AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset
Paper
•
2504.16891
•
Published
•
18
EuroPython 2022
non-profit
AI & ML interests
None defined yet.
Recent Activity
View all activity
EuroPython2022's activity
darragh
authored
a
paper
4 days ago
albertvillanova
posted
an
update
7 days ago
Post
2307
smolagents v1.14.0 is out! 🚀
🔌 MCPClient: A sleek new client for connecting to remote MCP servers, making integrations more flexible and scalable.
🪨 Amazon Bedrock: Native support for Bedrock-hosted models.
SmolAgents is now more powerful, flexible, and enterprise-ready. 💼
Full release 👉 https://github.com/huggingface/smolagents/releases/tag/v1.14.0
#smolagents #LLM #AgenticAI
🔌 MCPClient: A sleek new client for connecting to remote MCP servers, making integrations more flexible and scalable.
🪨 Amazon Bedrock: Native support for Bedrock-hosted models.
SmolAgents is now more powerful, flexible, and enterprise-ready. 💼
Full release 👉 https://github.com/huggingface/smolagents/releases/tag/v1.14.0
#smolagents #LLM #AgenticAI
Post
1547
AI Vision & SFT Titans 🌟 Turns PDFs into text, snaps pics, and births AI art.
https://huggingface.co./spaces/awacke1/TorchTransformers-Diffusion-CV-SFT
1. OCR a grocery list or train a titan while sipping coffee? ☕
2. Camera Snap 📷: Capture life’s chaos—your cat’s face or that weird receipt. Proof you’re a spy!
3. OCR 🔍: PDFs beg for mercy as GPT-4o extracts text.
4. Image Gen 🎨: Prompt “neon superhero me”
5. PDF 📄: Double-page OCR Single-page sniping
Build Titans 🌱: Train tiny AI models. 💪Characters🧑🎨: Craft quirky heroes.
🎥
https://huggingface.co./spaces/awacke1/TorchTransformers-Diffusion-CV-SFT
1. OCR a grocery list or train a titan while sipping coffee? ☕
2. Camera Snap 📷: Capture life’s chaos—your cat’s face or that weird receipt. Proof you’re a spy!
3. OCR 🔍: PDFs beg for mercy as GPT-4o extracts text.
4. Image Gen 🎨: Prompt “neon superhero me”
5. PDF 📄: Double-page OCR Single-page sniping
Build Titans 🌱: Train tiny AI models. 💪Characters🧑🎨: Craft quirky heroes.
🎥
Post
2285
I introduce MIT license
ML Model Specialize Fine Tuner app "SFT Tiny Titans" 🚀
Demo video with source.
Download, train, SFT, and test your models, easy as 1-2-3!
URL: awacke1/TorchTransformers-NLP-CV-SFT
ML Model Specialize Fine Tuner app "SFT Tiny Titans" 🚀
Demo video with source.
Download, train, SFT, and test your models, easy as 1-2-3!
URL: awacke1/TorchTransformers-NLP-CV-SFT
- 2 replies
ValeKnappich
authored
a
paper
about 2 months ago
albertvillanova
posted
an
update
about 2 months ago
Post
3985
🚀 New smolagents update: Safer Local Python Execution! 🦾🐍
With the latest release, we've added security checks to the local Python interpreter: every evaluation is now analyzed for dangerous builtins, modules, and functions. 🔒
Here's why this matters & what you need to know! 🧵👇
1️⃣ Why is local execution risky? ⚠️
AI agents that run arbitrary Python code can unintentionally (or maliciously) access system files, run unsafe commands, or exfiltrate data.
2️⃣ New Safety Layer in smolagents 🛡️
We now inspect every return value during execution:
✅ Allowed: Safe built-in types (e.g., numbers, strings, lists)
⛔ Blocked: Dangerous functions/modules (e.g., os.system, subprocess, exec, shutil)
3️⃣ Immediate Benefits 💡
- Prevent agents from accessing unsafe builtins
- Block unauthorized file or network access
- Reduce accidental security vulnerabilities
4️⃣ Security Disclaimer ⚠️
🚨 Despite these improvements, local Python execution is NEVER 100% safe. 🚨
If you need true isolation, use a remote sandboxed executor like Docker or E2B.
