Changes / Feeds / Qwen/Qwen2.5-Coder-3B-Instruct
Qwen/Qwen2.5-Coder-3B-Instruct
5 changes to a tracked key since 2024-11-06, newest first. Head as last read: 488639f1ff808d1d3d0ba301aef8c11461451ec5.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2024-11-18 | x_NXMC-2024-0142 | tokenizer model_max_length 131072 to 32768; truncation defaults change (2024-11-18).2038ec3efe49 -> 89fe5444e8ba |
| 2024-11-09 | x_NXMC-2024-0141 | generation defaults changed (repetition_penalty 1.1 to 1.05); a call that does not pass these explicitly now generates differently (2024-11-09).93d7dcdb8e99 -> 2038ec3efe49 |
| 2024-11-09 | x_NXMC-2024-0140 breaking | EOS changed from 151643 to 151645; anything fine-tuned or served against the old value stops at a different token (2024-11-09).4083ed00af13 -> 93d7dcdb8e99 |
| 2024-11-06 | x_NXMC-2024-0139 breaking | EOS changed from 151645 to 151643; anything fine-tuned or served against the old value stops at a different token (2024-11-06).fee34fb68a09 -> 4083ed00af13 |
| 2024-11-06 | x_NXMC-2024-0138 | generation defaults changed (repetition_penalty 1.05 to 1.1); a call that does not pass these explicitly now generates differently (2024-11-06).098f9cdcafcf -> fee34fb68a09 |
Pin it, and let a bot move the pin
from_pretrained("Qwen/Qwen2.5-Coder-3B-Instruct", revision="488639f1ff808d1d3d0ba301aef8c11461451ec5")
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-3B-Instruct.html)