Aramis

amenur

amenur

AI & ML interests

None yet

Recent Activity

upvoted an article about 12 hours ago

Open R1: Update #3

upvoted an article 10 days ago

SmolVLM2: Bringing Video Understanding to Every Device

upvoted an article 18 days ago

Open R1: Update #2

View all activity

Organizations

None yet

amenur's activity

upvoted an article about 12 hours ago

Article

Open R1: Update #3

and 9 others •

2 days ago

• 192

upvoted an article 10 days ago

Article

SmolVLM2: Bringing Video Understanding to Every Device

22 days ago

• 205

upvoted an article 18 days ago

Article

Open R1: Update #2

and 6 others •

Feb 10

• 202

upvoted an article 20 days ago

Article

SigLIP 2: A better multilingual vision language encoder

21 days ago

• 133

upvoted an article 29 days ago

Article

Open-source DeepResearch – Freeing our search agents

Feb 4

• 1.16k

upvoted 3 articles about 1 month ago

Article

Introducing smolagents: simple agents that write actions in code.

Dec 31, 2024

• 867

Article

Open-R1: Update #1

and 7 others •

Feb 2

• 295

Article

Open-R1: a fully open reproduction of DeepSeek-R1

Jan 28

• 803

upvoted an article 2 months ago

Article

Superposition in Transformers: A Novel Way of Building Mixture of Experts

•

Jan 4

• 14

upvoted a paper 3 months ago

Qwen2.5 Technical Report

Paper • 2412.15115 • Published Dec 19, 2024 • 352

upvoted a collection 3 months ago

Scaling Test-Time Compute with Open Models

Collection

Models and datasets used in our blog post: https://huggingface.co/spaces/HuggingFaceH4/blogpost-scaling-test-time-compute • 10 items • Updated Jan 6 • 23

liked a Space 3 months ago

534

Scaling test-time compute

📈

Enhance math problem solving by scaling test-time compute

reacted to lewtun's post with 🚀🔥 3 months ago

Post

6932

We outperform Llama 70B with Llama 3B on hard math by scaling test-time compute 🔥

How? By combining step-wise reward models with tree search algorithms :)

We show that smol models can match or exceed the performance of their much larger siblings when given enough "time to think"

We're open sourcing the full recipe and sharing a detailed blog post.

In our blog post we cover:

📈 Compute-optimal scaling: How we implemented DeepMind's recipe to boost the mathematical capabilities of open models at test-time.

🎄 Diverse Verifier Tree Search (DVTS): An unpublished extension we developed to the verifier-guided tree search technique. This simple yet effective method improves diversity and delivers better performance, particularly at large test-time compute budgets.

🧭 Search and Learn: A lightweight toolkit for implementing search strategies with LLMs and built for speed with vLLM

Here's the links:

- Blog post: HuggingFaceH4/blogpost-scaling-test-time-compute

- Code: https://github.com/huggingface/search-and-learn

Enjoy!