5️⃣ The Best Practice: Use Sandboxed Execution 🔐
For production-grade AI agents, we strongly recommend running code in a Docker or E2B sandbox to ensure complete isolation.
6️⃣ Upgrade Now & Stay Safe! 🚀
Check out the latest smolagents release and start building safer AI agents today.
🔗 https://github.com/huggingface/smolagents
What security measures do you take when running AI-generated code? Let’s discuss! 👇
#AI #smolagents #Python #Security
With the latest release, we've added security checks to the local Python interpreter: every evaluation is now analyzed for dangerous builtins, modules, and functions. 🔒
Here's why this matters & what you need to know! 🧵👇
1️⃣ Why is local execution risky? ⚠️
AI agents that run arbitrary Python code can unintentionally (or maliciously) access system files, run unsafe commands, or exfiltrate data.
2️⃣ New Safety Layer in smolagents 🛡️
We now inspect every return value during execution:
✅ Allowed: Safe built-in types (e.g., numbers, strings, lists)
⛔ Blocked: Dangerous functions/modules (e.g., os.system, subprocess, exec, shutil)
3️⃣ Immediate Benefits 💡
- Prevent agents from accessing unsafe builtins
- Block unauthorized file or network access
- Reduce accidental security vulnerabilities
4️⃣ Security Disclaimer ⚠️
🚨 Despite these improvements, local Python execution is NEVER 100% safe. 🚨
If you need true isolation, use a remote sandboxed executor like Docker or E2B.
5️⃣ The Best Practice: Use Sandboxed Execution 🔐
For production-grade AI agents, we strongly recommend running code in a Docker or E2B sandbox to ensure complete isolation.
6️⃣ Upgrade Now & Stay Safe! 🚀
Check out the latest smolagents release and start building safer AI agents today.
🔗 https://github.com/huggingface/smolagents
What security measures do you take when running AI-generated code? Let’s discuss! 👇
#AI #smolagents #Python #Security
- 2 replies
ZhangYuanhan
authored
a
paper
about 2 months ago
taesiri
authored
a
paper
about 2 months ago
albertvillanova
posted
an
update
about 2 months ago
Post
3918
🚀 Big news for AI agents! With the latest release of smolagents, you can now securely execute Python code in sandboxed Docker or E2B environments. 🦾🔒
Here's why this is a game-changer for agent-based systems: 🧵👇
1️⃣ Security First 🔐
Running AI agents in unrestricted Python environments is risky! With sandboxing, your agents are isolated, preventing unintended file access, network abuse, or system modifications.
2️⃣ Deterministic & Reproducible Runs 📦
By running agents in containerized environments, you ensure that every execution happens in a controlled and predictable setting—no more environment mismatches or dependency issues!
3️⃣ Resource Control & Limits 🚦
Docker and E2B allow you to enforce CPU, memory, and execution time limits, so rogue or inefficient agents don’t spiral out of control.
4️⃣ Safer Code Execution in Production 🏭
Deploy AI agents confidently, knowing that any generated code runs in an ephemeral, isolated environment, protecting your host machine and infrastructure.
5️⃣ Easy to Integrate 🛠️
With smolagents, you can simply configure your agent to use Docker or E2B as its execution backend—no need for complex security setups!
6️⃣ Perfect for Autonomous AI Agents 🤖
If your AI agents generate and execute code dynamically, this is a must-have to avoid security pitfalls while enabling advanced automation.
⚡ Get started now: https://github.com/huggingface/smolagents
What will you build with smolagents? Let us know! 🚀💡
Here's why this is a game-changer for agent-based systems: 🧵👇
1️⃣ Security First 🔐
Running AI agents in unrestricted Python environments is risky! With sandboxing, your agents are isolated, preventing unintended file access, network abuse, or system modifications.
