Changes / Feeds / nvidia/Qwen2.5-VL-7B-Instruct-NVFP4
nvidia/Qwen2.5-VL-7B-Instruct-NVFP4
2 changes to a tracked key since 2025-09-10, newest first. Head as last read: d13bb1f2d8fbbd9f16cbb7688c8d6b6932d797d7.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2025-12-06 | x_NXMC-2025-0082 breaking | quantization_config changed; the stored format of the weights is different (2025-12-06).7b5d4d62308c -> d13bb1f2d8fb |
| 2025-10-08 | x_NXMC-2025-0081 | format-only re-save, RoPE settings rewritten in the transformers v5 rope_parameters form with the same values; nothing it computes, tokenises or generates changed (2025-10-08).39a5817f4677 -> 7b5d4d62308c |
Pin it, and let a bot move the pin
from_pretrained("nvidia/Qwen2.5-VL-7B-Instruct-NVFP4", revision="d13bb1f2d8fbbd9f16cbb7688c8d6b6932d797d7")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/Qwen2.5-VL-7B-Instruct-NVFP4.html)