Pinned Loading
-
-
smriti-lm
smriti-lm PublicA from-scratch Hindi language model trained on 1B tokens of clean web text. 3-layer LSTM, 50M parameters, SentencePiece BPE tokenization.
Python
-
-
atomic-to-composite-mech-interp
atomic-to-composite-mech-interp PublicMechanistic interpretability study on RL complementary reasoning (Qwen-2.5), expanding work done in "From Atomic to Composite: Reinforcement Learning Enables Generalization in Complementary Reasoni…
Python
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.
