56 100 1306

NIONGOLO Chrys Fé-Marty PRO

Svngoku

AI & ML interests

African Culture, LLM, Fine-tuning & Quantization and i love experimenting Agentic RAGs & building synthetic datas

Recent Activity

reacted to albertvillanova's post with 🤗 about 14 hours ago

🚀 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

upvoted a paper about 14 hours ago

ProverbEval: Exploring LLM Evaluation Challenges for Low-resource Language Understanding

reacted to clem's post with ❤️ about 21 hours ago

10,000+ models based on Deepseek R1 have been publicly shared on Hugging Face! Which ones are your favorite ones: https://huggingface.co/models?sort=trending&search=r1. Truly game-changer!

View all activity

Organizations

Svngoku's activity

upvoted a paper about 14 hours ago

ProverbEval: Exploring LLM Evaluation Challenges for Low-resource Language Understanding

Paper • 2411.05049 • Published Nov 7, 2024 • 3

upvoted 2 articles 5 days ago

Article

Trace & Evaluate your Agent with Arize Phoenix

10 days ago

• 29

Article

A Deepdive into Aya Vision: Advancing the Frontier of Multilingual Multimodality

6 days ago

• 57

upvoted a paper 5 days ago

Qilin: A Multimodal Information Retrieval Dataset with APP-level User Sessions

Paper • 2503.00501 • Published 8 days ago • 11

upvoted a collection 12 days ago

olmOCR

Collection

olmOCR is a document recognition pipeline for efficiently converting documents into plain text. olmocr.allenai.org • 3 items • Updated 11 days ago • 89

upvoted a paper 20 days ago

Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning

Paper • 2502.06781 • Published 27 days ago • 60

upvoted a collection 25 days ago

OpenScholar_V1

Collection

The set of models, index, data associated with the paper "OpenScholar: Synthesizing Scientific Literature with Retrieval-Augmented LMs". • 8 items • Updated Nov 22, 2024 • 33

upvoted a paper 25 days ago

LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!

Paper • 2502.07374 • Published 26 days ago • 36

upvoted a collection about 1 month ago

Unsloth 4-bit Dynamic Quants

Collection

Unsloths Dynamic 4bit Quants selectively skips quantizing certain parameters; greatly improving accuracy while only using <10% more VRAM than BnB 4bit • 23 items • Updated 1 day ago • 56

upvoted an article about 1 month ago

Article

Open-source DeepResearch – Freeing our search agents

Feb 4

• 1.14k

upvoted a collection about 1 month ago

DeepSeek-R1-abliterated

Collection

7 items • Updated Jan 31 • 92

upvoted an article about 1 month ago

Article

We now support VLMs in smolagents!

Jan 24

• 91

upvoted 2 collections about 1 month ago

Qwen2.5-1M

Collection

The long-context version of Qwen2.5, supporting 1M-token context lengths • 3 items • Updated 11 days ago • 105

DeepSeek-R1

Collection

8 items • Updated Jan 21 • 567

upvoted 6 collections about 2 months ago