refact : fix convert script + zero out KV cache to avoid nans #3523
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Outdated suggestions cannot be applied.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.
ref: #3329 (comment)
convert-starcoder-hf-to-gguf.py
https://github.com/ggerganov/llama.cpp/blob/bdbe11719d81dfdc955b762b6d99796724e292b7/llama.cpp#L5024
If this data happens to contain
nan
, then the generation failsQuestion: should we first mask the KV tensor and then apply ALiBi?
https://github.com/ggerganov/llama.cpp/blob/bdbe11719d81dfdc955b762b6d99796724e292b7/llama.cpp#L3763-L3771
If that were the case, then the above KV cache initialization wouldn't be needed since any uninitialized values will be masked with
-INF