Introducing smolagents: simple agents that write actions in code.
•
384
Aymeric Roucher
m-ric
AI & ML interests
Leading Agents at Hugging Face 🤗
Recent Activity
updated
a Space
1 day ago
m-ric/get-travel-duration-tool
updated
a Space
2 days ago
m-ric/hf-model-downloads
liked
a Space
3 days ago
leonard-dls/benchmark_data_contamination
Articles
Organizations
Posts
81
Post
4746
Since I published it on GitHub a few days ago,
Hugging Face's new agentic library 𝘀𝗺𝗼𝗹𝗮𝗴𝗲𝗻𝘁𝘀 has gathered nearly 4k stars 🤯
➡️ But we are just getting started on agents: so we are hiring an ML Engineer to join me and double down on this effort!
The plan is to build GUI agents: agents that can act on your computer with mouse & keyboard, like Claude Computer Use.
We will make it work better, and fully open. ✨
Sounds like something you'd like to do? Apply here 👉 https://apply.workable.com/huggingface/j/AF1D4E3FEB/
Hugging Face's new agentic library 𝘀𝗺𝗼𝗹𝗮𝗴𝗲𝗻𝘁𝘀 has gathered nearly 4k stars 🤯
➡️ But we are just getting started on agents: so we are hiring an ML Engineer to join me and double down on this effort!
The plan is to build GUI agents: agents that can act on your computer with mouse & keyboard, like Claude Computer Use.
We will make it work better, and fully open. ✨
Sounds like something you'd like to do? Apply here 👉 https://apply.workable.com/huggingface/j/AF1D4E3FEB/
Post
2278
After 6 years, BERT, the workhorse of encoder models, finally gets a replacement: 𝗪𝗲𝗹𝗰𝗼𝗺𝗲 𝗠𝗼𝗱𝗲𝗿𝗻𝗕𝗘𝗥𝗧! 🤗
We talk a lot about ✨Generative AI✨, meaning "Decoder version of the Transformers architecture", but this is only one of the ways to build LLMs: encoder models, that turn a sentence in a vector, are maybe even more widely used in industry than generative models.
The workhorse for this category has been BERT since its release in 2018 (that's prehistory for LLMs).
It's not a fancy 100B parameters supermodel (just a few hundred millions), but it's an excellent workhorse, kind of a Honda Civic for LLMs.
Many applications use BERT-family models - the top models in this category cumulate millions of downloads on the Hub.
➡️ Now a collaboration between Answer.AI and LightOn just introduced BERT's replacement: ModernBERT.
𝗧𝗟;𝗗𝗥:
🏛️ Architecture changes:
⇒ First, standard modernizations:
- Rotary positional embeddings (RoPE)
- Replace GeLU with GeGLU,
- Use Flash Attention 2
✨ The team also introduced innovative techniques like alternating attention instead of full attention, and sequence packing to get rid of padding overhead.
🥇 As a result, the model tops the game of encoder models:
It beats previous standard DeBERTaV3 for 1/5th the memory footprint, and runs 4x faster!
Read the blog post 👉 https://huggingface.co/blog/modernbert
We talk a lot about ✨Generative AI✨, meaning "Decoder version of the Transformers architecture", but this is only one of the ways to build LLMs: encoder models, that turn a sentence in a vector, are maybe even more widely used in industry than generative models.
The workhorse for this category has been BERT since its release in 2018 (that's prehistory for LLMs).
It's not a fancy 100B parameters supermodel (just a few hundred millions), but it's an excellent workhorse, kind of a Honda Civic for LLMs.
Many applications use BERT-family models - the top models in this category cumulate millions of downloads on the Hub.
➡️ Now a collaboration between Answer.AI and LightOn just introduced BERT's replacement: ModernBERT.
𝗧𝗟;𝗗𝗥:
🏛️ Architecture changes:
⇒ First, standard modernizations:
- Rotary positional embeddings (RoPE)
- Replace GeLU with GeGLU,
- Use Flash Attention 2
✨ The team also introduced innovative techniques like alternating attention instead of full attention, and sequence packing to get rid of padding overhead.
🥇 As a result, the model tops the game of encoder models:
It beats previous standard DeBERTaV3 for 1/5th the memory footprint, and runs 4x faster!
Read the blog post 👉 https://huggingface.co/blog/modernbert
Collections
14
-
Scaling Autoregressive Models for Content-Rich Text-to-Image Generation
Paper • 2206.10789 • Published • 4 -
Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Laws
Paper • 2401.00448 • Published • 28 -
Training Compute-Optimal Large Language Models
Paper • 2203.15556 • Published • 10 -
Scaling Laws for Neural Language Models
Paper • 2001.08361 • Published • 7
spaces
27
pinned
Running
69
🗺️🏕️
AI Travel Planner
Plan your next vacation with the help of an AI!
pinned
Running
192
🍫👀
Chunk Visualizer
Pick a text splitter => visualize chunks. Great for RAG.
pinned
Running
on
Zero
124
✍👀
Beam Search Visualizer
View how beam search decoding works, in detail!
pinned
Running
111
🤔📊
Agent Data Analyst
Need to analyze data? Let a Llama-3.1 agent do it for you!
Running
9
📈
Get Travel Duration Tool
Running
3
🏢
Hf Model Downloads
models
3
datasets
18
m-ric/smol_agents_benchmark
Viewer
•
Updated
•
132
•
25
m-ric/agents_medium_benchmark_3
Viewer
•
Updated
•
132
•
6
m-ric/agents_medium_benchmark_2
Viewer
•
Updated
•
142
•
142
•
7
m-ric/agents_medium_benchmark
Viewer
•
Updated
•
172
•
96
•
3
m-ric/newsletter
Updated
•
29
m-ric/songs_july_24
Viewer
•
Updated
•
85.6k
•
32
m-ric/huggingface_doc_qa_eval
Viewer
•
Updated
•
65
•
208
•
9
m-ric/songs
Preview
•
Updated
•
7
m-ric/rag_scores_cookbook
Viewer
•
Updated
•
5
•
60
m-ric/images
Viewer
•
Updated
•
1
•
12