LLM Preference Tuning

Similar Flow to Instruction Tuning : The process remains the same as LLM Instruction Tuning, with a few key differences:

• Select “Train Model+” and create a repository.
• Set Task Type to Preference Tuning instead of Instruction Tuning.
• Choose a Pre-Uploaded Preference Tuning Dataset
  • Must be formatted as: prompt, chosen, rejected.
• Select a Model for Preference Tuning
  • Llama-1B
  • Llama-3B
  • Qwen-1.5B
  • Qwen-3B-Coder ,etc.
• Configure settings and initiate training.

Similar Flow for Reasoning Model

The process remains the same as LLM Tuning, with a few key differences:

• Select “Train Model+” and create a repository.

• Set Task Type to LLM-RL-Tuning instead.

• Select a Model

  • Llama-1B
  • Llama-3B
  • Qwen-3B-Coder
  • Qwen-1.5B, etc.

• Training Status Indicators:

  
  

  🟡 Yellow – Training in progress

  🟢 Green – Training completed successfully

  🔴 Red – Training failed (retry or report issue)

  
  

  💡Once training is complete, your model will be fine-tuned to prioritize better responses!