Changes / Feeds / Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8
Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8
3 changes to a tracked key since 2025-07-22, newest first. Head as last read: 003f183a92fbe5b9a8325aaa8b2ae797c91dd90f.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2025-08-21 | x_NXMC-2025-0134 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 (2025-08-21).1f6f99b0d0f8 -> 003f183a92fb |
| 2025-08-07 | x_NXMC-2025-0133 | the chat template changed; prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-08-07).8fe13515933c -> 1f6f99b0d0f8 |
| 2025-07-22 | x_NXMC-2025-0132 breaking | EOS changed from 151645 to [151645,151643]; anything fine-tuned or served against the old value stops at a different token; BOS 151643 removed; pad token unset to 151643; batched training masks a different id (2025-07-22).64ac916bdfc2 -> 8fe13515933c |
Pin it, and let a bot move the pin
from_pretrained("Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8", revision="003f183a92fbe5b9a8325aaa8b2ae797c91dd90f")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/Qwen3-Coder-480B-A35B-Instruct-FP8.html)