crfm-helm 0.5.4__py3-none-any.whl → 0.5.6__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.

This version of crfm-helm might be problematic. Click here for more details.

Files changed (652) hide show
  1. crfm_helm-0.5.6.dist-info/METADATA +427 -0
  2. crfm_helm-0.5.6.dist-info/RECORD +941 -0
  3. {crfm_helm-0.5.4.dist-info → crfm_helm-0.5.6.dist-info}/WHEEL +1 -1
  4. helm/benchmark/adaptation/adapter_spec.py +13 -1
  5. helm/benchmark/adaptation/adapters/adapter_factory.py +15 -1
  6. helm/benchmark/adaptation/adapters/binary_ranking_adapter.py +1 -1
  7. helm/benchmark/adaptation/adapters/chat_adapter.py +49 -0
  8. helm/benchmark/adaptation/adapters/ehr_instruction_adapter.py +108 -0
  9. helm/benchmark/adaptation/adapters/generation_adapter.py +1 -1
  10. helm/benchmark/adaptation/adapters/in_context_learning_adapter.py +4 -4
  11. helm/benchmark/adaptation/adapters/language_modeling_adapter.py +1 -1
  12. helm/benchmark/adaptation/adapters/multimodal/generation_multimodal_adapter.py +4 -2
  13. helm/benchmark/adaptation/adapters/multimodal/in_context_learning_multimodal_adapter.py +1 -1
  14. helm/benchmark/adaptation/adapters/multimodal/multiple_choice_joint_multimodal_adapter.py +1 -1
  15. helm/benchmark/adaptation/adapters/multimodal/test_in_context_learning_multimodal_adapter.py +4 -2
  16. helm/benchmark/adaptation/adapters/multimodal/test_multimodal_prompt.py +1 -1
  17. helm/benchmark/adaptation/adapters/multiple_choice_calibrated_adapter.py +1 -1
  18. helm/benchmark/adaptation/adapters/multiple_choice_joint_adapter.py +2 -2
  19. helm/benchmark/adaptation/adapters/multiple_choice_joint_chain_of_thought_adapter.py +87 -0
  20. helm/benchmark/adaptation/adapters/multiple_choice_separate_adapter.py +1 -1
  21. helm/benchmark/adaptation/adapters/test_adapter.py +4 -4
  22. helm/benchmark/adaptation/adapters/test_generation_adapter.py +3 -3
  23. helm/benchmark/adaptation/adapters/test_language_modeling_adapter.py +2 -2
  24. helm/benchmark/adaptation/adapters/test_multiple_choice_joint_adapter.py +2 -2
  25. helm/benchmark/adaptation/common_adapter_specs.py +69 -4
  26. helm/benchmark/adaptation/prompt.py +1 -1
  27. helm/benchmark/annotation/aci_bench_annotator.py +95 -0
  28. helm/benchmark/annotation/air_bench_annotator.py +21 -6
  29. helm/benchmark/annotation/annotator.py +5 -0
  30. helm/benchmark/annotation/annotator_factory.py +3 -20
  31. helm/benchmark/annotation/autobencher_capabilities_annotator.py +107 -0
  32. helm/benchmark/annotation/autobencher_safety_annotator.py +98 -0
  33. helm/benchmark/annotation/bigcodebench_annotator.py +108 -0
  34. helm/benchmark/annotation/bird_sql_annotator.py +58 -0
  35. helm/benchmark/annotation/chw_care_plan_annotator.py +93 -0
  36. helm/benchmark/annotation/czech_bank_qa_annotator.py +78 -0
  37. helm/benchmark/annotation/dischargeme_annotator.py +107 -0
  38. helm/benchmark/annotation/ehr_sql_annotator.py +87 -0
  39. helm/benchmark/annotation/helpdesk_call_summarization_annotator.py +131 -0
  40. helm/benchmark/annotation/image2struct/image_compiler_annotator.py +6 -1
  41. helm/benchmark/annotation/live_qa_annotator.py +1 -1
  42. helm/benchmark/annotation/med_dialog_annotator.py +99 -0
  43. helm/benchmark/annotation/medalign_annotator.py +100 -0
  44. helm/benchmark/annotation/medi_qa_annotator.py +98 -0
  45. helm/benchmark/annotation/medication_qa_annotator.py +87 -63
  46. helm/benchmark/annotation/mental_health_annotator.py +98 -0
  47. helm/benchmark/annotation/mimic_bhc_annotator.py +100 -0
  48. helm/benchmark/annotation/mimic_rrs_annotator.py +100 -0
  49. helm/benchmark/annotation/model_as_judge.py +214 -6
  50. helm/benchmark/annotation/mtsamples_procedures_annotator.py +98 -0
  51. helm/benchmark/annotation/mtsamples_replicate_annotator.py +101 -0
  52. helm/benchmark/annotation/omni_math/gpt_evaluation_template.txt +152 -0
  53. helm/benchmark/annotation/omni_math/gpt_evaluation_zero_shot_template.txt +36 -0
  54. helm/benchmark/annotation/omni_math_annotator.py +131 -0
  55. helm/benchmark/annotation/spider_annotator.py +18 -0
  56. helm/benchmark/annotation/starr_patient_instructions_annotator.py +98 -0
  57. helm/benchmark/annotation/wildbench/eval_template.pairwise.v2.md +75 -0
  58. helm/benchmark/annotation/wildbench/eval_template.score.v2.md +66 -0
  59. helm/benchmark/annotation/wildbench_annotator.py +119 -0
  60. helm/benchmark/annotation_executor.py +35 -15
  61. helm/benchmark/augmentations/cleva_perturbation.py +9 -8
  62. helm/benchmark/augmentations/contraction_expansion_perturbation.py +2 -2
  63. helm/benchmark/augmentations/contrast_sets_perturbation.py +2 -2
  64. helm/benchmark/augmentations/dialect_perturbation.py +4 -5
  65. helm/benchmark/augmentations/extra_space_perturbation.py +2 -2
  66. helm/benchmark/augmentations/filler_words_perturbation.py +2 -2
  67. helm/benchmark/augmentations/gender_perturbation.py +2 -2
  68. helm/benchmark/augmentations/lowercase_perturbation.py +2 -2
  69. helm/benchmark/augmentations/mild_mix_perturbation.py +6 -6
  70. helm/benchmark/augmentations/misspelling_perturbation.py +2 -2
  71. helm/benchmark/augmentations/person_name_perturbation.py +4 -5
  72. helm/benchmark/augmentations/perturbation.py +1 -1
  73. helm/benchmark/augmentations/space_perturbation.py +2 -2
  74. helm/benchmark/augmentations/suffix_perturbation.py +2 -2
  75. helm/benchmark/augmentations/synonym_perturbation.py +4 -3
  76. helm/benchmark/augmentations/test_perturbation.py +16 -13
  77. helm/benchmark/augmentations/translate_perturbation.py +2 -2
  78. helm/benchmark/augmentations/typos_perturbation.py +2 -2
  79. helm/benchmark/data_preprocessor.py +2 -2
  80. helm/benchmark/executor.py +11 -12
  81. helm/benchmark/huggingface_registration.py +2 -7
  82. helm/benchmark/metrics/aci_bench_metrics.py +14 -0
  83. helm/benchmark/metrics/basic_metrics.py +6 -6
  84. helm/benchmark/metrics/bbq_metrics.py +2 -2
  85. helm/benchmark/metrics/bias_metrics.py +12 -3
  86. helm/benchmark/metrics/bias_word_lists.py +1 -1
  87. helm/benchmark/metrics/bigcodebench_metrics.py +25 -0
  88. helm/benchmark/metrics/bird_sql_metrics.py +28 -0
  89. helm/benchmark/metrics/chw_care_plan_metrics.py +14 -0
  90. helm/benchmark/metrics/classification_metrics.py +76 -12
  91. helm/benchmark/metrics/cleva_harms_metrics.py +10 -9
  92. helm/benchmark/metrics/code_metrics.py +5 -5
  93. helm/benchmark/metrics/comet_metric.py +125 -0
  94. helm/benchmark/metrics/common_metric_specs.py +9 -2
  95. helm/benchmark/metrics/conv_fin_qa_calc_metrics.py +72 -0
  96. helm/benchmark/metrics/copyright_metrics.py +4 -4
  97. helm/benchmark/metrics/czech_bank_qa_metrics.py +29 -0
  98. helm/benchmark/metrics/decodingtrust_fairness_metrics.py +2 -2
  99. helm/benchmark/metrics/decodingtrust_privacy_metrics.py +2 -2
  100. helm/benchmark/metrics/decodingtrust_stereotype_bias_metrics.py +2 -2
  101. helm/benchmark/metrics/dischargeme_metrics.py +14 -0
  102. helm/benchmark/metrics/disinformation_metrics.py +4 -4
  103. helm/benchmark/metrics/dry_run_metrics.py +5 -5
  104. helm/benchmark/metrics/efficiency_metrics.py +6 -6
  105. helm/benchmark/metrics/ehr_sql_metrics.py +103 -0
  106. helm/benchmark/metrics/evaluate_instances_metric.py +3 -3
  107. helm/benchmark/metrics/evaluate_reference_metrics.py +144 -16
  108. helm/benchmark/metrics/gpqa_chain_of_thought_metric.py +103 -0
  109. helm/benchmark/metrics/gpt4_audio_critique_metrics.py +167 -0
  110. helm/benchmark/metrics/gpt4_audio_refusal_metrics.py +145 -0
  111. helm/benchmark/metrics/helpdesk_call_summarization_metrics.py +36 -0
  112. helm/benchmark/metrics/ifeval/__init__.py +0 -0
  113. helm/benchmark/metrics/ifeval/instructions.py +1574 -0
  114. helm/benchmark/metrics/ifeval/instructions_registry.py +182 -0
  115. helm/benchmark/metrics/ifeval/instructions_registry.pyi +3 -0
  116. helm/benchmark/metrics/ifeval/instructions_util.py +153 -0
  117. helm/benchmark/metrics/ifeval_metrics.py +55 -0
  118. helm/benchmark/metrics/image_generation/aesthetics_metrics.py +1 -1
  119. helm/benchmark/metrics/image_generation/detection_metrics.py +1 -1
  120. helm/benchmark/metrics/image_generation/detectors/vitdet.py +1 -1
  121. helm/benchmark/metrics/image_generation/fractal_dimension/test_fractal_dimension_util.py +1 -1
  122. helm/benchmark/metrics/image_generation/fractal_dimension_metric.py +1 -1
  123. helm/benchmark/metrics/image_generation/nsfw_metrics.py +1 -1
  124. helm/benchmark/metrics/image_generation/q16/test_q16.py +3 -1
  125. helm/benchmark/metrics/image_generation/q16_toxicity_metrics.py +1 -1
  126. helm/benchmark/metrics/image_generation/skin_tone_metrics.py +2 -2
  127. helm/benchmark/metrics/image_generation/watermark/test_watermark_detector.py +1 -1
  128. helm/benchmark/metrics/image_generation/watermark_metrics.py +1 -1
  129. helm/benchmark/metrics/instruction_following_critique_metrics.py +4 -4
  130. helm/benchmark/metrics/kpi_edgar_metrics.py +121 -0
  131. helm/benchmark/metrics/language_modeling_metrics.py +4 -4
  132. helm/benchmark/metrics/llm_jury_metrics.py +46 -0
  133. helm/benchmark/metrics/machine_translation_metrics.py +2 -2
  134. helm/benchmark/metrics/med_dialog_metrics.py +14 -0
  135. helm/benchmark/metrics/medalign_metrics.py +14 -0
  136. helm/benchmark/metrics/medcalc_bench_metrics.py +124 -0
  137. helm/benchmark/metrics/medec_metrics.py +101 -0
  138. helm/benchmark/metrics/medi_qa_metrics.py +14 -0
  139. helm/benchmark/metrics/medication_qa_metrics.py +10 -19
  140. helm/benchmark/metrics/melt_bias_metric.py +234 -0
  141. helm/benchmark/metrics/melt_bias_word_lists.py +1367 -0
  142. helm/benchmark/metrics/melt_metric_specs.py +43 -0
  143. helm/benchmark/metrics/melt_toxicity_metric.py +107 -0
  144. helm/benchmark/metrics/mental_health_metrics.py +14 -0
  145. helm/benchmark/metrics/metric.py +3 -3
  146. helm/benchmark/metrics/metric_service.py +11 -11
  147. helm/benchmark/metrics/mimic_bhc_metrics.py +14 -0
  148. helm/benchmark/metrics/mimic_rrs_metrics.py +14 -0
  149. helm/benchmark/metrics/mimiciv_billing_code_metrics.py +96 -0
  150. helm/benchmark/metrics/mtsamples_procedures_metrics.py +14 -0
  151. helm/benchmark/metrics/mtsamples_replicate_metrics.py +14 -0
  152. helm/benchmark/metrics/nltk_helper.py +32 -0
  153. helm/benchmark/metrics/numeracy_metrics.py +4 -4
  154. helm/benchmark/metrics/omni_math_metrics.py +32 -0
  155. helm/benchmark/metrics/openai_mrcr_metrics.py +52 -0
  156. helm/benchmark/metrics/output_processing_metric.py +60 -0
  157. helm/benchmark/metrics/output_processors.py +15 -0
  158. helm/benchmark/metrics/paraphrase_generation_metrics.py +2 -2
  159. helm/benchmark/metrics/ranking_metrics.py +3 -3
  160. helm/benchmark/metrics/reference_metric.py +3 -3
  161. helm/benchmark/metrics/ruler_qa_metrics.py +34 -0
  162. helm/benchmark/metrics/{bhasa_metrics.py → seahelm_metrics.py} +3 -3
  163. helm/benchmark/metrics/seahelm_metrics_specs.py +10 -0
  164. helm/benchmark/metrics/spider_metrics.py +7 -0
  165. helm/benchmark/metrics/starr_patient_instructions_metrics.py +14 -0
  166. helm/benchmark/metrics/statistic.py +1 -1
  167. helm/benchmark/metrics/summac/model_summac.py +2 -3
  168. helm/benchmark/metrics/summarization_critique_metrics.py +4 -4
  169. helm/benchmark/metrics/summarization_metrics.py +20 -9
  170. helm/benchmark/metrics/test_bias_metrics.py +5 -1
  171. helm/benchmark/metrics/test_classification_metrics.py +140 -68
  172. helm/benchmark/metrics/test_evaluate_reference_metrics.py +15 -0
  173. helm/benchmark/metrics/test_metric.py +1 -1
  174. helm/benchmark/metrics/test_statistic.py +2 -2
  175. helm/benchmark/metrics/tokens/ai21_token_cost_estimator.py +1 -1
  176. helm/benchmark/metrics/tokens/auto_token_cost_estimator.py +6 -6
  177. helm/benchmark/metrics/tokens/cohere_token_cost_estimator.py +1 -1
  178. helm/benchmark/metrics/tokens/free_token_cost_estimator.py +1 -1
  179. helm/benchmark/metrics/tokens/gooseai_token_cost_estimator.py +1 -1
  180. helm/benchmark/metrics/tokens/openai_token_cost_estimator.py +1 -1
  181. helm/benchmark/metrics/tokens/test_ai21_token_cost_estimator.py +1 -1
  182. helm/benchmark/metrics/tokens/test_openai_token_cost_estimator.py +3 -3
  183. helm/benchmark/metrics/toxicity_metrics.py +6 -6
  184. helm/benchmark/metrics/unitxt_metrics.py +7 -5
  185. helm/benchmark/metrics/vision_language/emd_utils.py +4 -2
  186. helm/benchmark/metrics/vision_language/image_metrics.py +1 -1
  187. helm/benchmark/metrics/vision_language/image_utils.py +2 -2
  188. helm/benchmark/metrics/wildbench_metrics.py +34 -0
  189. helm/benchmark/model_deployment_registry.py +6 -8
  190. helm/benchmark/model_metadata_registry.py +16 -0
  191. helm/benchmark/presentation/contamination.py +3 -3
  192. helm/benchmark/presentation/create_plots.py +33 -12
  193. helm/benchmark/presentation/run_display.py +13 -0
  194. helm/benchmark/presentation/schema.py +2 -1
  195. helm/benchmark/presentation/summarize.py +97 -67
  196. helm/benchmark/presentation/torr_robustness_summarizer.py +178 -0
  197. helm/benchmark/reeval_run.py +202 -0
  198. helm/benchmark/reeval_runner.py +355 -0
  199. helm/benchmark/run.py +86 -90
  200. helm/benchmark/run_expander.py +90 -9
  201. helm/benchmark/run_spec_factory.py +13 -0
  202. helm/benchmark/run_specs/air_bench_run_specs.py +21 -3
  203. helm/benchmark/run_specs/audio_run_specs.py +657 -0
  204. helm/benchmark/run_specs/call_center_run_specs.py +49 -0
  205. helm/benchmark/run_specs/capabilities_run_specs.py +308 -0
  206. helm/benchmark/run_specs/classic_run_specs.py +1 -69
  207. helm/benchmark/run_specs/enem_challenge_specs.py +31 -0
  208. helm/benchmark/run_specs/enterprise_run_specs.py +280 -0
  209. helm/benchmark/run_specs/experimental_run_specs.py +142 -3
  210. helm/benchmark/run_specs/imdb_ptbr_run_specs.py +30 -0
  211. helm/benchmark/run_specs/lite_run_specs.py +2 -2
  212. helm/benchmark/run_specs/long_context_run_specs.py +141 -0
  213. helm/benchmark/run_specs/medhelm_run_specs.py +1260 -0
  214. helm/benchmark/run_specs/melt_run_specs.py +783 -0
  215. helm/benchmark/run_specs/mmlu_clinical_afr_run_specs.py +49 -0
  216. helm/benchmark/run_specs/oab_exams_specs.py +32 -0
  217. helm/benchmark/run_specs/safety_run_specs.py +37 -0
  218. helm/benchmark/run_specs/{bhasa_run_specs.py → seahelm_run_specs.py} +44 -44
  219. helm/benchmark/run_specs/speech_disorder_audio_run_specs.py +169 -0
  220. helm/benchmark/run_specs/sql_run_specs.py +54 -0
  221. helm/benchmark/run_specs/tweetsentbr_run_specs.py +32 -0
  222. helm/benchmark/run_specs/unitxt_run_specs.py +14 -5
  223. helm/benchmark/run_specs/vlm_run_specs.py +103 -2
  224. helm/benchmark/run_specs/winogrande_afr_run_specs.py +47 -0
  225. helm/benchmark/runner.py +5 -5
  226. helm/benchmark/scenarios/aci_bench_scenario.py +126 -0
  227. helm/benchmark/scenarios/air_bench_scenario.py +6 -1
