YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

trained on v3 with 64 experts per token.

then reduced down to 32 (qwen3 30b originally used 8)

I trained on about 240 long examples of scenarios based RP as v3 had a lot of trouble.

Downloads last month
2
Safetensors
Model size
31B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for SuperbEmphasis/Black-Eclipse-Test-ERP-RP-V4-32E

Quantizations
3 models