2️⃣ Deterministic & Reproducible Runs 📦
By running agents in containerized environments, you ensure that every execution happens in a controlled and predictable setting—no more environment mismatches or dependency issues!
3️⃣ Resource Control & Limits 🚦
Docker and E2B allow you to enforce CPU, memory, and execution time limits, so rogue or inefficient agents don’t spiral out of control.
4️⃣ Safer Code Execution in Production 🏭
Deploy AI agents confidently, knowing that any generated code runs in an ephemeral, isolated environment, protecting your host machine and infrastructure.
5️⃣ Easy to Integrate 🛠️
With smolagents, you can simply configure your agent to use Docker or E2B as its execution backend—no need for complex security setups!
6️⃣ Perfect for Autonomous AI Agents 🤖
If your AI agents generate and execute code dynamically, this is a must-have to avoid security pitfalls while enabling advanced automation.
⚡ Get started now: https://github.com/huggingface/smolagents
What will you build with smolagents? Let us know! 🚀💡
Post
2480
🚀 Blast into the future with ZaxxonGalaxian – a thrilling 3D action game where you navigate epic battles through towering 3D cityscapes! Face off against relentless swarm bots, climb the leaderboard, and dominate the skies.
awacke1/ZaxxoGalaxian
taesiri
authored
a
paper
2 months ago
albertvillanova
posted
an
update
3 months ago
Post
3976
🚀 Introducing
@huggingface
Open Deep-Research💥
In just 24 hours, we built an open-source agent that:
✅ Autonomously browse the web
✅ Search, scroll & extract info
✅ Download & manipulate files
✅ Run calculations on data
55% on GAIA validation set! Help us improve it!💡
https://huggingface.co./blog/open-deep-research
In just 24 hours, we built an open-source agent that:
✅ Autonomously browse the web
✅ Search, scroll & extract info
✅ Download & manipulate files
✅ Run calculations on data
55% on GAIA validation set! Help us improve it!💡
https://huggingface.co./blog/open-deep-research
- 3 replies
ZhangYuanhan
authored
a
paper
3 months ago
Post
3201
Deep Research Evaluator was asked:
" design a coral defense mechanism that upon sensing say an acid that's causing coral reefs to have a carbon dioxide issue it develops... please create a plan and a design for this\n
"
It picks these three as best combined solution.
1. [Reef-insight: A framework for reef habitat mapping with clustering methods via remote sensing]...
2. Phone a friend: [Learning to Communicate and Collaborate in a Competitive Multi-Agent Setup to Clean the Ocean from Macroplastics]...
3. World Solve: [Dependence of Physiochemical Features on Marine Chlorophyll Analysis with Learning Techniques]
To design a system that allows coralows coral reefs to respond to increased acidity levels in their environment, we can create a network of pH sensors and dispersal units that can detect changes in pH levels and release a base solution to neutralize the acid.
1. pH Sensors: The first component of the system would be a network of pH sensors placed strategically throughout the coral reef. These sensors would be small, durable, and able to withstand the harsh conditions of the ocean. They would be placed at various depths and locations within the reef to ensure accurate and comprehensive monitoring of pH levels.
2. Base Dispersal Units: Once the pH sensors detect a decrease in pH levels, they would trigger the base dispersal units to release a base solution into the water. These units would be strategically placed around the reef and would be able to release a controlled amount of base solution to neutralize the acidity in the water.
3. Water Dispersal Mechanism: The base dispersal units would be connected to a water dispersal mechanism that would allow the base solution to be distributed evenly around the reef. This could be achieved through a series of pipes or channels that would distribute the base solution in a controlled and targeted manner.
" design a coral defense mechanism that upon sensing say an acid that's causing coral reefs to have a carbon dioxide issue it develops... please create a plan and a design for this\n
"
It picks these three as best combined solution.
