TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models
Paper • 2610.07767 • Published • 93
Philipp Krueger
muckrueger
·
AI & ML interests
None yet
Recent Activity
updated a dataset about 3 hours ago
muckrueger/image-audio-samples-2024 published a dataset about 3 hours ago
muckrueger/image-audio-samples-2024 liked a model about 3 hours ago
autotrust/JEV-27B-VLOrganizations
None yet
upvoted a paper 1 day ago