2 16 89

Alberto Cetoli PRO

fractalego

https://fractalego.social/@alberto

AI & ML interests

Entity/relation extraction, Q&A, Summarisation

Recent Activity

reacted to BrigitteTousi's post with 🔥 about 22 hours ago

LeRobot goes to driving school! 🚗🚗🚗 Hugging Face just announced a new collab with Yaak to bring the largest open-source self-driving dataset to LeRobot! Major kudos to HF's @cadene, as well as @sandhawalia, @Shnissen and the Yaak team! Check out the blog post here: https://huggingface.co/blog/lerobot-goes-to-driving-school

reacted to BrigitteTousi's post with 🚀 about 22 hours ago

reacted to csabakecskemeti's post with 🔥 12 days ago

Testing Training on AMD/ROCm the first time! I've got my hands on an AMD Instinct MI100. It's about the same price used as a V100 but on paper has more TOPS (V100 14TOPS vs MI100 23TOPS) also the HBM has faster clock so the memory bandwidth is 1.2TB/s. For quantized inference it's a beast (MI50 was also surprisingly fast) For LORA training with this quick test I could not make the bnb config works so I'm running the FT on the fill size model. Will share all the install, setup and setting I've learned in a blog post, together with the cooling shroud 3D design.

View all activity

Organizations

fractalego's activity

reacted to BrigitteTousi's post with 🔥🚀 about 22 hours ago

Post

2409

LeRobot goes to driving school! 🚗🚗🚗

Hugging Face just announced a new collab with Yaak to bring the largest open-source self-driving dataset to LeRobot!

Major kudos to HF's @cadene , as well as @sandhawalia , @Shnissen and the Yaak team!

Check out the blog post here: https://huggingface.co/blog/lerobot-goes-to-driving-school

1 reply

reacted to csabakecskemeti's post with 🔥 12 days ago

Post

2750

Testing Training on AMD/ROCm the first time!

I've got my hands on an AMD Instinct MI100. It's about the same price used as a V100 but on paper has more TOPS (V100 14TOPS vs MI100 23TOPS) also the HBM has faster clock so the memory bandwidth is 1.2TB/s.
For quantized inference it's a beast (MI50 was also surprisingly fast)

For LORA training with this quick test I could not make the bnb config works so I'm running the FT on the fill size model.

Will share all the install, setup and setting I've learned in a blog post, together with the cooling shroud 3D design.

8 replies

upvoted an article 12 days ago

Article

Open-R1: Update #1

and 7 others •

Feb 2

• 294

reacted to burtenshaw's post with 🔥 15 days ago

Post

6188

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 15 days ago

Article

FastRTC: The Real-Time Communication Library for Python

16 days ago

• 140

liked a Space 22 days ago

2.23k

The Ultra-Scale Playbook

🌌

The ultimate guide to training LLM on large GPU Clusters

liked a model 25 days ago

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

Text Generation • Updated 22 days ago • 15.7k • 291

reacted to csabakecskemeti's post with 👍 25 days ago

Post

1621

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 👍 27 days ago

Post

2967

⛓ 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)