legraphista/Higgs-Llama-3-70B-IMat-GGUF
Same weights, converted vs bosonai/Higgs-Llama-3-70B. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/1, Attention 0/320, Norms 0/161, MLP 0/240, lm_head 0/1
Same weights, converted vs bosonai/Higgs-Llama-3-70B. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/1, Attention 0/320, Norms 0/161, MLP 0/240, lm_head 0/1