Hugging Face's logo
六花牡丹（Rikka Botan）'s picture
🤝 Open to Collab

六花牡丹（Rikka Botan） PRO

RikkaBotan
2 8 7
dwablimol's profile picture tomo461's profile picture hotchpotch's profile picture
·
https://rikka-botan.github.io/

AI & ML interests

Japanese independent researcher having shy and pampered personality. Twin-tail hair is a charm point. Interested in nlp. Usually using python and C.

Recent Activity

upvoted an article 2 days ago
Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers
reacted to tardellirs's post with 🔥 2 days ago
Crivo-150M is now on the Pareto frontier of the Decision Index 🎯 Scored by the maintainers on the private tests: Full 22.21, the best of all submissions at or below 150M and higher than every model below 0.75B, including models up to 4× its size. Median latency on the board's GPU: 13 ms. It is a 149M typed-decision encoder (Ettin / ModernBERT): a state plus choice, noul or score questions in, a probability for every option out, in one forward pass. Trained on open data only. Next: tasks from new domains, the weak spot of every small encoder on the board. https://huggingface.co/tardellirs/crivo-150m https://huggingface.co/spaces/multimodalart/jev-decision-index Thanks to @multimodalart for the Decision Index and its open kit, @orionweller and the Ettin team, @tomaarsen for the Ettin rerankers, @hotchpotch for the Bekko System One data and @sileod for tasksource.
reacted to tomaarsen's post with 🔥 2 days ago
🤗 I've released Sentence Transformers v6.3 and wrote a blogpost about its key new feature: token pooling-aware training, teaching multi-vector models to preserve retrieval quality with fewer document vectors. Details: Multi-vector models keep a vector per token, letting different query tokens match different parts of a document. Great for retrieval, but those vectors add up! Token pooling makes the representations smaller by merging similar document vectors into cluster means. Pooling-aware training teaches the encoder to preserve useful matches after those vectors are merged. With MultiVectorTokenPoolingLoss, you can wrap your standard retrieval loss to train on both full and pooled representations, reusing the same token embeddings without another encoder pass. In short: small overhead. I trained two ModernBERT-base models on the same 120k MS MARCO triplets, changing just the loss. At ~49 vectors per document instead of 193, pooling-aware training raises NanoBEIR@13 mean nDCG@10 from 49.03 to 51.23. That's 97.8% of its own unpooled score with ~4x fewer document vectors, compared with 94.6% retention for ordinary training. v6.3 also adds: - Adaptive token budgets, allocating vectors according to each document's content - Matryoshka training for shorter multi-vector token embeddings - Hugging Face kernels support for MaxSim, Ward clustering & supported transformers layers - Native AWS Neuron inference You can combine pooling-aware and Matryoshka training to learn both fewer vectors and fewer dimensions, then stack these with quantization to reduce storage per coordinate. For kernels, install sentence-transformers[kernels] and set use_kernels=True. The blog walks through the method, training code, checkpoints & evaluation, building on Stefan Josef's Learn to Pool and LightOn's pooling regularization work: ht tps://huggingface.co/blog/token-pooling I'd love to see what you train with this!
View all activity

Organizations

Blog-explorers's profile picture