angie-chen55

alignment-game-public

Repository for the paper: https://arxiv.org/abs/2312.04792

angie-chen55.github.io

direct-preference-optimization

Reference implementation for DPO (Direct Preference Optimization)

holo-bench

Benchmark for Biophysical Sequence Optimization Algorithms

jiant

jiant is an NLP toolkit

lm-evaluation-harness

A framework for few-shot evaluation of language models.

lrqa

pref-learning-ranking-acc

PyTorch-Model-Compare

Compare neural networks by their feature similarity

reward-bench-policy-accuracies

Adapt RewardBench for evaluating ranking accuracy on final policies instead

angie-chen55/pref-learning-ranking-acc

angie-chen55/angie-chen55.github.io

angie-chen55/PyTorch-Model-Compare

Compare neural networks by their feature similarity

angie-chen55/alignment-game-public

Repository for the paper: https://arxiv.org/abs/2312.04792

angie-chen55/direct-preference-optimization

Reference implementation for DPO (Direct Preference Optimization)

angie-chen55/holo-bench

Benchmark for Biophysical Sequence Optimization Algorithms

angie-chen55/jiant

jiant is an NLP toolkit

angie-chen55/lm-evaluation-harness

A framework for few-shot evaluation of language models.

angie-chen55/lrqa

angie-chen55/reward-bench-policy-accuracies

Adapt RewardBench for evaluating ranking accuracy on final policies instead

angie-chen55/sudden-drops-in-the-loss