Changes / Feeds / Qwen/Qwen2.5-Coder-1.5B
Qwen/Qwen2.5-Coder-1.5B
6 changes to a tracked key since 2024-09-18, newest first. Head as last read: df3ce67c0e24480f20468b6ef2894622d69eb73b.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2024-11-18 | x_NXMC-2024-0178 | tokenizer model_max_length 131072 to 32768; truncation defaults change (2024-11-18).6df6cbb5f18a -> df3ce67c0e24 |
| 2024-11-12 | x_NXMC-2024-0177 breaking | sliding_window 131072 to 32768 (2024-11-12).102a5413ab6b -> 6df6cbb5f18a |
| 2024-09-20 | x_NXMC-2024-0176 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).d3586cfe7937 -> 102a5413ab6b |
| 2024-09-20 | x_NXMC-2024-0175 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 (2024-09-20).8fb5dcaecbef -> d3586cfe7937 |
| 2024-09-19 | x_NXMC-2024-0174 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).6a7051e60c0b -> 8fb5dcaecbef |
| 2024-09-18 | x_NXMC-2024-0173 breaking | sliding_window 32768 to 131072 (2024-09-18).94fddf431e34 -> 6a7051e60c0b |
Pin it, and let a bot move the pin
from_pretrained("Qwen/Qwen2.5-Coder-1.5B", revision="df3ce67c0e24480f20468b6ef2894622d69eb73b")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-1.5B.html)