Eval Request: DiffusionGemma 26B A4B IT

#681
by Redvodk - opened

Please evaluate edwixx/diffusiongemma-26B-A4B-it-HERETIC-Uncensored

Link: https://huggingface.co/edwixx/diffusiongemma-26B-A4B-it-HERETIC-Uncensored

I'm not sure what I'm using supports the architecture "DiffusionGemmaForBlockDiffusion" yet, so I'll have to come back to this later.

TransformersMultiModalMoEForCausalLM has no vLLM implementation, falling back to Transformers implementation.
...
ValueError: Argument input_ids not found in the forward method of <class 'transformers.models.diffusion_gemma.modeling_diffusion_gemma.DiffusionGemmaDecoderModel'>

Sign up or log in to comment