sgugger commited on
Commit
896a04b
1 Parent(s): d8740c6

Fix weights by putting the right value in `lm_head.weight`

Browse files

There was probably a bug in the initial conversion script that created those models, as the weights they have have a
different value for `lm_head.weight` and `model.decoder.embed_tokens.weight`. Those models are tied though.

This was not a problem until now as the model was tied after the load and the (wrong) value of `lm_head.weight` was
replaced by the value of `model.decoder.embed_tokens.weight`. This does not work any more if we tie the weights before
the load however, as the value picked might be the one from `lm_head.weight` depending on how the models are tied.
As far as I can see, the model stop generating properly on Transformers main.

This should fix the bug without any side effect.

Files changed (1) hide show
  1. pytorch_model.bin +2 -2
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf021b0f024caf716cd60857051e565bafa7bee2e08885a087ef4759e92d6522
3
- size 153136027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36807f12793eff840995bd681fa46778658faa02bbb5ff8c65477f789bd1ff7c
3
+ size 153133317