Quantization made by Richard Erkhov.

MN-Chinofun-12B-2 - GGUF

Model creator: https://huggingface.co/djuna/
Original model: https://huggingface.co/djuna/MN-Chinofun-12B-2/

Name	Quant method	Size
MN-Chinofun-12B-2.Q2_K.gguf	Q2_K	4.46GB
MN-Chinofun-12B-2.Q3_K_S.gguf	Q3_K_S	5.15GB
MN-Chinofun-12B-2.Q3_K.gguf	Q3_K	5.67GB
MN-Chinofun-12B-2.Q3_K_M.gguf	Q3_K_M	5.67GB
MN-Chinofun-12B-2.Q3_K_L.gguf	Q3_K_L	6.11GB
MN-Chinofun-12B-2.IQ4_XS.gguf	IQ4_XS	6.33GB
MN-Chinofun-12B-2.Q4_0.gguf	Q4_0	6.59GB
MN-Chinofun-12B-2.IQ4_NL.gguf	IQ4_NL	6.65GB
MN-Chinofun-12B-2.Q4_K_S.gguf	Q4_K_S	6.63GB
MN-Chinofun-12B-2.Q4_K.gguf	Q4_K	6.96GB
MN-Chinofun-12B-2.Q4_K_M.gguf	Q4_K_M	6.96GB
MN-Chinofun-12B-2.Q4_1.gguf	Q4_1	7.26GB
MN-Chinofun-12B-2.Q5_0.gguf	Q5_0	7.93GB
MN-Chinofun-12B-2.Q5_K_S.gguf	Q5_K_S	7.93GB
MN-Chinofun-12B-2.Q5_K.gguf	Q5_K	8.13GB
MN-Chinofun-12B-2.Q5_K_M.gguf	Q5_K_M	8.13GB
MN-Chinofun-12B-2.Q5_1.gguf	Q5_1	8.61GB
MN-Chinofun-12B-2.Q6_K.gguf	Q6_K	9.37GB
MN-Chinofun-12B-2.Q8_0.gguf	Q8_0	12.13GB

Original model description:

base_model:

grimjim/magnum-consolidatum-v1-12b
spow12/ChatWaifu_v1.4
GalrionSoftworks/Canidori-12B-v1
Nohobby/MN-12B-Siskin-v0.2
ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.2
RozGrov/NemoDori-v0.2.2-12B-MN-ties 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 ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.2 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: Nohobby/MN-12B-Siskin-v0.2
  - model: spow12/ChatWaifu_v1.4
  - model: grimjim/magnum-consolidatum-v1-12b
  - model: RozGrov/NemoDori-v0.2.2-12B-MN-ties
  - model: GalrionSoftworks/Canidori-12B-v1
merge_method: model_stock
base_model: ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.2
dtype: bfloat16