Commit History
-
Fix AIMv2 checkpoint/config compatibility with custom HF code
tewthVerified signatureThis PR makes the uploaded checkpoint consistent with the custom `modeling_aimv2.py` implementation shipped in the repository. - remap tensor names in `model.safetensors` to match `AIMv2Model.state_dict()` - update `config.json` so `architectures` and `model_type` align with the shipped config/model classes Without these changes, loading via `AutoModel.from_pretrained(..., trust_remote_code=True)` initializes most model weights from scratch instead of loading the published checkpoint.9835499
-
Fix missing revision
Verified signaturefcb5093 -
Update README.md
Verified signatureAdd correct revision for PyTorch71e44d6 -
Add HF compatible checkpoints (#6)
Verified signature- Update model (a4d9179cdd03e231f8ab6f52fe02481fa7787685) Co-authored-by: Yaswanth <yaswanthgali@users.noreply.huggingface.co>7b77aa7
-
AMLR license (#5)
Verified signature- AMLR license (abc6b4acaf452e1799f8914bb1e4c0eb47b3b65b)ac764a2
-
Add LICENSE
Verified signature368ec1b
-
Add `_no_split_modules`
b31a84b
-
Update README
7f072a1 -
Add link to paper (#1)
Verified signature- Add link to paper (55002eff8fa94ec0ab1ad2f0a8af40cd933c9680) Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>71ceef4
-
Upload files
0410f31
-
initial commit
Verified signature96a1ae9