  228. helm/benchmark/scenarios/anthropic_hh_rlhf_scenario.py +5 -3
  229. helm/benchmark/scenarios/anthropic_red_team_scenario.py +1 -1
  230. helm/benchmark/scenarios/audio_language/__init__.py +0 -0
  231. helm/benchmark/scenarios/audio_language/air_bench_chat_scenario.py +130 -0
  232. helm/benchmark/scenarios/audio_language/air_bench_foundation_scenario.py +154 -0
  233. helm/benchmark/scenarios/audio_language/ami_scenario.py +96 -0
  234. helm/benchmark/scenarios/audio_language/audio_mnist_scenario.py +62 -0
  235. helm/benchmark/scenarios/audio_language/audio_pairs_scenario.py +62 -0
  236. helm/benchmark/scenarios/audio_language/audiocaps_scenario.py +59 -0
  237. helm/benchmark/scenarios/audio_language/casual_conversations2_scenario.py +152 -0
  238. helm/benchmark/scenarios/audio_language/common_voice_15_scenario.py +99 -0
  239. helm/benchmark/scenarios/audio_language/corebench_scenario.py +77 -0
  240. helm/benchmark/scenarios/audio_language/covost2_scenario.py +163 -0
  241. helm/benchmark/scenarios/audio_language/fleurs_fairness_scenario.py +83 -0
  242. helm/benchmark/scenarios/audio_language/fleurs_scenario.py +312 -0
  243. helm/benchmark/scenarios/audio_language/iemocap_audio_scenario.py +83 -0
  244. helm/benchmark/scenarios/audio_language/librispeech_fairness_scenario.py +96 -0
  245. helm/benchmark/scenarios/audio_language/librispeech_scenario.py +80 -0
  246. helm/benchmark/scenarios/audio_language/meld_audio_scenario.py +113 -0
  247. helm/benchmark/scenarios/audio_language/multilingual_librispeech_scenario.py +80 -0
  248. helm/benchmark/scenarios/audio_language/mustard_scenario.py +142 -0
  249. helm/benchmark/scenarios/audio_language/mutox_scenario.py +254 -0
  250. helm/benchmark/scenarios/audio_language/parade_scenario.py +97 -0
  251. helm/benchmark/scenarios/audio_language/speech_robust_bench_scenario.py +124 -0
  252. helm/benchmark/scenarios/audio_language/ultra_suite_asr_classification.py +103 -0
  253. helm/benchmark/scenarios/audio_language/ultra_suite_classification_scenario.py +110 -0
  254. helm/benchmark/scenarios/audio_language/ultra_suite_disorder_breakdown_scenario.py +78 -0
  255. helm/benchmark/scenarios/audio_language/ultra_suite_disorder_symptoms_scenario.py +109 -0
  256. helm/benchmark/scenarios/audio_language/vocal_sound_scenario.py +83 -0
  257. helm/benchmark/scenarios/audio_language/voice_jailbreak_attacks_scenario.py +87 -0
  258. helm/benchmark/scenarios/audio_language/voxceleb2_scenario.py +105 -0
  259. helm/benchmark/scenarios/autobencher_capabilities_scenario.py +68 -0
  260. helm/benchmark/scenarios/autobencher_safety_scenario.py +51 -0
  261. helm/benchmark/scenarios/babi_qa_scenario.py +1 -1
  262. helm/benchmark/scenarios/banking77_scenario.py +6 -1
  263. helm/benchmark/scenarios/bbq_scenario.py +1 -1
  264. helm/benchmark/scenarios/big_bench_scenario.py +11 -1
  265. helm/benchmark/scenarios/bigcodebench_scenario.py +58 -0
  266. helm/benchmark/scenarios/bird_sql_scenario.py +94 -0
  267. helm/benchmark/scenarios/bird_sql_scenario_helper.py +118 -0
  268. helm/benchmark/scenarios/blimp_scenario.py +1 -1
  269. helm/benchmark/scenarios/bold_scenario.py +1 -1
  270. helm/benchmark/scenarios/boolq_scenario.py +1 -1
  271. helm/benchmark/scenarios/casehold_scenario.py +79 -0
  272. helm/benchmark/scenarios/chw_care_plan_scenario.py +106 -0
  273. helm/benchmark/scenarios/civil_comments_scenario.py +1 -1
  274. helm/benchmark/scenarios/clear_scenario.py +157 -0
  275. helm/benchmark/scenarios/cleva_scenario.py +2 -2
  276. helm/benchmark/scenarios/code_scenario.py +17 -4
  277. helm/benchmark/scenarios/commonsense_scenario.py +1 -1
  278. helm/benchmark/scenarios/conv_fin_qa_calc_scenario.py +97 -0
  279. helm/benchmark/scenarios/copyright_scenario.py +1 -1
  280. helm/benchmark/scenarios/covid_dialog_scenario.py +10 -1
  281. helm/benchmark/scenarios/cti_to_mitre_scenario.py +240 -0
  282. helm/benchmark/scenarios/custom_mcqa_scenario.py +1 -1
  283. helm/benchmark/scenarios/czech_bank_qa_scenario.py +130 -0
  284. helm/benchmark/scenarios/decodingtrust_adv_demonstration_scenario.py +1 -1
  285. helm/benchmark/scenarios/decodingtrust_privacy_scenario.py +1 -1
  286. helm/benchmark/scenarios/decodingtrust_stereotype_bias_scenario.py +1 -1
  287. helm/benchmark/scenarios/decodingtrust_toxicity_prompts_scenario.py +1 -1
  288. helm/benchmark/scenarios/dialogue_scenarios.py +13 -2
  289. helm/benchmark/scenarios/dischargeme_scenario.py +172 -0
  290. helm/benchmark/scenarios/disinformation_scenario.py +10 -1
  291. helm/benchmark/scenarios/dyck_language_scenario.py +10 -1
  292. helm/benchmark/scenarios/echr_judgment_classification_scenario.py +113 -0
  293. helm/benchmark/scenarios/ehr_sql_scenario.py +137 -0
  294. helm/benchmark/scenarios/ehrshot_scenario.py +1519 -0
  295. helm/benchmark/scenarios/enem_challenge_scenario.py +58 -0
  296. helm/benchmark/scenarios/entity_data_imputation_scenario.py +11 -1
  297. helm/benchmark/scenarios/entity_matching_scenario.py +12 -2
  298. helm/benchmark/scenarios/financial_phrasebank_scenario.py +94 -0
  299. helm/benchmark/scenarios/gold_commodity_news_scenario.py +124 -0
  300. helm/benchmark/scenarios/gpqa_scenario.py +80 -0
  301. helm/benchmark/scenarios/grammar.py +2 -2
  302. helm/benchmark/scenarios/grammar_scenario.py +2 -2
  303. helm/benchmark/scenarios/gsm_scenario.py +10 -1
  304. helm/benchmark/scenarios/harm_bench_gcg_transfer_scenario.py +50 -0
  305. helm/benchmark/scenarios/harm_bench_scenario.py +1 -1
  306. helm/benchmark/scenarios/headqa_scenario.py +136 -0
  307. helm/benchmark/scenarios/helpdesk_call_summarization_scenario.py +37 -0
  308. helm/benchmark/scenarios/ice_scenario.py +8 -4
  309. helm/benchmark/scenarios/ifeval_scenario.py +53 -0
  310. helm/benchmark/scenarios/imdb_ptbr_scenario.py +60 -0
  311. helm/benchmark/scenarios/imdb_scenario.py +11 -2
  312. helm/benchmark/scenarios/infinite_bench_en_qa_scenario.py +85 -0
  313. helm/benchmark/scenarios/infinite_bench_en_sum_scenario.py +79 -0
  314. helm/benchmark/scenarios/interactive_qa_mmlu_scenario.py +2 -2
  315. helm/benchmark/scenarios/koala_scenario.py +1 -1
  316. helm/benchmark/scenarios/kpi_edgar_scenario.py +151 -0
  317. helm/benchmark/scenarios/legal_contract_summarization_scenario.py +129 -0
  318. helm/benchmark/scenarios/legal_opinion_sentiment_classification_scenario.py +77 -0
  319. helm/benchmark/scenarios/legal_summarization_scenario.py +11 -1
  320. helm/benchmark/scenarios/legal_support_scenario.py +11 -1
  321. helm/benchmark/scenarios/legalbench_scenario.py +22 -3
  322. helm/benchmark/scenarios/lex_glue_scenario.py +12 -2
  323. helm/benchmark/scenarios/lextreme_scenario.py +11 -1
  324. helm/benchmark/scenarios/live_qa_scenario.py +1 -1
  325. helm/benchmark/scenarios/lm_entry_scenario.py +1 -1
  326. helm/benchmark/scenarios/lsat_qa_scenario.py +1 -1
  327. helm/benchmark/scenarios/math_scenario.py +9 -1
  328. helm/benchmark/scenarios/me_q_sum_scenario.py +10 -1
  329. helm/benchmark/scenarios/med_dialog_scenario.py +25 -22
  330. helm/benchmark/scenarios/med_mcqa_scenario.py +10 -1
  331. helm/benchmark/scenarios/med_paragraph_simplification_scenario.py +10 -1
  332. helm/benchmark/scenarios/med_qa_scenario.py +10 -1
  333. helm/benchmark/scenarios/medalign_scenario.py +94 -0
  334. helm/benchmark/scenarios/medalign_scenario_helper.py +432 -0
  335. helm/benchmark/scenarios/medbullets_scenario.py +145 -0
  336. helm/benchmark/scenarios/medcalc_bench_scenario.py +127 -0
  337. helm/benchmark/scenarios/medec_scenario.py +125 -0
  338. helm/benchmark/scenarios/medhallu_scenario.py +72 -0
  339. helm/benchmark/scenarios/medi_qa_scenario.py +111 -0
  340. helm/benchmark/scenarios/medication_qa_scenario.py +8 -2
  341. helm/benchmark/scenarios/melt_ir_scenario.py +171 -0
  342. helm/benchmark/scenarios/melt_knowledge_scenario.py +246 -0
  343. helm/benchmark/scenarios/melt_lm_scenarios.py +252 -0
  344. helm/benchmark/scenarios/melt_scenarios.py +793 -0
  345. helm/benchmark/scenarios/melt_srn_scenario.py +342 -0
  346. helm/benchmark/scenarios/melt_synthetic_reasoning_scenario.py +222 -0
  347. helm/benchmark/scenarios/melt_translation_scenario.py +152 -0
  348. helm/benchmark/scenarios/mental_health_scenario.py +123 -0
  349. helm/benchmark/scenarios/mimic_bhc_scenario.py +103 -0
  350. helm/benchmark/scenarios/mimic_rrs_scenario.py +98 -0
  351. helm/benchmark/scenarios/mimiciv_billing_code_scenario.py +77 -0
  352. helm/benchmark/scenarios/mmlu_clinical_afr_scenario.py +74 -0
  353. helm/benchmark/scenarios/mmlu_pro_scenario.py +95 -0
  354. helm/benchmark/scenarios/mmlu_scenario.py +11 -1
  355. helm/benchmark/scenarios/msmarco_scenario.py +1 -1
  356. helm/benchmark/scenarios/mtsamples_procedures_scenario.py +144 -0
  357. helm/benchmark/scenarios/mtsamples_replicate_scenario.py +142 -0
  358. helm/benchmark/scenarios/n2c2_ct_matching_scenario.py +277 -0
  359. helm/benchmark/scenarios/narrativeqa_scenario.py +1 -1
  360. helm/benchmark/scenarios/natural_qa_scenario.py +1 -1
  361. helm/benchmark/scenarios/newsqa_scenario.py +1 -1
  362. helm/benchmark/scenarios/numeracy_scenario.py +12 -2
  363. helm/benchmark/scenarios/oab_exams_scenario.py +57 -0
  364. helm/benchmark/scenarios/omni_math_scenario.py +53 -0
  365. helm/benchmark/scenarios/open_assistant_scenario.py +11 -2
  366. helm/benchmark/scenarios/openai_mrcr_scenario.py +79 -0
  367. helm/benchmark/scenarios/opinions_qa_scenario.py +1 -1
  368. helm/benchmark/scenarios/pubmed_qa_scenario.py +59 -43
  369. helm/benchmark/scenarios/quac_scenario.py +10 -1
  370. helm/benchmark/scenarios/race_based_med_scenario.py +152 -0
  371. helm/benchmark/scenarios/raft_scenario.py +17 -2
  372. helm/benchmark/scenarios/real_toxicity_prompts_scenario.py +1 -1
  373. helm/benchmark/scenarios/ruler_qa_scenario_helper.py +171 -0
  374. helm/benchmark/scenarios/ruler_qa_scenarios.py +88 -0
  375. helm/benchmark/scenarios/scenario.py +9 -1
  376. helm/benchmark/scenarios/{bhasa_scenario.py → seahelm_scenario.py} +7 -2
  377. helm/benchmark/scenarios/self_instruct_scenario.py +1 -1
  378. helm/benchmark/scenarios/shc_bmt_scenario.py +75 -0
  379. helm/benchmark/scenarios/shc_cdi_scenario.py +75 -0
  380. helm/benchmark/scenarios/shc_conf_scenario.py +76 -0
  381. helm/benchmark/scenarios/shc_ent_scenario.py +77 -0
  382. helm/benchmark/scenarios/shc_gip_scenario.py +74 -0
  383. helm/benchmark/scenarios/shc_privacy_scenario.py +78 -0
  384. helm/benchmark/scenarios/shc_proxy_scenario.py +76 -0
  385. helm/benchmark/scenarios/shc_ptbm_scenario.py +81 -0
  386. helm/benchmark/scenarios/shc_sei_scenario.py +94 -0
  387. helm/benchmark/scenarios/shc_sequoia_scenario.py +77 -0
  388. helm/benchmark/scenarios/simple_safety_tests_scenario.py +1 -1
  389. helm/benchmark/scenarios/spider_scenario.py +91 -0
  390. helm/benchmark/scenarios/starr_patient_instructions_scenario.py +97 -0
  391. helm/benchmark/scenarios/summarization_scenario.py +11 -1
  392. helm/benchmark/scenarios/sumosum_scenario.py +157 -0
  393. helm/benchmark/scenarios/synthetic_efficiency_scenario.py +1 -1
  394. helm/benchmark/scenarios/synthetic_reasoning_natural_scenario.py +11 -1
  395. helm/benchmark/scenarios/synthetic_reasoning_scenario.py +11 -1
  396. helm/benchmark/scenarios/test_bigcodebench_scenario.py +26 -0
  397. helm/benchmark/scenarios/test_czech_bank_qa_scenario.py +18 -0
  398. helm/benchmark/scenarios/test_enem_challenge_scenario.py +53 -0
  399. helm/benchmark/scenarios/test_ewok_scenario.py +6 -2
  400. helm/benchmark/scenarios/test_gold_commodity_news_scenario.py +18 -0
  401. helm/benchmark/scenarios/test_gpqa_scenario.py +44 -0
  402. helm/benchmark/scenarios/test_ifeval_scenario.py +36 -0
  403. helm/benchmark/scenarios/test_imdb_ptbr_scenario.py +27 -0
  404. helm/benchmark/scenarios/test_infinite_bench_en_qa_scenario.py +18 -0
  405. helm/benchmark/scenarios/test_infinite_bench_en_sum_scenario.py +31 -0
  406. helm/benchmark/scenarios/test_math_scenario.py +1 -0
  407. helm/benchmark/scenarios/test_mmlu_clinical_afr_scenario.py +21 -0
  408. helm/benchmark/scenarios/test_mmlu_pro_scenario.py +53 -0
  409. helm/benchmark/scenarios/test_oab_exams_scenario.py +51 -0
  410. helm/benchmark/scenarios/test_omni_math_scenario.py +27 -0
  411. helm/benchmark/scenarios/test_tweetsentbr_scenario.py +24 -0
  412. helm/benchmark/scenarios/test_wildbench_scenario.py +15 -0
  413. helm/benchmark/scenarios/test_winogrande_afr_scenario.py +19 -0
  414. helm/benchmark/scenarios/thai_exam_scenario.py +10 -1
  415. helm/benchmark/scenarios/the_pile_scenario.py +1 -1
  416. helm/benchmark/scenarios/truthful_qa_scenario.py +12 -2
  417. helm/benchmark/scenarios/tweetsentbr_scenario.py +66 -0
  418. helm/benchmark/scenarios/twitter_aae_scenario.py +1 -1
  419. helm/benchmark/scenarios/unitxt_scenario.py +8 -2
  420. helm/benchmark/scenarios/verifiability_judgment_scenario.py +1 -1
  421. helm/benchmark/scenarios/vicuna_scenario.py +1 -1
  422. helm/benchmark/scenarios/vision_language/blink_scenario.py +140 -0
  423. helm/benchmark/scenarios/vision_language/mm_star_scenario.py +95 -0
  424. helm/benchmark/scenarios/vision_language/msr_vtt_scenario.py +75 -0
  425. helm/benchmark/scenarios/vision_language/vqa_rad_scenario.py +88 -0
  426. helm/benchmark/scenarios/wikifact_scenario.py +11 -1
  427. helm/benchmark/scenarios/wikitext_103_scenario.py +1 -1
  428. helm/benchmark/scenarios/wildbench_scenario.py +83 -0
  429. helm/benchmark/scenarios/winogrande_afr_scenario.py +78 -0
  430. helm/benchmark/scenarios/wmt_14_scenario.py +14 -2
  431. helm/benchmark/scenarios/xstest_scenario.py +1 -1
  432. helm/benchmark/server.py +13 -1
  433. helm/benchmark/slurm_runner.py +1 -1
  434. helm/benchmark/static/schema_audio.yaml +763 -0
  435. helm/benchmark/static/schema_autobencher.yaml +150 -0
  436. helm/benchmark/static/schema_call_center.yaml +97 -60
  437. helm/benchmark/static/{schema_medical.yaml → schema_capabilities.yaml} +100 -101
  438. helm/benchmark/static/schema_czech_bank.yaml +148 -0
  439. helm/benchmark/static/schema_enem_challenge.yaml +146 -0
  440. helm/benchmark/static/schema_enterprise.yaml +319 -0
  441. helm/benchmark/static/schema_finance.yaml +14 -12
  442. helm/benchmark/static/schema_heim.yaml +1389 -0
  443. helm/benchmark/static/schema_long_context.yaml +283 -0
  444. helm/benchmark/static/schema_medhelm.yaml +1140 -0
  445. helm/benchmark/static/schema_melt.yaml +1257 -0
  446. helm/benchmark/static/schema_mmlu_winogrande_afr.yaml +1045 -0
  447. helm/benchmark/static/schema_safety.yaml +18 -1
  448. helm/benchmark/static/{schema_bhasa.yaml → schema_seahelm.yaml} +30 -16
  449. helm/benchmark/static/schema_slphelm.yaml +162 -0
  450. helm/benchmark/static/schema_social_audio.yaml +224 -0
  451. helm/benchmark/static/schema_sql.yaml +171 -0
  452. helm/benchmark/static/{schema_tables.yaml → schema_torr.yaml} +169 -36
