Changes / Feeds / Qwen/Qwen2.5-Coder-32B-Instruct
Qwen/Qwen2.5-Coder-32B-Instruct
5 changes to a tracked key since 2024-11-06, newest first. Head as last read: 381fc969f78efac66bc87ff7ddeadb7e73c218a7.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2024-11-18 | x_NXMC-2024-0116 | tokenizer model_max_length 131072 to 32768; truncation defaults change (2024-11-18).23efe921391d -> b47205940b83 |
| 2024-11-09 | x_NXMC-2024-0115 breaking | EOS changed from 151643 to 151645; anything fine-tuned or served against the old value stops at a different token (2024-11-09).d3d43e94121f -> 23efe921391d |
| 2024-11-09 | x_NXMC-2024-0114 | generation defaults changed (repetition_penalty 1.1 to 1.05); a call that does not pass these explicitly now generates differently (2024-11-09).ddff9da45d88 -> d3d43e94121f |
| 2024-11-06 | x_NXMC-2024-0113 breaking | EOS changed from 151645 to 151643; anything fine-tuned or served against the old value stops at a different token (2024-11-06).a7a975b22db7 -> ddff9da45d88 |
| 2024-11-06 | x_NXMC-2024-0112 | generation defaults changed (repetition_penalty 1.05 to 1.1); a call that does not pass these explicitly now generates differently (2024-11-06).f447f76906c7 -> a7a975b22db7 |
Pin it, and let a bot move the pin
from_pretrained("Qwen/Qwen2.5-Coder-32B-Instruct", revision="381fc969f78efac66bc87ff7ddeadb7e73c218a7")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-Coder-32B-Instruct.html)