Training
Anonymized accounts of recent client engagements: what the workload looked like, what we changed, what it measured, and what it cost. The methodology section in each one is transferable.
Anonymized case study. EdTech company running document Q&A at $24k/month on OpenAI. A 3-week audit + LLMLingua deployment dropped the bill to $6k/month with no measurable accuracy change.
Anonymized case study. Regional commercial law firm. We fine-tuned Llama-3.3 8B with QLoRA on 3,500 of their pre-labeled contract clauses. Eval accuracy went from 64% (base) to 91% (fine-tuned) on the firm's 500-example held-out test set.
Anonymized case study. SaaS company with a SQL-from-natural-language feature shipped on GPT-4o. We re-calibrated their on-prem 7B and beat the API baseline by 11pp at 1/10 the cost. Two weeks of work, $15k engagement fee.