Changes / Feeds / Qwen/Qwen2.5-1.5B
Qwen/Qwen2.5-1.5B
4 changes to a tracked key since 2024-09-15, newest first. Head as last read: 8faed761d45a263340a0528343f099c05c9a4323.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2024-10-08 | x_NXMC-2024-0120 breaking | context window 32768 to 131072 tokens; sliding_window 32768 to 131072 (2024-10-08).5f3adf4f8825 -> 8faed761d45a |
| 2024-09-20 | x_NXMC-2024-0119 breaking | EOS changed from "<|im_end|>" to "<|endoftext|>"; anything fine-tuned or served against the old value stops at a different token (2024-09-20).e5dfabbcffd9 -> 5f3adf4f8825 |
| 2024-09-19 | x_NXMC-2024-0118 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).033b7782da89 -> e5dfabbcffd9 |
| 2024-09-16 | x_NXMC-2024-0117 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 (2024-09-16).09e632842422 -> 033b7782da89 |
Pin it, and let a bot move the pin
from_pretrained("Qwen/Qwen2.5-1.5B", revision="8faed761d45a263340a0528343f099c05c9a4323")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/Qwen2.5-1.5B.html)