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