Changes / Feeds / deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
3 changes to a tracked key since 2025-01-20, newest first. Head as last read: ad9f0ae0864d7fbcd1cd905e3c6c5b069cc8b562.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2025-02-09 | x_NXMC-2025-0089 breaking | the chat template changed and renders differently (system+user, multi-turn); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-02-09).164af3f02f5b -> 530ca3e1ad39 |
| 2025-01-22 | x_NXMC-2025-0088 breaking | add_bos_token false to true; encoding the same text yields different ids (2025-01-22).e93784059177 -> 164af3f02f5b |
| 2025-01-22 | x_NXMC-2025-0087 breaking | add_bos_token true to false; encoding the same text yields different ids (2025-01-22).73d63fa6f97d -> e93784059177 |
Pin it, and let a bot move the pin
from_pretrained("deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B", revision="ad9f0ae0864d7fbcd1cd905e3c6c5b069cc8b562")
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/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B.html)