Changes / Feeds / Qwen/Qwen2.5-VL-7B-Instruct
Qwen/Qwen2.5-VL-7B-Instruct
3 changes to a tracked key since 2025-01-26, newest first. Head as last read: cc594898137f460bfe9f0759e9844b3ce807cfb5.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2025-04-06 | x_NXMC-2025-0176 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 (2025-04-06).5b5eecc7efc2 -> cc594898137f Open in app |
| 2025-03-23 | x_NXMC-2025-0175 | generation defaults changed (temperature 0.00001 to 0.000001); a call that does not pass these explicitly now generates differently (2025-03-23).b901af65fa3b -> 5b5eecc7efc2 Open in app |
| 2025-03-21 | x_NXMC-2025-0174 | generation defaults changed (temperature 0.1 to 0.00001, top_k 1 to unset, top_p 0.001 to unset); a call that does not pass these explicitly now generates differently (2025-03-21).a22b9b202f87 -> b901af65fa3b Open in app |
Pin it, and let a bot move the pin
from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct", revision="cc594898137f460bfe9f0759e9844b3ce807cfb5")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/Qwen/Qwen2.5-VL-7B-Instruct.html)