Changes / Feeds / OpenGVLab/InternVL2-1B
OpenGVLab/InternVL2-1B
2 changes to a tracked key since 2024-07-08, newest first. Head as last read: 0d75ccd166b1d0b79446ae6c5d1a4a667f1e6187.
GPU memory to fine-tune it, card by card: InternVL2-1B on /m/.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2024-12-06 | x_NXMC-2024-0018 breaking | derived parameters 798.6M to 934.6M (+136.0M, +0.27 GB of bf16 weights); tie_word_embeddings true to false; the output head is no longer shared with the embedding (2024-12-06).8d827904f96b -> b5e11b0270f6 |
| 2024-08-22 | x_NXMC-2024-0017 breaking | EOS declared as [151644,151645] (was unset); generation that relied on the library default now stops on this token (2024-08-22).055968f34f42 -> 8d827904f96b |
Pin it, and let a bot move the pin
from_pretrained("OpenGVLab/InternVL2-1B", revision="0d75ccd166b1d0b79446ae6c5d1a4a667f1e6187")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/OpenGVLab/InternVL2-1B.html)