base_model, datasets, language, library_name, license, tags, widget
| base_model | datasets | language | library_name | license | tags | widget | |||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
|
|
|
transformers | apache-2.0 |
|
|
🧬 Helix SCE 12B
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the SCE merge method using MuXodious/Mistral-Nemo-Instruct-2407-absolute-heresy as a base.
Models Merged
The following models were included in the merge:
- MuXodious/Mistral-Nemo-Instruct-2407-absolute-heresy
- Retreatcost/Evertide-RX-12B
- yamatazen/Aurora-SCE-12B
- Vortex5/Elysian-Sunrise-12B
- Vortex5/Mythic-Fabulist-12B
- Vortex5/Prototype-X-12b
Configuration
The following YAML configuration was used to produce this model:
architecture: MistralForCausalLM
base_model: B:\12B\MuXodious--Mistral-Nemo-Instruct-2407-absolute-heresy
models:
- model: B:\12B\Retreatcost--Evertide-RX-12B
- model: B:\12B\yamatazen--Aurora-SCE-12B
- model: B:\12B\Vortex5--Elysian-Sunrise-12B
- model: B:\12B\Vortex5--Mythic-Fabulist-12B
- model: B:\12B\Vortex5--Prototype-X-12b
merge_method: sce
dtype: float32
out_dtype: bfloat16
parameters:
normalize: true
select_topk: 0.5
tokenizer:
source: union
chat_template: auto