Changes / Feeds / Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4
Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4
4 changes to a tracked key since 2024-09-18, newest first. Head as last read: e9c932ac1893a49ae0fc497ad6e1e86e2e39af20.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2024-10-18 | x_NXMC-2024-0191 breaking | the chat template changed and renders differently (multi-turn); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2024-10-18).d3320b86ad38 -> e9c932ac1893 |
| 2024-10-18 | x_NXMC-2024-0190 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 (2024-10-18).6e497db5d9b6 -> d3320b86ad38 |
| 2024-09-19 | x_NXMC-2024-0189 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).22a88496da30 -> 6e497db5d9b6 |
| 2024-09-18 | x_NXMC-2024-0188 breaking | context window 8192 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).4014efd717cc -> 22a88496da30 |
Pin it, and let a bot move the pin
from_pretrained("Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4", revision="e9c932ac1893a49ae0fc497ad6e1e86e2e39af20")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-GPTQ-Int4.html)