bartowski/Qwen2.5-32b-RP-Ink-GGUF
Same weights, converted vs allura-org/Qwen2.5-32b-RP-Ink. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/129, MLP 0/192, Attention 0/448, lm_head 0/1
Same weights, converted vs allura-org/Qwen2.5-32b-RP-Ink. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/129, MLP 0/192, Attention 0/448, lm_head 0/1