  453. helm/benchmark/static/schema_tweetsentbr.yaml +146 -0
  454. helm/benchmark/static/schema_vhelm.yaml +129 -56
  455. helm/benchmark/static/schema_video.yaml +219 -0
  456. helm/benchmark/static_build/assets/helm-safety-2907a7b6.png +0 -0
  457. helm/benchmark/static_build/assets/index-94295e78.js +10 -0
  458. helm/benchmark/static_build/assets/index-b9779128.css +1 -0
  459. helm/benchmark/static_build/assets/medhelm-overview-eac29843.png +0 -0
  460. helm/benchmark/static_build/assets/medhelm-v1-overview-3ddfcd65.png +0 -0
  461. helm/benchmark/static_build/assets/{react-d4a0b69b.js → react-f82877fd.js} +1 -1
  462. helm/benchmark/static_build/assets/{recharts-6d337683.js → recharts-4037aff0.js} +1 -1
  463. helm/benchmark/static_build/assets/{tremor-54a99cc4.js → tremor-38a10867.js} +2 -2
  464. helm/benchmark/static_build/config.js +1 -1
  465. helm/benchmark/static_build/index.html +6 -6
  466. helm/benchmark/window_services/default_window_service.py +1 -1
  467. helm/benchmark/window_services/encoder_decoder_window_service.py +4 -4
  468. helm/benchmark/window_services/ice_window_service.py +1 -1
  469. helm/benchmark/window_services/image_generation/lexica_search_window_service.py +1 -1
  470. helm/benchmark/window_services/image_generation/openai_dalle_window_service.py +1 -1
  471. helm/benchmark/window_services/local_window_service.py +2 -2
  472. helm/benchmark/window_services/test_anthropic_window_service.py +3 -3
  473. helm/benchmark/window_services/test_bloom_window_service.py +3 -3
  474. helm/benchmark/window_services/test_gpt2_window_service.py +7 -2
  475. helm/benchmark/window_services/test_gpt4_window_service.py +8 -3
  476. helm/benchmark/window_services/test_gptj_window_service.py +8 -3
  477. helm/benchmark/window_services/test_gptneox_window_service.py +3 -3
  478. helm/benchmark/window_services/test_openai_window_service.py +8 -3
  479. helm/benchmark/window_services/test_opt_window_service.py +3 -3
  480. helm/benchmark/window_services/test_palmyra_window_service.py +3 -3
  481. helm/benchmark/window_services/test_t0pp_window_service.py +3 -3
  482. helm/benchmark/window_services/test_t511b_window_service.py +3 -3
  483. helm/benchmark/window_services/test_ul2_window_service.py +3 -3
  484. helm/benchmark/window_services/test_utils.py +4 -5
  485. helm/benchmark/window_services/test_yalm_window_service.py +3 -3
  486. helm/benchmark/window_services/tokenizer_service.py +7 -8
  487. helm/benchmark/window_services/yalm_window_service.py +1 -1
  488. helm/clients/ai21_client.py +3 -3
  489. helm/clients/aleph_alpha_client.py +1 -1
  490. helm/clients/anthropic_client.py +69 -29
  491. helm/clients/audio_language/__init__.py +0 -0
  492. helm/clients/audio_language/diva_llama_client.py +120 -0
  493. helm/clients/audio_language/llama_omni_client.py +198 -0
  494. helm/clients/audio_language/qwen2_5_omni_client.py +197 -0
  495. helm/clients/audio_language/qwen2_audiolm_client.py +190 -0
  496. helm/clients/audio_language/qwen_audiolm_client.py +152 -0
  497. helm/clients/audio_language/test.py +62 -0
  498. helm/clients/auto_client.py +4 -2
  499. helm/clients/azure_openai_client.py +55 -0
  500. helm/clients/bedrock_client.py +203 -7
  501. helm/clients/bedrock_utils.py +33 -0
  502. helm/clients/client.py +7 -7
  503. helm/clients/clip_scorers/clip_scorer.py +1 -1
  504. helm/clients/clip_scorers/multilingual_clip_scorer.py +1 -1
  505. helm/clients/cohere_client.py +3 -3
  506. helm/clients/google_client.py +1 -1
  507. helm/clients/grok_client.py +36 -0
  508. helm/clients/http_model_client.py +1 -1
  509. helm/clients/huggingface_client.py +52 -21
  510. helm/clients/huggingface_pipeline_client.py +138 -0
  511. helm/clients/ibm_client.py +267 -0
  512. helm/clients/image_generation/adobe_vision_client.py +1 -1
  513. helm/clients/image_generation/aleph_alpha_image_generation_client.py +1 -1
  514. helm/clients/image_generation/cogview2/sr_pipeline/__init__.py +3 -3
  515. helm/clients/image_generation/cogview2/sr_pipeline/direct_sr.py +5 -2
  516. helm/clients/image_generation/cogview2/sr_pipeline/iterative_sr.py +5 -2
  517. helm/clients/image_generation/cogview2/sr_pipeline/sr_group.py +2 -2
  518. helm/clients/image_generation/cogview2_client.py +1 -1
  519. helm/clients/image_generation/dalle2_client.py +1 -1
  520. helm/clients/image_generation/dalle3_client.py +2 -2
  521. helm/clients/image_generation/dalle_mini/__init__.py +1 -1
  522. helm/clients/image_generation/dalle_mini/data.py +1 -1
  523. helm/clients/image_generation/dalle_mini/model/__init__.py +5 -5
  524. helm/clients/image_generation/dalle_mini/model/configuration.py +2 -2
  525. helm/clients/image_generation/dalle_mini/model/modeling.py +3 -3
  526. helm/clients/image_generation/dalle_mini/model/processor.py +5 -5
  527. helm/clients/image_generation/dalle_mini/model/tokenizer.py +2 -2
  528. helm/clients/image_generation/dalle_mini/vqgan_jax/__init__.py +1 -1
  529. helm/clients/image_generation/dalle_mini/vqgan_jax/convert_pt_model_to_jax.py +2 -2
  530. helm/clients/image_generation/dalle_mini/vqgan_jax/modeling_flax_vqgan.py +1 -1
  531. helm/clients/image_generation/dalle_mini_client.py +1 -1
  532. helm/clients/image_generation/deep_floyd_client.py +1 -1
  533. helm/clients/image_generation/huggingface_diffusers_client.py +1 -1
  534. helm/clients/image_generation/lexica_client.py +1 -1
  535. helm/clients/image_generation/mindalle/models/__init__.py +6 -6
  536. helm/clients/image_generation/mindalle/models/stage1/vqgan.py +1 -1
  537. helm/clients/image_generation/mindalle/models/stage2/transformer.py +1 -1
  538. helm/clients/image_generation/mindalle/utils/__init__.py +3 -3
  539. helm/clients/image_generation/mindalle_client.py +1 -1
  540. helm/clients/image_generation/together_image_generation_client.py +1 -1
  541. helm/clients/lit_gpt_client.py +2 -2
  542. helm/clients/mistral_client.py +62 -18
  543. helm/clients/nvidia_nim_client.py +0 -3
  544. helm/clients/openai_client.py +308 -43
  545. helm/clients/openai_responses_client.py +174 -0
  546. helm/clients/palmyra_client.py +3 -9
  547. helm/clients/reka_client.py +3 -3
  548. helm/clients/stanfordhealthcare_azure_openai_client.py +58 -0
  549. helm/clients/stanfordhealthcare_claude_client.py +31 -0
  550. helm/clients/stanfordhealthcare_google_client.py +43 -0
  551. helm/clients/stanfordhealthcare_http_model_client.py +93 -0
  552. helm/clients/stanfordhealthcare_openai_client.py +62 -0
  553. helm/clients/stanfordhealthcare_shc_openai_client.py +42 -0
  554. helm/clients/test_client.py +1 -1
  555. helm/clients/test_together_client.py +6 -1
  556. helm/clients/together_client.py +76 -9
  557. helm/clients/upstage_client.py +23 -0
  558. helm/clients/vertexai_client.py +45 -13
  559. helm/clients/vision_language/huggingface_vision2seq_client.py +6 -4
  560. helm/clients/vision_language/huggingface_vlm_client.py +2 -2
  561. helm/clients/vision_language/idefics_client.py +6 -2
  562. helm/clients/vision_language/open_flamingo/__init__.py +2 -2
  563. helm/clients/vision_language/open_flamingo/src/factory.py +3 -3
  564. helm/clients/vision_language/open_flamingo/src/flamingo.py +2 -2
  565. helm/clients/vision_language/open_flamingo/src/flamingo_lm.py +2 -2
  566. helm/clients/vision_language/paligemma_client.py +2 -2
  567. helm/clients/vision_language/qwen2_vlm_client.py +188 -0
  568. helm/clients/vision_language/qwen_vlm_client.py +7 -5
  569. helm/clients/vllm_client.py +4 -6
  570. helm/clients/writer_client.py +102 -0
  571. helm/clients/yi_client.py +0 -3
  572. helm/common/audio_utils.py +111 -0
  573. helm/common/context.py +80 -0
  574. helm/common/credentials_utils.py +5 -5
  575. helm/common/file_caches/local_file_cache.py +1 -1
  576. helm/common/file_caches/test_local_file_cache.py +1 -1
  577. helm/common/general.py +9 -2
  578. helm/common/hierarchical_logger.py +46 -3
  579. helm/common/images_utils.py +2 -2
  580. helm/common/local_context.py +140 -0
  581. helm/common/media_object.py +2 -2
  582. helm/common/multimodal_request_utils.py +26 -0
  583. helm/common/reeval_parameters.py +12 -0
  584. helm/common/remote_context.py +61 -0
  585. helm/common/request.py +14 -2
  586. helm/common/response_format.py +18 -0
  587. helm/common/test_media_object.py +1 -1
  588. helm/config/model_deployments.yaml +1792 -28
  589. helm/config/model_metadata.yaml +1606 -51
  590. helm/config/tokenizer_configs.yaml +521 -4
  591. helm/proxy/cli.py +5 -3
  592. helm/proxy/critique/mechanical_turk_utils.py +1 -1
  593. helm/proxy/example_queries.py +1 -1
  594. helm/proxy/server.py +11 -4
  595. helm/proxy/services/remote_service.py +1 -1
  596. helm/proxy/services/server_service.py +22 -86
  597. helm/proxy/services/test_remote_service.py +2 -2
  598. helm/proxy/services/test_service.py +1 -1
  599. helm/proxy/static/general.js +122 -0
  600. helm/proxy/static/help.html +99 -0
  601. helm/proxy/static/index.css +57 -0
  602. helm/proxy/static/index.html +40 -0
  603. helm/proxy/static/index.js +456 -0
  604. helm/proxy/static/info-icon.png +0 -0
  605. helm/proxy/test_retry.py +1 -1
  606. helm/proxy/token_counters/auto_token_counter.py +1 -1
  607. helm/tokenizers/aleph_alpha_tokenizer.py +1 -1
  608. helm/tokenizers/caching_tokenizer.py +2 -30
  609. helm/tokenizers/grok_tokenizer.py +53 -0
  610. helm/tokenizers/http_model_tokenizer.py +1 -1
  611. helm/tokenizers/huggingface_tokenizer.py +3 -3
  612. helm/tokenizers/lit_gpt_tokenizer.py +1 -1
  613. helm/tokenizers/test_anthropic_tokenizer.py +6 -2
  614. helm/tokenizers/test_grok_tokenizer.py +33 -0
  615. helm/tokenizers/test_huggingface_tokenizer.py +1 -1
  616. helm/tokenizers/test_yalm_tokenizer.py +1 -1
  617. helm/tokenizers/tiktoken_tokenizer.py +1 -1
  618. helm/tokenizers/tokenizer.py +3 -1
  619. helm/tokenizers/yalm_tokenizer.py +3 -3
  620. helm/tokenizers/yalm_tokenizer_data/test_yalm_tokenizer.py +1 -1
  621. crfm_helm-0.5.4.dist-info/METADATA +0 -350
  622. crfm_helm-0.5.4.dist-info/RECORD +0 -697
  623. helm/benchmark/metrics/bhasa_metrics_specs.py +0 -10
  624. helm/benchmark/static_build/assets/01-694cb9b7.png +0 -0
  625. helm/benchmark/static_build/assets/accenture-6f97eeda.png +0 -0
  626. helm/benchmark/static_build/assets/ai21-0eb91ec3.png +0 -0
  627. helm/benchmark/static_build/assets/aisingapore-6dfc9acf.png +0 -0
  628. helm/benchmark/static_build/assets/aleph-alpha-7ce10034.png +0 -0
  629. helm/benchmark/static_build/assets/anthropic-70d8bc39.png +0 -0
  630. helm/benchmark/static_build/assets/bigscience-7f0400c0.png +0 -0
  631. helm/benchmark/static_build/assets/cohere-3550c6cb.png +0 -0
  632. helm/benchmark/static_build/assets/cresta-9e22b983.png +0 -0
  633. helm/benchmark/static_build/assets/cuhk-8c5631e9.png +0 -0
  634. helm/benchmark/static_build/assets/eleutherai-b9451114.png +0 -0
  635. helm/benchmark/static_build/assets/google-06d997ad.png +0 -0
  636. helm/benchmark/static_build/assets/index-05c76bb1.css +0 -1
  637. helm/benchmark/static_build/assets/index-3ee38b3d.js +0 -10
  638. helm/benchmark/static_build/assets/meta-5580e9f1.png +0 -0
  639. helm/benchmark/static_build/assets/microsoft-f5ee5016.png +0 -0
  640. helm/benchmark/static_build/assets/mistral-18e1be23.png +0 -0
  641. helm/benchmark/static_build/assets/nvidia-86fa75c1.png +0 -0
  642. helm/benchmark/static_build/assets/openai-3f8653e4.png +0 -0
  643. helm/benchmark/static_build/assets/scb10x-204bd786.png +0 -0
  644. helm/benchmark/static_build/assets/tii-24de195c.png +0 -0
  645. helm/benchmark/static_build/assets/together-a665a35b.png +0 -0
  646. helm/benchmark/static_build/assets/tsinghua-keg-97d4b395.png +0 -0
  647. helm/benchmark/static_build/assets/wellsfargo-a86a6c4a.png +0 -0
  648. helm/benchmark/static_build/assets/yandex-38e09d70.png +0 -0
  649. helm/tokenizers/anthropic_tokenizer.py +0 -52
  650. {crfm_helm-0.5.4.dist-info → crfm_helm-0.5.6.dist-info}/entry_points.txt +0 -0
  651. {crfm_helm-0.5.4.dist-info → crfm_helm-0.5.6.dist-info/licenses}/LICENSE +0 -0
  652. {crfm_helm-0.5.4.dist-info → crfm_helm-0.5.6.dist-info}/top_level.txt +0 -0
crfm_helm-0.5.4.dist-info/RECORD DELETED
@@ -1,697 +0,0 @@
1
- helm/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
2
- helm/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
3
- helm/benchmark/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
4
- helm/benchmark/annotation_executor.py,sha256=ZJCc5xT8E0E6gux8dq3HPS4YzQs2YPCNl4gx44ghuJM,4862
5
- helm/benchmark/config_registry.py,sha256=Cd25a8FHriUzAgvGGU5sBAPyhisdSIjdUJR4YbYs6T4,1603
6
- helm/benchmark/data_preprocessor.py,sha256=aNdM-o2t4qkLIQHiQeWUFg03DjjJ8HTBIphYCK8pXVo,2173
7
- helm/benchmark/executor.py,sha256=simd7SdJ7TciUpoq3D0uz_XUSCZj5KIWCIP57FYm4js,4906
8
- helm/benchmark/huggingface_registration.py,sha256=unEBO21V8K3-Ya0xLqjO9H1oq7RmU-f1MYV0tCIbXzY,4578
9
- helm/benchmark/model_deployment_registry.py,sha256=BjL0ghHgO7_Z5jZZ7kuSOj9saegI3BivaL-b699C0rc,9527
10
- helm/benchmark/model_metadata_registry.py,sha256=m39FqNaGdxP4r7W7Vmq6r-gOLjYtn_5WmRNsGzci6d8,8283
11
- helm/benchmark/multi_gpu_runner.py,sha256=WmTKpVfcKXyiiPzrmxpbvQoZy0Ua8IyPgxB8r_3jrRw,4773
12
- helm/benchmark/run.py,sha256=cPJh1Rwit8E_Kjf8Te2D75cd19ag4WgS2YrHHu2Fc8Q,13997
13
- helm/benchmark/run_expander.py,sha256=L9jvRjy3DGuNytA2eYQGBV-8VL_G8sry18FZ3OQoIlU,53323
14
- helm/benchmark/run_spec.py,sha256=GiIU8iGO2FGYFDWIxt51CeNPsW7rM7BzDqH1KgEL1cg,3217
15
- helm/benchmark/run_spec_factory.py,sha256=hp29n_Stb7RMwRm2jrP_qpyzxi8X8ojdqXTFN3KRSiY,6978
16
- helm/benchmark/runner.py,sha256=zlHDJ2Ys5-HxtXcwpkXcrdfXy_i886fBcq1iNeLyC3Q,14669
17
- helm/benchmark/runner_config_registry.py,sha256=2gW5wBLkHdYb2WNbZulto06hTcto2ROvjy8HULw3jNM,515
18
- helm/benchmark/server.py,sha256=kaGpUzBwzprmTDiMcy8-sfT8KfVEOb0wWytWODsAQ94,5925
19
- helm/benchmark/slurm_jobs.py,sha256=eNCAoaWDfT0Wk32ZJRIGo-x8kgjhDPnPB4Xrvw_eLB0,3225
20
- helm/benchmark/slurm_runner.py,sha256=Tozimrjr2R6mlKHcmrGgxTy9ga-ArIW6AoAWtxqzw-M,16567
21
- helm/benchmark/test_data_preprocessor.py,sha256=_esdtkqyU_8Yp5ZOO7n1b-Y4Qc28wpD5drG-4Y4UhIM,2219
22
- helm/benchmark/test_run_expander.py,sha256=gLeHkNt_nLgbwEJiYxhwda-eKA3sJAxkYolCvgRN5TY,1163
23
- helm/benchmark/tokenizer_config_registry.py,sha256=ZOImg38ta0FXZYAWna6q7A5xrG2mU7Ofr-8j4EqGlUY,1585
24
- helm/benchmark/adaptation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
25
- helm/benchmark/adaptation/adapter_spec.py,sha256=K5BwqTe2iimjswdw_SONlJo0xt-T-o5KH7VqxrPaov0,5072
26
- helm/benchmark/adaptation/common_adapter_specs.py,sha256=Er8aMbDi8RTBtGWjcI08E2mRDl5AoBzUaBT1EY38Nlw,10515
27
- helm/benchmark/adaptation/prompt.py,sha256=n0Ka3RGSWMr3CBnJrPNPy626x9TJE3k677wKbG8hO9A,2133
28
- helm/benchmark/adaptation/request_state.py,sha256=WAPyubn35on-Ry7xKpXsVz3wYBMCMc_LidDOdcKxatI,3053
29
- helm/benchmark/adaptation/scenario_state.py,sha256=mWEhgzk18SVoMEuj2pSnc_r9JrGAHLdOlteHJKUMA5k,1961
30
- helm/benchmark/adaptation/adapters/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
