Viewing profile — navar

As far as I can tell it should be possible to reuse this fine tuning code entirely and just replace `--embedder_name_or_path BAAI/bge-base-en-v1.5` with `--embedder_name_or_path Mo…

I interacted with the authors of these models quite a bit! These are very interesting models. The tradeoff here is that you get even faster inference, but lose on retrieval accurac…

For the retrieval stage, we have developed a highly efficient, CPU-only-friendly text embedding model: https://huggingface.co/MongoDB/mdbr-leaf-ir It ranks #1 on a bunch of leaderb…

You can refer to https://huggingface.co/spaces/mteb/leaderboard and use that to guide your selection. Check under the "Retrieval" section, either RTEB Multilingual or RTEB German (…

I created a small app that shows the difference between embedding-based ("semantic") and bm25 search: http://search-sensei.s3-website-us-east-1.amazonaws.com/ (warning! It will dow…

I believe it's because the way you measure things in RL, each episode only tells you whether it was good (say reward +1) or bad (say 0 or negative reward), it does not tell you any…

You can process a single word through a transformer and get the corresponding intermediate representations. Though it sounds odd there is no problem with it and it would indeed ret…

[dead]

Embeddings as a tool have been around for longer than LLMs. They were (and are) ubiquitous in, e.g., recommender systems. It sounds maybe this would be more in-line with what you a…