Changes / Feeds / Qwen/Qwen2.5-Coder-1.5B-Instruct
Qwen/Qwen2.5-Coder-1.5B-Instruct
7 changes to a tracked key since 2024-09-18, newest first. Head as last read: 2e1fd397ee46e1388853d2af2c993145b0f1098a.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2024-11-18 | x_NXMC-2024-0168 | tokenizer model_max_length 131072 to 32768; truncation defaults change (2024-11-18).357b899b4714 -> 50285f662d27 |
| 2024-11-12 | x_NXMC-2024-0167 breaking | sliding_window 131072 to 32768 (2024-11-12).253f7f91db97 -> 357b899b4714 |
| 2024-11-09 | x_NXMC-2024-0166 breaking | EOS changed from 151643 to 151645; anything fine-tuned or served against the old value stops at a different token (2024-11-09).19ddfaeed64b -> 253f7f91db97 |
| 2024-09-20 | x_NXMC-2024-0165 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 (2024-09-20).71754d9e15bc -> 19ddfaeed64b |
| 2024-09-19 | x_NXMC-2024-0164 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).9ce57ed54f45 -> 71754d9e15bc |
| 2024-09-19 | x_NXMC-2024-0163 breaking | EOS changed from 151643 to [151645,151643]; anything fine-tuned or served against the old value stops at a different token; pad token unset to 151643; batched training masks a different id; generation defaults changed (do_sample unset to true, max_new_tokens 2048 to unset, repetition_penalty unset to 1.1, temperature unset to 0.7); a call that does not pass these explicitly now generates differently (2024-09-19).098145f275b4 -> 9ce57ed54f45 |
| 2024-09-18 | x_NXMC-2024-0162 breaking | sliding_window 32768 to 131072 (2024-09-18).e3b23484d3a9 -> 098145f275b4 |
Pin it, and let a bot move the pin
from_pretrained("Qwen/Qwen2.5-Coder-1.5B-Instruct", revision="2e1fd397ee46e1388853d2af2c993145b0f1098a")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-Coder-1.5B-Instruct.html)