link TECHNICAL.md + ENVIRONMENT.md from the card
Browse files
README.md
CHANGED
|
@@ -15,6 +15,8 @@ here as they finish training, checkpoints push every 30 minutes mid-run, and
|
|
| 15 |
while the run table below says IN PROGRESS, you are watching the experiment
|
| 16 |
happen.
|
| 17 |
|
|
|
|
|
|
|
| 18 |
## The question
|
| 19 |
|
| 20 |
Mixture-of-experts models normally route with a learned softmax over expert
|
|
|
|
| 15 |
while the run table below says IN PROGRESS, you are watching the experiment
|
| 16 |
happen.
|
| 17 |
|
| 18 |
+
> 📄 **Technical companion:** [TECHNICAL.md](https://huggingface.co/AbstractPhil/alephlm-0/blob/main/TECHNICAL.md) — the complete two-seed verdict, toggle decomposition, basin tables, instruments, and laws. Execution provenance (versions, container quotas, per-arm code revision): [ENVIRONMENT.md](https://huggingface.co/AbstractPhil/alephlm-0/blob/main/ENVIRONMENT.md).
|
| 19 |
+
|
| 20 |
## The question
|
| 21 |
|
| 22 |
Mixture-of-experts models normally route with a learned softmax over expert
|