ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
Paper
•
2505.24864
•
Published
•
118
Rafael Pierre
rvpierre
AI & ML interests
LLMs, Gen AI, MLOps, Machine Learning Engineering
Recent Activity
liked
a model
10 months ago
jackhhao/jailbreak-classifier
liked
a model
11 months ago
meta-llama/Llama-3.1-8B-Instruct
Organizations
rvpierre's activity
upvoted
a
paper
8 days ago
liked
a
model
10 months ago
liked
a
model
11 months ago
liked
a
Space
11 months ago
liked
a
model
12 months ago
reacted to
mitkox's
post with 🔥
12 months ago
Post
2220
I'm decentralizing my AI end2end, from the AI model distribution to on device AI inferencing. llama-ipfs - llama.cpp integrated with Interplanetary File System for distributing peer2peer and loading AI models without the need for cloud storage or AI model Hub.
llama.cpp now supports decentralized inferencing with RPC, allowing the distribution of workload across all home devices. This functionality can be enhanced with a P2P ad-hoc VPN, enabling the extension of distributed inferencing to any device on any network.
Imagine an open-source AI that's as decentralized as a potluck dinner - everyone brings something to the table, and there's ZERO need for blockchain. It's like a digital fortress, with security and privacy baked right in, not to mention a dollop of integrity and trust. This could be the secret sauce for an enterprise AI platform, complete with an integrated IT policy. It might just be the cherry on top for the next generation of Apple Intelligence and Copilot+ PCs.
Make sure you own your AI. AI in the cloud is not aligned with you; it's aligned with the company that owns it.
llama.cpp now supports decentralized inferencing with RPC, allowing the distribution of workload across all home devices. This functionality can be enhanced with a P2P ad-hoc VPN, enabling the extension of distributed inferencing to any device on any network.
Imagine an open-source AI that's as decentralized as a potluck dinner - everyone brings something to the table, and there's ZERO need for blockchain. It's like a digital fortress, with security and privacy baked right in, not to mention a dollop of integrity and trust. This could be the secret sauce for an enterprise AI platform, complete with an integrated IT policy. It might just be the cherry on top for the next generation of Apple Intelligence and Copilot+ PCs.
Make sure you own your AI. AI in the cloud is not aligned with you; it's aligned with the company that owns it.
liked
a
model
about 1 year ago
reacted to
mlabonne's
post with 🤝👍❤️
over 1 year ago
Post
🌳 Model Family Tree
Merging models has become a powerful way to compress information and build powerful models for cheap. Right now, the process is still quite experimental: which models to merge? which parameters should I use? We have some intuition but no principled approach.
I made a little tool to make things a little clearer. It allows you to visualize the family tree of any model on the Hub. It also displays the type of license they use: permissive (green), noncommercial (red), and unknown (gray). It should help people select the right license based on the parent models.
In addition, I hope it can be refined to extract more information about these models: do models from very different branches work better when merged? Can we select them based on the weight difference? There are a lot of questions to explore in this new space. :)
Here's a link to the colab notebook I made: https://colab.research.google.com/drive/1s2eQlolcI1VGgDhqWIANfkfKvcKrMyNr
If you want to know more about model merging or build you own merges, here's the article I wrote about this topic: https://huggingface.co/blog/mlabonne/merge-models
Merging models has become a powerful way to compress information and build powerful models for cheap. Right now, the process is still quite experimental: which models to merge? which parameters should I use? We have some intuition but no principled approach.
I made a little tool to make things a little clearer. It allows you to visualize the family tree of any model on the Hub. It also displays the type of license they use: permissive (green), noncommercial (red), and unknown (gray). It should help people select the right license based on the parent models.
In addition, I hope it can be refined to extract more information about these models: do models from very different branches work better when merged? Can we select them based on the weight difference? There are a lot of questions to explore in this new space. :)
Here's a link to the colab notebook I made: https://colab.research.google.com/drive/1s2eQlolcI1VGgDhqWIANfkfKvcKrMyNr
If you want to know more about model merging or build you own merges, here's the article I wrote about this topic: https://huggingface.co/blog/mlabonne/merge-models
- 8 replies
liked
a
model
almost 2 years ago
