Tutorials
okay maybe it's a good time? We have a small colbert model trained at pplx, it is a continue-training of pplx-embed-0.6b, so native multilin…
okay maybe it's a good time? We have a small colbert model trained at pplx, it is a continue-training of pplx-embed-0.6b, so native multilingual, just made it open and added a section how to use MaxSi
okay maybe it's a good time? We have a small colbert model trained at pplx, it is a continue-training of pplx-embed-0.6b, so native multilingual, just made it open and added a section how to use MaxSim kernel: https://huggingface.co/perplexity-ai/pplx-embed-v1-late-0.6b Releasing my first kernel on @huggingface: MaxSim Late-interaction retrieval (ColBERT / PyLate) bottlenecks on materializing the full similarity matrix. This kernel avoids it by using tiled scoring with simdgroup_matrix (Metal) and WMMA. Result is 3–5× speedup compared to naive P…
Source: Clem Delangue (X) | 2026-05-18