Introducing smolagents: simple agents that write actions in code.
•
232
Thomas Wolf PRO
thomwolf
AI & ML interests
NLP and open-source :-)
Recent Activity
updated
a Space
about 5 hours ago
science/README
liked
a model
1 day ago
deepseek-ai/DeepSeek-V3
Articles
Organizations
thomwolf's activity
reacted to
lewtun's
post with 🔥
about 21 hours ago
Post
1474
I was initially pretty sceptical about Meta's Coconut paper [1] because the largest perf gains were reported on toy linguistic problems. However, these results on machine translation are pretty impressive!
https://x.com/casper_hansen_/status/1875872309996855343
Together with the recent PRIME method [2] for scaling RL, reasoning for open models is looking pretty exciting for 2025!
[1] Training Large Language Models to Reason in a Continuous Latent Space (2412.06769)
[2] https://huggingface.co/blog/ganqu/prime
https://x.com/casper_hansen_/status/1875872309996855343
Together with the recent PRIME method [2] for scaling RL, reasoning for open models is looking pretty exciting for 2025!
[1] Training Large Language Models to Reason in a Continuous Latent Space (2412.06769)
[2] https://huggingface.co/blog/ganqu/prime
reacted to
julien-c's
post with 😎🤝👍🤗❤️🔥
27 days ago
Post
8025
After some heated discussion 🔥, we clarify our intent re. storage limits on the Hub
TL;DR:
- public storage is free, and (unless blatant abuse) unlimited. We do ask that you consider upgrading to PRO and/or Enterprise Hub if possible
- private storage is paid above a significant free tier (1TB if you have a paid account, 100GB otherwise)
docs: https://huggingface.co/docs/hub/storage-limits
We optimize our infrastructure continuously to scale our storage for the coming years of growth in Machine learning, to the benefit of the community 🔥
cc: @reach-vb @pierric @victor and the HF team
TL;DR:
- public storage is free, and (unless blatant abuse) unlimited. We do ask that you consider upgrading to PRO and/or Enterprise Hub if possible
- private storage is paid above a significant free tier (1TB if you have a paid account, 100GB otherwise)
docs: https://huggingface.co/docs/hub/storage-limits
We optimize our infrastructure continuously to scale our storage for the coming years of growth in Machine learning, to the benefit of the community 🔥
cc: @reach-vb @pierric @victor and the HF team
- 28 replies
posted
an
update
29 days ago
Post
4572
We are proud to announce
HuggingFaceFW/fineweb-2: A sparkling update to
HuggingFaceFW/fineweb with 1000s of 🗣️languages.
We applied the same data-driven approach that led to SOTA English performance in🍷 FineWeb to thousands of languages.
🥂 FineWeb2 has 8TB of compressed text data and outperforms other multilingual datasets in our experiments.
The dataset is released under the permissive 📜 ODC-By 1.0 license, and the 💻 code to reproduce it and our evaluations is public.
We will very soon announce a big community project, and are working on a 📝 blogpost walking you through the entire dataset creation process. Stay tuned!
In the mean time come ask us question on our chat place: HuggingFaceFW/discussion
H/t @guipenedo @hynky @lvwerra as well as @vsabolcec Bettina Messmer @negar-foroutan and @mjaggi
We applied the same data-driven approach that led to SOTA English performance in🍷 FineWeb to thousands of languages.
🥂 FineWeb2 has 8TB of compressed text data and outperforms other multilingual datasets in our experiments.
The dataset is released under the permissive 📜 ODC-By 1.0 license, and the 💻 code to reproduce it and our evaluations is public.
We will very soon announce a big community project, and are working on a 📝 blogpost walking you through the entire dataset creation process. Stay tuned!
In the mean time come ask us question on our chat place: HuggingFaceFW/discussion
H/t @guipenedo @hynky @lvwerra as well as @vsabolcec Bettina Messmer @negar-foroutan and @mjaggi
- 2 replies
reacted to
garrethlee's
post with ❤️🔥
about 1 month ago
Post
1911
The latest o1 model from OpenAI is still unable to answer 9.11 > 9.9 correctly 🤔
A possible explanation? Tokenization - and our latest work investigates how it affects a model's ability to do math!
