Allow continuation in Instruct and Interact executors; fix a minor leak #852
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The LLaVA path needs tested; I haven't used LLaVA in any capacity yet, myself. I tested both InstructExecutor and InteractiveExecutor in my actual applications by repeatedly pausing and continuing, and I found no cases where the model cut off a word/switched trains of thought when continuing, nor cases where it clearly misunderstood the next prompt after a continuation.