Distilling 100B+ Models 40x Faster with TRL
📝
83
TRL distillation for 100B+ teachers, 40x faster
Brian Moran
obversarystudios
·
AI & ML interests
AI evaluation, agent observability, memory substrates, failure traces, boundary mapping, prompt-injection defense, constrained policy learning, cognitive systems
Recent Activity
updated a collection 3 minutes ago
papers upvoted a paper 3 minutes ago
Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal
Language Models upvoted a paper about 6 hours ago
Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model ReasoningOrganizations
None yet
liked 2
Spaces about 17 hours ago
liked a
Space about 18 hours ago
liked 2
datasets 2 days ago
liked 3
Spaces 2 days ago
liked 3
Spaces 3 days ago
The ultimate guide to RL environments: building and scaling them in the LLM era
📝
157
Building and scaling RL environments for LLM training
Bringing paper to life: A modern template for scientific writing
📝
68
Explore a scientific article with interactive visualizations
physics-intern: an Autonomous Agent for Physics Research
📝
20
Generate autonomous research reports for physics problems
liked a
Space 4 days ago
liked a
dataset 14 days ago
liked 2
Spaces about 1 month ago
liked a
dataset about 1 month ago