2 16 89

Alberto Cetoli PRO

fractalego

https://fractalego.social/@alberto

AI & ML interests

Entity/relation extraction, Q&A, Summarisation

Recent Activity

reacted to burtenshaw's post with 🔥 2 days ago

Now the Hugging Face agent course is getting real! With frameworks like smolagents, LlamaIndex, and LangChain. 🔗 Follow the org for updates https://huggingface.co./agents-course This week we are releasing the first framework unit in the course and it’s on smolagents. This is what the unit covers: - why should you use smolagents vs another library? - how to build agents that use code - build multiagents systems - use vision language models for browser use The team has been working flat out on this for a few weeks. Led by @sergiopaniego and supported by smolagents author @m-ric.

upvoted an article 2 days ago

FastRTC: The Real-Time Communication Library for Python

liked a Space 9 days ago

nanotron/ultrascale-playbook

View all activity

Organizations

fractalego's activity

reacted to burtenshaw's post with 🔥 2 days ago

Post

5405

Now the Hugging Face agent course is getting real! With frameworks like smolagents, LlamaIndex, and LangChain.

🔗 Follow the org for updates https://huggingface.co./agents-course

This week we are releasing the first framework unit in the course and it’s on smolagents. This is what the unit covers:

- why should you use smolagents vs another library?
- how to build agents that use code
- build multiagents systems
- use vision language models for browser use

The team has been working flat out on this for a few weeks. Led by @sergiopaniego and supported by smolagents author @m-ric .

upvoted an article 2 days ago

Article

FastRTC: The Real-Time Communication Library for Python

4 days ago

• 96

liked a Space 9 days ago

1.78k

The Ultra-Scale Playbook

🌌

The ultimate guide to training LLM on large GPU Clusters

liked a model 12 days ago

NousResearch/DeepHermes-3-Llama-3-8B-Preview

Text Generation • Updated 9 days ago • 9.38k • 264

reacted to csabakecskemeti's post with 👍 12 days ago

Post

1615

I found if we apply the reasoning system prompt (that has been published on the NousResearch/DeepHermes-3-Llama-3-8B-Preview model card) other models are also react to it and start mimicking reasoning. Some better some worse. I've seen internal monologue and self questioning.

Here's a blogpost about it:
http://devquasar.com/ai/reasoning-system-prompt/

reacted to mmhamdy's post with 👍 14 days ago

Post

2961

⛓ Evaluating Long Context #2: SCROLLS and ZeroSCROLLS

In this series of posts about tracing the history of long context evaluation, we started with Long Range Arena (LRA). Introduced in 2020, Long Range Arens (LRA) is one of the earliest benchmarks designed to tackle the challenge of long context evaluation. But it wasn't introduced to evaluate LLMs, but rather the transformer architecture in general.

📜 The SCROLLS benchmark, introduced in 2022, addresses this gap in NLP/LLM research. SCROLLS challenges models with tasks that require reasoning over extended sequences (according to 2022 standards). So, what does it offer?

1️⃣ Long Text Focus: SCROLLS (unlike LRA) focus mainly on text and contain inputs with thousands of words, testing models' ability to synthesize information across lengthy documents.
2️⃣ Diverse Tasks: Includes summarization, question answering, and natural language inference across domains like literature, science, and business.
3️⃣ Unified Format: All datasets are available in a text-to-text format, facilitating easy evaluation and comparison of models.

Building on SCROLLS, ZeroSCROLLS takes long text evaluation to the next level by focusing on zero-shot learning. Other features include:

1️⃣ New Tasks: Introduces tasks like sentiment aggregation and sorting book chapter summaries.
2️⃣ Leaderboard: A live leaderboard encourages continuous improvement and competition among researchers.

💡 What are some other landmark benchmarks in the history of long context evaluation? Feel free to share your thoughts and suggestions in the comments.

- SCROLLS Paper: SCROLLS: Standardized CompaRison Over Long Language Sequences (2201.03533)
- ZeroSCROLLS Paper: ZeroSCROLLS: A Zero-Shot Benchmark for Long Text Understanding (2305.14196)

liked a dataset 15 days ago

open-thoughts/OpenThoughts-114k

Viewer • Updated 8 days ago • 228k • 115k • 621

liked a model 18 days ago

Zyphra/Zonos-v0.1-hybrid

Text-to-Speech • Updated 13 days ago • 52.4k • 1.01k

liked a model 26 days ago

Almawave/Velvet-14B

Text Generation • Updated 8 days ago • 5.89k • 126

upvoted an article 26 days ago

Article

Open-R1: Update #1

and 7 others •

27 days ago

• 289

liked a model 27 days ago

iGeniusAI/Italia-9B-Instruct-v0.1

Text Generation • Updated Jul 23, 2024 • 8.73k • 50

upvoted an article 29 days ago

Article

ColPali: Efficient Document Retrieval with Vision Language Models 👀

•

Jul 5, 2024

• 208

upvoted 2 papers about 1 month ago

DeepSeek-V3 Technical Report

Paper • 2412.19437 • Published Dec 27, 2024 • 53

Towards Best Practices for Open Datasets for LLM Training

Paper • 2501.08365 • Published Jan 14 • 55

upvoted an article about 1 month ago

Article

Visualize and understand GPU memory in PyTorch

Dec 24, 2024

• 188

liked a dataset about 2 months ago

liminghao1630/TableBank

Updated Aug 11, 2024 • 391 • 9

liked a model about 2 months ago

stabilityai/stable-video-diffusion-img2vid-xt

Image-to-Video • Updated Jul 10, 2024 • 588k • 2.91k

reacted to mitkox's post with 🤯🔥➕ about 2 months ago

Post

2482

Can it run DeepSeek V3 671B is the new 'can it run Doom'.

How minimalistic can I go with on device AI with behemoth models - here I'm running DeepSeek V3 MoE on a single A6000 GPU.

Not great, not terrible, for this minimalistic setup. I love the Mixture of Experts architectures. Typically I'm running my core LLM distributed over the 4 GPUs.

Make sure you own your AI. AI in the cloud is not aligned with you; it's aligned with the company that owns it.

5 replies