Hugging Face's logo

gg-tt
company
Activity Feed

AI & ML interests

None defined yet.

Recent Activity
RyanMullins  authored a paper 5 days ago
Gemma 4 Technical Report
RyanMullins  authored a paper 5 days ago
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
osanseviero  authored a paper 7 days ago
EmbeddingGemma 2: Unified and Efficient Multimodal Representations
View all activity
danielhanchen 
posted an update 1 day ago
view post
Post
4,515
Today, we're releasing the highest accuracy Qwen3.8-27B GGUFs!

Our new Dynamic V3.1 GGUFs lead by 5–10% on average across Terminal Bench, DeepSWE & more. We’re working on an even better version for Qwen4.

Run on 12GB RAM setups

GGUF: unsloth/Qwen3.8-27B-GGUF
Blog: https://unsloth.ai/docs/models/qwen3.8
tomaarsen 
posted an update 1 day ago
view post
Post
4,195
🤗 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!
danielhanchen 
posted an update 5 days ago
view post
Post
5,834
Qwen3.8-Flash-Next GGUFs now run faster with less thinking and less token use.

Unsloth Dynamic V3.1 GGUFs bring thinking & token use to match 95% of full precision Qwen3.8-Flash.

Results: 50% fewer tokens + 15% higher accuracy vs same size quants.

GGUF: unsloth/Qwen3.8-Flash-Next-GGUF
Analysis/Guide: https://unsloth.ai/docs/models/qwen3.8-next
  • 3 replies
·
RyanMullins 
authored 2 papers 5 days ago
osanseviero 
authored a paper 7 days ago
danielhanchen 
posted an update 8 days ago
bebechien 
authored 2 papers 11 days ago
danielhanchen 
posted an update 13 days ago
danielhanchen 
posted an update 15 days ago
tomaarsen 
submitted a paper to Daily Papers 15 days ago
danielhanchen 
posted an update 24 days ago
danielhanchen 
posted an update about 1 month ago
danielhanchen 
posted an update about 1 month ago
danielhanchen 
posted an update about 2 months ago
view post
Post
9,213
Unsloth has surpassed 500M model downloads on Hugging Face! 🦥🤗

Qwen3.8-27B GGUF is already Unsloth’s #1 most-downloaded model ever.

Thanks for all your support! Follow us:
unsloth
  • 1 reply
·
danielhanchen 
posted an update about 2 months ago
danielhanchen 
posted an update 2 months ago
tomaarsen 
posted an update 3 months ago
view post
Post
4,658
🚨 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
danielhanchen 
posted an update 3 months ago
view post
Post
7,595
Introducing Unsloth Desktop 🦥
The first desktop app to run and train models locally.

• Open-source. Runs on Mac, Windows and Linux
• Supports MLX, diffusion image/video, audio, GGUF
• Connect Claude Code and Codex to local LLMs
• 50% more accurate, self-healing tool calls + sandboxed code exec
• Works for CPU + multiGPU setups - NVIDIA, AMD, Intel, Mac
• Train models 2× faster with 70% less VRAM
• Private web search, deep research, RAG, MCP and exports (NVFP4, GGUF)
• Use Unsloth’s OpenAI-compatible API and cloud models
• Securely deploy LLMs remotely and access anywhere

Unsloth Desktop is now available on http://unsloth.ai
and GitHub.

GitHub: https://github.com/unslothai/unsloth
Blog and Guide: https://unsloth.ai/docs/desktop
  • 6 replies
·