Changes / Feeds / Qwen/Qwen2.5-32B-Instruct
Qwen/Qwen2.5-32B-Instruct
3 changes to a tracked key since 2024-09-17, newest first. Head as last read: 5ede1c97bbab6ce5cda5812749b4c0bdf79b18dd.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2024-09-19 | x_NXMC-2024-0087 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).e47090056c77 -> 70e8dfb9ad18 |
| 2024-09-18 | x_NXMC-2024-0086 breaking | context window 131072 to 32768 tokens; rope_scaling removed (was {"factor":4,"original_max_position_embeddings":32768,"typ...); positions are no longer scaled (2024-09-18).a7e76d7ea0d6 -> e47090056c77 |
| 2024-09-18 | x_NXMC-2024-0085 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 (2024-09-18).59eaef4212cf -> a7e76d7ea0d6 |
Pin it, and let a bot move the pin
from_pretrained("Qwen/Qwen2.5-32B-Instruct", revision="5ede1c97bbab6ce5cda5812749b4c0bdf79b18dd")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/Qwen2.5-32B-Instruct.html)