Contents Menu Expand Light mode Dark mode Auto light/dark, in light mode Auto light/dark, in dark mode Skip to content
RapidFire AI 0.16.1
Light Logo Dark Logo
RapidFire AI 0.16.1
  • Install and Get Started
    • Install and Get Started: RAG and Context Engineering
    • Install and Get Started: Fine-Tuning and Post-Training
  • Troubleshooting
  • What Makes RapidFire AI Different?
  • Online Aggregation for Evals
  • API: Experiment
  • API: Multi-Config Specification
  • APIs for RAG and Context Engineering
    • API: LangChain RAG Spec
    • API: Generator Configs
    • API: Prompt Manager and Other Eval Config Knobs
    • API: User-Provided Functions for Run Evals
  • APIs for SFT and RFT
    • API: LoRA and Model Configs
    • API: Trainer Configs
    • API: User-Provided Functions for Run Fit
  • Example Use Case Tutorials
    • FiQA: RAG for Financial Opinion Q&A Chatbot
    • GSM8K: Context Engineering for Math Reasoning
    • SciFact: RAG for Scientific Claim Verification
    • SFT for Q&A Chatbot
    • DPO for Alignment
    • GRPO for Math Reasoning
  • Metrics Dashboard
  • AI Gateway
  • Dashboard: Interactive Control (IC) Ops
  • Known Issues and Updates Coming Soon
  • Glossary of Key Terms and Concepts
Back to top
View this page

APIs for SFT and RFTΒΆ

  • API: LoRA and Model Configs
    • RFLoraConfig
    • RFModelConfig
      • RFModelConfig
  • API: Trainer Configs
    • RFSFTConfig
    • RFDPOConfig
    • RFGRPOConfig
  • API: User-Provided Functions for Run Fit
    • Create Model Function
      • create_model_fn()
    • Compute Metrics Function
      • fit.compute_metrics_fn()
    • Formatting Function
      • sample_formatting_fn()
    • Reward Functions
      • reward_function()
Next
API: LoRA and Model Configs
Previous
API: User-Provided Functions for Run Evals
Made with Sphinx and @pradyunsg's Furo