Edit model card

Magnum-Instruct-12B

Simple della_linear merge done at a 50/50 split with high density using Mini-Magnum and Nemo Instruct. Nothing fancy to it, really. Seems good on both intelligence and creativity so far.

Big thanks to the MistralAI and Anthracite/SillyTilly teams for the models used!

GGUF quants made by mradermacher:

https://huggingface.co/mradermacher/Magnum-Instruct-12B-GGUF

Settings

Temperature @ 0.7

Min-P @ 0.02

Smoothing Factor @ 0.3

Smoothing Curve @ 1.5

DRY Multiplier (plus standard DRY settings) @ 0.8

Skip Special Tokens @ On

Everything else @ Off

Prompt Format: Nemo-Mistral

[INST] user prompt[/INST] character response</s>[INST] user prompt[/INST]

Models Merged

The following models were included in the merge:

https://huggingface.co/intervitens/mini-magnum-12b-v1.1

https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407

Downloads last month
19
Safetensors
Model size
12.2B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for ParasiticRogue/Magnum-Instruct-12B