In this blog post, we discuss:
🔢 The different ways numbers are tokenized in modern LLMs
🧪 Our detailed approach in comparing these various methods
🥪 How we got a free boost in arithmetic performance by adding a few lines of code to the base Llama 3 tokenizer
👑 and a definitive, best tokenization method for math in LLMs!
Check out our work here: huggingface/number-tokenization-blog
A possible explanation? Tokenization - and our latest work investigates how it affects a model's ability to do math!
In this blog post, we discuss:
🔢 The different ways numbers are tokenized in modern LLMs
🧪 Our detailed approach in comparing these various methods
🥪 How we got a free boost in arithmetic performance by adding a few lines of code to the base Llama 3 tokenizer
👑 and a definitive, best tokenization method for math in LLMs!
Check out our work here: huggingface/number-tokenization-blog
-
- 2 replies
posted
an
update
about 1 month ago
Post
1030
Exponentially growing number of open-source AI models over the course of the past 30 months – from a few thousands to over 1 million and more
Interactive data viz: huggingface/open-source-ai-year-in-review-2024
Interactive data viz: huggingface/open-source-ai-year-in-review-2024
posted
an
update
about 1 month ago
Post
1411
Most liked and most downloaded open-source AI models from 2022 to 2024
Interactive viz: https://aiworld.eu/embed/model/model/treemap
Discussion: huggingface/open-source-ai-year-in-review-2024
Interactive viz: https://aiworld.eu/embed/model/model/treemap
Discussion: huggingface/open-source-ai-year-in-review-2024
reacted to
m-ric's
post with 🚀🔥
about 1 month ago
Post
1277
🤖 𝗔𝗱𝗼𝗯𝗲'𝘀 𝗰𝗼𝗱𝗲-𝗴𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗻𝗴 𝗮𝗴𝗲𝗻𝘁 𝗿𝗲𝗮𝗰𝗵𝗲𝘀 𝘁𝗵𝗲 𝘁𝗼𝗽 𝗼𝗳 𝗚𝗔𝗜𝗔 𝗹𝗲𝗮𝗱𝗲𝗿𝗯𝗼𝗮𝗿𝗱 - and their paper cites my work!
💡 Reminder: In short, Agentic systems are a vehicle in which you put your LLM to allow it access to the outside world.
➡️ The team of researchers at Adobe started from the idea that current agentic systems lack the ability to define their own tools. So they decided to make an agent that writes actions as code, thus allowing it to write python functions that can be re-used later as tools!
Here's what the LLM generations can look like with the proper prompt:
Thought: I need to access the excel file using a different method.
Action:
Then your system executes this and appends the observation to the agent's memory.
Why is this code formulation better than classical tool use formulation as JSON? The paper explains:
"Most existing work uses text or JSON as the representation of actions, which significantly lacks the two criteria mentioned earlier: generality and composability. In contrast, DynaSaur can utilize available actions or create new ones if necessary, using code as a unified representation. In principle, acting with code enables agents to solve any Turing-complete problem."
The idea of using code is not new: in fact, we do it in transformers.agents (thus the citation that I got). They implementation adds further refinements, like using RAG to retrieve relevant functions before generating an action, which increases performance further.
And they observe that code agents perform much better, reaching the top of GAIA leaderboard! 🥇
Go take a look, it's really clear and informative!
Paper added to my agents collection 👉 m-ric/agents-65ba776fbd9e29f771c07d4e
💡 Reminder: In short, Agentic systems are a vehicle in which you put your LLM to allow it access to the outside world.
➡️ The team of researchers at Adobe started from the idea that current agentic systems lack the ability to define their own tools. So they decided to make an agent that writes actions as code, thus allowing it to write python functions that can be re-used later as tools!
Here's what the LLM generations can look like with the proper prompt:
Thought: I need to access the excel file using a different method.
Action:
def access_excel_file(file_path)
... # rest of the code (the agent does writes it, but I don't have room in this post)
return rowsThen your system executes this and appends the observation to the agent's memory.
