Changes / Feeds / Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4
Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4
3 changes to a tracked key since 2024-09-17, newest first. Head as last read: c83e67dfb2664f5039fd4cd99e206799e27dd800.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2024-09-19 | x_NXMC-2024-0137 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).8604ddb8831d -> 34f0b153f75f |
| 2024-09-18 | x_NXMC-2024-0136 breaking | 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).9239191be9d2 -> 8604ddb8831d |
| 2024-09-18 | x_NXMC-2024-0135 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).3fa9c79b1c7a -> 9239191be9d2 |
Pin it, and let a bot move the pin
from_pretrained("Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4", revision="c83e67dfb2664f5039fd4cd99e206799e27dd800")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-GPTQ-Int4.html)