EpistemeAI LLM Guide

Phi 4 Series

• DeepThink-Phi4 – highest reasoning model in EpistemeAI lineup.

Llama Series

• 1B Model
• 3B Model
  • EpistemeAI/ReasoningCore-3B-RE1-V2 – (GRPO with math with ReasoningCore-3B-0)
  • EpistemeAI/ReasoningCore-3B-0 – (Original Reasoning model)
• 8B Model
  • Non Reasoning: EpistemeAI/Fireball-Alpaca-Llama3.1.07-8B-Philos-Math-KTO-beta
  • Reasoning: EpistemeAI/Fireball-R1-Llama-3.1-8B-Medical-COT (Medical)
  • Reasoning: EpistemeAI/Fireball-R1-Llama-3.1-8B-Freedom-9000 General