Swapan jain's picture

1

Swapan jain

hull11

·

AI & ML interests

None yet

Recent Activity

liked a Space 2 days ago

HuggingFaceH4/blogpost-scaling-test-time-compute

replied to lewtun's post 2 days ago

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 🎄 Diverse Verifier Tree Search (DVTS): An unpublished extension we developed to the verifier-guided tree search technique.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: https://huggingface.co/spaces/HuggingFaceH4/blogpost-scaling-test-time-compute - Code: https://github.com/huggingface/search-and-learn Enjoy!

Reacted to lewtun's post with 👍 2 days ago

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 🎄 Diverse Verifier Tree Search (DVTS): An unpublished extension we developed to the verifier-guided tree search technique.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: https://huggingface.co/spaces/HuggingFaceH4/blogpost-scaling-test-time-compute - Code: https://github.com/huggingface/search-and-learn Enjoy!

View all activity

Organizations

None yet

hull11's activity

liked a Space 2 days ago

Scaling test-time compute

replied to lewtun's post 2 days ago

Thank You for open sourcing this!!

reacted to lewtun's post with 👍❤️🔥 2 days ago

Post

4795

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!

2 replies

·