--- license: apache-2.0 inference: false --- # Given-MPT-7B This is a merge of the following MPT-7B models: - **g**orilla-llm/gorilla-mpt-7b-hf-v0 - **i**bm/mpt-7b-instruct2 - Teh**V**enom/MPT-7b-WizardLM_Uncensored-Storywriter-Merge - **e**mozilla/mpt-7b-storysummarizer - **n**omic-ai/gpt4all-mpt ## Model License Apache 2.0 ## Purpose This model is for experimenting with merging and routing to expert layers. # Test eval on only 10% of eval set hf-causal (pretrained=Multi-Domain-Expert-Layers/given-mpt-7b,dtype=bfloat16,trust_remote_code=True), limit: 0.1, provide_description: False, num_fewshot: 0, batch_size: None | Task |Version| Metric | Value | |Stderr| |-------------------------------------------------|------:|-----------|------:|---|-----:| |arc_challenge | 0|acc | 0.4274|± |0.0459| | | |acc_norm | 0.3846|± |0.0452| |arc_easy | 0|acc | 0.7863|± |0.0381| | | |acc_norm | 0.7350|± |0.0410| |hellaswag | 0|acc | 0.5556|± |0.0461| | | |acc_norm | 0.8120|± |0.0363| |hendrycksTest-college_chemistry | 0|acc | 0.3600|± |0.0482| | | |acc_norm | 0.3700|± |0.0485| |hendrycksTest-college_computer_science | 0|acc | 0.3400|± |0.0476| | | |acc_norm | 0.3600|± |0.0482| |hendrycksTest-college_mathematics | 0|acc | 0.2500|± |0.0435| | | |acc_norm | 0.2900|± |0.0456| |hendrycksTest-college_medicine | 0|acc | 0.3675|± |0.0448| | | |acc_norm | 0.3162|± |0.0432| |hendrycksTest-college_physics | 0|acc | 0.2451|± |0.0428| | | |acc_norm | 0.2941|± |0.0453| |hendrycksTest-computer_security | 0|acc | 0.4800|± |0.0502| | | |acc_norm | 0.4400|± |0.0499| |hendrycksTest-conceptual_physics | 0|acc | 0.2051|± |0.0375| | | |acc_norm | 0.1709|± |0.0350| |hendrycksTest-econometrics | 0|acc | 0.2982|± |0.0430| | | |acc_norm | 0.2368|± |0.0400| |hendrycksTest-electrical_engineering | 0|acc | 0.3248|± |0.0435| | | |acc_norm | 0.3590|± |0.0445| |hendrycksTest-elementary_mathematics | 0|acc | 0.3333|± |0.0438| | | |acc_norm | 0.3162|± |0.0432| |hendrycksTest-formal_logic | 0|acc | 0.3077|± |0.0429| | | |acc_norm | 0.3248|± |0.0435| |hendrycksTest-global_facts | 0|acc | 0.3000|± |0.0461| | | |acc_norm | 0.2700|± |0.0446| |hendrycksTest-high_school_biology | 0|acc | 0.3675|± |0.0448| | | |acc_norm | 0.3077|± |0.0429| |hendrycksTest-high_school_chemistry | 0|acc | 0.2564|± |0.0405| | | |acc_norm | 0.2906|± |0.0422| |hendrycksTest-high_school_computer_science | 0|acc | 0.4100|± |0.0494| | | |acc_norm | 0.4400|± |0.0499| |hendrycksTest-high_school_european_history | 0|acc | 0.4359|± |0.0460| | | |acc_norm | 0.3590|± |0.0445| |hendrycksTest-high_school_geography | 0|acc | 0.3248|± |0.0435| | | |acc_norm | 0.3675|± |0.0448| |hendrycksTest-high_school_government_and_politics| 0|acc | 0.3932|± |0.0454| | | |acc_norm | 0.3932|± |0.0454| |hendrycksTest-high_school_macroeconomics | 0|acc | 0.3333|± |0.0438| | | |acc_norm | 0.3248|± |0.0435| |hendrycksTest-high_school_mathematics | 0|acc | 0.2051|± |0.0375| | | |acc_norm | 0.2564|± |0.0405| |hendrycksTest-high_school_microeconomics | 0|acc | 0.3504|± |0.0443| | | |acc_norm | 0.4188|± |0.0458| |hendrycksTest-high_school_physics | 0|acc | 0.2650|± |0.0410| | | |acc_norm | 0.2906|± |0.0422| |hendrycksTest-high_school_psychology | 0|acc | 