2-mistral-7B - GGUF

Model creator: https://huggingface.co/nbeerbower/
Original model: https://huggingface.co/nbeerbower/bophades-v2-mistral-7B/

Name	Quant method	Size
bophades-v2-mistral-7B.Q2_K.gguf	Q2_K	2.53GB
bophades-v2-mistral-7B.IQ3_XS.gguf	IQ3_XS	2.81GB
bophades-v2-mistral-7B.IQ3_S.gguf	IQ3_S	2.96GB
bophades-v2-mistral-7B.Q3_K_S.gguf	Q3_K_S	2.95GB
bophades-v2-mistral-7B.IQ3_M.gguf	IQ3_M	3.06GB
bophades-v2-mistral-7B.Q3_K.gguf	Q3_K	3.28GB
bophades-v2-mistral-7B.Q3_K_M.gguf	Q3_K_M	3.28GB
bophades-v2-mistral-7B.Q3_K_L.gguf	Q3_K_L	3.56GB
bophades-v2-mistral-7B.IQ4_XS.gguf	IQ4_XS	3.67GB
bophades-v2-mistral-7B.Q4_0.gguf	Q4_0	3.83GB
bophades-v2-mistral-7B.IQ4_NL.gguf	IQ4_NL	3.87GB
bophades-v2-mistral-7B.Q4_K_S.gguf	Q4_K_S	3.86GB
bophades-v2-mistral-7B.Q4_K.gguf	Q4_K	4.07GB
bophades-v2-mistral-7B.Q4_K_M.gguf	Q4_K_M	4.07GB
bophades-v2-mistral-7B.Q4_1.gguf	Q4_1	4.24GB
bophades-v2-mistral-7B.Q5_0.gguf	Q5_0	4.65GB
bophades-v2-mistral-7B.Q5_K_S.gguf	Q5_K_S	4.65GB
bophades-v2-mistral-7B.Q5_K.gguf	Q5_K	4.78GB
bophades-v2-mistral-7B.Q5_K_M.gguf	Q5_K_M	4.78GB
bophades-v2-mistral-7B.Q5_1.gguf	Q5_1	5.07GB
bophades-v2-mistral-7B.Q6_K.gguf	Q6_K	5.53GB
bophades-v2-mistral-7B.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: apache-2.0 base_model:

paulml/NeuralOmniWestBeaglake-7B
yam-peleg/Experiment21-7B
paulml/OmniBeagleSquaredMBX-v3-7B
Gille/StrangeMerges_16-7B-slerp
vanillaOVO/correction_1
yam-peleg/Experiment26-7B
Kukedlc/NeuralMaths-Experiment-7b library_name: transformers tags:
mergekit
merge

bophades-v2-mistral-7B

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 yam-peleg/Experiment26-7B 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: paulml/OmniBeagleSquaredMBX-v3-7B
    - model: paulml/NeuralOmniWestBeaglake-7B
    - model: Gille/StrangeMerges_16-7B-slerp
    - model: yam-peleg/Experiment21-7B
    - model: vanillaOVO/correction_1
    - model: Kukedlc/NeuralMaths-Experiment-7b
merge_method: model_stock
base_model: yam-peleg/Experiment26-7B
dtype: bfloat16