├── .gitignore ├── LICENSE ├── evaluation ├── analysis.ipynb ├── automated_evaluation_labels │ ├── xstest_v2_completions_gpt4_gpteval.csv │ ├── xstest_v2_completions_gpt4_streval.csv │ ├── xstest_v2_completions_llama2new_gpteval.csv │ ├── xstest_v2_completions_llama2new_streval.csv │ ├── xstest_v2_completions_llama2orig_gpteval.csv │ ├── xstest_v2_completions_llama2orig_streval.csv │ ├── xstest_v2_completions_mistralguard_gpteval.csv │ ├── xstest_v2_completions_mistralguard_streval.csv │ ├── xstest_v2_completions_mistralinstruct_gpteval.csv │ └── xstest_v2_completions_mistralinstruct_streval.csv ├── classify_completions_gpt.py └── classify_completions_strmatch.py ├── model_completions ├── xstest_v2_completions_gpt4.csv ├── xstest_v2_completions_llama2new.csv ├── xstest_v2_completions_llama2orig.csv ├── xstest_v2_completions_mistralguard.csv └── xstest_v2_completions_mistralinstruct.csv ├── readme.md └── xstest_prompts.csv /.gitignore: -------------------------------------------------------------------------------- 1 | .DS_Store -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/paul-rottger/xstest/HEAD/LICENSE -------------------------------------------------------------------------------- /evaluation/analysis.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/paul-rottger/xstest/HEAD/evaluation/analysis.ipynb -------------------------------------------------------------------------------- /evaluation/automated_evaluation_labels/xstest_v2_completions_gpt4_gpteval.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/paul-rottger/xstest/HEAD/evaluation/automated_evaluation_labels/xstest_v2_completions_gpt4_gpteval.csv -------------------------------------------------------------------------------- /evaluation/automated_evaluation_labels/xstest_v2_completions_gpt4_streval.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/paul-rottger/xstest/HEAD/evaluation/automated_evaluation_labels/xstest_v2_completions_gpt4_streval.csv -------------------------------------------------------------------------------- /evaluation/automated_evaluation_labels/xstest_v2_completions_llama2new_gpteval.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/paul-rottger/xstest/HEAD/evaluation/automated_evaluation_labels/xstest_v2_completions_llama2new_gpteval.csv -------------------------------------------------------------------------------- /evaluation/automated_evaluation_labels/xstest_v2_completions_llama2new_streval.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/paul-rottger/xstest/HEAD/evaluation/automated_evaluation_labels/xstest_v2_completions_llama2new_streval.csv -------------------------------------------------------------------------------- /evaluation/automated_evaluation_labels/xstest_v2_completions_llama2orig_gpteval.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/paul-rottger/xstest/HEAD/evaluation/automated_evaluation_labels/xstest_v2_completions_llama2orig_gpteval.csv -------------------------------------------------------------------------------- /evaluation/automated_evaluation_labels/xstest_v2_completions_llama2orig_streval.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/paul-rottger/xstest/HEAD/evaluation/automated_evaluation_labels/xstest_v2_completions_llama2orig_streval.csv -------------------------------------------------------------------------------- /evaluation/automated_evaluation_labels/xstest_v2_completions_mistralguard_gpteval.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/paul-rottger/xstest/HEAD/evaluation/automated_evaluation_labels/xstest_v2_completions_mistralguard_gpteval.csv -------------------------------------------------------------------------------- /evaluation/automated_evaluation_labels/xstest_v2_completions_mistralguard_streval.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/paul-rottger/xstest/HEAD/evaluation/automated_evaluation_labels/xstest_v2_completions_mistralguard_streval.csv -------------------------------------------------------------------------------- /evaluation/automated_evaluation_labels/xstest_v2_completions_mistralinstruct_gpteval.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/paul-rottger/xstest/HEAD/evaluation/automated_evaluation_labels/xstest_v2_completions_mistralinstruct_gpteval.csv -------------------------------------------------------------------------------- /evaluation/automated_evaluation_labels/xstest_v2_completions_mistralinstruct_streval.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/paul-rottger/xstest/HEAD/evaluation/automated_evaluation_labels/xstest_v2_completions_mistralinstruct_streval.csv -------------------------------------------------------------------------------- /evaluation/classify_completions_gpt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/paul-rottger/xstest/HEAD/evaluation/classify_completions_gpt.py -------------------------------------------------------------------------------- /evaluation/classify_completions_strmatch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/paul-rottger/xstest/HEAD/evaluation/classify_completions_strmatch.py -------------------------------------------------------------------------------- /model_completions/xstest_v2_completions_gpt4.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/paul-rottger/xstest/HEAD/model_completions/xstest_v2_completions_gpt4.csv -------------------------------------------------------------------------------- /model_completions/xstest_v2_completions_llama2new.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/paul-rottger/xstest/HEAD/model_completions/xstest_v2_completions_llama2new.csv -------------------------------------------------------------------------------- /model_completions/xstest_v2_completions_llama2orig.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/paul-rottger/xstest/HEAD/model_completions/xstest_v2_completions_llama2orig.csv -------------------------------------------------------------------------------- /model_completions/xstest_v2_completions_mistralguard.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/paul-rottger/xstest/HEAD/model_completions/xstest_v2_completions_mistralguard.csv -------------------------------------------------------------------------------- /model_completions/xstest_v2_completions_mistralinstruct.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/paul-rottger/xstest/HEAD/model_completions/xstest_v2_completions_mistralinstruct.csv -------------------------------------------------------------------------------- /readme.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/paul-rottger/xstest/HEAD/readme.md -------------------------------------------------------------------------------- /xstest_prompts.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/paul-rottger/xstest/HEAD/xstest_prompts.csv --------------------------------------------------------------------------------