Changes / Feeds / Qwen/Qwen2.5-14B-Instruct
Qwen/Qwen2.5-14B-Instruct
3 changes to a tracked key since 2024-09-16, newest first. Head as last read: cf98f3b3bbb457ad9e2bb7baf9a0125b6b88caa8.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2024-09-19 | x_NXMC-2024-0104 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).76ca6ba7b68f -> 502e5d8bfd66 |
| 2024-09-18 | x_NXMC-2024-0103 breaking | context window 131072 to 32768 tokens; rope_scaling removed (was {"factor":4,"original_max_position_embeddings":32768,"typ...); positions are no longer scaled; sliding_window 32768 to 131072 (2024-09-18).e648520a381c -> 76ca6ba7b68f |
| 2024-09-18 | x_NXMC-2024-0102 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).336cd7ff9b3a -> e648520a381c |
Pin it, and let a bot move the pin
from_pretrained("Qwen/Qwen2.5-14B-Instruct", revision="cf98f3b3bbb457ad9e2bb7baf9a0125b6b88caa8")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/Qwen2.5-14B-Instruct.html)