bartowski/SubtleOne_Qwen2.5-32b-Erudite-Writer-GGUF

Same weights, converted vs SubtleOne/Qwen2.5-32b-Erudite-Writer. Same weights stored in another dtype (BF16 → BF16/F32).

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/129, MLP 0/192, Attention 0/448

On the Hub · Downloads on Model Pulse