]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
model-conversion : add embedding prompt file support (#15871)
authorDaniel Bevenius <redacted>
Thu, 25 Sep 2025 10:02:36 +0000 (12:02 +0200)
committerGitHub <redacted>
Thu, 25 Sep 2025 10:02:36 +0000 (12:02 +0200)
commitaa3ee0eb0b80efca126cedf9bcb4fb5864b46ce3
tree53e43e00f979065b748247c767ced210cbde169b
parentd0991da39d3c39b3980c24cdfccb9a4c95a46870
model-conversion : add embedding prompt file support (#15871)

This commit adds support for passing a prompt file to the model
conversion targets/scripts. It also updates the logits.cpp to print out
embedding information in the same format as when running the original
embedding model.

The motivation for this is that it allows us to pass files of different
sizes when running the converted models and validating the logits.

This can be particularly important when testing the sliding window
functionality of models where the sequence length needs to exceed a
certain number of tokens to trigger the sliding window logic.
examples/model-conversion/Makefile
examples/model-conversion/logits.cpp
examples/model-conversion/scripts/embedding/compare-embeddings-logits.sh
examples/model-conversion/scripts/embedding/run-converted-model.sh
examples/model-conversion/scripts/embedding/run-original-model.py
examples/model-conversion/scripts/utils/inspect-org-model.py
examples/model-conversion/scripts/utils/semantic_check.py