Aramis

amenur

amenur

AI & ML interests

None yet

Recent Activity

upvoted an article about 11 hours ago

Open-source DeepResearch – Freeing our search agents

upvoted an article about 14 hours ago

Introducing smolagents: simple agents that write actions in code.

upvoted an article 1 day ago

Open-R1: Update #1

View all activity

Organizations

None yet

amenur's activity

upvoted an article about 11 hours ago

Article

Open-source DeepResearch – Freeing our search agents

1 day ago

• 307

upvoted an article about 14 hours ago

Article

Introducing smolagents: simple agents that write actions in code.

Dec 31, 2024

• 555

upvoted an article 1 day ago

Article

Open-R1: Update #1

•

3 days ago

• 221

upvoted an article 8 days ago

Article

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

8 days ago

• 626

upvoted an article 29 days ago

Article

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

•

Jan 4

• 14

upvoted a paper about 2 months ago

Qwen2.5 Technical Report

Paper • 2412.15115 • Published Dec 19, 2024 • 345

upvoted a collection about 2 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 about 1 month ago • 22

liked a Space about 2 months ago

494

Scaling test-time compute

📈

Enhance math problem solving by scaling test-time compute

reacted to lewtun's post with 🚀🔥 about 2 months ago

Post

6824

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🎄 Diverse Verifier Tree Search (DVTS): An unpublished extension we developed to the verifier-guided tree search technique.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!