Closed BenoitHardier closed 2 weeks ago
Hello,
Indeed, breaking changes were introduced in this commit of ST, hence why we fixed the version of sentence-transformers to the last version before 3.1 (sentence-transformers == 3.0.1).
The fix is indeed what you suggested and during my preliminary tests, it seemed to work fine, but I wanted to make sure there was no regression before doing a PR for the fix and bump the version of ST. I might do the PR in the next days if it becomes needed. In the mean time, you can either use your own hacked version or use the 3.0.1 version if you do not need the latest change (e.g, ONNX backend if you are training on CPU)!
Hello again,
I fixed the issue in #65 and now the training with the model from Ordalie works fine with ST 3.2.0! I'll merge the PR during the day alongside with other improvements and bump the version of PyLate.
Hey
Great, It's also working on my setup.
I will try to continue digging into the repo. (I am specially interested in training/fine-tuning french retrieval models) I let you close the issue when you have merged the fix.
Benoît HARDIER
Cool! We are also working on French models right now (on est une entreprise française à la base), hopefully we'll have cool things for you very soon!
Closing since the PR has been merged.
Hey, thanks for your work. I am trying to finetuned a model based on
OrdalieTech/Solon-embeddings-base-0.1
. like that:Unfortunatly, it seems that the
_load_sbert_model
should output bothmodules
andmodule_kwargs
(The SentenceTranformer doc seems wrong) . I am not sure if it's related to the SentenceTransformer version but I am using the last one 3.2.0I finally succeed to load solon changing the
_load_sbert_model
incolbert.py
It should be modified: https://github.com/lightonai/pylate/blob/ddaf8f82dfd8725275c2362c2560c78565b5a874/pylate/models/colbert.py#L1153 and here https://github.com/lightonai/pylate/blob/ddaf8f82dfd8725275c2362c2560c78565b5a874/pylate/models/colbert.py#L1194-L1199Let me know, if I am doing something wrong or if my issue is useful.
Benoît HARDIER