31
- helm/benchmark/adaptation/adapters/adapter.py,sha256=NbsvNITD_xByHxwknkHS_vWrzvO1peA9T1rjWbz_cy0,1239
32
- helm/benchmark/adaptation/adapters/adapter_factory.py,sha256=fJgOdJnaVNoBu-aP7GCoXlk8tOY1wyFgDMJVvhiblDQ,2837
33
- helm/benchmark/adaptation/adapters/binary_ranking_adapter.py,sha256=zF5KcGip5CAMfg5mzisYQ2jlIuChbraujN-UaxCV8E8,5782
34
- helm/benchmark/adaptation/adapters/generation_adapter.py,sha256=F7Aou6r9CZ1xEuAXxfxgQa6hrbrnuBtE7tgmCgOa7N0,2146
35
- helm/benchmark/adaptation/adapters/in_context_learning_adapter.py,sha256=BbcBEJjY8Cp58me9sUktd2p3dEVFL8ZJ7RFfus3hSYE,14997
36
- helm/benchmark/adaptation/adapters/language_modeling_adapter.py,sha256=LhZHmciP8lAfu7T0p634GOPTHrJR7qRCRRIxPgVlW9E,14873
37
- helm/benchmark/adaptation/adapters/multiple_choice_calibrated_adapter.py,sha256=VJ66MfIGQWJg0VXCV0MJEMwF9Jx1DeJ7RxsgYlOTx_4,1889
38
- helm/benchmark/adaptation/adapters/multiple_choice_joint_adapter.py,sha256=S38Y_MjLRE86LS9RfB4qHmNy5x5n2KyYa4DtA63lees,4402
39
- helm/benchmark/adaptation/adapters/multiple_choice_separate_adapter.py,sha256=aMe-y4iiyEnM7_bqIoddeZBsVLoDxMmjKY2eZKB6Y2Q,2156
40
- helm/benchmark/adaptation/adapters/test_adapter.py,sha256=0-JrYnogZu4kENQG1eQMXHWnuSurCLRbkLpDuSnfRqs,745
41
- helm/benchmark/adaptation/adapters/test_generation_adapter.py,sha256=NyhVTvLznCVMB-DJeX2DRjWx91XmW3FBcrkm0RN-fJU,12766
42
- helm/benchmark/adaptation/adapters/test_language_modeling_adapter.py,sha256=BCEhKRVEDKPHsLKhpnIv0krV37a8Eu78r8EtJxH_MXA,7980
43
- helm/benchmark/adaptation/adapters/test_multiple_choice_joint_adapter.py,sha256=BoozcN0zPWwk6HKEPN0b61ieqwk5y8bwKvr9m8DR_2k,11874
44
- helm/benchmark/adaptation/adapters/multimodal/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
45
- helm/benchmark/adaptation/adapters/multimodal/generation_multimodal_adapter.py,sha256=o7CGClyVWYOuJ4G56-whq5fTvCr7QIn51Mo6DTdvwg0,1881
46
- helm/benchmark/adaptation/adapters/multimodal/in_context_learning_multimodal_adapter.py,sha256=bvY8xT2ak_3WG4m2Z5bCM6FLImPIWG1qAn9H2ZNwNv0,6359
47
- helm/benchmark/adaptation/adapters/multimodal/multimodal_prompt.py,sha256=jyL61UxBsIr68hUz-jtjBUnyB2HBp5ESNyECGp_Gf6Q,2129
48
- helm/benchmark/adaptation/adapters/multimodal/multiple_choice_joint_multimodal_adapter.py,sha256=PWI_WrfDolipj7Zs43YxFQk36jBgU76PU-kL8R9gRno,4759
49
- helm/benchmark/adaptation/adapters/multimodal/test_in_context_learning_multimodal_adapter.py,sha256=VjSqWiZEcW6K2jrokGUmky7syEOqJ6cbHImR7YZgwzU,10151
50
- helm/benchmark/adaptation/adapters/multimodal/test_multimodal_prompt.py,sha256=KKOOlna6SHLJHSPgfgguPQysc2Nf4kKrqumqwlG27bs,3542
51
- helm/benchmark/annotation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
52
- helm/benchmark/annotation/air_bench_annotator.py,sha256=9W3zLO2f4OzxGdavkDI2dDUStxpExa7sgrI-ATGG7NY,3048
53
- helm/benchmark/annotation/annotator.py,sha256=2UIXY71S5dRaZBLb1v4lcv8-O6pyJ9zTeSJl78AEWGI,1538
54
- helm/benchmark/annotation/annotator_factory.py,sha256=3Soh0V3lbsIR_HGHLg-XTc3eKVRj7SL9lLT_AoqUVTs,2997
55
- helm/benchmark/annotation/anthropic_red_team_annotator.py,sha256=4hob15m2k9e2A97E0aG9FstCbJ_oMM7-9y-nh2EaYqc,2395
56
- helm/benchmark/annotation/call_center_annotator.py,sha256=pTEjwfA4tgZhroFbamoQ8IO_D1O9r6k5GIlD50JEg5c,11601
57
- helm/benchmark/annotation/financebench_annotator.py,sha256=gNERLY35t2kcpayXGGrY4-pBs2jbEUomqElRYbb9nho,4150
58
- helm/benchmark/annotation/harm_bench_annotator.py,sha256=zhkWnV3qZgY-nvHgQRHGrrCMC7605JwFHesY7UC3ZnQ,2293
59
- helm/benchmark/annotation/live_qa_annotator.py,sha256=9d2YKBlK4m0Bu5eWtc-CcwECCurU5yFGpQFIPIBC138,3548
60
- helm/benchmark/annotation/medication_qa_annotator.py,sha256=5ayy-ZBEOjKBFxJRgSXgUxhNJ71sL7EtbCD69p5K8Xg,3297
61
- helm/benchmark/annotation/model_as_judge.py,sha256=f3iQaBBwr-OYPLVkDp8Boutme_k83ZlLnfprHfv1alw,3689
62
- helm/benchmark/annotation/simple_safety_tests_annotator.py,sha256=if4S8MaENr1HZ42ZsOjDPXZ-kJ0p4l4B2j9m994RuxQ,2140
63
- helm/benchmark/annotation/test_annotator_factory.py,sha256=ifv5hxSbFe113AHeXLqTPkVJ-C2PW_gb9L3a0SHNi-M,986
64
- helm/benchmark/annotation/test_dummy_annotator.py,sha256=LfY1ErJDUJ7rD8JUy92RUDD1b91jUs4Nk8Gvope-Z98,1644
65
- helm/benchmark/annotation/xstest_annotator.py,sha256=arL5DyA_nYkiSCAtl6G7MliZz5ZYRsyc7xQJNu0RBcA,3604
66
- helm/benchmark/annotation/image2struct/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
67
- helm/benchmark/annotation/image2struct/image_compiler_annotator.py,sha256=eJFm3iyBe_eEN5Yt0G2IpeA1xdKxRmyR4krsNd6eXoE,3524
68
- helm/benchmark/annotation/image2struct/latex_compiler_annotator.py,sha256=drbxogMMGwGxgVFbhT7hxPGDh7uyhptlmEmeP1Gq2xM,2471
69
- helm/benchmark/annotation/image2struct/lilypond_compiler_annotator.py,sha256=odIGciLX2oVq_O8_H15lWUZoSfVvY-jRb0ILjs7GCIg,4061
70
- helm/benchmark/annotation/image2struct/webpage_compiler_annotator.py,sha256=w6RKv7Fz__j_abKXnsTn98kHPv9tWKipdLW3NVT55m8,6389
71
- helm/benchmark/augmentations/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
72
- helm/benchmark/augmentations/cleva_perturbation.py,sha256=arUkY_luc274YEMZocOos9rpAZVbEFZphbMlobAxTy0,29208
73
- helm/benchmark/augmentations/contraction_expansion_perturbation.py,sha256=yni1UR2fviN0Wig8MpOp0zzLn4H-gYocTjKTpxBwywg,4850
74
- helm/benchmark/augmentations/contrast_sets_perturbation.py,sha256=OvuntCLHYZoWHXO1JTixWmnZD5iQDNy_yYrLwgAO15M,3338
75
- helm/benchmark/augmentations/correct_to_misspelling.json,sha256=L44RiJXlJCa6zQzTLf0MFHCOhFyRDRKfLQNXH-n3XIs,213429
76
- helm/benchmark/augmentations/data_augmenter.py,sha256=Uk7rMDEgJGDoFyJLuOepjclBiNLB7Y3fATCH0HP_k_4,3847
77
- helm/benchmark/augmentations/dialect_perturbation.py,sha256=4DJB2gDj-JzhYtu-uxh9zgebChRDHpwMgKhju8OqP44,6317
78
- helm/benchmark/augmentations/extra_space_perturbation.py,sha256=D7y7oA4LwKJnVgTuLZOF3nQjmYRtkezuxY75qVQkD8I,843
79
- helm/benchmark/augmentations/filler_words_perturbation.py,sha256=NihLbpyxlXnncxM635pIyQ5LJvu4uPb4oKiLb8UU5dQ,2922
80
- helm/benchmark/augmentations/gender_perturbation.py,sha256=rnFREHD3FawmFaaQMsI-bhS52fhma7i1m8mZghX1hww,9387
81
- helm/benchmark/augmentations/lowercase_perturbation.py,sha256=e-lhkuKOV5QR_GnOp71vr2lHI97tiWSZ_jz57jcFbvg,519
82
- helm/benchmark/augmentations/mild_mix_perturbation.py,sha256=q27-c8_di1jaLhUuo5LzqOStnJcWIjSJ0a8Sr3S5TOs,1787
83
- helm/benchmark/augmentations/misspelling_perturbation.py,sha256=IE45qEE0HuIln62tAGvCP9B_RjNMJ5Xu06goL6b0fWQ,2144
84
- helm/benchmark/augmentations/person_name_perturbation.py,sha256=AIF5VVjNJ1OlUyCC1bt2dcP1KDn4gdgqd7Y2KGvHPqs,14422
85
- helm/benchmark/augmentations/perturbation.py,sha256=GapQckD3zkzZZB-PIVO1KKOy7aISGOhRbGGXEzuAFeQ,3880
86
- helm/benchmark/augmentations/perturbation_description.py,sha256=VKOwBRPQY-0vuxhGvtac1Z5F10metPfpFnfs8ykFVmU,1184
87
- helm/benchmark/augmentations/space_perturbation.py,sha256=g4rbyoureBaOVf_lrRXIWYlL6YZpqbCOJk554iOCuIs,935
88
- helm/benchmark/augmentations/suffix_perturbation.py,sha256=P3AfJj_ajTVdjO7AJRQ9dKS-cT1PyRSt8Un57iZQDVc,785
89
- helm/benchmark/augmentations/synonym_perturbation.py,sha256=komOV5M342_8unopnwN6gkPWpJIZXidywiu6PO9_riU,4151
90
- helm/benchmark/augmentations/test_perturbation.py,sha256=4EooKVcyub70I81trzpNx3Ij-m1vpFa5cFIo6O52icE,13185
91
- helm/benchmark/augmentations/translate_perturbation.py,sha256=vMXCYXGVSo8E78IAzH9HI4p2pvyLzcvO77BnvR2QB0k,1097
92
- helm/benchmark/augmentations/typos_perturbation.py,sha256=_F9zwvrLie8hX7mzUtQmYq6oq6yqaFiKGsvc9LAuBr4,2798
93
- helm/benchmark/efficiency_data/inference_denoised_runtimes.json,sha256=ios_dt-_8wtXvkVAx0iI2zwCxqHvk3XKTx31qHPalsI,4203
94
- helm/benchmark/efficiency_data/inference_idealized_runtimes.json,sha256=5w7reeZc0yc4cjH8kJGxQQSoe8yaRVX2SSlSrx0QWFQ,12348
95
- helm/benchmark/efficiency_data/training_efficiency.json,sha256=aH2moiBLStOLVi8Ci2KTK5ZkWlTBLK-B3fRfNZwhoSg,9763
96
- helm/benchmark/metrics/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
97
- helm/benchmark/metrics/air_bench_metrics.py,sha256=VMNQDDEtz2CiK4U55lCHLz0b_DxHprTAZ1WtYtGXjcY,2282
98
- helm/benchmark/metrics/annotation_metrics.py,sha256=JbXNleQsPJVF2uc1xXgUW2bzvJqwLPZyhnndqc6THv0,4268
99
- helm/benchmark/metrics/basic_metrics.py,sha256=7hk5PZL7d09uG1y7wHBhY_ox8hlXw-n7Yt_FDv_AIKw,20375
100
- helm/benchmark/metrics/bbq_metrics.py,sha256=Dqccr7GdfKNs1S_1QSB75d8AY7moovEPAqvacGfrCAE,6157
101
- helm/benchmark/metrics/bhasa_metrics.py,sha256=Nw5fdZrYedYUEVJXFFnGSdOBxJ4-99GELd699TBmcSg,6958
102
- helm/benchmark/metrics/bhasa_metrics_specs.py,sha256=fwXd1fRoeizd4kVQfLZ9ny-PzHTe1ieFKsGesiPDef0,440
103
- helm/benchmark/metrics/bias_metrics.py,sha256=GQ4CwOk1Sa9g-LcJCxcoQLD1vWY2Hvujck9l-9qsmf4,11418
104
- helm/benchmark/metrics/bias_word_lists.py,sha256=mx5JjW3mHffXIqo4GcQN-zENUEttBqQnEjPTz3J3J_4,13909
105
- helm/benchmark/metrics/classification_metrics.py,sha256=uB23jRFzkmtJgs1sTO5pPjdV_mOg35gWubjGS8pynLM,5654
106
- helm/benchmark/metrics/cleva_accuracy_metrics.py,sha256=1eDxHxVk-JW1mF9SBcuplIefAoi_edUwKpp-XxYbmeU,2740
107
- helm/benchmark/metrics/cleva_harms_metrics.py,sha256=c_x9MYg8WjM1yym1S374GKxH_lwP6wZOiXrknf0mJis,11077
108
- helm/benchmark/metrics/cleva_metrics_helper.py,sha256=8UwiGhekUmp7DxYWU4rxqX2v3ewkg-O5-jOh49iOGmc,304
109
- helm/benchmark/metrics/code_metrics.py,sha256=e0aqLcxBAdCc0qAqebzK40Ilv2Py6xZbosud5v169x8,5121
110
- helm/benchmark/metrics/code_metrics_helper.py,sha256=UNai154RuhYRZM_YK-rveLct4Ui5iEBNPYmYdKq34Xs,22712
111
- helm/benchmark/metrics/common_metric_specs.py,sha256=k_IW0A6BevAskS0_C6ZaP9XvIfrdLI974_NhC89rMoo,5846
112
- helm/benchmark/metrics/copyright_metrics.py,sha256=X9j3YsfzWEoGpgPpIvCzm18-JggLAW5QFooifE1KqaM,7729
113
- helm/benchmark/metrics/decodingtrust_fairness_metrics.py,sha256=TcyklpfcTMXrpJeaHQfxS9QQxe-gwmT-HD0g_DmIFLQ,3253
114
- helm/benchmark/metrics/decodingtrust_ood_knowledge_metrics.py,sha256=TxTkkWdx6d6ym0MirZTiucl_TWFdn4uJLnlTfLjQvgk,2925
115
- helm/benchmark/metrics/decodingtrust_privacy_metrics.py,sha256=l6TmAflBSgQGLjB-U7wmMCvY0Sui4ni29K7mkajsdtY,3412
116
- helm/benchmark/metrics/decodingtrust_stereotype_bias_metrics.py,sha256=KhiJ_7tnK8kHg2acKPAUWBQvAtyvjJTwcWJMUSUBHak,6416
117
- helm/benchmark/metrics/disinformation_metrics.py,sha256=BsLBG5krHGQh_nKDAeSDpp-li89s7fYoYTf5T0RZfMM,7782
118
- helm/benchmark/metrics/dry_run_metrics.py,sha256=d8RgltW4nGTH1tZeGOIlQRwRaJLIxL60h46NXv_wv1s,3674
119
- helm/benchmark/metrics/efficiency_metrics.py,sha256=v8Eg56HHIWEMQruODKBvwdUfR6ZLGgrNifo-senCaUo,11786
120
- helm/benchmark/metrics/evaluate_instances_metric.py,sha256=EBUf0ONnNoi7pcxYab7RD0B_JqGksqDX8TOaosSmJk8,2847
121
- helm/benchmark/metrics/evaluate_reference_metrics.py,sha256=vUJavaLVfbWtrwyrIA81npK_1iirhko7_zMF1kL7Gfw,15559
122
- helm/benchmark/metrics/fin_qa_metrics.py,sha256=MtXxGMGYiCiwCD1CclBXPopzly-Tz3zJTrXJaHYTXn4,2470
123
- helm/benchmark/metrics/fin_qa_metrics_helper.py,sha256=sH5FIpsxxGUkXO21YGS2EtVsev1EdQ44lYoqFZPSSGo,11884
124
- helm/benchmark/metrics/gpt4v_originality_critique_metrics.py,sha256=1m7IWy9vu66svnmdBRjZQI-2YsGYzH2vXZMptlRGM0Y,5654
125
- helm/benchmark/metrics/instruction_following_critique_metrics.py,sha256=QJxGzyERQv_vMn3PM9fy3IxfBgSg0BjcOf_mv574lGA,9786
126
- helm/benchmark/metrics/language_modeling_metrics.py,sha256=ofqwj1PMJQu16QhLDULXBmZ5iFz91ducwLRpNsRYELE,4510
127
- helm/benchmark/metrics/live_qa_metrics.py,sha256=f2XFmQaohjQNqYqNg8NcDVavCzyP4cd8Cl8rLArn9EM,816
128
- helm/benchmark/metrics/machine_translation_metrics.py,sha256=bp_EDXyxntIty5gORDa7va-C73quOzoTc5o8MpxFmL4,3816
129
- helm/benchmark/metrics/medication_qa_metrics.py,sha256=Z939iAc0A5xn_GdnCtfiefhUZK9qk6jZjtde2-F7IH8,840
130
- helm/benchmark/metrics/metric.py,sha256=dPq7ZMB0w-LgJKMzWYDJtfn-oYD4oG4jJX0yiUEziJM,14245
131
- helm/benchmark/metrics/metric_name.py,sha256=POhgmUqqIWh_LjCbYpiKkzGqqChBLeW3FADy9u_FcWw,1354
132
- helm/benchmark/metrics/metric_service.py,sha256=mlX_MEFSYNzME6GFS3El_VVOvzPYnOMosKI0XIxygP4,1802
133
- helm/benchmark/metrics/numeracy_metrics.py,sha256=panMWD3a1NPerg3Ix7l6NhR7jGOIQOQV9i_KysBeDA8,2818
134
- helm/benchmark/metrics/paraphrase_generation_metrics.py,sha256=-VkAknRhAEBmC_lpz_1aeXU8OppL8KfEPtIYCJkHTmw,1981
135
- helm/benchmark/metrics/prometheus_vision_critique_metrics.py,sha256=pexBbEFF3-bzWoPWNFuVs-3fm7XJw2EC4xgiSb3gSa4,8508
136
- helm/benchmark/metrics/ranking_metrics.py,sha256=5hDRapsxx_cmo-ag_80kOQnrgZn3lfVsLZVtWxuxH-s,17391
137
- helm/benchmark/metrics/reference_metric.py,sha256=RlIM_PFTEkBo0_EEMq8d4_BSagNSBR_XyovMtjDeqqU,6026
138
- helm/benchmark/metrics/reka_vibe_critique_metrics.py,sha256=CwzzQ13bBT0r_o75TqFj2Zr0ST9vzQi74K_ezWTnLCU,6568
139
- helm/benchmark/metrics/safety_metrics.py,sha256=oARko_EwVnykBKYxi-w3ytKme4qcb1waz_0N2GKbSlg,3348
140
- helm/benchmark/metrics/statistic.py,sha256=FuxNxMtAfiCkOxBS9KHlhEyxe61e0YXt2emvsufgPZQ,3424
141
- helm/benchmark/metrics/summarization_critique_metrics.py,sha256=Lf7PDuce62HDzyofsyxaOvH0QvzcaS-vJvDWtIs8xKk,4694
142
- helm/benchmark/metrics/summarization_metrics.py,sha256=laLMGRDy1wjcFvgSWXvzOZwBXshkmPr0S2Ofu79Z01Q,16461
143
- helm/benchmark/metrics/test_bias_metrics.py,sha256=N22a5UKqSd7TfYBrZS6ciFSOIc1s85pYMwk7m9ufpG0,6274
144
- helm/benchmark/metrics/test_classification_metrics.py,sha256=8A7UqgSkJzVgQ0IIMfozL4HTrj8GiDFxsf4_dov3Amk,5613
145
- helm/benchmark/metrics/test_disinformation_metrics.py,sha256=U3ZmS9s33oimTQbKO-7pgWeX_WiDB9chlOCtf_vslXw,2249
146
- helm/benchmark/metrics/test_evaluate_reference_metrics.py,sha256=cRZwInR-XLr9Q-q_3d-TXk2kIx8RJQ8w15-_VSUS7HI,1128
147
- helm/benchmark/metrics/test_metric.py,sha256=kLP6oANAuvR-MQmZJJybN2DQGXYa6oQarO96a4QDhOg,749
148
- helm/benchmark/metrics/test_numeracy_metrics.py,sha256=ls1ZIHDePKpHMoqAbf4HmJ1SIBjLFuLIzGbfg6OiZvM,4162
149
- helm/benchmark/metrics/test_statistic.py,sha256=AejuYLSeUwEOqpEMRKZFjnxu4HKUraeExU8TPmZEqW4,1229
150
- helm/benchmark/metrics/toxicity_metrics.py,sha256=6MCpHuCXbXZqWwvO57ifKYHnHWBzszN9cZjwgPQQF2Y,4027
151
- helm/benchmark/metrics/toxicity_utils.py,sha256=-bfittLtMkHyV5wu-hj6KVtaiNGgVIO5duUmThBlX8w,988
152
- helm/benchmark/metrics/unitxt_metrics.py,sha256=YXuq2wWwP8ccfd5CG0ZDyDd_PqBHguSqb57H_m9b55g,4749
153
- helm/benchmark/metrics/image_generation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
154
- helm/benchmark/metrics/image_generation/aesthetics_metrics.py,sha256=AXQjWBd9zBZOoCF8vQV9FjUy33teC0IF7pdbq-XiHjM,2101
155
- helm/benchmark/metrics/image_generation/aesthetics_scorer.py,sha256=ISdThDKMrx-SHQe69dCcr8qUrMCa_GsxX3BeZnd0WPA,2538
156
- helm/benchmark/metrics/image_generation/clip_score_metrics.py,sha256=tUnAoew24jjjbjPaoE2-4iyRTq6YNW8Xfk1p5JWZkAU,3338
157
- helm/benchmark/metrics/image_generation/denoised_runtime_metric.py,sha256=Nom_yw15ePU7wUuV2DFHpLnEAqaZQjlkW9LowRElOAI,1646
158
- helm/benchmark/metrics/image_generation/detection_metrics.py,sha256=n2SmrnQ9izucMjwD9KBThgVBo3_R5AGTZJXwqXdbZvg,2121
159
- helm/benchmark/metrics/image_generation/efficiency_metrics.py,sha256=neeNJNtHAVUMWqr5rvRIRlPKl225cXUGCURLB0z-rKQ,1459
160
- helm/benchmark/metrics/image_generation/fidelity_metrics.py,sha256=Vewml_NOcM2jK-yyKHWsHB0KC3NVG8HfweA4rGZ9RAQ,7583
161
