Increase server timeout to 600s for large model experiments
044ff0a
AdriBat1
commited on
Spaces:
Paused
Paused
Commit History
Add DeepSeek-Lite Protocol: 50M params, FineWeb-Edu, TikToken, BFloat16
6ec2818
AdriBat1
commited on
Add Tower of Babel (V3) experiment: 120-layer, gradient monitoring, val loss
938275a
AdriBat1
commited on
Add Deep-NanoGPT experiment (Phase 1 & 2): resumable training, inference, 72-layer models
671ce97
AdriBat1
commited on
Add and verify LLM training and inference examples
5f654f8
AdriBat1
commited on
Implement and verify remote persistence workflow
979e977
AdriBat1
commited on
Reorganize client files into examples, tests, and output folders
1b272e7
AdriBat1
commited on