SmolLM-135M-Instruct aligned on HumanLLMs/Human-Like-DPO-Dataset: DPO from scratch, reward model and PPO with TRL.
Timur Aliev
Timur-th
AI & ML interests
None yet
Recent Activity
updated a collection 4 days ago
LLM course HW2: DPO, Reward Model, PPO updated a collection 4 days ago
LLM course HW2: DPO, Reward Model, PPO updated a collection 4 days ago
LLM course HW2: DPO, Reward Model, PPOOrganizations
None yet