mradermacher/LLaDA-MoE-7B-A1B-Instruct-GGUF

Same weights, converted vs inclusionAI/LLaDA-MoE-7B-A1B-Instruct. Same weights stored in another dtype (BF16 → F16/F32), plus 48 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/16, Attention 0/64, lm_head 0/1

On the Hub · Downloads on Model Pulse