Changes / Feeds / Qwen/Qwen2.5-Coder-7B
Qwen/Qwen2.5-Coder-7B
6 changes to a tracked key since 2024-09-16, newest first. Head as last read: 0396a76181e127dfc13e5c5ec48a8cee09938b02.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2024-11-18 | x_NXMC-2024-0197 | tokenizer model_max_length 131072 to 32768; truncation defaults change (2024-11-18).9ec1a913b848 -> 0396a76181e1 |
| 2024-09-20 | x_NXMC-2024-0196 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).30b6a7e874a7 -> 9ec1a913b848 |
| 2024-09-20 | x_NXMC-2024-0195 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).4c1c1611f306 -> 30b6a7e874a7 |
| 2024-09-19 | x_NXMC-2024-0194 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).f07775da2cd8 -> 4c1c1611f306 |
| 2024-09-18 | x_NXMC-2024-0193 breaking | context window 131072 to 32768 tokens; rope_scaling removed (was {"factor":4,"original_max_position_embeddings":32768,"typ...); positions are no longer scaled (2024-09-18).f52e93b2dd07 -> f07775da2cd8 |
| 2024-09-17 | x_NXMC-2024-0192 breaking | rope_scaling added ({"factor":4,"original_max_position_embeddings":32768,"typ...); positions are now scaled (2024-09-17).e1a210cef2e7 -> f52e93b2dd07 |
Pin it, and let a bot move the pin
from_pretrained("Qwen/Qwen2.5-Coder-7B", revision="0396a76181e127dfc13e5c5ec48a8cee09938b02")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-7B.html)