Changes / Feeds / Qwen/Qwen2.5-7B-Instruct-AWQ
Qwen/Qwen2.5-7B-Instruct-AWQ
2 changes to a tracked key since 2024-09-18, newest first. Head as last read: b25037543e9394b818fdfca67ab2a00ecc7dd641.
GPU memory to fine-tune it, card by card: Qwen2.5-7B-Instruct-AWQ on /m/.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2024-09-19 | x_NXMC-2024-0068 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).d20af0af7b0d -> 617b26a2e255 |
| 2024-09-18 | x_NXMC-2024-0067 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).73f22df4e9ab -> d20af0af7b0d |
Pin it, and let a bot move the pin
from_pretrained("Qwen/Qwen2.5-7B-Instruct-AWQ", revision="b25037543e9394b818fdfca67ab2a00ecc7dd641")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/Qwen2.5-7B-Instruct-AWQ.html)