- helm/benchmark/metrics/image_generation/fractal_dimension_metric.py,sha256=i71ACxshXW6zVI5D8UzkNtIU5hMrPQR6byV4cKJFVJE,2096
162
- helm/benchmark/metrics/image_generation/gender_metrics.py,sha256=j_sHhAkq1fA2VL483OX80cC9EQjzOIWGHQAeGVEN8fY,2371
163
- helm/benchmark/metrics/image_generation/image_critique_metrics.py,sha256=fVgb-GdA9QmNywq7byNlG1TTxb_zvzP_bcURruZ54Wo,12958
164
- helm/benchmark/metrics/image_generation/lpips_metrics.py,sha256=naVxg-yXdXum-yQD6MgRcemVr0L567Y2drGjfehravQ,3582
165
- helm/benchmark/metrics/image_generation/multi_scale_ssim_metrics.py,sha256=z3xaiKrfarF-lfQ8Aa-Dveaun3LfMMpQIWR8bHbQIrY,3507
166
- helm/benchmark/metrics/image_generation/nsfw_detector.py,sha256=X1hsWRBa-1KOhT_TTfCk9_jsXXMXHadAxddsFmTKQHc,3914
167
- helm/benchmark/metrics/image_generation/nsfw_metrics.py,sha256=ZlJfqsFh6DNFLBBTNBDB2UK85wlsxtsxTlN9k5_i-5Q,4626
168
- helm/benchmark/metrics/image_generation/nudity_metrics.py,sha256=KQG-jybgaWuXB5rL-kLBWBD7gdZKWdTJYYrAEEMnZAU,1553
169
- helm/benchmark/metrics/image_generation/photorealism_critique_metrics.py,sha256=0bwfJZ5pOAQFec4TEf_eUd9qQxwximwzDrYFkZnO9Yk,6951
170
- helm/benchmark/metrics/image_generation/psnr_metrics.py,sha256=VLq9gOkaoIZNAGII9fMI3tOCMpKAzbfLuqGbWo_mOV8,3126
171
- helm/benchmark/metrics/image_generation/q16_toxicity_metrics.py,sha256=g85Rtc6MJPO1dcjD_V1oK6-k91ES_GKmB1QKoVSZcnE,1924
172
- helm/benchmark/metrics/image_generation/skin_tone_metrics.py,sha256=0QXFXvG5bvBZ5eXVrj0N08Gz6xqlyPjZ3oqv0jD4OCE,6023
173
- helm/benchmark/metrics/image_generation/uiqi_metrics.py,sha256=NaBxJvZJdNw8g7Z6jxUC3mtUhdPXsib45TSK2fr5DUM,3904
174
- helm/benchmark/metrics/image_generation/watermark_metrics.py,sha256=GxxHK8i6WzCaR9YDYyn0mte6T9EcgyMy1BV2HtJQInA,1885
175
- helm/benchmark/metrics/image_generation/detectors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
176
- helm/benchmark/metrics/image_generation/detectors/base_detector.py,sha256=e4c8vPfioGzl2ftYzWOFIBDJcZJxBmpjU13n4fXaSvY,226
177
- helm/benchmark/metrics/image_generation/detectors/vitdet.py,sha256=fhjEs-iMlpKFAWw-qpKZS4wko5nn09Fm5SYt0FFUQzs,7477
178
- helm/benchmark/metrics/image_generation/fractal_dimension/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
179
- helm/benchmark/metrics/image_generation/fractal_dimension/fractal_dimension_util.py,sha256=vFO6s8QHo6Pt1QfbOKAI0m3mJrc0BeH1Hcf7u2uWMIk,2116
180
- helm/benchmark/metrics/image_generation/fractal_dimension/test_fractal_dimension_util.py,sha256=O2EDENxDfDmbrL54N4ev2LdhouAaTh0xXP3NhNyW_ww,1415
181
- helm/benchmark/metrics/image_generation/q16/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
182
- helm/benchmark/metrics/image_generation/q16/q16_toxicity_detector.py,sha256=8Y5h-6RMjivm50RnNbNwV7wCug4RhKT5g8R_YeEp54I,3467
183
- helm/benchmark/metrics/image_generation/q16/test_q16.py,sha256=f3Ycj7gGz1-tSxATvfYEGh1yyJwzcHbC2Yru73f3mPs,716
184
- helm/benchmark/metrics/image_generation/watermark/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
185
- helm/benchmark/metrics/image_generation/watermark/test_watermark_detector.py,sha256=__f7NVsVQatDFn_2Bfx7ObiQ68kAMvyyClApaTxqx80,649
186
- helm/benchmark/metrics/image_generation/watermark/watermark_detector.py,sha256=w6WnTc6t6zx0W0gTjgedXC9OO5dq5iWpx9UcnioKml4,3641
187
- helm/benchmark/metrics/summac/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
188
- helm/benchmark/metrics/summac/model_summac.py,sha256=PJ2lPa-JQPnM86N0T2rPcAviTNHmSV721PTnbL1eGnk,17460
189
- helm/benchmark/metrics/summac/utils_misc.py,sha256=7_Q1c72cKt8PWtxn8u4R8nB53HK6_JF2nP8bBXYNk-A,1485
190
- helm/benchmark/metrics/tokens/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
191
- helm/benchmark/metrics/tokens/ai21_token_cost_estimator.py,sha256=WeNP4yiM4TVrD9Kid-uVRmWIVDqETnBsMycZmIBiTZ0,665
192
- helm/benchmark/metrics/tokens/auto_token_cost_estimator.py,sha256=MAVCme5cK_ryPjoA6cQPvfpKwqdSfnliTaxwT0vi4R4,1974
193
- helm/benchmark/metrics/tokens/cohere_token_cost_estimator.py,sha256=5igmDhWu7H8-qiJnAQqCTQd1WXRewMrpdJdo4qhvSWc,523
194
- helm/benchmark/metrics/tokens/free_token_cost_estimator.py,sha256=G_6UK6Js_NZ_eqY0ZQnrC9QJVMERGhV1f6v7xq2lM-Y,461
195
- helm/benchmark/metrics/tokens/gooseai_token_cost_estimator.py,sha256=9zjtuxMbvfPBYuxOYMFEmNP8ZKFDVywrZ08n6nrjbA4,1520
196
- helm/benchmark/metrics/tokens/openai_token_cost_estimator.py,sha256=7jgjcgmbcVfLA_nTOrWXKIF8TEXng_KnE6cSgsSXWmE,1398
197
- helm/benchmark/metrics/tokens/test_ai21_token_cost_estimator.py,sha256=eVnCYhRq2LT7F4BXsiIDb1bkmhvoHLgDAdMR73Xz5p8,1071
198
- helm/benchmark/metrics/tokens/test_openai_token_cost_estimator.py,sha256=h5ggZCGpgCQUjfqS0JS4Bxmx7NBaT4w43pXAgbCEnw4,2628
199
- helm/benchmark/metrics/tokens/token_cost_estimator.py,sha256=fTGUfhHV6yMwpTkCEMTGMxKO8jskqJz4sAtwXT6M_C8,425
200
- helm/benchmark/metrics/vision_language/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
201
- helm/benchmark/metrics/vision_language/emd_utils.py,sha256=KdZdcqu3eo016FdAjAm_83v92-wWuR90EPsTogfTcok,15196
202
- helm/benchmark/metrics/vision_language/image_metrics.py,sha256=y3md3sCuAa63wRpcwIYo464cE4mq14YWqAwUfVFDGhA,23835
203
- helm/benchmark/metrics/vision_language/image_utils.py,sha256=4E0NYh09O6-5sGhAPo6KZqYaZfBpCtuYbD3vLt-wQzk,3755
204
- helm/benchmark/presentation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
205
- helm/benchmark/presentation/contamination.py,sha256=PiIdcaD3-xfExjOmyL5q4Ao2ASa-OlScJAB9u1Zxe7o,2811
206
- helm/benchmark/presentation/create_plots.py,sha256=T6ewj8rXZfRlqg01bgbhdU1rsABK4xyrLpruhRG-7Fc,28691
207
- helm/benchmark/presentation/run_display.py,sha256=tC1DciLvDTQJog4BDo8StWDdX7DbBkhrG2sX_SwXSPQ,11838
208
- helm/benchmark/presentation/run_entry.py,sha256=J1QgLOP99N7N4bs7nzXWxyU3pOd-a1j8xwL9ag1nP_Y,1158
209
- helm/benchmark/presentation/schema.py,sha256=cblGmgkhuqQRWPh-IT75u3Il_-SVXipeq-mh64lvgWY,10947
210
- helm/benchmark/presentation/summarize.py,sha256=iweYi83j_nogmMyCibjJtKwpbY4HzMfoIuLSeqyanHw,59084
211
- helm/benchmark/presentation/table.py,sha256=-foH1BIfMiD6YvpwoGJ910CH7Hib-_pYtHH1hE8zwNc,2904
212
- helm/benchmark/presentation/test_contamination.py,sha256=RlihBOF6vx2tKEj6_EMnJojTYoStx0FUeJSLT1bdf8w,509
213
- helm/benchmark/presentation/test_create_plots.py,sha256=5PPPegMTdBZurxyyUxI4rN13AVsjV3eQrwFqlobJ8UA,1286
214
- helm/benchmark/presentation/test_run_entry.py,sha256=4n484sSYT0gQ4WVt67Fs3ctKa4vi97hI32O5XXxGY1o,794
215
- helm/benchmark/presentation/test_schema.py,sha256=6mq6CeAOLW2Kxi1lX_ZW8QCVqVR73XImR8ylcRGFkBE,378
216
- helm/benchmark/presentation/test_summarize.py,sha256=GzZNwBDybpstzl6wT0Rgqn75N9iCNrUIzrdjOfUolu0,6317
217
- helm/benchmark/run_specs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
218
- helm/benchmark/run_specs/air_bench_run_specs.py,sha256=VdXis1HN8_KLrMHDCVi0J7WdqjRjAGbZMhrsnpzC-Kg,1604
219
- helm/benchmark/run_specs/bhasa_run_specs.py,sha256=GEIC1Ye4zn17hPWet3QFQr1rvwmX6aEVg5fNuQ7Jwes,23815
220
- helm/benchmark/run_specs/call_center_run_specs.py,sha256=GX5P2tTj4YS037EEZ8so_mX9LlPWyfJ-pF8ICoErpio,5324
221
- helm/benchmark/run_specs/classic_run_specs.py,sha256=Cn0z-6QY-ehbLaHJMvCwjw11DFBQgUyqVCaXwTVFyJ8,58331
222
- helm/benchmark/run_specs/cleva_run_specs.py,sha256=lEIHEqQY3Efx-sl2Z6Rq9Qq_1HEWHqFYuUkZbGvq66s,13387
223
- helm/benchmark/run_specs/decodingtrust_run_specs.py,sha256=7slILDS9f0_Z0y-Pz5xEspoGQUmOCOI2K2r4XWUVsm8,14428
224
- helm/benchmark/run_specs/experimental_run_specs.py,sha256=wduA6K3mpIRHmr8g3h0c5k7rUsKiPFOqJktdbbGxtoE,2950
225
- helm/benchmark/run_specs/finance_run_specs.py,sha256=5mwb7GbAcSLVZiumqCiAr9dr8qBYApkEt5Oben5CFXs,4371
226
- helm/benchmark/run_specs/heim_run_specs.py,sha256=Pt1eVbzvwZ5EXq8WB2b3XYw62SWYN_i1P_H3oE4i8KY,22096
227
- helm/benchmark/run_specs/instruction_following_run_specs.py,sha256=GElJhgbQhlZMYSAM4YyGcYq0pqycR32kBCoHqG6m-ZY,4177
228
- helm/benchmark/run_specs/lite_run_specs.py,sha256=ViCPJ86Aah8301GTEk6z4_MtP0g8iik33t4GudobhWQ,11113
229
- helm/benchmark/run_specs/safety_run_specs.py,sha256=ZTvLbRBxHWMIKPapugNfXPStJRBHfiaiXUHgpWMBONY,5469
230
- helm/benchmark/run_specs/simple_run_specs.py,sha256=0kK_e8U4JUWZ6wO4N-GPFRE1iGT4ilvSMUGfirvpIE0,3837
231
- helm/benchmark/run_specs/unitxt_run_specs.py,sha256=ejp_knrcIjf0J4WiKj9LTgDTcUr29-XFZYHYz0w_dkM,1518
232
- helm/benchmark/run_specs/vlm_run_specs.py,sha256=wHq-FCP2dgbWtBHoe0NUSgiJfifMtZAvSiJIdn114zk,34249
233
- helm/benchmark/scenarios/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
234
- helm/benchmark/scenarios/air_bench_scenario.py,sha256=WUZvsUTqlsjNzQsd2baZZIgO30B4Zf3g0QjsyEaGmLc,1772
235
- helm/benchmark/scenarios/anthropic_hh_rlhf_scenario.py,sha256=Wyt7J5BAvAqC5JTqCW4fh7ex9-itX11P_9rLTocqvtk,4973
236
- helm/benchmark/scenarios/anthropic_red_team_scenario.py,sha256=Ic0ak_5vGHeNT5PFgOptl-Ns8nQuM5nKpiQlhB1H3X0,3158
237
- helm/benchmark/scenarios/babi_qa_scenario.py,sha256=S1tPQY2x1I3hQL1JQ6wvUwvKyiSe7SqpRSW6N3_T0mo,5043
238
- helm/benchmark/scenarios/banking77_scenario.py,sha256=pVA2LXB9uJ12GnjiEvjhRV-P8YNEjpFhyZr-J8MV2SA,1747
239
- helm/benchmark/scenarios/bbq_scenario.py,sha256=lT1XKSM-PXYtENI-ryScC4yb1TtII7YoH8kt_S1dZQo,9579
240
- helm/benchmark/scenarios/bhasa_scenario.py,sha256=f8Z_xEbg9CoVyMJE4tTs7WU6B-QeIxYUI4g2IJWdj8k,78011
241
- helm/benchmark/scenarios/big_bench_scenario.py,sha256=bSk8Ia4u_6OqMjiyadpYQAWN-8GFWqvd3Ft3JiVGpi8,8081
242
- helm/benchmark/scenarios/blimp_scenario.py,sha256=o1MDcHT14KFDET4K9otx8pDiIgXrhsD19pvO0mR2ADU,6260
243
- helm/benchmark/scenarios/bold_scenario.py,sha256=NEfECMVzlVP_yo6sOuIzj6vZ5jd72_nvtEQ1lWrq85Q,4106
244
- helm/benchmark/scenarios/boolq_scenario.py,sha256=rvSp5SwXMCVzBo5BFxfhj1Xv06_ksqKrtTQR7nPiS-o,8013
245
- helm/benchmark/scenarios/call_center_scenario.py,sha256=19J2N57WnUkPMGRRbJyZak8YCeMTRwD3BRK1SArQlL0,3037
246
- helm/benchmark/scenarios/ci_mcqa_scenario.py,sha256=slZZT74QI3OMQAgT-ybcR_xVcRDoopXw6mMu4iy3XCY,3074
247
- helm/benchmark/scenarios/civil_comments_scenario.py,sha256=VO5G-cQ9qctmBN0O76uSewnO_mFslMo5mbR2ZTrjuds,4851
248
- helm/benchmark/scenarios/cleva_scenario.py,sha256=xhwZ616iz0CN3fYIfrXHcV1XlcRQjyPSzML8fq8D3l4,57939
249
- helm/benchmark/scenarios/code_scenario.py,sha256=s4AGW8eBY0gFnu6EXvVWL0xbFYO28N9sgP1V8eBO7EI,12171
250
- helm/benchmark/scenarios/code_scenario_apps_pinned_file_order.py,sha256=KC-5MQ-d8Nn46aDN4FaPxmd6yk1DtVUmVR-CIZsNCp4,1738
251
- helm/benchmark/scenarios/code_scenario_helper.py,sha256=TnXAlY-wdAFwIDylFItf0z7HOu93WD6dNThwzZYe330,5904
252
- helm/benchmark/scenarios/commonsense_scenario.py,sha256=Wgry4P4W0hHmeBrN61u5h6VTjET5TZI0oozC2ri3nbQ,9487
253
- helm/benchmark/scenarios/copyright_scenario.py,sha256=qw-ijottZ28DjMqMWSZzL9_FuRDAHf0YmGV27YstmVI,3673
254
- helm/benchmark/scenarios/covid_dialog_scenario.py,sha256=LqNtfb9XQestluN0Bz7yi-Zo0VRkLjl4F9IOYzhPw3I,3971
255
- helm/benchmark/scenarios/custom_mcqa_scenario.py,sha256=aZkt1Ums-kIVpLfd4Pfhe7Rf_fZLxjO2ANLL2aN2qVM,1915
256
- helm/benchmark/scenarios/decodingtrust_adv_demonstration_scenario.py,sha256=hznH_Xe5vY269vtuApWwAaGUC9_1Pz9D-nfdG1a06cQ,7909
257
- helm/benchmark/scenarios/decodingtrust_adv_robustness_scenario.py,sha256=9qo3l44aby1EfQqohh1M2DVtHXqY1fuvj1XT3_n4hBk,5588
258
- helm/benchmark/scenarios/decodingtrust_fairness_scenario.py,sha256=rAOZnFSxO3ENOvcNz688P_f3Y7NzdwiWgoYTNvAaw3A,2866
259
- helm/benchmark/scenarios/decodingtrust_machine_ethics_scenario.py,sha256=qhzqW614WnsiyN7TiHUdZY_NpEdW_iMO0AMrLK8DmK0,14116
260
- helm/benchmark/scenarios/decodingtrust_ood_robustness_scenario.py,sha256=RSigvRdqjeFTwFfXNmslz8zyAGSmLf6UtBDA4NrQBCo,8304
261
- helm/benchmark/scenarios/decodingtrust_privacy_scenario.py,sha256=goGmHtN7MYnAQIXhffZZhuuuMWN0gHNOXyI9_injiZM,20119
262
- helm/benchmark/scenarios/decodingtrust_stereotype_bias_scenario.py,sha256=Qkwhg1s5f2_5rnCoX4BxjQGKKGVRp2StIwONvBjJVqo,2909
263
- helm/benchmark/scenarios/decodingtrust_toxicity_prompts_scenario.py,sha256=AI8HX16_Lw9MKqrck62q8IFLUU-P5hxaOEHcmTS4rdA,2928
264
- helm/benchmark/scenarios/dialogue_scenarios.py,sha256=-I7FY6q1b11zpFd1_oAgar5qlfaFcXsNCKGVln9etPI,5629
265
- helm/benchmark/scenarios/disinformation_scenario.py,sha256=kQi0MVVoSDhx2vOTnUaCIttPXMf8zz7Eld2FD_77tnA,8504
266
- helm/benchmark/scenarios/dyck_language_scenario.py,sha256=vMxND9wPJenrGlCLhSw5UxOw3TV2Jq8cTmIXGpzEWaA,9318
267
- helm/benchmark/scenarios/entity_data_imputation_scenario.py,sha256=4cv7u2lmUFcigkAX_eMwIn49Pa3p-aHClkT-r-0roLU,6616
268
- helm/benchmark/scenarios/entity_matching_scenario.py,sha256=YjBX61TlL3CDQ3X6D-JyR-qlOYGLdoRXJxl9AEeqxYs,7022
269
- helm/benchmark/scenarios/entity_matching_scenario_fixed_random_state.py,sha256=TklbX7Kx4y-estV-YHUbI5O08q2qCZRrOmX9D3gZS9c,2193
270
- helm/benchmark/scenarios/ewok_scenario.py,sha256=vrbJg9vakAxE6n-1jURUcwb-ihrsYoY9e32BpnEGDaQ,4684
271
- helm/benchmark/scenarios/fin_qa_scenario.py,sha256=Dm_kGOivaxiKVhcqFgN8pRPs1eqm2LdBZxWy0yFhFuE,5958
272
- helm/benchmark/scenarios/financebench_scenario.py,sha256=cHMljdg0_9HA3FbwcwwMt3DR9rxl0jkyFN9jNrUStSE,1956
273
- helm/benchmark/scenarios/grammar.py,sha256=Pb9vEP_0Ki87UdQCj1ym7QWJ24M4DRP6TXB5d3GnhLs,5597
274
- helm/benchmark/scenarios/grammar_scenario.py,sha256=bl-Cm9caDs077zSu38mzaS9maZ2gM-QazgjOEMFvxYg,1454
275
- helm/benchmark/scenarios/gsm_scenario.py,sha256=9fV2SEw3ocKNAD-TrDZZTpq4l7mbttQQWbO0YNz4e6k,2613
276
- helm/benchmark/scenarios/harm_bench_scenario.py,sha256=wzzia3HlfwALgRLFLABv3blxBh1ras-YtHk4iQ_EX30,2454
277
- helm/benchmark/scenarios/ice_scenario.py,sha256=vvk11cFPGUhg_CcGh3wEfVsGzrvMFgkByN-xcF-OOjI,16473
278
- helm/benchmark/scenarios/ice_scenario_pinned_file_order.py,sha256=fuirubIdi-rkJMfSd7YoDdBX2q0f5K7GGTN4XVapAUY,1613
279
- helm/benchmark/scenarios/imdb_scenario.py,sha256=X1k76AweFECCpYCXy8HuvjRbXbfmDfwK3SES_t_wkUs,6174
280
- helm/benchmark/scenarios/imdb_scenario_pinned_file_order.py,sha256=fjW0Gkzg2Y3IAbtYJ3KC7MueWd9U8h0tlcBCqxYmRrM,1621
281
- helm/benchmark/scenarios/interactive_qa_mmlu_scenario.py,sha256=PuwcuHnx3nCuRYEEzEQ6aRI9i7QAHtfg4DmLAG4M6AM,2205
282
- helm/benchmark/scenarios/koala_scenario.py,sha256=ihx39W1C9KyOh5MkdMqw1twUwzA8S5QPsBKeQRZcZGM,1365
283
- helm/benchmark/scenarios/legal_summarization_scenario.py,sha256=DTYYsf-74NFjHvrNa5ZWSgMywq9ss16r5eFZI2-xZJk,8644
284
- helm/benchmark/scenarios/legal_support_scenario.py,sha256=hu8SlDGrU6oUTQjnrLEagjFNniW96wMahKjnrtuyjzo,3925
285
- helm/benchmark/scenarios/legalbench_scenario.py,sha256=jLo8HFE24M7pcS4PgrpAYhiZNuXSfPUb6LrGoaGCT1A,4490
286
- helm/benchmark/scenarios/lex_glue_scenario.py,sha256=vsy8Y03hoCwTJFgBdQf0koxlHDRFm2V9wT04n2K1tlk,10268
287
- helm/benchmark/scenarios/lextreme_scenario.py,sha256=HEpXLdLLywo6yfXaGF3zRgx1PiGPE2ILnpKYs9Dmsow,20396
288
- helm/benchmark/scenarios/live_qa_scenario.py,sha256=meJvkkbqRUQ2odKkmlOLYOVVFd0LGDhGzK5nHCjXW6Y,3642
289
- helm/benchmark/scenarios/lm_entry_scenario.py,sha256=_7lTn2kfUQHi3ynX7fEaoseUYkpBx-ANn62kqHr-bY4,9085
290
- helm/benchmark/scenarios/lsat_qa_scenario.py,sha256=Ui68mi05N3WxGMZfCznJBscKkqaJ0ZEUO3PhIiD1xNE,6129
291
- helm/benchmark/scenarios/math_scenario.py,sha256=LvoQJUwZ0w78h5X1tIaa6SRsef_W_PNn4L_r5L3Cus8,14168
292
- helm/benchmark/scenarios/me_q_sum_scenario.py,sha256=WLfED6DiIOUPd4PowydPmrQ4v26OsjG4iHumq7ka9do,4001