1. [Reef-insight: A framework for reef habitat mapping with clustering methods via remote sensing]...
2. Phone a friend: [Learning to Communicate and Collaborate in a Competitive Multi-Agent Setup to Clean the Ocean from Macroplastics]...
3. World Solve: [Dependence of Physiochemical Features on Marine Chlorophyll Analysis with Learning Techniques]
To design a system that allows coralows coral reefs to respond to increased acidity levels in their environment, we can create a network of pH sensors and dispersal units that can detect changes in pH levels and release a base solution to neutralize the acid.
1. pH Sensors: The first component of the system would be a network of pH sensors placed strategically throughout the coral reef. These sensors would be small, durable, and able to withstand the harsh conditions of the ocean. They would be placed at various depths and locations within the reef to ensure accurate and comprehensive monitoring of pH levels.
2. Base Dispersal Units: Once the pH sensors detect a decrease in pH levels, they would trigger the base dispersal units to release a base solution into the water. These units would be strategically placed around the reef and would be able to release a controlled amount of base solution to neutralize the acidity in the water.
3. Water Dispersal Mechanism: The base dispersal units would be connected to a water dispersal mechanism that would allow the base solution to be distributed evenly around the reef. This could be achieved through a series of pipes or channels that would distribute the base solution in a controlled and targeted manner.
albertvillanova
posted
an
update
4 months ago
Post
2131
Discover all the improvements in the new version of Lighteval: https://huggingface.co./docs/lighteval/
Post
2687
LLMs and LRMs - Logical Reasoning and Chain of Thought.
This is a read-aloud lecture to answer questions of using language reasoning techniques in advanced AGI style chain of thought AI pipelines.
Produced using DeepResearchEvaluator located here: awacke1/DeepResearchEvaluator
Videos:
https://x.com/Aaron_Wacker/status/1874835790087463063
https://www.youtube.com/watch?v=fW_A1hH_7RM
This is a read-aloud lecture to answer questions of using language reasoning techniques in advanced AGI style chain of thought AI pipelines.
Produced using DeepResearchEvaluator located here: awacke1/DeepResearchEvaluator
Videos:
https://x.com/Aaron_Wacker/status/1874835790087463063
https://www.youtube.com/watch?v=fW_A1hH_7RM
- 1 reply
Post
17652
Google drops Gemini 2.0 Flash Thinking
a new experimental model that unlocks stronger reasoning capabilities and shows its thoughts. The model plans (with thoughts visible), can solve complex problems with Flash speeds, and more
now available in anychat, try it out: https://huggingface.co./spaces/akhaliq/anychat
a new experimental model that unlocks stronger reasoning capabilities and shows its thoughts. The model plans (with thoughts visible), can solve complex problems with Flash speeds, and more
now available in anychat, try it out: https://huggingface.co./spaces/akhaliq/anychat
- 4 replies
Post
17669
QwQ-32B-Preview is now available in anychat
A reasoning model that is competitive with OpenAI o1-mini and o1-preview
try it out: https://huggingface.co./spaces/akhaliq/anychat
A reasoning model that is competitive with OpenAI o1-mini and o1-preview
try it out: https://huggingface.co./spaces/akhaliq/anychat
- 1 reply
Post
4461
New model drop in anychat
allenai/Llama-3.1-Tulu-3-8B is now available
try it here: https://huggingface.co./spaces/akhaliq/anychat
allenai/Llama-3.1-Tulu-3-8B is now available
try it here: https://huggingface.co./spaces/akhaliq/anychat
Post
3335
anychat
supports chatgpt, gemini, perplexity, claude, meta llama, grok all in one app
try it out there: https://huggingface.co./spaces/akhaliq/anychat
supports chatgpt, gemini, perplexity, claude, meta llama, grok all in one app
try it out there: https://huggingface.co./spaces/akhaliq/anychat