Changes / Feeds / HuggingFaceTB/SmolLM2-1.7B-Instruct
HuggingFaceTB/SmolLM2-1.7B-Instruct
2 changes to a tracked key since 2024-10-31, newest first. Head as last read: 31b70e2e869a7173562077fd711b654946d38674.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2025-01-07 | x_NXMC-2025-0165 | tokenizer model_max_length 2048 to 8192; truncation defaults change (2025-01-07).d1bb90bcfbe0 -> 450ff1f12781 |
| 2024-10-31 | x_NXMC-2024-0211 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 (2024-10-31).a587c08a0ba9 -> e4f7834c8f51 |
Pin it, and let a bot move the pin
from_pretrained("HuggingFaceTB/SmolLM2-1.7B-Instruct", revision="31b70e2e869a7173562077fd711b654946d38674")
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/HuggingFaceTB/SmolLM2-1.7B-Instruct.html)