Hugging Face's logo

yamatazen
/
Shisa-K-12B

Text Generation
Transformers
Safetensors
English
Japanese
mistral
mergekit
Merge
conversational
text-generation-inference
Model card Files
xet
Community
Shisa-K-12B / README.md
yamatazen's picture
yamatazen
Update README.md
d2afd76 verified
preview code
|
raw
history blame contribute delete
1.33 kB
metadata
base_model:
  - natong19/Mistral-Nemo-Instruct-2407-abliterated
  - yamatazen/Himeyuri-Magnum-12B
  - shisa-ai/shisa-v2-mistral-nemo-12b
library_name: transformers
tags:
  - mergekit
  - merge
language:
  - en
  - ja

image/png

Shisa-K-12B

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

Merge Details

Merge Method

This model was merged using the Karcher Mean merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

merge_method: karcher
dtype: bfloat16
out_dtype: bfloat16
models:
  - model: natong19/Mistral-Nemo-Instruct-2407-abliterated
  - model: shisa-ai/shisa-v2-mistral-nemo-12b
  - model: yamatazen/Himeyuri-Magnum-12B
tokenizer:
  source: natong19/Mistral-Nemo-Instruct-2407-abliterated