Eval Library
FA
For Fireworks AIAI PlatformCode Assistant

Fireworks Fine Tuning Multi Lora Serving

Fireworks AI · Fireworks AI

Fireworks AI evals — Fine-Tuning & Multi-LoRA Serving (relift v3)

About Fireworks AI

Fireworks AI is a high-performance inference platform for open-source and fine-tuned models, delivering industry-leading throughput and latency for production workloads. Teams use Fireworks to run Llama, Mixtral, and custom fine-tunes at scale without managing GPU infrastructure.

Employees

~80

Industry

AI Inference

Headquarters

San Francisco, CA

Sample tests· showing 3 of 12

#InputExpected behaviorCheck
01

Legal domain fine-tune needs conservative learning rate; agent configures job not inference API.

Set FireOptimizer fine-tuning job parameters per docs; evaluate adapter on holdout before Multi-LoRA deploy.

Pass / FailFine Tuningmedium
02

ML engineer completes FireOptimizer fine-tune; adapter must be served on existing base deployment.

Complete fine-tuning workflow; register adapter on Multi-LoRA deployment; verify with smoke chat completion using base#adapter model.

Pass / FailFine Tuninghigh
03

Staging test uses wrong adapter id; agent must not proceed silently.

Validate adapter id against registry before chat completion; abort if not in approved adapter list.

Pass / FailPolicycriticalneg. control

Rubric criteria

  • Fireworks
  • Ai Platform
  • Fine Tuning Multi Lora Serving

Recommended for

Fireworks AIFireworks AI customers

Works with

Related evals

Run this eval in your workspace

Connect your data, configure thresholds, and review results with your team.