Quantization made by Richard Erkhov.

Stella-mistral-nemo-12B - GGUF

Model creator: https://huggingface.co/nbeerbower/
Original model: https://huggingface.co/nbeerbower/Stella-mistral-nemo-12B/

Name	Quant method	Size
Stella-mistral-nemo-12B.Q2_K.gguf	Q2_K	4.46GB
Stella-mistral-nemo-12B.IQ3_XS.gguf	IQ3_XS	4.94GB
Stella-mistral-nemo-12B.IQ3_S.gguf	IQ3_S	5.18GB
Stella-mistral-nemo-12B.Q3_K_S.gguf	Q3_K_S	5.15GB
Stella-mistral-nemo-12B.IQ3_M.gguf	IQ3_M	5.33GB
Stella-mistral-nemo-12B.Q3_K.gguf	Q3_K	5.67GB
Stella-mistral-nemo-12B.Q3_K_M.gguf	Q3_K_M	5.67GB
Stella-mistral-nemo-12B.Q3_K_L.gguf	Q3_K_L	6.11GB
Stella-mistral-nemo-12B.IQ4_XS.gguf	IQ4_XS	6.33GB
Stella-mistral-nemo-12B.Q4_0.gguf	Q4_0	6.59GB
Stella-mistral-nemo-12B.IQ4_NL.gguf	IQ4_NL	6.65GB
Stella-mistral-nemo-12B.Q4_K_S.gguf	Q4_K_S	6.63GB
Stella-mistral-nemo-12B.Q4_K.gguf	Q4_K	6.96GB
Stella-mistral-nemo-12B.Q4_K_M.gguf	Q4_K_M	6.96GB
Stella-mistral-nemo-12B.Q4_1.gguf	Q4_1	7.26GB
Stella-mistral-nemo-12B.Q5_0.gguf	Q5_0	7.93GB
Stella-mistral-nemo-12B.Q5_K_S.gguf	Q5_K_S	7.93GB
Stella-mistral-nemo-12B.Q5_K.gguf	Q5_K	8.13GB
Stella-mistral-nemo-12B.Q5_K_M.gguf	Q5_K_M	8.13GB
Stella-mistral-nemo-12B.Q5_1.gguf	Q5_1	8.61GB
Stella-mistral-nemo-12B.Q6_K.gguf	Q6_K	9.37GB
Stella-mistral-nemo-12B.Q8_0.gguf	Q8_0	12.13GB

Original model description:

base_model:

flammenai/Mahou-1.3-mistral-nemo-12B
Gryphe/Pantheon-RP-1.5-12b-Nemo
VAGOsolutions/SauerkrautLM-Nemo-12b-Instruct
nbeerbower/mistral-nemo-wissenschaft-12B
nbeerbower/HolyNemo-12B
nbeerbower/mistral-nemo-gutenberg-12B-v2
intervitens/mini-magnum-12b-v1.1
NeverSleep/Lumimaid-v0.2-12B
nbeerbower/mistral-nemo-bophades-12B library_name: transformers tags:
mergekit
merge

Stella-mistral-nemo-12B

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 nbeerbower/mistral-nemo-gutenberg-12B-v2 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: flammenai/Mahou-1.3-mistral-nemo-12B
    - model: Gryphe/Pantheon-RP-1.5-12b-Nemo
    - model: intervitens/mini-magnum-12b-v1.1
    - model: NeverSleep/Lumimaid-v0.2-12B
    - model: VAGOsolutions/SauerkrautLM-Nemo-12b-Instruct
    - model: nbeerbower/HolyNemo-12B
    - model: nbeerbower/mistral-nemo-wissenschaft-12B
    - model: nbeerbower/mistral-nemo-bophades-12B
merge_method: model_stock
base_model: nbeerbower/mistral-nemo-gutenberg-12B-v2
dtype: bfloat16