Hugging Face's logo
estnafinema0 's Collections
PEFT variations
NER Extraction. Active Learning Approach.
SmolLM Variation: PPO & DPO Fine-Tuning for RLHF

SmolLM Variation: PPO & DPO Fine-Tuning for RLHF

This collection presents the fine-tuning of the SmolLM model using two (RLHF) approaches: DPO and PPO.

Upvote
1