Adam Belfki

I have come across an important issue related to setting `.grad` to a new tensor object. After setting `.grad` and saving it; the values returned by the Proxy reflect the...

Adding functionality to save the Intervention Graph generated during a tracing context. This is particularly useful for debugging and acquiring a better understanding of how the intervention graph is formed....

Accessing the `Iterator` object when creating an `Iterator` context has become optional. ```python with model.session() as session: l = session.apply(list).save() with session.iter([0, 1, 2]) as item: l.append(item) print("List: ", l)...

Reverting to the previous API design for creating Conditional contexts, using any graph-based context. ## Implementation Changes `ConditionalProtocol` nodes don't have to strictly depend on Intervention Proxies anymore, as the...

Debugging

1

**New Feature!** `NNsight` support now more user-friendly error handling which shows the exact line in the context that caused the exception to be raised. Simply set `debug=True` on your `.trace(...)`...

UnifiedTransformer -> nnsight0.5

3

Reintroduce the implementation of the UnifiedTransformer class to work with the latest version nnsight. Add unit tests to validate this functionality.