Indicators / series
cl_ladder.baseten_rank1_lora.rung_research.pt
Source: Baseten blog and research posts (Baseten) · Baseten; short quotation · CSV
Baseten
| id | value | grade | as of date | published date | tier | audited vs reported | extraction method | review status | retrieved at | http status | content hash | supersedes id | url | flags |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 9d52a59f8076617e | 5.00 rung | grade D, evidence tier 7 | 2025-10-12 | 2025-10-12 | 7 | company_stated | manual | approved | 2026-09-10T06:54:23.253147Z | 200 | e62b0936982b | — | source page |
Raw snippets and dispute text
- 9d52a59f8076617e Continuously (or close to continuously) merging rank-1 LoRA adapters into the model on the same GPUs running inference felt like the right answer to that to us.