YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

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
5
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