Hugging Face's logo

gg-tt
company
Activity Feed

AI & ML interests

None defined yet.

Recent Activity
bebechien  authored a paper 3 days ago
EmbeddingGemma 2: Unified and Efficient Multimodal Representations
bebechien  authored a paper 3 days ago
Gemma 4 Technical Report
tomaarsen  submitted a paper 7 days ago
EmbeddingGemma 2: Unified and Efficient Multimodal Representations
View all activity
danielhanchen 
posted an update about 5 hours ago
bebechien 
authored 2 papers 3 days ago
danielhanchen 
posted an update 5 days ago
danielhanchen 
posted an update 7 days ago
tomaarsen 
submitted a paper to Daily Papers 7 days ago
danielhanchen 
posted an update 16 days ago
danielhanchen 
posted an update 27 days ago
danielhanchen 
posted an update 29 days ago
danielhanchen 
posted an update about 1 month ago
view post
Post
9,201
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 1 month ago
danielhanchen 
posted an update about 2 months ago
tomaarsen 
posted an update 3 months ago
view post
Post
4,570
🚨 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
7,587
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
·
danielhanchen 
posted an update 3 months ago
mlabonne 
posted an update 3 months ago
view post
Post
6,901
Deploy local agents everywhere with LiquidAI/LFM2.5-2.6B

Unlike agents that depend on cloud APIs, local agents give you free inference, low latency, and real privacy.

Removing the per-token cost changes how developers build: agents can now be massively parallelized on local hardware, running background tasks that burn through millions of tokens at no marginal cost!
  • 8 replies
·
danielhanchen 
posted an update 3 months ago
view post
Post
3,587
We compared 1-bit Kimi K3 to Claude Opus 5 and GPT 5.6. 🤯

We gave 4 models the same prompt: Create a glass aquarium whose side panel develops a visible crack and then bursts...

1-bit Kimi K3 GGUF ran locally on 4x B200s at 36 tok/s.

GGUF: unsloth/Kimi-K3-GGUF
GitHub repo: https://github.com/unslothai/unsloth
  • 1 reply
·
danielhanchen 
posted an update 3 months ago
view post
Post
5,787
Kimi K3 can now be run locally! ✨

The 1-bit model retains ~78.9% accuracy after we shrunk it from 1.56TB to 594GB (-62% size).

Run on a Mac Studio connected with 128GB RAM device. Kimi K3 is the strongest open model to date.

GGUF: unsloth/Kimi-K3-GGUF
Guide: https://unsloth.ai/docs/models/kimi-k3
  • 5 replies
·
danielhanchen 
posted an update 4 months ago
view post
Post
6,077
Introducing Unsloth for AMD 🚀
You can now train & run LLMs on your AMD hardware

• We collaborated with AMD to enable you to train & run 500+ models on AMD GPUs
• Works on Windows, WSL, Linux
• Train Qwen, Gemma on just 3GB VRAM

GitHub: https://github.com/unslothai/unsloth
Blog + Guide: https://unsloth.ai/docs/basics/amd
  • 3 replies
·
danielhanchen 
posted an update 4 months ago