Max Ryabinin
mryab
AI & ML interests
Distributed training, natural language generation, efficient architectures for DL
Recent Activity
upvoted
a
paper
about 1 month ago
Quartet: Native FP4 Training Can Be Optimal for Large Language Models
authored
a paper
6 months ago
Towards Best Practices for Open Datasets for LLM Training
authored
a paper
8 months ago
RedPajama: an Open Dataset for Training Large Language Models