Text Generation
Transformers
Safetensors
English
qwen3_moe
conversational

32B?

#1
by jacek2024 - opened

Will you also finetune 32B model?

MegaScience org

Initially, we planned to finetune the 32B model. However, since the Qwen team did not open-source Qwen3-32B-base, we were unable to proceed.

I understand, could you try some other models, like Mistral?

MegaScience org

Thank you for your interest. Due to computational resource limitations, it may take some time before we can provide larger models.

Sign up or log in to comment