Helsinki-NLP/tatoeba_mt_full
Updated
โข
575
Language Technology Research Group at the University of Helsinki
university
AI & ML interests
At the University of Helsinki, we focus on: - NLP for morphologically-rich languages - Cross-lingual NLP - NLP in the humanities
Recent Activity
Helsinki-NLP's activity
michal-stefanikย
updated
a
dataset
about 2 hours ago
odegiberย
authored
6
papers
6 days ago
Are Multilingual Models the Best Choice for Moderately Under-resourced Languages? A Comprehensive Assessment for Catalan
Paper
โข
2107.07903
โข
Published
Spanish Biomedical Crawled Corpus: A Large, Diverse Dataset for Spanish Biomedical Language Models
Paper
โข
2109.07765
โข
Published
The Catalan Language CLUB
Paper
โข
2112.01894
โข
Published
Sequence-to-Sequence Resources for Catalan
Paper
โข
2202.06871
โข
Published
A New Massive Multilingual Dataset for High-Performance Language Technologies
Paper
โข
2403.14009
โข
Published
โข
1
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
Paper
โข
2211.05100
โข
Published
โข
31
tiedemanย
authored
a
paper
6 days ago
odegiberย
authored
a
paper
6 days ago
albertvillanovaย
posted
an
update
18 days ago
Post
3673
๐ New smolagents update: Safer Local Python Execution! ๐ฆพ๐
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. ๐
Here's why this matters & what you need to know! ๐งต๐
1๏ธโฃ Why is local execution risky? โ ๏ธ
AI agents that run arbitrary Python code can unintentionally (or maliciously) access system files, run unsafe commands, or exfiltrate data.
2๏ธโฃ New Safety Layer in smolagents ๐ก๏ธ
We now inspect every return value during execution:
โ Allowed: Safe built-in types (e.g., numbers, strings, lists)
โ Blocked: Dangerous functions/modules (e.g., os.system, subprocess, exec, shutil)
3๏ธโฃ Immediate Benefits ๐ก
- Prevent agents from accessing unsafe builtins
- Block unauthorized file or network access
- Reduce accidental security vulnerabilities
4๏ธโฃ Security Disclaimer โ ๏ธ
๐จ Despite these improvements, local Python execution is NEVER 100% safe. ๐จ
If you need true isolation, use a remote sandboxed executor like Docker or E2B.
5๏ธโฃ The Best Practice: Use Sandboxed Execution ๐
For production-grade AI agents, we strongly recommend running code in a Docker or E2B sandbox to ensure complete isolation.
6๏ธโฃ Upgrade Now & Stay Safe! ๐
Check out the latest smolagents release and start building safer AI agents today.
๐ https://github.com/huggingface/smolagents
What security measures do you take when running AI-generated code? Letโs discuss! ๐
#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. ๐
Here's why this matters & what you need to know! ๐งต๐
1๏ธโฃ Why is local execution risky? โ ๏ธ
AI agents that run arbitrary Python code can unintentionally (or maliciously) access system files, run unsafe commands, or exfiltrate data.
2๏ธโฃ New Safety Layer in smolagents ๐ก๏ธ
We now inspect every return value during execution:
โ Allowed: Safe built-in types (e.g., numbers, strings, lists)
โ Blocked: Dangerous functions/modules (e.g., os.system, subprocess, exec, shutil)
3๏ธโฃ Immediate Benefits ๐ก
- Prevent agents from accessing unsafe builtins
- Block unauthorized file or network access
- Reduce accidental security vulnerabilities
4๏ธโฃ Security Disclaimer โ ๏ธ
๐จ Despite these improvements, local Python execution is NEVER 100% safe. ๐จ
If you need true isolation, use a remote sandboxed executor like Docker or E2B.
5๏ธโฃ The Best Practice: Use Sandboxed Execution ๐
For production-grade AI agents, we strongly recommend running code in a Docker or E2B sandbox to ensure complete isolation.
6๏ธโฃ Upgrade Now & Stay Safe! ๐
Check out the latest smolagents release and start building safer AI agents today.
๐ https://github.com/huggingface/smolagents
What security measures do you take when running AI-generated code? Letโs discuss! ๐
#AI #smolagents #Python #Security
- 2 replies
albertvillanovaย
posted
an
update
19 days ago
Post
3838
๐ Big news for AI agents! With the latest release of smolagents, you can now securely execute Python code in sandboxed Docker or E2B environments. ๐ฆพ๐
Here's why this is a game-changer for agent-based systems: ๐งต๐
1๏ธโฃ Security First ๐
Running AI agents in unrestricted Python environments is risky! With sandboxing, your agents are isolated, preventing unintended file access, network abuse, or system modifications.
2๏ธโฃ Deterministic & Reproducible Runs ๐ฆ
By running agents in containerized environments, you ensure that every execution happens in a controlled and predictable settingโno more environment mismatches or dependency issues!
3๏ธโฃ Resource Control & Limits ๐ฆ
Docker and E2B allow you to enforce CPU, memory, and execution time limits, so rogue or inefficient agents donโt spiral out of control.
4๏ธโฃ Safer Code Execution in Production ๐ญ
Deploy AI agents confidently, knowing that any generated code runs in an ephemeral, isolated environment, protecting your host machine and infrastructure.
5๏ธโฃ Easy to Integrate ๐ ๏ธ
With smolagents, you can simply configure your agent to use Docker or E2B as its execution backendโno need for complex security setups!
6๏ธโฃ Perfect for Autonomous AI Agents ๐ค
If your AI agents generate and execute code dynamically, this is a must-have to avoid security pitfalls while enabling advanced automation.
