Ogundepo Odunayo

This is one `@inproceedings{a-gorog-2014-quality, title = "Quality evaluation today: the Dynamic Quality Framework", author = {{A.G{\"o}r{\"o}g}}, booktitle = "Proceedings of Translating and the Computer 36", month = nov # "...

The scores are the same using Lucene 9.0 and 8.0

I guess this is a Tevatron issue

@MXueguang

Hi @ingride , Oh when you get the output_ids, you can decode back to text using the model tokenizer ```rust tokenizer.decode(output) ``` source: https://github.com/huggingface/candle/blob/9bd94c1ffa0ccfd2bbc9526569b8b8a2a3812027/candle-examples/src/token_output_stream.rs#L27

Side Note: We have some duplicated code e.g. https://github.com/castorini/pyserini/blob/184a212e7d578fac453ead64f7f796bc2e44bcf2/pyserini/encode/_tct_colbert.py#L72 and https://github.com/castorini/pyserini/blob/184a212e7d578fac453ead64f7f796bc2e44bcf2/pyserini/search/faiss/_searcher.py#L147 Is there a particular reason we are keeping both?

Bump on this @jacklin64 @justram . Evaluating with this ```bash python -m pyserini.search.faiss \ --index msmarco-v1-passage.tct_colbert.hnsw \ --topics msmarco-passage-dev-subset \ --encoder castorini/tct_colbert-msmarco \ --encoder-class mlx_tct_colbert \ --output runs/run.msmarco-passage.tct_colbert.hnsw.tsv \ --output-format...

> The new [JinaBert](https://huggingface.co/jinaai/jina-embeddings-v2-base-en) Embeddings is small and has Apache license This looks like one I'd love to help migrate; @LaurentMazare I can create an issue and get started on...

> > > The new [JinaBert](https://huggingface.co/jinaai/jina-embeddings-v2-base-en) Embeddings is small and has Apache license > > > > > > This looks like one I'd love to help migrate; @LaurentMazare I...

> I had same issue you need just copy libfaiss_c.dylib to /usr/local/lib. sudo cp build/c_api/libfaiss_c.dylib /usr/local/lib/libfaiss_c.dylib > > After that everything worked fine. > > In total on MacOs I...