0.3761|± |0.0450| | | |acc_norm | 0.3419|± |0.0440| |hendrycksTest-high_school_statistics | 0|acc | 0.3077|± |0.0429| | | |acc_norm | 0.3504|± |0.0443| |hendrycksTest-high_school_us_history | 0|acc | 0.3333|± |0.0438| | | |acc_norm | 0.3333|± |0.0438| |hendrycksTest-high_school_world_history | 0|acc | 0.3333|± |0.0438| | | |acc_norm | 0.3419|± |0.0440| |hendrycksTest-human_aging | 0|acc | 0.3761|± |0.0450| | | |acc_norm | 0.3162|± |0.0432| |hendrycksTest-human_sexuality | 0|acc | 0.4274|± |0.0459| | | |acc_norm | 0.3761|± |0.0450| |hendrycksTest-international_law | 0|acc | 0.4188|± |0.0458| | | |acc_norm | 0.4957|± |0.0464| |hendrycksTest-jurisprudence | 0|acc | 0.3148|± |0.0449| | | |acc_norm | 0.4815|± |0.0483| |hendrycksTest-logical_fallacies | 0|acc | 0.3504|± |0.0443| | | |acc_norm | 0.3675|± |0.0448| |hendrycksTest-machine_learning | 0|acc | 0.3214|± |0.0443| | | |acc_norm | 0.2946|± |0.0433| |hendrycksTest-management | 0|acc | 0.3786|± |0.0480| | | |acc_norm | 0.3495|± |0.0472| |hendrycksTest-marketing | 0|acc | 0.5043|± |0.0464| | | |acc_norm | 0.4188|± |0.0458| |hendrycksTest-medical_genetics | 0|acc | 0.3200|± |0.0469| | | |acc_norm | 0.4100|± |0.0494| |hendrycksTest-miscellaneous | 0|acc | 0.5299|± |0.0463| | | |acc_norm | 0.4872|± |0.0464| |hendrycksTest-moral_disputes | 0|acc | 0.3248|± |0.0435| | | |acc_norm | 0.3162|± |0.0432| |hendrycksTest-moral_scenarios | 0|acc | 0.3248|± |0.0435| | | |acc_norm | 0.2479|± |0.0401| |hendrycksTest-nutrition | 0|acc | 0.3675|± |0.0448| | | |acc_norm | 0.3932|± |0.0454| |hendrycksTest-philosophy | 0|acc | 0.2991|± |0.0425| | | |acc_norm | 0.3504|± |0.0443| |hendrycksTest-prehistory | 0|acc | 0.2821|± |0.0418| | | |acc_norm | 0.3248|± |0.0435| |hendrycksTest-professional_accounting | 0|acc | 0.2137|± |0.0381| | | |acc_norm | 0.2222|± |0.0386| |hendrycksTest-professional_law | 0|acc | 0.3077|± |0.0429| | | |acc_norm | 0.2735|± |0.0414| |hendrycksTest-professional_medicine | 0|acc | 0.2991|± |0.0425| | | |acc_norm | 0.2650|± |0.0410| |hendrycksTest-professional_psychology | 0|acc | 0.3248|± |0.0435| | | |acc_norm | 0.3419|± |0.0440| |hendrycksTest-public_relations | 0|acc | 0.3909|± |0.0467| | | |acc_norm | 0.3545|± |0.0458| |hendrycksTest-security_studies | 0|acc | 0.3419|± |0.0440| | | |acc_norm | 0.2906|± |0.0422| |hendrycksTest-sociology | 0|acc | 0.3761|± |0.0450| | | |acc_norm | 0.3162|± |0.0432| |hendrycksTest-us_foreign_policy | 0|acc | 0.5000|± |0.0503| | | |acc_norm | 0.4100|± |0.0494| |hendrycksTest-virology | 0|acc | 0.3932|± |0.0454| | | |acc_norm | 0.3248|± |0.0435| |hendrycksTest-world_religions | 0|acc | 0.5299|± |0.0463| | | |acc_norm | 0.5128|± |0.0464| |truthfulqa_gen | 1|bleurt_max |-0.8551|± |0.0501| | | |bleurt_acc | 0.3590|± |0.0445| | | |bleurt_diff|-0.1292|± |0.0483| | | |bleu_max |19.3738|± |1.8461| | | |bleu_acc | 0.3932|± |0.0454| | | |bleu_diff |-4.3883|± |2.1748| | | |rouge1_max |41.8428|± |2.6156| | | |rouge1_acc | 0.3162|± |0.0432| | | |rouge1_diff|-8.8583|± |2.7745| | | |rouge2_max |26.3956|± |2.8311| | | |rouge2_acc | 0.2137|± |0.0381| | | |rouge2_diff|-9.5287|± |3.3258| | | |rougeL_max |39.5215|± |2.5620| | | |rougeL_acc | 0.3162|± |0.0432| | | |rougeL_diff|-8.5753|± |2.8259|