โก Get started now: https://github.com/huggingface/smolagents
What will you build with smolagents? Let us know! ๐๐ก
Here's why this is a game-changer for agent-based systems: ๐งต๐
1๏ธโฃ Security First ๐
Running AI agents in unrestricted Python environments is risky! With sandboxing, your agents are isolated, preventing unintended file access, network abuse, or system modifications.
2๏ธโฃ Deterministic & Reproducible Runs ๐ฆ
By running agents in containerized environments, you ensure that every execution happens in a controlled and predictable settingโno more environment mismatches or dependency issues!
3๏ธโฃ Resource Control & Limits ๐ฆ
Docker and E2B allow you to enforce CPU, memory, and execution time limits, so rogue or inefficient agents donโt spiral out of control.
4๏ธโฃ Safer Code Execution in Production ๐ญ
Deploy AI agents confidently, knowing that any generated code runs in an ephemeral, isolated environment, protecting your host machine and infrastructure.
5๏ธโฃ Easy to Integrate ๐ ๏ธ
With smolagents, you can simply configure your agent to use Docker or E2B as its execution backendโno need for complex security setups!
6๏ธโฃ Perfect for Autonomous AI Agents ๐ค
If your AI agents generate and execute code dynamically, this is a must-have to avoid security pitfalls while enabling advanced automation.
โก Get started now: https://github.com/huggingface/smolagents
What will you build with smolagents? Let us know! ๐๐ก
Atnafuย
authored
a
paper
about 2 months ago
albertvillanovaย
posted
an
update
about 2 months ago
Post
3850
๐ Introducing
@huggingface
Open Deep-Research๐ฅ
In just 24 hours, we built an open-source agent that:
โ Autonomously browse the web
โ Search, scroll & extract info
โ Download & manipulate files
โ Run calculations on data
55% on GAIA validation set! Help us improve it!๐ก
https://huggingface.co/blog/open-deep-research
In just 24 hours, we built an open-source agent that:
โ Autonomously browse the web
โ Search, scroll & extract info
โ Download & manipulate files
โ Run calculations on data
55% on GAIA validation set! Help us improve it!๐ก
https://huggingface.co/blog/open-deep-research
- 3 replies
albertvillanovaย
posted
an
update
3 months ago
Post
2109
Discover all the improvements in the new version of Lighteval: https://huggingface.co/docs/lighteval/
aleraganatoย
authored
a
paper
4 months ago
albertvillanovaย
posted
an
update
4 months ago
Post
1820
๐จ How green is your model? ๐ฑ Introducing a new feature in the Comparator tool: Environmental Impact for responsible #LLM research!
๐ open-llm-leaderboard/comparator
Now, you can not only compare models by performance, but also by their environmental footprint!
๐ The Comparator calculates COโ emissions during evaluation and shows key model characteristics: evaluation score, number of parameters, architecture, precision, type... ๐ ๏ธ
Make informed decisions about your model's impact on the planet and join the movement towards greener AI!
๐ open-llm-leaderboard/comparator
Now, you can not only compare models by performance, but also by their environmental footprint!
๐ The Comparator calculates COโ emissions during evaluation and shows key model characteristics: evaluation score, number of parameters, architecture, precision, type... ๐ ๏ธ
Make informed decisions about your model's impact on the planet and join the movement towards greener AI!
Post
3583
Native tensor parallel has landed in transformers!!! https://github.com/huggingface/transformers/pull/34184 thanks a lot to the torch team for their support!
Contributions are welcome to support more models! ๐ฅ
Contributions are welcome to support more models! ๐ฅ
albertvillanovaย
posted
an
update
5 months ago
Post
1608
๐ New feature of the Comparator of the ๐ค Open LLM Leaderboard: now compare models with their base versions & derivatives (finetunes, adapters, etc.). Perfect for tracking how adjustments affect performance & seeing innovations in action. Dive deeper into the leaderboard!
๐ ๏ธ Here's how to use it:
1. Select your model from the leaderboard.
2. Load its model tree.
3. Choose any base & derived models (adapters, finetunes, merges, quantizations) for comparison.
4. Press Load.
See side-by-side performance metrics instantly!
Ready to dive in? ๐ Try the ๐ค Open LLM Leaderboard Comparator now! See how models stack up against their base versions and derivatives to understand fine-tuning and other adjustments. Easier model analysis for better insights! Check it out here: open-llm-leaderboard/comparator ๐
๐ ๏ธ Here's how to use it:
1. Select your model from the leaderboard.
2. Load its model tree.
3. Choose any base & derived models (adapters, finetunes, merges, quantizations) for comparison.
4. Press Load.
See side-by-side performance metrics instantly!
Ready to dive in? ๐ Try the ๐ค Open LLM Leaderboard Comparator now! See how models stack up against their base versions and derivatives to understand fine-tuning and other adjustments. Easier model analysis for better insights! Check it out here: open-llm-leaderboard/comparator ๐
albertvillanovaย
posted
an
update
5 months ago
Post
3193
๐ Exciting update! You can now compare multiple models side-by-side with the Hugging Face Open LLM Comparator! ๐
open-llm-leaderboard/comparator
Dive into multi-model evaluations, pinpoint the best model for your needs, and explore insights across top open LLMs all in one place. Ready to level up your model comparison game?
open-llm-leaderboard/comparator
Dive into multi-model evaluations, pinpoint the best model for your needs, and explore insights across top open LLMs all in one place. Ready to level up your model comparison game?
albertvillanovaย
posted
an
update
5 months ago
Post
1259
๐จ Instruct-tuning impacts models differently across families! Qwen2.5-72B-Instruct excels on IFEval but struggles with MATH-Hard, while Llama-3.1-70B-Instruct avoids MATH performance loss! Why? Can they follow the format in examples? ๐ Compare models:
open-llm-leaderboard/comparator