Changes / Feeds / nvidia/Gemma-4-31B-IT-NVFP4
nvidia/Gemma-4-31B-IT-NVFP4
3 changes to a tracked key since 2026-04-02, newest first. Head as last read: 4135a98a9b728a548947683219633b25682223ac.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2026-05-01 | x_NXMC-2026-0066 | the chat template text changed but rendered byte-identically on the fixed conversation set (system+user, multi-turn, tool call) (2026-05-01).61521ee452a4 -> 05fa17010ac2 |
| 2026-04-18 | x_NXMC-2026-0065 breaking | the chat template changed and renders differently (tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2026-04-18).50687fbbadad -> 61521ee452a4 |
| 2026-04-02 | x_NXMC-2026-0064 | pad token "<eos>" to "<pad>"; batched training masks a different id (2026-04-02).5d24e54bc060 -> 4caa7d91810d |
Pin it, and let a bot move the pin
from_pretrained("nvidia/Gemma-4-31B-IT-NVFP4", revision="4135a98a9b728a548947683219633b25682223ac")With the Renovate preset, a pull request moves this pin when the head moves, and links back here.
[](https://www.neurarch.com/changes-feeds/models/nvidia/Gemma-4-31B-IT-NVFP4.html)