Pinned Loading
-
Reinforcement-Calibration-SimCSE
Reinforcement-Calibration-SimCSE PublicReinforcement Calibration SimCSE, combining contrastive learning, artificial potential fields, perceptual loss, and RLHF to achieve improved Semantic Textual Similarity (STS) embeddings. PyTorch-baβ¦
Python 10
-
event-timeline-generation-olympics
event-timeline-generation-olympics PublicA toy system for generating event timelines from social media data, specifically focusing on the Olympic Game medalist events.
Jupyter Notebook 6
-
byte_pair_encoding_BPE_subword_tokenization_implementation_python
byte_pair_encoding_BPE_subword_tokenization_implementation_python PublicByte-Pair Encoding (BPE) (subword-based tokenization) algorithm implementaions from scratch with python
Python 13
-
Logic-RL-Lite
Logic-RL-Lite PublicLightweight replication study of DeepSeek-R1-Zero. Explores pure RL without SFT for post-training for reasoning capability. "No Aha Moment", and "Longer CoT β Accuracy".
Python 1
If the problem persists, check the GitHub status page or contact support.