chatllm: fix deserialization version mismatch #1859
Merged
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Outdated suggestions cannot be applied.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.
I wrote
>= 6
when I meant either> 6
or>= 7
. Change it to the latter, which is what makes the most sense to me (n_ctx only applies to versions 7 and above).This was causing a crash when loading chat files from versions of GPT4All prior to v2.6, at least when deserializeKV is true (KV cache saved to disk).
Fixes #1846 (symptom is a std::bad_alloc because tokensSize is too large, thanks to @ShadowsArt for helping debug this over Discord)