293
- helm/benchmark/scenarios/med_dialog_scenario.py,sha256=f7hTcEpxGfoxJ-WXNrSRrgVfbyuYpB624HbyRuMP-KI,7295
294
- helm/benchmark/scenarios/med_mcqa_scenario.py,sha256=JdVQuzKM4TRyWT6c1zpsMvNk1RYHnKdy_fRM6W7PCLI,5035
295
- helm/benchmark/scenarios/med_paragraph_simplification_scenario.py,sha256=e9WRx41XKJI06l3ZGkZe_LKNx-qd4hoWopfDncrr3KE,7591
296
- helm/benchmark/scenarios/med_qa_scenario.py,sha256=R0iDMzu3U0TnYEOiyjnlOWHGFwhvOJBVwJ5-Hos2eP8,4417
297
- helm/benchmark/scenarios/medication_qa_scenario.py,sha256=F7Pi_vYzFzKxAF0ruDaHE4soz32PjxeI6T_qxX6TeV4,2217
298
- helm/benchmark/scenarios/mmlu_scenario.py,sha256=wZjoGjaZNERyqSDHgIsv8fIANyUUQZ1ExQAa4cPzmM8,3790
299
- helm/benchmark/scenarios/msmarco_scenario.py,sha256=5DTWSDuinXVomlUTYfwOijXLifCSeG4be9Tvb7SANQM,34026
300
- helm/benchmark/scenarios/narrativeqa_scenario.py,sha256=FIzd4CTS6ZTOI_TJ8aPlkXYNfqbTIs13ZUqAt7ie8U4,5608
301
- helm/benchmark/scenarios/natural_qa_scenario.py,sha256=khKCR8xVhRqJtZoAfGQ9_CV6REkfrYn5ahLpci6rUzk,12540
302
- helm/benchmark/scenarios/newsqa_scenario.py,sha256=g7bFXWCTvRjofmmUJhx3jmCOvcVwi_P9LSVrNofvMLg,7260
303
- helm/benchmark/scenarios/numeracy_scenario.py,sha256=ED38H_AKxTFhKEJizhQXlfgkBColxjIdv4j9KvFI0Zw,30824
304
- helm/benchmark/scenarios/open_assistant_scenario.py,sha256=PH8F8zqYXXakr1xttBtFmENGMGciIpyijK4RCkJol_0,5495
305
- helm/benchmark/scenarios/opinions_qa_scenario.py,sha256=s0dGhsgcgud_bSqXw6p-w-nC_cme1Vjt9T9AwU4-K84,7371
306
- helm/benchmark/scenarios/pubmed_qa_scenario.py,sha256=zVL1gb3eVz-LbK2hfdnRR9ItaMSPlAGJorByWLt-4wk,7506
307
- helm/benchmark/scenarios/quac_scenario.py,sha256=SRAhMp6TAsmTRq6VRONLl3SEayFIe23He_mBhzkZ7qM,6628
308
- helm/benchmark/scenarios/raft_scenario.py,sha256=RKRUJQIVkz7reugeRK7hXD47Z2H52Qm6w0BLJnLbC_s,4459
309
- helm/benchmark/scenarios/real_toxicity_prompts_scenario.py,sha256=GkgJo_13MWQQQTZbhlknvTR6ZrYr7NEn1WdMZrPs4y4,2400
310
- helm/benchmark/scenarios/scenario.py,sha256=1HC8EjiZ-5k5AJhxtwRreLe3hBbTyZJWrs-Aa3Uq43Q,8229
311
- helm/benchmark/scenarios/self_instruct_scenario.py,sha256=jZ2MksT4N_4g_sp5egw7ycrsM-Ya786_RFmiYYdMvG8,2285
312
- helm/benchmark/scenarios/simple_safety_tests_scenario.py,sha256=grYOqccYBtB4m-_UUV20EOXsY6tkukwC6kwPOBAmdnY,1223
313
- helm/benchmark/scenarios/simple_scenarios.py,sha256=ersSzp9bFEFfpJ-SNy368AuonwswLnuyA1n7FOgkw4U,6459
314
- helm/benchmark/scenarios/summarization_scenario.py,sha256=MlNMgsY369DC04nhMUdG2o9Ydi6yze1fGOjC0bK-UwQ,6847
315
- helm/benchmark/scenarios/synthetic_efficiency_scenario.py,sha256=pzifpsJJbucmTjujNqQnwQa4Y7wpQjkS6QjNXOrgTAQ,3096
316
- helm/benchmark/scenarios/synthetic_reasoning_natural_scenario.py,sha256=1b3e3WpFMNBV3li17-0Ug6QCSKO4qRFaWDF23bYNsvQ,16326
317
- helm/benchmark/scenarios/synthetic_reasoning_scenario.py,sha256=k8IGK6VABOr6wuha4HynP47peoAkmIViAVhScOtCANo,8345
318
- helm/benchmark/scenarios/test_air_bench_scenario.py,sha256=9o92CK57xxgPaA9Xt9uJPPie4Cxllzq-KbMt3G35UQ0,1320
319
- helm/benchmark/scenarios/test_commonsense_scenario.py,sha256=V5Mq4cxWqU6j1U3icfIuzcnCZsZO7NTKLQgF0lEpdyc,924
320
- helm/benchmark/scenarios/test_ewok_scenario.py,sha256=9piplj3i53_-xNSMkIN47JYEU3JB65WgEPT7qdyK4Ng,953
321
- helm/benchmark/scenarios/test_financebench_scenario.py,sha256=EFZLJXXBoyjlTiMQFaQ6MiYkve1lfQDjQWjn4BjqgAQ,1184
322
- helm/benchmark/scenarios/test_grammar.py,sha256=sPlA36sHpThbXgnGlXyOuqHfDPe2epIafmzIeL0nkoU,1364
323
- helm/benchmark/scenarios/test_gsm_scenario.py,sha256=I-Sl8Sg8kmFd7u0zZbwbNmeFV1mQLuOHoQ1cQDDwovs,1123
324
- helm/benchmark/scenarios/test_legalbench_scenario.py,sha256=FqbgwBAhHWyTIUYSzI5FOnTDx0A3u1o2ANKa_6bfA4g,1212
325
- helm/benchmark/scenarios/test_math_scenario.py,sha256=ieI8-c6yx-3U3iaEz2yiCGSwnQTBJE_06-dMKX7a8Vk,723
326
- helm/benchmark/scenarios/test_med_qa_scenario.py,sha256=Ekp6r5eYPkCxV3FCzVvLemKxlhENhelqdO0Mdhg5yFo,1515
327
- helm/benchmark/scenarios/test_mmlu_scenario.py,sha256=mxEsTydKUOt8OD1Ei82nPgUFV1Tlvu5Z6drEMToEURM,1593
328
- helm/benchmark/scenarios/test_narrativeqa_scenario.py,sha256=Rac_OrUpd2ruT95YvSrmoVz2Jpycgq3Roiyogm_0aAc,6420
329
- helm/benchmark/scenarios/test_scenario.py,sha256=HexTZBKphMDJbhIYj-HRCDwltPTDqHFHdT7FjPmu8Xs,2070
330
- helm/benchmark/scenarios/test_simple_scenarios.py,sha256=9b-gtuRnd638q_JevVlEVsHzMZSzOe8j0FrUQmMyZM4,1736
331
- helm/benchmark/scenarios/thai_exam_scenario.py,sha256=5Q-KL6fVrk2FKApVyY2ulreFduwBaUG0iJOsJ8M6El8,6008
332
- helm/benchmark/scenarios/the_pile_scenario.py,sha256=RqU8yXQJ4FkmEc6rO9J3QMXenyUZrsEZlLAQUx4-Wnk,4995
333
- helm/benchmark/scenarios/truthful_qa_scenario.py,sha256=iqL-tuqUQZjF9-DKAnI6wV-oLGC_I3aFuofdtJYHt8E,6035
334
- helm/benchmark/scenarios/twitter_aae_scenario.py,sha256=CRlPxVfkg3HPZV-lUMyCUSFOiAqg5IIPt-dq3qR9LU4,2096
335
- helm/benchmark/scenarios/unitxt_scenario.py,sha256=adz6mNQFQgSbEpiOPePGMXh9aynABovHoCW3wWYA_wQ,1692
336
- helm/benchmark/scenarios/verifiability_judgment_scenario.py,sha256=AaCq9n_YC1BJ_cjNlR9Mtm_6it_eu14mtNCPbiBC5rI,6043
337
- helm/benchmark/scenarios/vicuna_scenario.py,sha256=zLwLuEr6n9VQjVxQwgFIM-os23kJewr4Uiq_1zPiScM,1661
338
- helm/benchmark/scenarios/wikifact_scenario.py,sha256=cOVKgDisBdjPcmVMCLhTekdgX3hpDJUT-aKbvRSaMoM,5791
339
- helm/benchmark/scenarios/wikitext_103_scenario.py,sha256=PAPkmZdC4aIBQ1k29dDvTFBEFaPV1ZR1Ifif4FHoZqs,3087
340
- helm/benchmark/scenarios/wmt_14_scenario.py,sha256=NArkTZntYdYlegHo_-fkzeyCUOjosOONQKlquPbZRxY,4498
341
- helm/benchmark/scenarios/xstest_scenario.py,sha256=wpagohfuFE1juuXjq0dleSIHr5Uk6hnClIv-wABbzEI,1285
342
- helm/benchmark/scenarios/image_generation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
343
- helm/benchmark/scenarios/image_generation/common_syntactic_processes_scenario.py,sha256=c8zcoGCOFqBGE4TAEx1uLsUmGXw_jIS8alI99ubGeDA,5477
344
- helm/benchmark/scenarios/image_generation/cub200_scenario.py,sha256=7p3G4mJRc8QHR4Mw2GLsfAFuJcEe6OeZbezVhbyc55E,4103
345
- helm/benchmark/scenarios/image_generation/daily_dalle_scenario.py,sha256=yiaX_2Aut3hZdfggCsTCcTPOdraaX-cOjPHyE5D1lYg,9045
346
- helm/benchmark/scenarios/image_generation/demographic_stereotypes_scenario.py,sha256=yAFh8Kn84b3RpHZVsVMYnk4GvbMgxB7oIPUzv5sp78I,3216
347
- helm/benchmark/scenarios/image_generation/detection_scenario.py,sha256=E4tqQXmPSLutPYdk9Ngil7LteUwRe7p55MXSURxk_rU,3188
348
- helm/benchmark/scenarios/image_generation/draw_bench_scenario.py,sha256=b4WcbttcjoIY5gcOMk6e7c_mqfjlQsfowo9-D_-wccY,3179
349
- helm/benchmark/scenarios/image_generation/i2p_scenario.py,sha256=8VXVyWZmW6k4Q43GBDwqzYDj1pCKuAraGKaulZ_0MPk,2233
350
- helm/benchmark/scenarios/image_generation/landing_page_scenario.py,sha256=0R1sAuS7txLxpaJOuvojg6dZEcRFGo4WabjX2ieo0FA,1361
351
- helm/benchmark/scenarios/image_generation/logos_scenario.py,sha256=Sbc_vlMdHAr6AhJ6rr4TjBIMEbzcw_hdGhYGufHSlJc,10245
352
- helm/benchmark/scenarios/image_generation/magazine_cover_scenario.py,sha256=swcdlPAYYwtidMUIHWCW1-xxHH2QF3wm3IKDBkr6-DU,3599
353
- helm/benchmark/scenarios/image_generation/mental_disorders_scenario.py,sha256=kybgeSjY0nm3Wya2vQeoBtJGtHZra4XhT4VY7Izjxrk,1879
354
- helm/benchmark/scenarios/image_generation/mscoco_scenario.py,sha256=KMzu0II1F8ajL7NrYBWe74UXKcLugg7bhubpSZR4TQw,4201
355
- helm/benchmark/scenarios/image_generation/paint_skills_scenario.py,sha256=6nm_uo6rmkyBzbU0BntvLq9jhWlfunBEy9Vc1d7_RVU,2967
356
- helm/benchmark/scenarios/image_generation/parti_prompts_scenario.py,sha256=pTSd1XidvWwTPFpVinl28s6150a2w3iK4d1Ce81lijA,5165
357
- helm/benchmark/scenarios/image_generation/radiology_scenario.py,sha256=7JN8OYap8kA36Od1_bZTkhZd-H9Qjw_dh4TIzr9UTms,1701
358
- helm/benchmark/scenarios/image_generation/relational_understanding_scenario.py,sha256=DoabanZhd-2MHFDZeR9EoPit0T2TvbVwZGUR0RfJyW0,2362
359
- helm/benchmark/scenarios/image_generation/time_most_significant_historical_figures_scenario.py,sha256=IB4_GbzQjjXBp-551XZ6PTNUCRX1jLcGfB3bVFI5lo4,3547
360
- helm/benchmark/scenarios/image_generation/winoground_scenario.py,sha256=E2xPQNQzylDSmqLjjMkQB8D7A6g7bzqtSF4bXPgfVbI,2889
361
- helm/benchmark/scenarios/vision_language/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
362
- helm/benchmark/scenarios/vision_language/a_okvqa_scenario.py,sha256=s-sdEFVx2BgqDFTzuQCCQr4oXaYHUUeQpFgblcCU97I,3052
363
- helm/benchmark/scenarios/vision_language/bingo_scenario.py,sha256=6YlGGGZW04Oy5A1-UG8JrN6jwR5eBuzrQ5qAise88o4,4108
364
- helm/benchmark/scenarios/vision_language/crossmodal_3600_scenario.py,sha256=lfRHjhhXCo0YeDQe4_gfSHCzVKtqQVZ6DALLABcCmtI,4637
365
- helm/benchmark/scenarios/vision_language/exams_v_scenario.py,sha256=pLD--gtL5q7jLSWQ8iwAdsiOrTJ_rBsLbwWMWKRhPbs,3853
366
- helm/benchmark/scenarios/vision_language/fair_face_scenario.py,sha256=V6_1Kl2nWDRyHvwnKcSxkP0DChzKDBW0i_-t9oAxps0,4721
367
- helm/benchmark/scenarios/vision_language/flickr30k_scenario.py,sha256=CDutFh1PHLyeMdJ9HojzYKE1zJidL9ktcsfn9uHNLZY,2612
368
- helm/benchmark/scenarios/vision_language/gqa_scenario.py,sha256=k4E6JAN8a_KT1jjV2Ch3K5YhWKJ0f-9iCXLO-_2Xl8M,3535
369
- helm/benchmark/scenarios/vision_language/hateful_memes_scenario.py,sha256=qiLLdiSzhnSyjmqCAvMxjhcZ7yBiX37L1cdsZvHL4ds,3845
370
- helm/benchmark/scenarios/vision_language/heim_human_eval_scenario.py,sha256=7GK_jAOfCgRIGiN_GInDePwuT2wZqmWHp1rqdx18xQg,4994
371
- helm/benchmark/scenarios/vision_language/math_vista_scenario.py,sha256=HnzA0L1Mm9rw9uyK-hnCGrxo33z_U_86TLnlELjDV6E,4738
372
- helm/benchmark/scenarios/vision_language/mementos_scenario.py,sha256=7ZHpRD7TdQQ-Mp5XQV5yyiLUE0k1KpgbLSYKLBJMxs0,4343
373
- helm/benchmark/scenarios/vision_language/mm_safety_bench_scenario.py,sha256=cM7eTE4bpcIzLyEDye86Ud3rD4Id-0ju73EXjg0DYoI,4340
374
- helm/benchmark/scenarios/vision_language/mme_scenario.py,sha256=7Aa3y0TWGZH3QrPDiqIMkj83LU2Klrzgcb46jv5uytY,5498
375
- helm/benchmark/scenarios/vision_language/mmmu_scenario.py,sha256=deDMdg2-ORZPV623ngncDPlRn6z6cq_QbQtMu-z0Ydo,7665
376
- helm/benchmark/scenarios/vision_language/mscoco_captioning_scenario.py,sha256=HUO09uM2rBXOfCsxzwovmwtihq53xjuzDOtQO_S3J4I,4161
377
- helm/benchmark/scenarios/vision_language/mscoco_categorization_scenario.py,sha256=c7YfclYMDtygsLnEfA8oP6Vl7evdrqqTZazmuD9Oy-8,5353
378
- helm/benchmark/scenarios/vision_language/multipanelvqa_scenario.py,sha256=HuizbYsN5Nlihfzu4bfGuC8KSBbeIc6TVknMS4kpVJY,7149
379
- helm/benchmark/scenarios/vision_language/originality_scenario.py,sha256=1inr-klQEz08CM2GWqbYdy-AuXQmMhOAywAlA0lJHik,1029
380
- helm/benchmark/scenarios/vision_language/pairs_scenario.py,sha256=D3nNu3uU87eMDiMZZafuRTntXjwbqPaSDygUgQm45F8,9943
381
- helm/benchmark/scenarios/vision_language/pope_scenario.py,sha256=gWrBG5U8uoU92JPGNm5kuzo1GekoJo1rKQaNhv6MYGA,3996
382
- helm/benchmark/scenarios/vision_language/real_world_qa_scenario.py,sha256=OJtiGhSN_KYgEz0VGXjCjQik_Xihtgiali70Z00XOzk,2083
383
- helm/benchmark/scenarios/vision_language/seed_bench_scenario.py,sha256=YNwuIMJBo7wwftx-T5tCYmGo2oy_794fZ330lkDyqb0,5171
384
- helm/benchmark/scenarios/vision_language/unicorn_scenario.py,sha256=DxGZ7EL22SzxpAkuiA5twuGVTm96wG_RBg3dU3Vh_c4,4241
385
- helm/benchmark/scenarios/vision_language/vibe_eval_scenario.py,sha256=wRa_OuOdyf-qcy9hml-Kj6YtVP5MDzeTbGcqva6LqdA,3707
386
- helm/benchmark/scenarios/vision_language/viz_wiz_scenario.py,sha256=zCnkiSya-PHc3ywAhmw03bFdsvLCxAUwGfE6OviEXDQ,4153
387
- helm/benchmark/scenarios/vision_language/vqa_scenario.py,sha256=cC8_Vyqw2f4K4hJY-eo9ptj6ANfWgiFAK7b6OOTIPLI,5239
388
- helm/benchmark/scenarios/vision_language/image2struct/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
389
- helm/benchmark/scenarios/vision_language/image2struct/chart2csv_scenario.py,sha256=qcs3o9dPsXoeaP0bu9UVZ6P0GPEcRLoaqABxysLN6VY,1802
390
- helm/benchmark/scenarios/vision_language/image2struct/image2struct_scenario.py,sha256=uDYN10CuXWXvgZ2BYNxlTmBsdfPNlK9G9e_VMGDKvA4,9400
391
- helm/benchmark/scenarios/vision_language/image2struct/latex_scenario.py,sha256=SnZuHATg5i764MAdgaGwjIGdjCZNrOqP83Y5jE_fkHs,1153
392
- helm/benchmark/scenarios/vision_language/image2struct/musicsheet_scenario.py,sha256=c08cquz2IALY7PlpOoEfAjupKZmn5GDVZ1H8Gbj4r8s,831
393
- helm/benchmark/scenarios/vision_language/image2struct/utils_latex.py,sha256=jW3_c63a6u39PJGJw6lM9pIa3dnF8CQgZlPNZdH0sfs,15001
394
- helm/benchmark/scenarios/vision_language/image2struct/webpage_scenario.py,sha256=DJQIa8NaKV-nhkXEBuY97MJ8a1O3x-Yr6hACVa-67Ns,11117
395
- helm/benchmark/scenarios/vision_language/image2struct/webpage/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
396
- helm/benchmark/scenarios/vision_language/image2struct/webpage/driver.py,sha256=WBFbb3N_eHIa7OFvHQS3Pmwbmkl6r9VyobxlIEKhty8,2823
397
- helm/benchmark/scenarios/vision_language/image2struct/webpage/jekyll_server.py,sha256=9WntahzuhVv54IH1m7_z0IxwLma3dbaMOne_pUx751Y,7652
398
- helm/benchmark/scenarios/vision_language/image2struct/webpage/utils.py,sha256=UYe3PnxCKBYEbZTTEzdIoTY9gW7ZZAWmVISRIdItD-A,940
399
- helm/benchmark/static/contamination.yaml,sha256=rAfh1DqwyUcDtyzHPQ2QiUK5eY7QfuuRtBXpZMn4TeA,3171
400
- helm/benchmark/static/schema_air_bench.yaml,sha256=LapSMj3Ecl1Gp9XIwVCYfrerqS93GNErvp6oDnBCtgw,142378
401
- helm/benchmark/static/schema_bhasa.yaml,sha256=5q-jjK-YvE8C_wVal2H2C-fbW0g4env9-Skbu8o-L1k,27774
402
- helm/benchmark/static/schema_call_center.yaml,sha256=Mt7_rLG6IT701YrjiJdNb7HpoMVkFjabrawnBieUUhM,8049
403
- helm/benchmark/static/schema_classic.yaml,sha256=sK3yVQCrk3Tn3Kmg9WITBmJZI7AKVjmIY0f3zgH_t0c,104611
404
- helm/benchmark/static/schema_cleva.yaml,sha256=TDh-zcCzzTTs7bu0IWlY5dXYaTFhxly8sJIBGQdBvug,25401
405
- helm/benchmark/static/schema_decodingtrust.yaml,sha256=2VPxzcyKYea7mx-qmswyVRjPfVatjVH4Rs3OU82mgII,15670
406
- helm/benchmark/static/schema_ewok.yaml,sha256=MluPnZSy22wZLFB2pR7ycBRgUSvIUsqvq4qM0Vk2ur4,12113
407
- helm/benchmark/static/schema_finance.yaml,sha256=OgsYMSFK__8ZZS96ktsgVRfM40-BhbOY15j9OlV-rNE,7010
408
- helm/benchmark/static/schema_image2struct.yaml,sha256=cD1X99YcPI8BMAnNfDmXlM-FN0yPsYgu_MB7uu5pwHE,19894
409
- helm/benchmark/static/schema_instruction_following.yaml,sha256=mYLpMv-iNtsmrv9ewfN9ceDOBBg8nSxOWfc6ByATmIk,6056
410
- helm/benchmark/static/schema_legal.yaml,sha256=RpoFOuVSIowNgxlPn3UMfJC-68RFr3CGDciUGLPfVqc,28806
411
- helm/benchmark/static/schema_lite.yaml,sha256=rFSoG7zGPNOtKkJyGgOViWf5WJbMiJMAXrgmqCAi9X4,36611
412
- helm/benchmark/static/schema_medical.yaml,sha256=hDk4834FKn-5cMr6pHcu1P60sh6cXJ2J0Z1ADIj2MSc,8455
413
- helm/benchmark/static/schema_mmlu.yaml,sha256=KI3XnzEwBRpzfYGjP77yKL-hBklEg72D3vL0kVl1BeI,49666
414
- helm/benchmark/static/schema_safety.yaml,sha256=k4LBKZbnxRgofejJE-hHadTcHpRTlx4NAt19j3fe4NA,8872
415
- helm/benchmark/static/schema_tables.yaml,sha256=c2HZlGa_vTOlbc2ByuTW2FpsuLVGyRyOSXeocwkeSgY,11047
416
- helm/benchmark/static/schema_thai.yaml,sha256=yJUrevvgTJ46TpyXfNecW_B9urh7LPwSbBi_mT4ZngA,8348
417
- helm/benchmark/static/schema_unitxt.yaml,sha256=9FQhoueYNNYQ2xMuJ2KHzpg_9-_ZhZ9efk6jtTQ3tlc,11855
418
- helm/benchmark/static/schema_vhelm.yaml,sha256=4DkACpY3RPNOdk6-vBKoQTlsV8Q5AL7gNc8gZDSYiWs,31185
419
- helm/benchmark/static/schema_vhelm_lite.yaml,sha256=4I68Em9q5wW8sFzj5GCJz8m49fBEuMyVmSZM0-wbfOk,4024
