mradermacher/Marx-3B-V2-GGUF
Same weights, converted vs acrastt/Marx-3B-V2. Same weights stored in another dtype (F16/F32 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/53, MLP 0/78, Attention 0/104
Same weights, converted vs acrastt/Marx-3B-V2. Same weights stored in another dtype (F16/F32 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/53, MLP 0/78, Attention 0/104