AI & ML interests

None defined yet.

Recent Activity

victor 
posted an update 1 day ago
view post
Post
108
In case you haven’t seen (or tried) it yet: Ava is an AI character you can talk to face to face, right in your browser 🙂

townbox/ava

- No login, nothing to install
- Runs 100% in the browser via WebGPU
- Powered by LiquidAI/LFM3-Omni-2B-GGUF, running locally on your device via WebGPU
- Your conversations stay on your machine

Really bullish on 100% local experiences lately. No backend inference bill, no account to create, and you keep your data.
tomaarsen 
posted an update 7 days ago
view post
Post
7,099
🤗 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!
albertvillanova 
posted an update 20 days ago
view post
Post
363
Day-0 Mistral Large 4 support in TRL 🚀

- LoRA SFT of the 1T-A52B model on one 8xB300 node, on top of the FP8 checkpoint
- Experts split 8 ways with expert parallelism, everything else sharded with FSDP, all set at load time
- Assistant-only loss out of the box with its training chat template
- ~32.7k tokens per step in ~8 s

Script + Slurm launcher 👇
https://github.com/huggingface/trl/tree/main/examples/sft_mistral_large_4
https://huggingface.co/posts/sergiopaniego/408182860646834
tomaarsen 
posted an update 3 months ago
view post
Post
4,666
🚨 I've just published Sentence Transformers v6.0, introducing MultiVectorEncoder: ColBERT-style late interaction models are now a fourth model type, for training, inference, and interpretation, alongside the dense, sparse, and reranker models! Details:

Where a regular embedding model compresses a whole text into one vector, a multi-vector model keeps one vector per token and scores query against document with the MaxSim operator. That preserves token-level matching information that a single vector has to average away. It is also the state of the art for visual document retrieval, where a text query is matched against page images directly, charts and tables included, with no OCR step in between.

Any PyLate, Stanford ColBERT, or ColPali checkpoint loads straight into the same familiar API: model.encode_query(), model.encode_document(), and model.similarity() just work, whether the documents are texts or page images.

Does it help? LightOn trained LateOn (multi-vector) and DenseOn (dense) on the same data with the same 149M ModernBERT backbone, and the multi-vector model wins on 9 of the 13 NanoBEIR datasets: 0.6868 vs 0.6764 mean NDCG@10. The price is a bigger index, and the new HierarchicalTokenPooling module halves it at roughly no retrieval cost.

Antoine Chaffin, Raphaël Sourty, and I wrote a blog post walking through multi-vector models in practice: loading the various checkpoint formats, encoding and scoring, plugging them into a search stack, running them on page images, and keeping the index affordable. Check it out if you want to get started, or just point your Agent to the URL: https://huggingface.co/blog/multi-vector-encoder

pip install sentence-transformers==6.0.0

Release notes: https://github.com/huggingface/sentence-transformers/releases/tag/v6.0.0
badaoui 
posted an update 4 months ago
view post
Post
2,537
432 GB of ultra-fast HBM4 and up to 23.3 TB/s of memory bandwidth on a single GPU 🤯.

Two weeks ago, we got early access to AMD's new Instinct MI455X, and our first goal was simple: make sure 🤗 Transformers works on day one.

Over the past few weeks, we worked closely with the AMD team to validate the platform, enable Flash Attention, add torchcodec support for multimodal models, and resolve issues uncovered during testing.

The result:
✅ 99.5% success rate across our 24 core Transformers model architectures - already on par with our daily CI on previous AMD and NVIDIA platforms.

The hardware is just as exciting. With 432 GB of HBM per GPU, our early capacity experiments showed more than 3× the concurrent long-context requests compared to MI300, thanks to the much larger KV cache capacity.

A huge thanks to the AMD team for the early access and the great collaboration!

Read the full blog 👇
https://huggingface.co/blog/badaoui/transformers-on-amd-mi455
  • 1 reply
·