TalkToModel
TalkToModel gives anyone with the powers of XAI through natural language conversations ๐ฌ!
File Explorer
Download Latest Version (.zip)- python-app.yml
- readme.md
- compas-config.gin
- diabetes-config.gin
- german-config.gin
- __init__.py
- compas.csv
- compas_model_grad_boosted_tree.pkl
- compas_raw.csv
- compas_test.csv
- compas_train.csv
- diabetes.csv
- diabetes_model_grad_boosted_tree.pkl
- diabetes_model_grad_tree.pkl
- diabetes_model_logistic_regression.pkl
- diabetes_test.csv
- diabetes_train.csv
- german_credit.csv
- german_model_grad_tree.pkl
- german_raw.csv
- german_test.csv
- german_train.csv
- processing_functions.py
- train_compas_model.py
- train_diabetes_model.py
- train_german_model.py
- ttm-user-study-responses.csv
- parsing_table_template.txt
- compas_mturk_data_raw.json
- compas_test_suite.txt
- diabetes_mturk_data_raw.json
- diabetes_test_suite.txt
- final_parsing_results.csv
- german_mturk_data_raw.json
- german_test_suite.txt
- split_mturk_data_raw.py
- compas_templates.csv
- diabetes_templates.csv
- german_templates.csv
- readme.md
- compute_parsing_accuracy.py
- compute_parsing_accuracy_model_sweep.py
- generate_parsing_results.py
- get_compositional_queries.py
- notification.py
- utils.py
- count_data_points.py
- data_summary.py
- define.py
- explanation.py
- feature_stats.py
- filter.py
- followup.py
- function.py
- get_action_functions.py
- important.py
- interaction_effects.py
- labels.py
- last_turn_filter.py
- last_turn_operation.py
- mistakes.py
- model.py
- predict.py
- prediction_likelihood.py
- README.md
- score.py
- self.py
- show_data.py
- utils.py
- what_if.py
- __init__.py
- base_explainer.py
- explainer.py
- lime_explainer.py
- perturbation_methods.py
- shap_explainer.py
- cfe_prompts.txt
- comparisons.txt
- count_data_points_prompts.txt
- dataset_description.txt
- describe_self.txt
- explanation_prompts.txt
- interactions.txt
- label_prompts.txt
- lastturn_prompts.txt
- likelihood_prompts.txt
- mistakes.txt
- most_important_feature_prompts.txt
- mturk_generated.txt
- predict_prompts.txt
- README.md
- score_prompts.txt
- show_data_prompts.txt
- whatif_prompts.txt
- filter_fillers.txt
- yes_or_no.txt
- __init__.py
- action.py
- complete.py
- conversation.py
- dataset_description.py
- decoder.py
- explanation.py
- feature_interaction.py
- grammar.py
- logic.py
- parser.py
- prompts.py
- sample_prompts_by_action.py
- utils.py
- write_to_log.py
- few_shot_inference.py
- gd_logits_processor.py
- compas_pandas.csv
- derm_pandas.csv
- diabetes_pandas.csv
- german_pandas.csv
- inference-t5-base.gin
- inference-t5-large.gin
- inference-t5-small.gin
- t5-3b.gin
- t5-base.gin
- t5-large.gin
- t5-small.gin
- t5_small_diabetes_debug.gin
- t5_base_sweep_0.2.sh
- t5_base_sweep_0.4.sh
- t5_base_sweep_0.6.sh
- t5_base_sweep_0.8.sh
- t5_base_sweep_1.0.sh
- compas.sh
- diabetes.sh
- diabetes_sweep.sh
- finetune_t5_3b.sh
- finetune_t5_base.sh
- finetune_t5_large.sh
- finetune_t5_small.sh
- finetune_t5_small_debug.sh
- german.sh
- get_data_set.py
- start_fine_tuning.py
- t5_dataset.py
- t5_inference.py
- t5_trainer.py
- t5_training_val_loops.py
- __init__.py
- diego.png
- sad.png
- banner.png
- output.gif
- ren.png
- ren2.png
- style.css
- scripts.js
- batman.png
- robot.png
- index.html
- diabetes-config-debug.gin
- diabetes.csv
- diabetes_model_logistic_regression.pkl
- diabetes_test.csv
- diabetes_train.csv
- predict_promtps.txt
- test_action.py
- test_dataset_description.py
- test_explanations.py
- test_feature_interaction_index.py
- test_from_load.py
- test_mega_explainer.py
- tests-config.gin
- background_derm.csv
- dataset_derm.csv
- derm.csv
- derm_model.pkl
- extending-ttm.md
- running-on-your-own-model.ipynb
- .gitignore
- CITATION.cff
- Dockerfile
- flask_app.py
- global_config.gin
- LICENSE
- README.md
- requirements.txt
# Installation Guide
1. Get the code
git clone https://github.com/dylan-slack/TalkToModel
Downloads the entire project code from GitHub to your computer.
cd TalkToModel
Moves into the project folder you just downloaded.
2. Docker
Easy RecommendedPrerequisites
- Git Needed to download the project code from GitHub.
- Docker Desktop Needed to build and run containers. Install it and keep it running in the background.
sudo docker build -t ttm .
Builds a runnable image based on the Dockerfile.
sudo docker run -d -p 4000:4000 ttm
Runs the built image as an actual container.
Run docker compose ps to check the containers are Up. If the README mentions a port, open http://localhost:PORT in your browser.
Pulled directly from this repo's README.
3. Python
EasyPrerequisites
pip install -r requirements.txt
Installs the Python libraries listed in requirements.txt (or similar).
If it runs without errors and prints output in the terminal, it worked.
Pulled directly from this repo's README.
// repository documentation
Was this content helpful?
(0 ratings)