dicksondickson/Qwen3.8-Flash-Next-NVFP4-reshard-mtp-fix
Same weights, repacked vs nvidia/Qwen3.8-Flash-Next-NVFP4. Same weights in different files (re-saved, re-sharded or new metadata), plus 2 new tensors.
Tensors changed: Embeddings 0/138, MLP 0/1923, Attention 0/608, Norms 0/302, other 0/8, lm_head 0/1