Visualize and understand GPU memory in PyTorch
•
63
Quentin Gallouédec
qgallouedec
AI & ML interests
None yet
Recent Activity
updated
a dataset
about 18 hours ago
qgallouedec/trl-metrics
updated
a Space
2 days ago
qgallouedec/train_memory
updated
a dataset
2 days ago
huggingface/documentation-images
Articles
Organizations
qgallouedec's activity
updated
a
dataset
about 18 hours ago
updated
a
Space
2 days ago
updated
a
dataset
2 days ago
liked
a
dataset
5 days ago
updated
a
dataset
6 days ago
upvoted
a
paper
7 days ago
updated
a
dataset
7 days ago
updated
3
datasets
8 days ago
reacted to
lewtun's
post with 🔥
8 days ago
Post
6430
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🎄 Diverse Verifier Tree Search (DVTS): An unpublished extension we developed to the verifier-guided tree search technique.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!
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🎄 Diverse Verifier Tree Search (DVTS): An unpublished extension we developed to the verifier-guided tree search technique.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
upvoted
a
paper
9 days ago
Use HF papers
1
#2 opened 9 days ago
by
qgallouedec
updated
a
Space
9 days ago
Update app/src/index.html
1
#1 opened 9 days ago
by
qgallouedec
updated
a
Space
9 days ago
Update app/src/index.html
1
#1 opened 9 days ago
by
qgallouedec
updated
a
dataset
10 days ago