Changes / Feeds / Qwen/Qwen2.5-Coder-14B-Instruct
Qwen/Qwen2.5-Coder-14B-Instruct
5 changes to a tracked key since 2024-11-06, newest first. Head as last read: aedcc2d42b622764e023cf882b6652e646b95671.
Differs from Qwen/Qwen2.5-Coder-14B in 579 of 579 aligned tensors (at most 100.0% of elements). Compared tensor by tensor from sha256 fingerprints: aedcc2d42b62 against Qwen/Qwen2.5-Coder-14B at f2ad5164aade. A hash is equal or not; it says nothing about what an edit does.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2024-11-18 | x_NXMC-2024-0082 | tokenizer model_max_length 131072 to 32768; truncation defaults change (2024-11-18).ec98bf0d6c08 -> 7fc9a75b07a3 Open in app |
| 2024-11-09 | x_NXMC-2024-0081 | config.json eos_token_id 151643 to 151645, but generation_config.json still declares [151645,151643], which generate() reads first, so default generation stops on the same tokens; only code that reads config.eos_token_id directly sees the new value (2024-11-09).156d6e6c8fc7 -> f72a6280d956 Open in app |
| 2024-11-09 | x_NXMC-2024-0080 | generation defaults changed (repetition_penalty 1.1 to 1.05); a call that does not pass these explicitly now generates differently (2024-11-09).715887aa3a74 -> 156d6e6c8fc7 Open in app |
| 2024-11-06 | x_NXMC-2024-0079 | generation defaults changed (repetition_penalty 1.05 to 1.1); a call that does not pass these explicitly now generates differently (2024-11-06).93e1f0b72787 -> 715887aa3a74 Open in app |
| 2024-11-06 | x_NXMC-2024-0078 | config.json eos_token_id 151645 to 151643, but generation_config.json still declares [151645,151643], which generate() reads first, so default generation stops on the same tokens; only code that reads config.eos_token_id directly sees the new value (2024-11-06).215507574115 -> 93e1f0b72787 Open in app |
Pin it, and let a bot move the pin
from_pretrained("Qwen/Qwen2.5-Coder-14B-Instruct", revision="aedcc2d42b622764e023cf882b6652e646b95671")
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-14B-Instruct.html)