BoHF (Best of Hugging Face)
This is a highly experimental mixture of experts model, containing 4 expert models. The individual expert models are based on Llama 3.2 3B fine tunes that represent some of the most popular models of this kind.
Expert Source Models
Big shout out to the makers of these original models, now serving as experts in BoHF!
- dphn/Dolphin3.0-Llama3.2-3B for general inquiries.
- HenryShan/Llama-3.2-3B-GSM8K-CoT for math.
- theprint/Llama-3.2-3B-VanRossum for Python coding.
- ConicCat/Litbench-Creative-Writing-RM-3B for creative writing.
- Downloads last month
- 360
Hardware compatibility
Log In
to view the estimation
2-bit
3-bit
4-bit
5-bit
6-bit
8-bit
16-bit
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for theprint/Bohf-12B-MoE-3A-GGUF
Base model
meta-llama/Llama-3.2-3B-Instruct
Finetuned
ConicCat/Litbench-Creative-Writing-RM-3B
Finetuned
theprint/Bohf-12B-MoE-3A