File:Heretic inplace.py

heretic_inplace.py applies the pqhaz "heretic" FP8 patch to the attn.wo_b weights of the official DeepSeek V4.1 Flash shards, in place, for engines that read attention weights straight from the official checkpoint. Only the 38 layers.N.attn.wo_b.weight tensors change (same dtype F8_E4M3, same shape, same offsets); the FP8 scales are untouched. Three commands: apply, restore and status. Python standard library only.

Usage

heretic_inplace.py apply   OFFICIAL_DIR PATCH.safetensors BACKUP.safetensors
heretic_inplace.py restore OFFICIAL_DIR PATCH.safetensors BACKUP.safetensors
heretic_inplace.py status  OFFICIAL_DIR PATCH.safetensors BACKUP.safetensors

• OFFICIAL_DIR: the official DeepSeek-V4.1-Flash-1017 checkpoint (with model.safetensors.index.json).
• apply first writes an exact byte backup of every original tensor (a safetensors file with the same names),

 then overwrites, fsyncs and reads back. It refuses a shard that has more than one hard link, and refuses to run when
 a tensor is already patched and there is no backup.

• restore writes the backup back; status counts tensors that are patched, stock (match the

 backup) or neither. Both are safe to repeat: a tensor already in the wanted state is skipped.

License

MIT (the file carries no license header).

Source: @darkmaniac7, 2026-10-29 (lab notes)