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 mistralai/Mistral-Nemo-Instruct-2407 as a base.
Models Merged
The following models were included in the merge:
- mergekit-community/MN-Hekate-Kleidoukhos-12B
- mergekit-community/MN-Hekate-Panopaia-12B
- LatitudeGames/Wayfarer-12B
- mistralai/Mistral-Nemo-Base-2407
- nbeerbower/mistral-nemo-wissenschaft-12B + jtatman/mistral_nemo_12b_reasoning_psychology_lora
- HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407
- mergekit-community/MN-Nyx-Chthonia-12B
- nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B
- Aleteian/DarkCamelot
Configuration
The following YAML configuration was used to produce this model:
dtype: float32
out_dtype: bfloat16
merge_method: model_stock
base_model: mistralai/Mistral-Nemo-Instruct-2407
models:
- model: Aleteian/DarkCamelot
- model: HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407
parameters:
weight: [0.5, 2]
- model: LatitudeGames/Wayfarer-12B
parameters:
weight: [0.5, 1.5, 0]
- model: mergekit-community/MN-Hekate-Kleidoukhos-12B
- model: mergekit-community/MN-Hekate-Panopaia-12B
parameters:
weight: 2
- model: mergekit-community/MN-Nyx-Chthonia-12B
- model: mistralai/Mistral-Nemo-Base-2407
parameters:
weight: [3, 1]
- model: nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B
parameters:
weight: [0, 1, 1.5]
- model: nbeerbower/mistral-nemo-wissenschaft-12B+jtatman/mistral_nemo_12b_reasoning_psychology_lora
parameters:
weight: [2, 1, 0]
tokenizer:
source: union
tokens:
"[INST]":
source: mistralai/Mistral-Nemo-Instruct-2407
force: true
"[/INST]":
source: mistralai/Mistral-Nemo-Instruct-2407
force: true
"<|im_start|>":
source: mergekit-community/MN-Nyx-Chthonia-12B
force: true
"<|im_end|>":
source: mergekit-community/MN-Nyx-Chthonia-12B
force: true
- Downloads last month
- 48
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
๐
Ask for provider support
Model tree for mergekit-community/MN-Hekate-Geneteira-12B
Merge model
this model