Changes / Feeds / Qwen/Qwen2.5-Math-1.5B
Qwen/Qwen2.5-Math-1.5B
3 changes to a tracked key since 2024-09-16, newest first. Head as last read: 4a83ca6e4526a4f2da3aa259ec36c259f66b2ab2.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2024-09-20 | x_NXMC-2024-0210 breaking | EOS changed from "<|im_end|>" to "<|endoftext|>"; anything fine-tuned or served against the old value stops at a different token (2024-09-20).32c01b0b4180 -> 6d29d576340a |
| 2024-09-19 | x_NXMC-2024-0209 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 (2024-09-19).37193e87a152 -> 32c01b0b4180 |
| 2024-09-17 | x_NXMC-2024-0208 breaking | the chat template changed and renders differently (multi-turn, 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 (2024-09-17).b53e4e3adbbb -> 37193e87a152 |
Pin it, and let a bot move the pin
from_pretrained("Qwen/Qwen2.5-Math-1.5B", revision="4a83ca6e4526a4f2da3aa259ec36c259f66b2ab2")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-Math-1.5B.html)