mradermacher/MemReader-4B-thinking-GGUF
Same weights, converted vs IAAR-Shanghai/MemReader-4B-thinking. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Norms 0/145, MLP 0/108, Attention 0/144, Embeddings 0/1
Same weights, converted vs IAAR-Shanghai/MemReader-4B-thinking. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Norms 0/145, MLP 0/108, Attention 0/144, Embeddings 0/1