Giorgio Gilestro
84124de143
Clarity pass over the main text (36-item audit), Discussion rewrite and cut, acknowledgements, Souly et al. as ref 62, lettered SI panels, model section moved under Results; plus the untracked curriculum/society/compose/smol configs, runners, figures, stats and tests that the SI already cites. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Y64o8FKP7rCuXzC48pxpMm
28 lines
No EOL
586 B
JSON
28 lines
No EOL
586 B
JSON
{
|
|
"experiment": "llm_moe_hard_hpc",
|
|
"master_seed": 1,
|
|
"git_commit": null,
|
|
"python": "3.11.13",
|
|
"libraries": {
|
|
"numpy": "2.4.6",
|
|
"scipy": "1.17.1",
|
|
"pandas": "3.0.3",
|
|
"pyarrow": "24.0.0",
|
|
"torch": "2.12.1",
|
|
"transformers": "5.13.0",
|
|
"peft": "0.19.1"
|
|
},
|
|
"rows": 47,
|
|
"results_sha256": "a4e7c37e7cd900b56aa24ffc827e38e9a9d5cbb44dcff8d83cf010e992ed5c8a",
|
|
"layer": "2",
|
|
"tier": "llm",
|
|
"base_model": "Qwen/Qwen2.5-7B-Instruct",
|
|
"hard": true,
|
|
"operators": [
|
|
"soup",
|
|
"ties",
|
|
"moe_oracle",
|
|
"moe_learned",
|
|
"max_merge"
|
|
]
|
|
} |