Changes / Feeds / microsoft/Phi-3-mini-128k-instruct
microsoft/Phi-3-mini-128k-instruct
3 changes to a tracked key since 2024-04-22, newest first. Head as last read: f3c06aed622e14ca0abf5115094e4fc9a9948f36.
GPU memory to fine-tune it, card by card: Phi-3-mini-128k-instruct on /m/.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2024-07-01 | x_NXMC-2024-0057 breaking | rope_scaling values changed ({"long_factor":[1.0299999713897705,1.0499999523162842,1.0... to {"long_factor":[1.0700000524520874,1.1200000047683716,1.1...); positions are computed differently; the chat template changed and renders differently (system+user, 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; add_bos_token true to false; encoding the same text yields different ids (2024-07-01).bb5bf1e40012 -> 10d25dfa1593 |
| 2024-04-29 | x_NXMC-2024-0056 breaking | the chat template changed and renders differently (system+user); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2024-04-29).48788d7704a9 -> fc313b051490 |
| 2024-04-25 | x_NXMC-2024-0055 | tokenizer model_max_length 4096 to 131072; truncation defaults change (2024-04-25).7de6f02aba40 -> 48788d7704a9 |
Pin it, and let a bot move the pin
from_pretrained("microsoft/Phi-3-mini-128k-instruct", revision="f3c06aed622e14ca0abf5115094e4fc9a9948f36")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/microsoft/Phi-3-mini-128k-instruct.html)