Coherence experiments

For reviewers:

To view and run our MDP experiments in our paper, go to 'MDP classifier/RR_classifier.ipynb'
To view and run our RL experiments, go to 'RL gym coherence/Taxi_classifying.py' and 'RL gym coherence/Taxi_classifying_sandbox.py'
To view and run our LLM experiments, go to 'new_experiments/experiments_orca/llama7b_lora_fine_tune_orca.py'

Name		Name	Last commit message	Last commit date
Latest commit History 101 Commits
.vscode		.vscode
MDP classifier		MDP classifier
RL gym coherence		RL gym coherence
__pycache__		__pycache__
big experiments		big experiments
images		images
logs		logs
my_dir/sparsity_prediction		my_dir/sparsity_prediction
new_experiments		new_experiments
not my work		not my work
old experiments		old experiments
wandb		wandb
.gitattributes		.gitattributes
.gitignore		.gitignore
Coherence_gpt2_small.ipynb		Coherence_gpt2_small.ipynb
MDP.py		MDP.py
README.md		README.md
activation_pseudocode.ipynb		activation_pseudocode.ipynb
activation_pseudocode.txt		activation_pseudocode.txt
connect_4_lookup.ipynb		connect_4_lookup.ipynb
gradients_dense_epoch_0.pkl		gradients_dense_epoch_0.pkl
gradients_dense_epoch_1.pkl		gradients_dense_epoch_1.pkl
gradients_dense_epoch_2.pkl		gradients_dense_epoch_2.pkl
gradients_sparse_epoch_0.pkl		gradients_sparse_epoch_0.pkl
gradients_sparse_epoch_1.pkl		gradients_sparse_epoch_1.pkl
gradients_sparse_epoch_2.pkl		gradients_sparse_epoch_2.pkl
llama7b_lora_fine_tune.py		llama7b_lora_fine_tune.py
llama7b_lora_fine_tune_stable.py		llama7b_lora_fine_tune_stable.py
temp.md		temp.md

Provide feedback