Hugging Face's logo

gg-tt
company
Activity Feed

AI & ML interests

None defined yet.

Recent Activity
clefourrier  authored a paper about 2 months ago
Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections
mlabonne  authored a paper 3 months ago
LFM2 Technical Report
mlabonne  authored a paper 3 months ago
Zero-Overhead Introspection for Adaptive Test-Time Compute
View all activity
mlabonne 
posted an update 1 day ago
view post
Post
248
Big update to llm-datasets, my curated list of datasets and tools for post-training LLMs.

> Added many new datasets
> New "thinking" column
> Refreshed recommended tools.

Thanks to everyone who told me they used it for their research at ICLR, you motivated this update!
  • 1 reply
·
danielhanchen 
posted an update 6 days ago
danielhanchen 
posted an update 12 days ago
tomaarsen 
posted an update 19 days ago
view post
Post
684
🌐 I've just published Sentence Transformers v5.4 to make the project fully multimodal for embeddings and reranking. The release also includes a modular CrossEncoder, and automatic Flash Attention 2 input flattening. Details:

You can now use SentenceTransformer and CrossEncoder with text, images, audio, and video, with the same familiar API. That means you can compute embeddings for an image and a text query using model.encode(), compare them with model.similarity(), and it just works. Models like Qwen3-VL-Embedding-2B and jinaai/jina-reranker-m0 are supported out of the box.

Beyond multimodal, I also fully modularized the CrossEncoder class. It's now a torch.nn.Sequential of composable modules, just like SentenceTransformer has been. This unlocked support for generative rerankers (CausalLM-based models like mxbai-rerank-v2 and the Qwen3 rerankers) via a new LogitScore module, which wasn't possible before without custom code.

Also, Flash Attention 2 now automatically skips padding for text-only inputs. If your batch has a mix of short and long texts, this gives you a nice speedup and lower VRAM usage for free.

I wrote a blog post walking through the multimodal features with practical examples. Check it out if you want to get started, or just point your Agent to the URL: https://huggingface.co/blog/multimodal-sentence-transformers

This release has set up the groundwork for more easily introducing late-interaction models (both text-only and multimodal) into Sentence Transformers in the next major release. I'm looking forward to it!
danielhanchen 
posted an update 21 days ago
danielhanchen 
posted an update 26 days ago
danielhanchen 
posted an update 28 days ago
view post
Post
2741
A new way to use Unsloth.

Coming soon...
danielhanchen 
posted an update about 1 month ago
view post
Post
923
You don’t need to set LLM parameters anymore! 🚀

llama.cpp uses only the context length + compute your local setup needs. Unsloth also auto-applies the correct model settings

Try in Unsloth Studio - now with precompiled llama.cpp binaries.

GitHub: https://github.com/unslothai/unsloth
  • 2 replies
·
danielhanchen 
posted an update about 1 month ago
view post
Post
3402
Introducing Unsloth Studio ✨
A new open-source web UI to train and run LLMs.

• Run models locally on Mac, Windows, Linux
• Train 500+ models 2x faster with 70% less VRAM
• Supports GGUF, vision, audio, embedding models
• Auto-create datasets from PDF, CSV, DOCX
• Self-healing tool calling and code execution
• Compare models side by side + export to GGUF

GitHub: https://github.com/unslothai/unsloth
Blog and Guide: https://unsloth.ai/docs/new/studio

Available now on Hugging Face, NVIDIA, Docker and Colab.
danielhanchen 
posted an update about 2 months ago
view post
Post
3928
We collaborated with NVIDIA to teach you about Reinforcement Learning and RL environments. 💚 Learn:

• Why RL environments matter + how to build them
• When RL is better than SFT
• GRPO and RL best practices
• How verifiable rewards and RLVR work

Blog: https://unsloth.ai/blog/rl-environments
  • 4 replies
·
clefourrier 
authored a paper about 2 months ago
danielhanchen 
posted an update 2 months ago
view post
Post
3457
100,000+ models trained with Unsloth have now been open-sourced on 🤗Hugging Face! 🦥

Here are the most popular ones you can run local:
1. TeichAI - GLM-4.7-Flash distilled from Claude 4.5 Opus (high)
2. Zed - Qwen Coder 7B fine-tuned for stronger coding
3. DavidAU - Llama-3.3-8B distilled from Claude 4.5 Opus (high)
4. huihui - gpt-oss made “abliberated”

Links to models:
1. TeichAI: TeichAI/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-GGUF
2. Zed: zed-industries/zeta
3. DavidAU: DavidAU/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning
4. huihui: huihui-ai/Huihui-gpt-oss-20b-BF16-abliterated

See all the 100K latest models fine-tuned with Unsloth here: https://huggingface.co/models?other=u
  • 2 replies
·
danielhanchen 
posted an update 2 months ago
danielhanchen 
posted an update 3 months ago
view post
Post
5222
We collaborated with Hugging Face to enable you to train MoE models 12× faster with 35% less VRAM via our new Triton kernels (no accuracy loss). 🤗

Train gpt-oss locally on 12.8GB VRAM with our free notebooks: https://unsloth.ai/docs/new/faster-moe
  • 1 reply
·
danielhanchen 
posted an update 3 months ago
mlabonne 
authored 2 papers 3 months ago
danielhanchen 
posted an update 3 months ago
view post
Post
2650
You can now fine-tune embedding models in our free Unsloth notebook! 🤗

Fine-tuning embedding models improves retrieval & RAG by aligning vectors to your domain-specific notion of similarity, improving search, clustering, and recommendations on your data.

⭐ Blog + Notebooks: https://unsloth.ai/docs/new/embedding-finetuning

Unsloth trains embedding models 1.8-3.3x faster with 20% less VRAM, 2x longer context & no accuracy loss vs. FA2 setups.

We'd like to thank Hugging Face and Unsloth contributor: electroglyph for making this possible!
  • 3 replies
·
danielhanchen 
posted an update 3 months ago
danielhanchen 
posted an update 3 months ago
view post
Post
2900
You can now do reinforcement learning training with 7× longer context and no accuracy loss, via our new batching algorithms.

Long reasoning chains in RL are costly, but now we enable you to train gpt-oss with GRPO & reach 380K context on a 192GB GPU.

Blog: https://unsloth.ai/docs/new/grpo-long-context