420
- helm/benchmark/static_build/config.js,sha256=ER8utDIqVZi9uge7Qrk1gmlT88TOOkFF9xYp3j10m8U,165
421
- helm/benchmark/static_build/index.html,sha256=YoxWJa-SHRtdMnB5V44wD-2wMj3cUEVXqA60QfK4f_I,1149
422
- helm/benchmark/static_build/assets/01-694cb9b7.png,sha256=aUy5t0DYCg4r52HDOmeNi1S2CHsnv3mE7ySokJg3Ouo,8903
423
- helm/benchmark/static_build/assets/accenture-6f97eeda.png,sha256=b5fu2p7L_mnwg-p5jjPk1sFRwJEBRtGwXsVyQU_Runk,9537
424
- helm/benchmark/static_build/assets/ai21-0eb91ec3.png,sha256=Drkew6Vlwi2_4_S8hjagK2x8smOwLKTNiXIT3rDiurs,10208
425
- helm/benchmark/static_build/assets/air-overview-d2e6c49f.png,sha256=0ubEn4J0T51-jx7IlwjaEGSrofZWlW_e67MJw47Ujzg,733055
426
- helm/benchmark/static_build/assets/aisingapore-6dfc9acf.png,sha256=bfyazxJvVs5GTSSlnm6nOb2r_jzo3TJybqF04S5Dxhw,69372
427
- helm/benchmark/static_build/assets/aleph-alpha-7ce10034.png,sha256=fOEANHS8RymKaCzUWn9gQWebts2ghSmtW9Fdda_TjR8,7224
428
- helm/benchmark/static_build/assets/anthropic-70d8bc39.png,sha256=cNi8OdIshIIb8PdodcX8mAj-khaUD0O6nhah-_6nYfs,8017
429
- helm/benchmark/static_build/assets/bigscience-7f0400c0.png,sha256=fwQAwN1x2Fr_ztD_HZdcOkdFcyxuDjtS3B5-VuRNkuc,19036
430
- helm/benchmark/static_build/assets/cohere-3550c6cb.png,sha256=NVDGy09xliCqZy2TKUAka-B90jVDB_VRCS9A2_sN7VU,4414
431
- helm/benchmark/static_build/assets/cresta-9e22b983.png,sha256=niK5g8HYADkbhKM9gSVtYEdPegBS40zZXF4nNe9Fu4o,8131
432
- helm/benchmark/static_build/assets/crfm-logo-74391ab8.png,sha256=dDkauL_wJR_Luu7L7pltphS3a9HSLjDkpVLa6C9vcA4,62712
433
- helm/benchmark/static_build/assets/cuhk-8c5631e9.png,sha256=jFYx6Xx-SGYANpsSnqrlaQytYuOBOsTHhpqPJZk3EwE,30385
434
- helm/benchmark/static_build/assets/eleutherai-b9451114.png,sha256=uUURFF8YWY85mwGoKVEjArO5DUBCy4es5naCXsBzn6c,4526
435
- helm/benchmark/static_build/assets/google-06d997ad.png,sha256=BtmXrVQZHr3WH5c8c23ent2FO8aPWeNwO8czl22lDCo,4914
436
- helm/benchmark/static_build/assets/heim-logo-3e5e3aa4.png,sha256=Pl46pKbC_TU3L6kZQ_3G-0wTseluAhIYwb3EqpdQAjQ,1344452
437
- helm/benchmark/static_build/assets/helm-logo-simple-2ed5400b.png,sha256=LtVAC4OgcWgMAob53rTrf7cRDu-O0z85ZOGGj9wR9hw,86133
438
- helm/benchmark/static_build/assets/helmhero-28e90f4d.png,sha256=KOkPTf-q28PdvGOBp1G5O4q1eWUJjuij3z2h_SUUf8s,55314
439
- helm/benchmark/static_build/assets/index-05c76bb1.css,sha256=BcdrsQgUFadqYf5z-wdFNosV_c2MlxV8xktld2BFKBk,489017
440
- helm/benchmark/static_build/assets/index-3ee38b3d.js,sha256=Mtgoy__VC4YN1GxN234HDVfEqq4ONNaj3vTfKDEtqPs,93905
441
- helm/benchmark/static_build/assets/meta-5580e9f1.png,sha256=VYDp8arkAe2eYRJhAOcIAsZY1qY0hqyOEQDgVMbX9M8,4646
442
- helm/benchmark/static_build/assets/microsoft-f5ee5016.png,sha256=9e5QFl23yTbnAk8u7lZKaQOf4oPHbr_aiQda5n4MZqE,50850
443
- helm/benchmark/static_build/assets/mistral-18e1be23.png,sha256=GOG-Ix7XlctGOUmvJfO2oVSBM7E5O562G88OnoxsjBw,14402
444
- helm/benchmark/static_build/assets/nvidia-86fa75c1.png,sha256=hvp1wZMwYxkfrVMvJs73PX71JwY5L8ZvxIH_fL4n6Po,27945
445
- helm/benchmark/static_build/assets/openai-3f8653e4.png,sha256=P4ZT5ISIlt6Dl0mOp7juSM4Y7dfyRNPqdc0PJuwNoqg,16877
446
- helm/benchmark/static_build/assets/overview-74aea3d8.png,sha256=dK6j2Nn3j9O-FMUIVRT5HGBpR_GL78vrKi8oHdG1eaI,74685
447
- helm/benchmark/static_build/assets/process-flow-bd2eba96.png,sha256=vS66lq700aPEKTJR7maMrmepAyBZySaL42tBNCRjFWA,190822
448
- helm/benchmark/static_build/assets/react-d4a0b69b.js,sha256=rNTpl8Is3LkYXqJowRMc8vc4SXQwP94Ozy4DZZWwldU,275141
449
- helm/benchmark/static_build/assets/recharts-6d337683.js,sha256=rDrVmtTCCSLY2hpcxSDxhlQ6CQmTTSQOESNeO3oVQgg,432466
450
- helm/benchmark/static_build/assets/scb10x-204bd786.png,sha256=IEvXhlxgBA9NCH4RrGWJkMx0Yc7V9EK6o7vrAI5KZCE,4990
451
- helm/benchmark/static_build/assets/tii-24de195c.png,sha256=JN4ZXAa0rbR2IlxPfd_mKtntFZcYpDcXocSiqrC2rNg,63389
452
- helm/benchmark/static_build/assets/together-a665a35b.png,sha256=pmWjW4r7GnlKqFhKLPTiBeILiOighL3XzcSCsxWtB7U,48053
453
- helm/benchmark/static_build/assets/tremor-54a99cc4.js,sha256=x_K5Bp7szI2zsvESrKqffUOHbm8ohjjvuoIeY_yD_CA,293015
454
- helm/benchmark/static_build/assets/tsinghua-keg-97d4b395.png,sha256=l9SzlZCsLF18BY876wYJcVgiQbgvwte7uoILPDcVwHk,7776
455
- helm/benchmark/static_build/assets/vhelm-aspects-1437d673.png,sha256=FDfWcwGcJhJco4qmZli_ROomLiASrrnsX-wtKSDvMkc,542231
456
- helm/benchmark/static_build/assets/vhelm-framework-a1ca3f3f.png,sha256=oco_P6kwqp0cC3YaT_2H2RhJ6p1sh3sEQq3R0RA_cT0,71934
457
- helm/benchmark/static_build/assets/vhelm-model-8afb7616.png,sha256=ivt2FhDk8dwnzp1MAle5WfbXzht_Mxg4rpy-xHRybjs,180285
458
- helm/benchmark/static_build/assets/wellsfargo-a86a6c4a.png,sha256=qGpsSjEu7HFlPAk_zXuUEdDqj0wkCfFHA1bCtu8Ugdw,8531
459
- helm/benchmark/static_build/assets/yandex-38e09d70.png,sha256=OOCdcKubAP4x7h4VW7z5a-AHPWBiSDTjsIJea6ZiovA,27964
460
- helm/benchmark/window_services/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
461
- helm/benchmark/window_services/default_window_service.py,sha256=F099qF-YeM7YPVtph0dRFPry5vP8_BiudHTy2CpuICQ,151
462
- helm/benchmark/window_services/encoder_decoder_window_service.py,sha256=EU3QevFOiQYBN2te54FsVRnGYZdgDxK6KqOWSQOa0q4,2125
463
- helm/benchmark/window_services/ice_window_service.py,sha256=9NeBN_tmOvwrK1miUnX3wJA70BP5ifIIeHpNR2gVwls,1070
464
- helm/benchmark/window_services/local_window_service.py,sha256=e9JHG72kFWlV6UKg_IhRCipOWQUrOD6ZjsT-_Mwewps,5232
465
- helm/benchmark/window_services/no_decoding_window_service.py,sha256=s_i_cqIuU9p0GDRIBApaOHzjH7gHrBPTJ2X5NEcN33Y,1375
466
- helm/benchmark/window_services/test_anthropic_window_service.py,sha256=lnxLiW5BPaWN6m03L93qCFugsxnVBbLmYPCarlrO-So,4196
467
- helm/benchmark/window_services/test_bloom_window_service.py,sha256=x7WBh0S223ABC9KvL2-y9G-cUxFUPm6oIkqvYO_4mt8,4288
468
- helm/benchmark/window_services/test_flan_t5_window_service.py,sha256=IhQMWBq2d39O3uNKGwbaMWJkz8585Zc-J_yqvPJfwu4,695
469
- helm/benchmark/window_services/test_gpt2_window_service.py,sha256=2UHKt4Wmh6XmSCdepjuMbZHFpb1oUcrKRSxcdOzBE1s,2671
470
- helm/benchmark/window_services/test_gpt4_window_service.py,sha256=tV5WdpxYxewchEp1rnsIlEfdJFrHVFKYQ-_8NhGK2yo,1052
471
- helm/benchmark/window_services/test_gptj_window_service.py,sha256=0lu4Os_3x3N-AbejG3LZ3-_ikxEHg1Lbmfq-Pzg_D9Y,2374
472
- helm/benchmark/window_services/test_gptneox_window_service.py,sha256=8CaOW_ln9bxKA4--dVLfLdsASo6RrR7ouP6EcSruzdA,4210
473
- helm/benchmark/window_services/test_openai_window_service.py,sha256=Mt-dDtjQmz25n7hwNVyy1T_rl0TMvcvJfuhWNe_AvSw,2314
474
- helm/benchmark/window_services/test_opt_window_service.py,sha256=Gh1GzWnlgYIGwDNBw4EnHds3fXwMaSjzkfFXeLn47os,4215
475
- helm/benchmark/window_services/test_palmyra_window_service.py,sha256=yy7D2C0ZzExCbptYNsEI9zuX2AEGsEUTj0a_vbqub4o,4212
476
- helm/benchmark/window_services/test_t0pp_window_service.py,sha256=pvp55FyqjunkDpHVAhPup3h-iNkepQpxyr4nC87-5iY,3998
477
- helm/benchmark/window_services/test_t511b_window_service.py,sha256=zwgUxmkpV0IJ-SW15Ugic08KEx-ZwLXPCl91Mt87XDk,4001
478
- helm/benchmark/window_services/test_ul2_window_service.py,sha256=JUehWFC5P1sosoFzPacLJwZQ3D7_GUn6yLi8oBPkido,4061
479
- helm/benchmark/window_services/test_utils.py,sha256=TQ5Ba3rq-0k9fCqGJ-gfEr2NavP_hzvxwZ42SRPfIlI,3376
480
- helm/benchmark/window_services/test_yalm_window_service.py,sha256=tO1ZsUCXD1E0QZWarABJjn5Q-g-d1PyM8PFOmGMcynI,4301
481
- helm/benchmark/window_services/tokenizer_service.py,sha256=RNznJBAxcCUMCurb7mbraZULx_ZtB0G7IxbrnUe0Urk,865
482
- helm/benchmark/window_services/window_service.py,sha256=y6BthPY1V-ugmYfaJElm5Wfy3PSgoJLj10vHcXZZGNA,4727
483
- helm/benchmark/window_services/window_service_factory.py,sha256=T55F0Y2jiOYxUHHZxT4YX4fFXY5gfFhn56zIwUBhc7s,3423
484
- helm/benchmark/window_services/yalm_window_service.py,sha256=_Yz4NwbMx9Px8raJlMMA5Aw80iA8G_bQnd8pxRK-By8,1059
485
- helm/benchmark/window_services/image_generation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
486
- helm/benchmark/window_services/image_generation/clip_window_service.py,sha256=2JHld8GiR_eIQyHMPSN8K2VOswmKJEPMPJLsxlLpU-Q,631
487
- helm/benchmark/window_services/image_generation/lexica_search_window_service.py,sha256=g7usb-xefJtUXpgywm0cnCgYYAHq5qTX3o0V0tTQGQ4,407
488
- helm/benchmark/window_services/image_generation/openai_dalle_window_service.py,sha256=GFz7xf0uuN7ah7QC7SFq2833QHvefNJvBu5L310MAfs,406
489
- helm/benchmark/window_services/image_generation/test_clip_window_service.py,sha256=domn2MRduHVAdruSUuGPDIGKyDrh-gFxW-fZaBYR7cg,1430
490
- helm/benchmark/window_services/image_generation/test_openai_dalle_window_service.py,sha256=nSyKK-cQxZnase3Bw4X6DyAWZEy1OZi4stDZpKtolF4,1411
491
- helm/clients/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
492
- helm/clients/ai21_client.py,sha256=PYyqpbnMK1l18Rv_qhE5KdHHqZHgHePaJtJOowTyG7I,8128
493
- helm/clients/ai21_utils.py,sha256=mlg3h615kyckccGZv9rqsP4Y60O3XpwyE-UURRMrxII,471
494
- helm/clients/aleph_alpha_client.py,sha256=koPqXF6uRD905atoiCaPg5yxr6B25J0g2OTWk8geebQ,4969
495
- helm/clients/anthropic_client.py,sha256=s3eCwHh8mbhxLi8up1WtQWKkUsHJa-LO44prNd7XYFc,34059
496
- helm/clients/auto_client.py,sha256=uK9EWQFWBt4DoV1oytm0dIeA3YpcfGi_H0rCRZSVE8c,11438
497
- helm/clients/bedrock_client.py,sha256=BsH9UopsP6ZHf-K0Yzg1PYSMLDwY0yIUmPHDhJVMUi0,5293
498
- helm/clients/bedrock_utils.py,sha256=okZ6Z8pviGOUNlrdF2QquAqFs8-QYgcqci95eij8giM,2574
499
- helm/clients/client.py,sha256=InjCQi62TWhWHmfyi-mC3fSAVztd-YDyfB3BkpacHXk,9002
500
- helm/clients/clip_score_client.py,sha256=ct3GHZ2Zh3fGwyvQ9DyoIPT6PwDPI-nUaFkUFuc8PIE,1622
501
- helm/clients/cohere_client.py,sha256=PtVrDdm_-dXBiWzu_dfwiJPt5GLGw3wdN-Qw3u8ugtU,10976
502
- helm/clients/cohere_utils.py,sha256=aYmj60m0e9RF9BIdxp1vmA-uZv17TEALw0dbgTUSpCc,504
503
- helm/clients/gcs_client.py,sha256=1sK5x5uWtThgz9gqBLaA8oyiXGD_9nn1WyfMzJRyPQ8,3231
504
- helm/clients/google_client.py,sha256=EOpPzK5_9yzWkMjK-4ILiixDF3aeOa8AbR2SPnEO-nw,2900
505
- helm/clients/google_translate_client.py,sha256=TgiQEscjOae58Ptgp9f4n0LXUtl1Jf6v9BI-Z1_wcuw,1304
506
- helm/clients/http_model_client.py,sha256=DBgkVDZPmg99DCcO_1Xdf6nFQo2kyxLkgoQpwC-wkHI,2806
507
- helm/clients/huggingface_client.py,sha256=k-8J4nnDbve8UtGsa0RytWhS9IpAy8hoJAUw4nRZTMI,15734
508
- helm/clients/lit_gpt_client.py,sha256=Sjec16bNODosEhDoBkRc4t-LNS-nCUY_jVivWj5zvfU,6205
509
- helm/clients/lit_gpt_generate.py,sha256=8DdBE9ReQ00NbV3KMFYc--PlO9X-HMOR0Rhm5CADWEA,3103
510
- helm/clients/megatron_client.py,sha256=KFL1BBBDqxr5mtd5iu0dA6uK8_v6d4g_D6RsZrHx3a0,4107
511
- helm/clients/mistral_client.py,sha256=thOLMcEfrzWR00JUabIZ_PnW2o9YZsdSmNf9z3jbYKo,5982
512
- helm/clients/moderation_api_client.py,sha256=I5pYWRb2MmcLDYrScnC3P5N7OUFzQiVQ828_hf7zjM4,4719
513
- helm/clients/nvidia_nim_client.py,sha256=f3ZWoTnJmBIFeWsHeUDaTCbDZLK_kdlUWNO1hWumUOo,987
514
- helm/clients/open_lm_client.py,sha256=qFgYqlV_3UiW8WJKz66lLqRqg2jt1qtJ1bHMRAtBn40,1749
515
- helm/clients/openai_client.py,sha256=Am7xfDkWV4l3MuPEwuF7ImZ6qOe6rmsjI7sRVTfMhMA,14997
516
- helm/clients/palmyra_client.py,sha256=vnlGL3F4ZUK3-UXlIq4OgbP9sA3_C2ItJPiM7RDelo8,7224
517
- helm/clients/perspective_api_client.py,sha256=o_1FFTCrTny6AZ4EJTstX1H9t8SQSQ8dvhi321RTcL4,6105
518
- helm/clients/reka_client.py,sha256=K8b9p7U6LLAy4PRjgYrUS06gF4G2xjhjRoMEO4XDe0o,8329
519
- helm/clients/simple_client.py,sha256=55S_y1eWD1bjktcG21Vs8G5bF6QbKKwmJyqs6lCUJeI,2048
520
- helm/clients/test_auto_client.py,sha256=bc-rsMJ8JM0MFnQ4B48hBJ1jL3RtRyVvmPwOgzF2mF8,3155
521
- helm/clients/test_client.py,sha256=6cLpQc2IMR5o7iBxZYPvoRtHJa5i0E7JHh1VKaCtfBw,3842
522
- helm/clients/test_huggingface_client.py,sha256=x2NjMuIrinfUy0wQ1S6F5cYZVr09YfvN6LfhWmyGNAM,3388
523
- helm/clients/test_simple_client.py,sha256=G0JRQX69ypQN2VxhlNQXs5u2Tdtkcl_aeHqudDUVKi4,702
524
- helm/clients/test_together_client.py,sha256=yYNrhU3kQjmHwhILuoP5QwUgbmkm2gg2NHiNycHjoeE,6145
525
- helm/clients/together_client.py,sha256=J9rQQCqPSLftTNR6BEei28bTL-eXwGAvvyiyw2SVbe0,21836
526
- helm/clients/toxicity_classifier_client.py,sha256=AI_FizxMurubTIyeceRdkixSnhWQbcD-oEEONj5ve7o,464
527
- helm/clients/vertexai_client.py,sha256=K_vCanJU97o2P_WJOeLhUFJA8SdfJDlVNl7Mi1HuIrQ,21860
528
- helm/clients/vllm_client.py,sha256=p9atBtq3PBOoPkOPSifkMrYZjNLnNM_sWM6tL_3N-WY,1675
529
- helm/clients/yi_client.py,sha256=0t4WJ8MTLOpB1LCZ-P6UdYa-KbGB7hkDrBluSkioot0,835
530
- helm/clients/clip_scorers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
531
- helm/clients/clip_scorers/base_clip_scorer.py,sha256=NfXe79g6M4Wype3Xf-oXxscaUgjbZLmy9dRnBaLiWwk,695
532
- helm/clients/clip_scorers/clip_scorer.py,sha256=waLI_rI6dQPjmtywvGeQKK7bGCWXyoIgIuBc8P3zSB8,1907
533
- helm/clients/clip_scorers/multilingual_clip_scorer.py,sha256=7ntUK2XiQSnlrjjlNO0ywI3LNSOBvMLtWELewBKdSjg,2041
534
- helm/clients/image_generation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
535
- helm/clients/image_generation/adobe_vision_client.py,sha256=-jhhKtgD8cV12fqoY5ws5SbOnlNX00lvgUtfpn9X6Eo,2863
536
- helm/clients/image_generation/aleph_alpha_image_generation_client.py,sha256=6CQCF1vtPgr5hMJAHrRYLNCM9lniYv1udZu0sy-8Hec,3999
537
- helm/clients/image_generation/cogview2_client.py,sha256=1sH-18x_Lo3h8r5gH4kT9p3vzfU_ughxQkSsLFoIKi4,8426
538
- helm/clients/image_generation/dalle2_client.py,sha256=ztW1BeTw1FaUdAMJeH-kihIOTgILmoTP8Zuuxe9mEN4,8401
539
- helm/clients/image_generation/dalle3_client.py,sha256=kVdP1jTTEWKnEFJ9wZWCTjQjP0X7vjjFoLCtLKfHviA,4581
540
- helm/clients/image_generation/dalle_mini_client.py,sha256=9JS_4w1egJlFSG_ACoxAlPiXY_mCi-bN8yXG3vaPxHM,8146
541
- helm/clients/image_generation/deep_floyd_client.py,sha256=i2Fp-jk1tXGjpXqGU39w3i-g3zNz1KlXEL-JWojMRKw,2999
542
- helm/clients/image_generation/huggingface_diffusers_client.py,sha256=LiX-0XbHV0GY2BMIwRdZcFN0saqEfWNzzXKDDY7VnL8,12284
543
- helm/clients/image_generation/image_generation_client_utils.py,sha256=N130PbHLLvE9Q1iVefPvTCJzs3hG3osZCeYdJyjLjCw,437
544
- helm/clients/image_generation/lexica_client.py,sha256=9Xpb3Oc0aaseZ1eAM0H3ShlgVy_UpFtuLXs74vD1zWU,3652
545
- helm/clients/image_generation/mindalle_client.py,sha256=kze8F_-mrJN2vVeq9fxSdWd0Ho0KES__CHH2zpDt2vA,4624
546
- helm/clients/image_generation/nudity_check_client.py,sha256=TeFga6HvBKgdX7LitBoioXUD4BQGavVwzr5BFFE29x8,2599
547
- helm/clients/image_generation/together_image_generation_client.py,sha256=T3HiE6em0Wwq_ilVThuCVWyej2jpK6Z4osw1M-Twa9w,4364
548
- helm/clients/image_generation/cogview2/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
549
- helm/clients/image_generation/cogview2/coglm_strategy.py,sha256=P3NU3Z4jsj171PrHPtGDiCRq05kEh-KHjSTgxPDw6R8,3766
550
- helm/clients/image_generation/cogview2/coglm_utils.py,sha256=EJPOEQJInCDVi2LHqkjEUsgw6GgVlLDrIptlT9cXk-Y,2900
551
- helm/clients/image_generation/cogview2/sr_pipeline/__init__.py,sha256=OsI4b5Lh0cuP7mDCCdMxzNVATEJk5A9S2unE2u21_Ko,338
552
- helm/clients/image_generation/cogview2/sr_pipeline/direct_sr.py,sha256=Vv6WDClDPAbwIW3S5qWObKm2hBGI8h9aIcHtVa5ZMbA,3603
553
- helm/clients/image_generation/cogview2/sr_pipeline/dsr_model.py,sha256=xYn3acxU4BRdDeRjk98Vj0qq8qqty93kPCLdz-bOMKs,10818