Why is this code formulation better than classical tool use formulation as JSON? The paper explains:
"Most existing work uses text or JSON as the representation of actions, which significantly lacks the two criteria mentioned earlier: generality and composability. In contrast, DynaSaur can utilize available actions or create new ones if necessary, using code as a unified representation. In principle, acting with code enables agents to solve any Turing-complete problem."
The idea of using code is not new: in fact, we do it in transformers.agents (thus the citation that I got). They implementation adds further refinements, like using RAG to retrieve relevant functions before generating an action, which increases performance further.
And they observe that code agents perform much better, reaching the top of GAIA leaderboard! 🥇
Go take a look, it's really clear and informative!
Paper added to my agents collection 👉 m-ric/agents-65ba776fbd9e29f771c07d4e
reacted to
merve's
post with 🔥👍
about 1 month ago
Post
2183
The authors of ColPali trained a retrieval model based on SmolVLM 🤠
vidore/colsmolvlm-alpha
TLDR;
- ColSmolVLM performs better than ColPali and DSE-Qwen2 on all English tasks
- ColSmolVLM is more memory efficient than ColQwen2 💗
TLDR;
- ColSmolVLM performs better than ColPali and DSE-Qwen2 on all English tasks
- ColSmolVLM is more memory efficient than ColQwen2 💗
reacted to
davanstrien's
post with ❤️
about 1 month ago
Post
2482
First dataset for the new Hugging Face Bluesky community organisation:
bluesky-community/one-million-bluesky-posts 🦋
📊 1M public posts from Bluesky's firehose API
🔍 Includes text, metadata, and language predictions
🔬 Perfect to experiment with using ML for Bluesky 🤗
Excited to see people build more open tools for a more open social media platform!
📊 1M public posts from Bluesky's firehose API
🔍 Includes text, metadata, and language predictions
🔬 Perfect to experiment with using ML for Bluesky 🤗
Excited to see people build more open tools for a more open social media platform!
reacted to
ZennyKenny's
post with 👍
about 1 month ago
Post
1211
I've joined the Bluesky community. Interested to see what decentralized social media looks like in action: https://bsky.app/profile/kghamilton.bsky.social
Looking forward to following other AI builders, tech enthusiasts, goth doomscrollers, and ironic meme creators.
Looking forward to following other AI builders, tech enthusiasts, goth doomscrollers, and ironic meme creators.
reacted to
as-cle-bert's
post with 🔥
about 1 month ago
Post
1264
Hi HuggingFacers!🤗
I'm thrilled to introduce my latest project: 𝗦𝗲𝗻𝗧𝗿𝗘𝘃 (𝗦𝗲𝗻tence 𝗧𝗿ansformers 𝗘𝘃aluator), a python package that offers simple customizable evaluation for text retrieval accuracy and time performance of Sentence Transformers-compatible text embedders on PDF data!📊
Learn more in my LinkedIn post: https://www.linkedin.com/posts/astra-clelia-bertelli-583904297_python-embedders-semanticsearch-activity-7266754133557190656-j1e3
And on the GitHub repo: https://github.com/AstraBert/SenTrEv
Have fun!🍕
I'm thrilled to introduce my latest project: 𝗦𝗲𝗻𝗧𝗿𝗘𝘃 (𝗦𝗲𝗻tence 𝗧𝗿ansformers 𝗘𝘃aluator), a python package that offers simple customizable evaluation for text retrieval accuracy and time performance of Sentence Transformers-compatible text embedders on PDF data!📊
Learn more in my LinkedIn post: https://www.linkedin.com/posts/astra-clelia-bertelli-583904297_python-embedders-semanticsearch-activity-7266754133557190656-j1e3
And on the GitHub repo: https://github.com/AstraBert/SenTrEv
Have fun!🍕
posted
an
update
about 1 month ago
Post
1670
Interesting long read from
@evanmiller-anthropic
on having a better founded statistical approach to Language Model Evaluations:
https://www.anthropic.com/research/statistical-approach-to-model-evals
Worth a read if you're into LLM evaluations!
Cc @clefourrier
https://www.anthropic.com/research/statistical-approach-to-model-evals
Worth a read if you're into LLM evaluations!
Cc @clefourrier
- 1 reply