Chris Esposo

icon indicating a website link linkedin.com/in/chrisesposo

icon location Data Scientist, balancing building up coding muscle, while I develop domain knowledge in ML, specifically interested in various applications of NN

Results 2 issues of Chris Esposo

Refactored code from different base based on leyan_branch

Summary This PR addresses two things, the extension of model_ext.py and train_sat.py from leyan_branch with my additions from the previous PR. Second it addresses some run-time issues in the flash...

Dec branch commit

Option 1 - Flag Ablation code - ReLU - Restricted Setting - Softmax q-error + Option 2 - Flag Scale Attention Weights based on the context window * log(query_position) [error...