554
- helm/clients/image_generation/cogview2/sr_pipeline/dsr_sampling.py,sha256=OonYjdtNKJo12cNb-t-gFHLXRFxItCXjKgS9YxWAI-k,7718
555
- helm/clients/image_generation/cogview2/sr_pipeline/iterative_sr.py,sha256=dPz15YXG-XCzWKTduCIU7FYA2uBNyd9g-YUNz2L-iMk,5007
556
- helm/clients/image_generation/cogview2/sr_pipeline/itersr_model.py,sha256=5D1QWyAcY0CpwITk7EBN6ylUtc7mvZaE9iHG628AqMQ,10390
557
- helm/clients/image_generation/cogview2/sr_pipeline/itersr_sampling.py,sha256=d8voNZnXfqh-LzIzAqcMD4h4XJx_u_mvu9mewMrJC5k,4392
558
- helm/clients/image_generation/cogview2/sr_pipeline/sr_group.py,sha256=7Dzpf0iSGgVJFDaVgnPd8tPyPbKuFsy_Z0m5Z7NwO7w,1457
559
- helm/clients/image_generation/dalle_mini/__init__.py,sha256=KL0VUc5S9ygXUk06LUt6vJMV8BY2YTGtQZKFw2DtCDo,72
560
- helm/clients/image_generation/dalle_mini/data.py,sha256=UpiI2uWpwr9Eqxk8Al7iOZ6XcQgl1EawwVGpqvmvQjM,17582
561
- helm/clients/image_generation/dalle_mini/model/__init__.py,sha256=hRuE_LlrKedI68aXWN7DrgiVvd5PYqLxrbnZ8M7p6J0,198
562
- helm/clients/image_generation/dalle_mini/model/configuration.py,sha256=c-v-2ZUo7XX80txnWz4gduLcxmS-phYcWDBuLLJ5tNk,7815
563
- helm/clients/image_generation/dalle_mini/model/modeling.py,sha256=9SFAtImIr2IPBJt3BHG5ou-74oPG5S1MRbtL1kFfrr4,69610
564
- helm/clients/image_generation/dalle_mini/model/partitions.py,sha256=_fDpk34GL6NhNecHuP78y_gmKpWjbfw3fxMCWVEO4pc,2721
565
- helm/clients/image_generation/dalle_mini/model/processor.py,sha256=nTZMHRApm_PaUdQLhcBvxLI0BE_MfuQZ_pDkx-1MMZs,2222
566
- helm/clients/image_generation/dalle_mini/model/text.py,sha256=Kfba8JdO2LrSmCVlQtgc7J2kSordCgjeg7WV9V45B80,7302
567
- helm/clients/image_generation/dalle_mini/model/tokenizer.py,sha256=iu6YS1oNMEkamClQNxbsNlnYpEyC8-2bS7wyBnku-p0,199
568
- helm/clients/image_generation/dalle_mini/model/utils.py,sha256=clu2IiIpAT0DzTc2HvmI0ySnETFsJtpi7tocPkqOreY,1171
569
- helm/clients/image_generation/dalle_mini/vqgan_jax/__init__.py,sha256=4nOBVLNyIYohjXzZup9l2bSWdxEWZ1kckQ5ct7VKcJ4,17
570
- helm/clients/image_generation/dalle_mini/vqgan_jax/configuration_vqgan.py,sha256=4q39kdTUxeW55SN8NNkA9MdFZtH6rWssN8XauuOwyi0,1213
571
- helm/clients/image_generation/dalle_mini/vqgan_jax/convert_pt_model_to_jax.py,sha256=RicCxKNF7AUeeXYxpkPahN3Aq_aMqM3yAM8igdq48GU,4512
572
- helm/clients/image_generation/dalle_mini/vqgan_jax/modeling_flax_vqgan.py,sha256=O6FWL9jmzEa0sbP4Qc6E7gmwaEL9L5lbrbQ1_zQ8CCw,21017
573
- helm/clients/image_generation/mindalle/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
574
- helm/clients/image_generation/mindalle/models/__init__.py,sha256=D7flcmyXa26YG-C7KNx6ovUu-p0tb4Je4suy7RZ8MD4,8127
575
- helm/clients/image_generation/mindalle/models/tokenizer.py,sha256=NFFdLUhoxEkv9SZqU3QIFk0ukaCcn6w_xFWQIRGhZJ4,1190
576
- helm/clients/image_generation/mindalle/models/stage1/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
577
- helm/clients/image_generation/mindalle/models/stage1/layers.py,sha256=cg5c6KShCMbMmHFuzDBIG-WgIBBkDrG9XvXC1DxqowA,11044
578
- helm/clients/image_generation/mindalle/models/stage1/vqgan.py,sha256=NCQSrFN-Ojknu-nt6Z1CDweQvL1P_thbsyf6ejJ4X4o,3983
579
- helm/clients/image_generation/mindalle/models/stage2/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
580
- helm/clients/image_generation/mindalle/models/stage2/layers.py,sha256=LvDADun5nMaencaRT0pm-dq78xHpPPkpi8rlu7RLHco,5306
581
- helm/clients/image_generation/mindalle/models/stage2/transformer.py,sha256=WJCvWUuY-U7nQT_6-KOB9phd1Q8IgsJy2O0f4Al2Vj0,10335
582
- helm/clients/image_generation/mindalle/utils/__init__.py,sha256=QnQ8JdgxsV89J7XOEGUO0uZEA-R_87_zua8XZ7wEdHE,67
583
- helm/clients/image_generation/mindalle/utils/config.py,sha256=lh8dXvL7ctKmuYEbeTQZfXN-_DkHQLjGuFuvo53u5pM,3234
584
- helm/clients/image_generation/mindalle/utils/sampling.py,sha256=soTHaJrN4FV1lDdh9HMveJs6F49UMK57Xfa0ccnHqI8,5029
585
- helm/clients/image_generation/mindalle/utils/utils.py,sha256=ESugpzG-_73GKl07mj-8o-_nim_FOICxfYkczy3s9x4,3119
586
- helm/clients/vision_language/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
587
- helm/clients/vision_language/huggingface_vision2seq_client.py,sha256=hTywh5nM95BmPoDyKOSDWg9G3-QwLO3KZEJZVkmFroo,6478
588
- helm/clients/vision_language/huggingface_vlm_client.py,sha256=H7AE8mm506PkEcUO8VaLVtptHTwVX58nZx1A_BWdKzA,4968
589
- helm/clients/vision_language/idefics_client.py,sha256=hi1VCDBegHfBssmW0C62H3OX3U2ISVRhaSkd24gb1K4,7692
590
- helm/clients/vision_language/open_flamingo_client.py,sha256=QH6el-wkEl4PMZM9b3_H-o2PRaMvumGbN29ee9dmkMU,6519
591
- helm/clients/vision_language/paligemma_client.py,sha256=IU_T8r1RgpGkEAqabLKBbmoUOWV6c1a9_FXgiTy8exE,6835
592
- helm/clients/vision_language/palmyra_vision_client.py,sha256=4elEdmwllMr2qzTzBdlRC8L5Ut3vOXFtanGGYrx4lv8,4074
593
- helm/clients/vision_language/qwen_vlm_client.py,sha256=6rCH4gJMDyQHyjAE_GDIrLsInH_bvd6to-4RMWbRLeM,7407
594
- helm/clients/vision_language/open_flamingo/__init__.py,sha256=i1tGJj6ckeE6eS1EWV5tbQKYLmPCrdSI45mPchfv_Ic,88
595
- helm/clients/vision_language/open_flamingo/src/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
596
- helm/clients/vision_language/open_flamingo/src/factory.py,sha256=1gFPR-hu520Jdzl2EWE9LSSlF-uuSOHoX3CLWUT4YWs,5652
597
- helm/clients/vision_language/open_flamingo/src/flamingo.py,sha256=0tn9uAyUbNVk3XDgZLndRRf2RN_Cy3qGOooBB51r0YQ,14661
598
- helm/clients/vision_language/open_flamingo/src/flamingo_lm.py,sha256=pUKtQ0gaR68S7IMR7M-NNlgg-MscsyIZ-FammqlX5Z8,6225
599
- helm/clients/vision_language/open_flamingo/src/helpers.py,sha256=pq_BgkUflYBDw8gxTO2evuiqvjw3bE9rx06iYHp0kTw,8595
600
- helm/clients/vision_language/open_flamingo/src/utils.py,sha256=6FYU0NgshZadF3QYWQkPW8jyEFiOd6jyb8p5rv_vOj0,1444
601
- helm/common/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
602
- helm/common/authentication.py,sha256=RlMx29_TSrfU7ujE7dJkxmFub5EqLj2NswV5lAVFFDk,179
603
- helm/common/cache.py,sha256=0gXq97M9JgSO5aO2puEV1WRpEy8jdc_wRsKL4rVVoY0,6725
604
- helm/common/cache_backend_config.py,sha256=4u5A6BHNBmGnnrDNhCVgrdwhXQtyAbWcUeoo7hdgZSo,1530
605
- helm/common/clip_score_request.py,sha256=WnNg89owDCmG7tyy8nnQL0RdKQLsUdMWiYH9XqqbGw8,840
606
- helm/common/codec.py,sha256=gTh6AwIQ0Bbul_QSnIO7eItwMZmYtnkIrG1jkc4GOL4,7100
607
- helm/common/concurrency.py,sha256=8THtHlCtXo5c8iCuz_UcBBdzZX6aiEALLc4u0M4SYL0,856
608
- helm/common/credentials_utils.py,sha256=O-57nUgkWLbZF0k3lsSaVGPPHj2_OYeVuCMe0to3bRE,1118
609
- helm/common/critique_request.py,sha256=yo4aRe-DEjudUmydthtpTj6LdhRXfZ3JZptxTkWzZ3U,3068
610
- helm/common/file_upload_request.py,sha256=OZeAW1_zsiNdXnWDwNNvhPs0b48TUmW_e4kzzCYmyiY,543
611
- helm/common/general.py,sha256=nMfHNPXyAAorAMmgDClD8r8XXeJcvfF0QXTP-FgH5PQ,11690
612
- helm/common/gpu_utils.py,sha256=pmLq6ipYNLEm28VxxSNeZuVt-gAw-WnYmBvxP1P1p6M,480
613
- helm/common/hierarchical_logger.py,sha256=EnKLnfbQftca08EJfjGEQb4tcnCKbx-JtwLnoCnhMQs,2908
614
- helm/common/image_generation_parameters.py,sha256=nsbuk_-BlRMK6IwP5y6BnTXbTRTOcvZ6uLblL5VHLOo,916
615
- helm/common/images_utils.py,sha256=icE0tH9P3FT_qggfbi8vVwkmIjOAN5l3HcGDF9gmNnY,3345
616
- helm/common/key_value_store.py,sha256=D9ZBORzZncf3zHQOP4AuNbQnV8cZpO_kqHY1mDRugqQ,3174
617
- helm/common/media_object.py,sha256=3VZqfb0py5dDKwWtnLp2kdl8svaike-Cn7Mjk-b0cvM,5130
618
- helm/common/moderations_api_request.py,sha256=3xTsErSsCr2PHD2jpdV1JglHaYHwP2Yqu25_JFtfa68,2234
619
- helm/common/mongo_key_value_store.py,sha256=G0TIWQcvwMjyXh4TnN6xJ462HKHUAZtQJJYQOrHK-K8,3887
620
- helm/common/multimodal_request_utils.py,sha256=GNZQQCcwsARyFCO-uoeeglyK2PEfC4MjClAKDeKqokk,1404
621
- helm/common/nudity_check_request.py,sha256=VMsujI_RBy5u_cGEk0teE4KyX1dL2Zt3Pb4U6LpBdSY,728
622
- helm/common/object_spec.py,sha256=_usgTDQULBF6_jy7C6m-9ZNVvNxbGoTE_CdGcSvBASU,4327
623
- helm/common/optional_dependencies.py,sha256=Qam3QCHff8tuXbS-fCw-MVe-pK18gSvHw-uQoXXxT7M,616
624
- helm/common/perspective_api_request.py,sha256=WAVwtajNVmi5XJNsPcorGEAVrqkpPSk-Kd3b0hJghbA,2427
625
- helm/common/request.py,sha256=Z_YUd77WQ15yeSN8YYdT48dI4ehUc869KuaDisAiyIA,8806
626
- helm/common/test_cache.py,sha256=j19p-qzv_98X_TMW4b39ZHwSJ-MX3p91PrkYumarS6Y,4870
627
- helm/common/test_codec.py,sha256=igL--k-2DwAy0eoMr8D9Xs8MOjBoT0LutbMPzDlTNkM,5885
628
- helm/common/test_general.py,sha256=c8Lh0mK8I-SfcMprq909B6zWRBxSBngq2nNL1L6-cYA,1788
629
- helm/common/test_media_object.py,sha256=AAm9DD7MC-ZvTwiqXA-e52U6L4S1noxItW8f7ARi6DY,1650
630
- helm/common/tokenization_request.py,sha256=NND9ESiiDE0H8QRNpfHVjXS7MQfKKIwtVRKDIjPnnJM,3344
631
- helm/common/file_caches/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
632
- helm/common/file_caches/file_cache.py,sha256=QfF1hlF8FQ-rcPn9Zyl6L0dOCokvYgd-dFqx4ftRuPA,359
633
- helm/common/file_caches/local_file_cache.py,sha256=wBOAbbkGLiClaX4YdunokRfSQCKNkTYmMVx2KTLy4Lc,1921
634
- helm/common/file_caches/test_local_file_cache.py,sha256=bOCWR9MglwQXV98xk8auyjgFxaOr85zRdxWwxMBQW9s,663
635
- helm/config/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
636
- helm/config/model_deployments.yaml,sha256=CXYtq1I6jRZJODiyfN0ha_i-2XHbWHv1-pBM5cfsHhA,94192
637
- helm/config/model_metadata.yaml,sha256=nrQO6SbsSwKUXwtAUlfb8_Xai6TLSBKN0p1NrbtL2sU,168593
638
- helm/config/tokenizer_configs.yaml,sha256=ZiOhsxOcEpLpK7Rv-zBw0s1ZWCQOMT9dya7DTV_lPQE,19665
639
- helm/proxy/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
640
- helm/proxy/accounts.py,sha256=gd5cKhKeqklf_cXCAISl65AUvZeD6afBNrs6WK3IBvQ,14764
641
- helm/proxy/cli.py,sha256=l8F7UYqrIOoBD9ZCIxJFA4fhxlzhae0-2Nn8A7FMkzk,8244
642
- helm/proxy/example_queries.py,sha256=rVGmQ2ej4OS7m5Y3uI5dp9Mfdw6bv53c0o2QknsmYes,4379
643
- helm/proxy/query.py,sha256=eftbiUICMh8QIHVs-7cLtv_rDXKeKdRPmwjLMu0TDxQ,645
644
- helm/proxy/retry.py,sha256=iLZmKATEJQa9jsSpOIx6YDRhmrA8G1Qm21cUxCuo2Ug,3490
645
- helm/proxy/server.py,sha256=caho64BgGogbYMby8vecRFTtexmdg_fNxi3H0jzCVgE,10512
646
- helm/proxy/test_accounts.py,sha256=Vs1iOzTPN29LosDAAEs6IagQ3PccvutrJTlR1qNIcj0,1146
647
- helm/proxy/test_retry.py,sha256=8h398auzjW9VnlTJWllxR-bdpub-XFp8EN8LWDEnEHM,1049
648
- helm/proxy/critique/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
649
- helm/proxy/critique/critique_client.py,sha256=ATZuXw77lejwtpgLg3Soy3VDyv8D8xetl0o4guxDM2M,1764
650
- helm/proxy/critique/mechanical_turk_critique_client.py,sha256=OcppmFOMweBSfVTiLIICIwjvPpHHTkdu9fFUTaubitQ,574
651
- helm/proxy/critique/mechanical_turk_critique_exporter.py,sha256=taULrc_cIP0O9c5UpGz3l9DmWQadTVzN_v-qzTgMoyo,8470
652
- helm/proxy/critique/mechanical_turk_critique_importer.py,sha256=NL97joO5pRkcICRdVyG4kf9JhfYRaySsxRoZ7KWDYv0,5581
653
- helm/proxy/critique/mechanical_turk_utils.py,sha256=mKpUv4zz3s5ptzDY7UrwuI7Cr5HmNgSjPC10BnN9AL4,1766
654
- helm/proxy/critique/model_critique_client.py,sha256=QMFiMpALXnneumKbJpXOZDEb3lPPdkIaSCasmdXHB8o,12806
655
- helm/proxy/critique/scale_critique_client.py,sha256=B4povtceyfal95eE3N7em9cC_B5Vy4jMrHXcsXc_5m4,15889
656
- helm/proxy/critique/surge_ai_critique_client.py,sha256=HnzgAoF4Du9Me0GS_lbNaozZslS4a2OZx735gh-coo0,8357
657
- helm/proxy/services/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
658
- helm/proxy/services/remote_service.py,sha256=nqqNisHoYXGidqPOdWauTgSca04LimWDBcr-KieuLdI,8787
659
- helm/proxy/services/server_service.py,sha256=tb1JUIG8pVhY5t634advtMGYh9ZnhwTeKIwhweJYegU,10672
660
- helm/proxy/services/service.py,sha256=YFG5ZlBYBz3IdSVRKDIKVlAmA-oLjFCeBHE3iIe_SU8,6020
661
- helm/proxy/services/test_remote_service.py,sha256=NFnLjg3QNHoDKdK0DlcrtylwlKXx1vdzheNZRrLEv7c,6605
662
- helm/proxy/services/test_service.py,sha256=FUZoI8pGiUg5adgB1wTJ869QOgFYjPtM6yf6FGMdE64,8968
663
- helm/proxy/token_counters/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
664
- helm/proxy/token_counters/auto_token_counter.py,sha256=34PWvF96DurTrUtUxW4Td5VNV1_BhAebCkXQLl3xp4M,2046
665
- helm/proxy/token_counters/test_auto_token_counter.py,sha256=LO3H_NbVeoeaMmEuFNCmhoEWKjWVvxeW5U4yTKfE-84,8590
666
- helm/proxy/token_counters/token_counter.py,sha256=TCij1Cp08RoFTLLLdjNPoaeDGHpA1A2hQsrRV775Kf4,425
667
- helm/tokenizers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
668
- helm/tokenizers/ai21_tokenizer.py,sha256=CE-u39ZY5Y4XQHONpiPHKK7uvEmySYLBQi2n70OV004,2059
669
- helm/tokenizers/aleph_alpha_tokenizer.py,sha256=UlWC_SjObBvexpZ3OfKZT2yjhbSsHlKjQe_oWuRrXno,3818
670
- helm/tokenizers/anthropic_tokenizer.py,sha256=d-HO9OEFkhYzFZu0VkOsHjxbqqSUseCNX0KQqgb3s2Q,2114
671
- helm/tokenizers/auto_tokenizer.py,sha256=Of-T-CFOhLAjjU45T1hnrEPG_k_hzPufuDE7FRAcSN8,4251
672
- helm/tokenizers/caching_tokenizer.py,sha256=kSegrCFotRevSDgJsn0g52dWiSUCNa7_EZpRNrELeUE,8163
673
- helm/tokenizers/cohere_tokenizer.py,sha256=6WwHIt7SsICmYR2QQpwDJ7pfNF8VWrFHFxF5Kynq6aY,2116
674
- helm/tokenizers/http_model_tokenizer.py,sha256=wBTtDA2UdEYspffa1wqgkT3y3YHoyLXXoucnJ5PGjhs,3109
675
- helm/tokenizers/huggingface_tokenizer.py,sha256=vmzcbgzMMlwx1x2n0syyp6KuN47nskgoP9yi1BNEGMQ,8696
676
- helm/tokenizers/lit_gpt_tokenizer.py,sha256=LMrpaje64UmnDKoYjPG_RQeXVA4xQUwW5t48IJIeLaQ,1660
677
- helm/tokenizers/simple_tokenizer.py,sha256=6_NROqVbygs-HRA7bYAZluN4YB5gUhVaRsYQeRTjA1E,1147
678
- helm/tokenizers/test_ai21_tokenizer.py,sha256=V8orjdKxmEV44VYoZ9Sq5E7CIq2caNnr6vjdk0T_w1A,1646
679
- helm/tokenizers/test_anthropic_tokenizer.py,sha256=_wzXp9FVR2Ml0s2A79TTXbSPHyTRp28i9tiEyQ9S6Ko,3792
680
- helm/tokenizers/test_cohere_tokenizer.py,sha256=15z2GJtZ-VlrliC2_Fk5DIZhQYFkJS7J73fjxYMf8YM,1431
681
- helm/tokenizers/test_huggingface_tokenizer.py,sha256=8tFyZQb4DLg6MdKg13a66bLbp0yf4Ar1fGWM_sYeSjg,6309
682
- helm/tokenizers/test_simple_tokenizer.py,sha256=vUNdcnJqZV99-E8H1rwUH85AQPJ2HTnDr5DrZ_-zRL4,1219
683
- helm/tokenizers/test_yalm_tokenizer.py,sha256=qWpKnUuAlePd6t-UJB_mAiBwtAacnC8caKXLJ_GdTkk,2477
684
- helm/tokenizers/tiktoken_tokenizer.py,sha256=FU2g_FF0pVoyspYhHcz3SyCBGNbsTby-nWVrj0Cq4_c,1265
685
- helm/tokenizers/tokenizer.py,sha256=1zi9fhgrs2znINKDnoEhW-6UatsVj30hRjQbTDbOdZg,1583
686
- helm/tokenizers/vertexai_tokenizer.py,sha256=lf-xckyeachaJI86ujNC2Cp_AVZ-BBcFgLZQy4lg7aA,4105
687
- helm/tokenizers/yalm_tokenizer.py,sha256=TBA6tlDH4A4OBKjghYfKxI-VujIhkQP83nsDgWF_x3Y,1451
688
- helm/tokenizers/yalm_tokenizer_data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
689
- helm/tokenizers/yalm_tokenizer_data/test_yalm_tokenizer.py,sha256=W9p5QNn1GSm-y85yVEQe_82zn5CVK_vR6jvhk7JTs_k,869
690
- helm/tokenizers/yalm_tokenizer_data/voc_100b.sp,sha256=LmPD0_OIOXi8dWuNjXUYOSPhf8kPp2xhvK-g3bXcwrQ,2815034
691
- helm/tokenizers/yalm_tokenizer_data/yalm_tokenizer.py,sha256=kH5Qig1_6r_sKbAHinX7C83tqBUoTwbe-gGZCbGVkko,6389
692
- crfm_helm-0.5.4.dist-info/LICENSE,sha256=bJiay7Nn5SHQ2n_4ZIT3AE0W1RGq4O7pxOApgBsaT64,11349
693
- crfm_helm-0.5.4.dist-info/METADATA,sha256=7kuGQSYOgZrB1nra46gop4xc4e40TeQ8qThnbWgtiqU,19187
694
- crfm_helm-0.5.4.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
695
- crfm_helm-0.5.4.dist-info/entry_points.txt,sha256=AvH9soAH3uey9xffisWewd0yrmPWGASC036jHd1SFyg,300
696
- crfm_helm-0.5.4.dist-info/top_level.txt,sha256=s9yl-XmuTId6n_W_xRjCS99MHTwPXOlkKxmTr8xZUNY,5
697
- crfm_helm-0.5.4.dist-info/RECORD,,