mradermacher/Marx-3B-V3-GGUF
Same weights, converted vs acrastt/Marx-3B-V3. Same weights stored in another dtype (F16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/130, MLP 0/96, Attention 0/128
Same weights, converted vs acrastt/Marx-3B-V3. Same weights stored in another dtype (F16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/130, MLP 0/96, Attention 0/128