Changes / Feeds / nvidia/NVIDIA-Nemotron-Nano-9B-v2
nvidia/NVIDIA-Nemotron-Nano-9B-v2
2 changes to a tracked key since 2025-08-12, newest first. Head as last read: 6533e8de2c68e4536bf7c411d7a3ce5734111476.
GPU memory to fine-tune it, card by card: NVIDIA-Nemotron-Nano-9B-v2 on /m/.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2025-08-21 | x_NXMC-2025-0056 | tokenizer model_max_length 1e+30 to 131072; truncation defaults change (2025-08-21).7659b750c2aa -> d99d9740c5ac |
| 2025-08-15 | x_NXMC-2025-0055 breaking | the chat template changed and renders differently (multi-turn, 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; add_bos_token true to false; encoding the same text yields different ids (2025-08-15).85507799cec2 -> b27e3876f3db |
Pin it, and let a bot move the pin
from_pretrained("nvidia/NVIDIA-Nemotron-Nano-9B-v2", revision="6533e8de2c68e4536bf7c411d7a3ce5734111476")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/NVIDIA-Nemotron-Nano-9B-v2.html)