Changes / Feeds / Qwen/Qwen2.5-VL-7B-Instruct-AWQ
Qwen/Qwen2.5-VL-7B-Instruct-AWQ
1 change to a tracked key since 2025-02-15, newest first. Head as last read: 536a35794df8831aa814970ee8f89eff577e7718.
A quantization of Qwen/Qwen2.5-VL-7B-Instruct: 196 layers re-encoded; of the 449 tensors left unquantized, 393 byte-identical to the base, 56 changed at the same dtype (all norm weights). Compared tensor by tensor from sha256 fingerprints: 536a35794df8 against Qwen/Qwen2.5-VL-7B-Instruct at cc594898137f. A hash is equal or not; it says nothing about what an edit does.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2025-04-06 | x_NXMC-2025-0184 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).58f8ed7b27cd -> 536a35794df8 Open in app |
Pin it, and let a bot move the pin
from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct-AWQ", revision="536a35794df8831aa814970ee8f89eff577e7718")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-AWQ.html)