detector_benchmark.run_human_eval¶
Functions¶
|
|
|
|
Module Contents¶
- detector_benchmark.run_human_eval.generate_one_completion(prompt, gen_model, gen_config, tokenizer)¶
- detector_benchmark.run_human_eval.generate_batch_completions(prompts, gen_model, gen_config, tokenizer, batch_size=2)¶
- detector_benchmark.run_human_eval.run_human_eval()¶