David Friehs 8a963fc10e convert : fix conversion for Mistral-Medium-3.5-128B (#24268) ...

Mistral explicitly sets `moe` and `llama_4_scaling` to `null` in
params.json, breaking `key in dict` checks during conversion. Replace
with `dict.get(key) is not None` where this matters.

Fixes `convert-hf-to-gguf.py --mistral-format Mistral-Medium-3.5-128B`

2026-06-07 21:41:39 +02:00

9.2 KiB

Raw Permalink Blame History

View Raw