Quantization made by Richard Erkhov.

flammen18-mistral-7B - GGUF

Model creator: https://huggingface.co/flammenai/
Original model: https://huggingface.co/flammenai/flammen18-mistral-7B/

Name	Quant method	Size
flammen18-mistral-7B.Q2_K.gguf	Q2_K	2.53GB
flammen18-mistral-7B.IQ3_XS.gguf	IQ3_XS	2.81GB
flammen18-mistral-7B.IQ3_S.gguf	IQ3_S	2.96GB
flammen18-mistral-7B.Q3_K_S.gguf	Q3_K_S	2.95GB
flammen18-mistral-7B.IQ3_M.gguf	IQ3_M	3.06GB
flammen18-mistral-7B.Q3_K.gguf	Q3_K	3.28GB
flammen18-mistral-7B.Q3_K_M.gguf	Q3_K_M	3.28GB
flammen18-mistral-7B.Q3_K_L.gguf	Q3_K_L	3.56GB
flammen18-mistral-7B.IQ4_XS.gguf	IQ4_XS	3.67GB
flammen18-mistral-7B.Q4_0.gguf	Q4_0	3.83GB
flammen18-mistral-7B.IQ4_NL.gguf	IQ4_NL	3.87GB
flammen18-mistral-7B.Q4_K_S.gguf	Q4_K_S	3.86GB
flammen18-mistral-7B.Q4_K.gguf	Q4_K	4.07GB
flammen18-mistral-7B.Q4_K_M.gguf	Q4_K_M	4.07GB
flammen18-mistral-7B.Q4_1.gguf	Q4_1	4.24GB
flammen18-mistral-7B.Q5_0.gguf	Q5_0	4.65GB
flammen18-mistral-7B.Q5_K_S.gguf	Q5_K_S	4.65GB
flammen18-mistral-7B.Q5_K.gguf	Q5_K	4.78GB
flammen18-mistral-7B.Q5_K_M.gguf	Q5_K_M	4.78GB
flammen18-mistral-7B.Q5_1.gguf	Q5_1	5.07GB
flammen18-mistral-7B.Q6_K.gguf	Q6_K	5.53GB
flammen18-mistral-7B.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: apache-2.0 base_model:

nbeerbower/flammen11-mistral-7B
nbeerbower/flammen15-gutenberg-DPO-v1-7B
nbeerbower/Flammen-Kunoichi-7B
nbeerbower/flammen11X-mistral-7B
nbeerbower/Maidphin-Kunoichi-7B
nbeerbower/Suppe-v1-7B
nbeerbower/flammen10-mistral-7B
nbeerbower/bruphin-lambda
nbeerbower/flammen13-mistral-7B
nbeerbower/bophades-mistral-truthy-DPO-7B
nbeerbower/flammen17-mistral-7B
nbeerbower/bophades-mistral-math-DPO-7B library_name: transformers tags:
mergekit
merge

flammen18-mistral-7B

A Mistral 7B LLM built from merging pretrained models and finetuning. Flammen specializes in exceptional character roleplay, creative writing, and general intelligence

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/flammen17-mistral-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: nbeerbower/bophades-mistral-truthy-DPO-7B
    - model: nbeerbower/flammen11-mistral-7B
    - model: nbeerbower/Suppe-v1-7B
    - model: nbeerbower/bophades-mistral-math-DPO-7B
    - model: nbeerbower/flammen10-mistral-7B
    - model: nbeerbower/flammen15-gutenberg-DPO-v1-7B
    - model: nbeerbower/bruphin-lambda
    - model: nbeerbower/Maidphin-Kunoichi-7B
    - model: nbeerbower/flammen11X-mistral-7B
    - model: nbeerbower/flammen13-mistral-7B
    - model: nbeerbower/Flammen-Kunoichi-7B
merge_method: model_stock
base_model: nbeerbower/flammen17-mistral-7B
dtype: bfloat16