DevQuasar-7/internlm.OREAL-32B-SFT-GGUF
Same weights, converted vs internlm/OREAL-32B-SFT. 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 internlm/OREAL-32B-SFT. 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