↓ 1 callersMethodconfigure(
self, bits, perchannel=False, sym=True, mse=False, norm=2.4, grid=100, maxshrink=0.8, trits=False
inference/compression/dependencies/AutoGPTQ/auto_gptq/quantization/quantizer.py:23
↓ 1 callersFunctioneval_hf_model(args, subject, model, tokenizer, dev_df, test_df, batch_size=1)
inference/eval/mmlu/run_eval.py:50
↓ 1 callersMethodfasterquant(self, blocksize=128, percdamp=0.01, group_size=-1, actorder=False, static_groups=False)
inference/compression/dependencies/AutoGPTQ/auto_gptq/quantization/gptq.py:61
↓ 1 callersMethodfewshot_context(self, doc, num_fewshot, provide_description=None, rnd=None, description=None)
inference/efficiency/dependencies/efficiency-pentathlon/efficiency_benchmark/dependencies/lm_eval/tasks/truthfulqa.py:204
↓ 1 callersMethodfewshot_context(self, doc, num_fewshot, provide_description=None, rnd=None, description=None)
inference/efficiency/dependencies/previous_version/efficiency_benchmark/dependencies/lm_eval/tasks/truthfulqa.py:204