18 days ago
-
Upload re-run checkpoints and results
23 days ago
-
Upload assets/part3/beam_search_runtime.png with huggingface_hub
-
Upload assets/part3/rocstories_generations.json with huggingface_hub
-
Upload assets/dynamics_muon.png with huggingface_hub
-
Upload assets/heatmap_moe_shared.png with huggingface_hub
-
Upload assets/heatmap_moe_top2.png with huggingface_hub
-
Upload assets/dynamics_adamw.png with huggingface_hub
-
Upload assets/dynamics_lion.png with huggingface_hub
-
Upload assets/heatmap_moe_top1.png with huggingface_hub
-
Upload assets/dynamics_sophia.png with huggingface_hub
-
Upload assets/heatmap_moe_active_match.png with huggingface_hub
-
Upload assets/dynamics_adafactor.png with huggingface_hub
-
Upload part2/sophia_1.0x.pt with huggingface_hub
-
Upload part2/muon_1.0x.pt with huggingface_hub
-
Upload part2/adafactor_1.0x.pt with huggingface_hub
-
Upload part2/lion_1.0x.pt with huggingface_hub
-
Upload part2/adamw_1.0x.pt with huggingface_hub
-
Upload part1/best_moe_active_match.pt with huggingface_hub
-
Upload part1/best_moe_shared.pt with huggingface_hub
-
Upload part1/best_moe_top2.pt with huggingface_hub
-
Upload part1/best_moe_top1.pt with huggingface_hub
-
Upload part1/best_dense.pt with huggingface_hub
-
Upload assets/tokenizer_vi_ja_en.json with huggingface_hub
-
Upload README.md with huggingface_hub
-
initial commit