--- license: apache-2.0 pipeline_tag: text-generation library_name: transformers language: ['en', 'am', 'ar', 'as', 'az', 'be', 'bg', 'bn', 'br', 'bs', 'ca', 'cs', 'cy', 'da', 'de', 'el', 'eo', 'es', 'et', 'eu', 'fa', 'ff', 'fi', 'fr', 'fy', 'ga', 'gd', 'gl', 'gn', 'gu', 'ha', 'he', 'hi', 'hr', 'ht', 'hu', 'hy', 'id', 'ig', 'is', 'it', 'ja', 'jv', 'ka', 'kk', 'km', 'kn', 'ko', 'ku', 'ky', 'la', 'lg', 'li', 'ln', 'lo', 'lt', 'lv', 'mg', 'mk', 'ml', 'mn', 'mr', 'ms', 'my', 'ne', 'nl', 'no', 'ns', 'om', 'or', 'pa', 'pl', 'ps', 'pt', 'qu', 'rm', 'ro', 'ru', 'sa', 'si', 'sc', 'sd', 'sk', 'sl', 'so', 'sq', 'sr', 'ss', 'su', 'sv', 'sw', 'ta', 'te', 'th', 'tl', 'tn', 'tr', 'ug', 'uk', 'ur', 'uz', 'vi', 'wo', 'xh', 'yi', 'yo', 'zu'] datasets: [ 'bigcode/programming-languages-keywords', 'bigcode/the-stack-smol-xs', 'nampdn-ai/tiny-textbooks', 'xu-song/cc100-samples', 'm-a-p/CodeFeedback-Filtered-Instruction', 'nampdn-ai/tiny-codes', 'ajibawa-2023/Maths-College', 'microsoft/orca-math-word-problems-200k', 'mlabonne/FineTome-100k', 'arcee-ai/agent-data', 'cognitivecomputations/SystemChat-2.0', 'badrex/llm-emoji-dataset', ] tags: - litgpt - litdata --- # tangled-llama-33m-32k-base-v0.1 ## lm-evaluation-harness | Tasks |Version| Filter |n-shot| Metric | |Value | |Stderr| |---------------------------------------|------:|----------------|-----:|-----------|---|-----:|---|-----:| |arc_challenge | 1|none | 0|acc |↑ |0.2065|± |0.0118| | | |none | 0|acc_norm |↑ |0.2338|± |0.0124| |gsm8k | 3|flexible-extract| 5|exact_match|↑ |0.0144|± |0.0033| | | |strict-match | 5|exact_match|↑ |0.0000|± |0.0000| |hellaswag | 1|none | 0|acc |↑ |0.2614|± |0.0044| | | |none | 0|acc_norm |↑ |0.2604|± |0.0044| |mmlu | 2|none | |acc |↑ |0.2280|± |0.0035| | - humanities | 2|none | |acc |↑ |0.2376|± |0.0062| | - formal_logic | 1|none | 0|acc |↑ |0.2698|± |0.0397| | - high_school_european_history | 1|none | 0|acc |↑ |0.2000|± |0.0312| | - high_school_us_history | 1|none | 0|acc |↑ |0.2500|± |0.0304| | - high_school_world_history | 1|none | 0|acc |↑ |0.2785|± |0.0292| | - international_law | 1|none | 0|acc |↑ |0.2149|± |0.0375| | - jurisprudence | 1|none | 0|acc |↑ |0.2407|± |0.0413| | - logical_fallacies | 1|none | 0|acc |↑ |0.2270|± |0.0329| | - moral_disputes | 1|none | 0|acc |↑ |0.2341|± |0.0228| | - moral_scenarios | 1|none | 0|acc |↑ |0.2380|± |0.0142| | - philosophy | 1|none | 0|acc |↑ |0.1833|± |0.0220| | - prehistory | 1|none | 0|acc |↑ |0.2160|± |0.0229| | - professional_law | 1|none | 0|acc |↑ |0.2399|± |0.0109| | - world_religions | 1|none | 0|acc |↑ |0.3275|± |0.0360| | - other | 2|none | |acc |↑ |0.2481|± |0.0077| | - business_ethics | 1|none | 0|acc |↑ |0.3100|± |0.0465| | - clinical_knowledge | 1|none | 0|acc |↑ |0.2264|± |0.0258| | - college_medicine | 1|none | 0|acc |↑ |0.2486|± |0.0330| | - global_facts | 1|none | 0|acc |↑ |0.1700|± |0.0378| | - human_aging | 1|none | 0|acc |↑ |0.3229|± |0.0314| | - management | 1|none | 0|acc |↑ |0.1845|± |0.0384| | - marketing | 1|none | 0|acc |↑ |0.3034|± |0.0301| | - medical_genetics | 1|none | 0|acc |↑ |0.3100|± |0.0465| | - miscellaneous | 1|none | 0|acc |↑ |0.2401|± |0.0153| | - nutrition | 1|none | 0|acc |↑ |0.2418|± |0.0245| | - professional_accounting | 1|none | 0|acc |↑ |0.2411|± |0.0255| | - professional_medicine | 1|none | 0|acc |↑ |0.1838|± |0.0235| | - virology | 1|none | 0|acc |↑ |0.2831|± |0.0351| | - social sciences | 2|none | |acc |↑ |0.2155|± |0.0074| | - econometrics | 1|none | 0|acc |↑ |0.2281|± |0.0395| | - high_school_geography | 1|none | 0|acc |↑ |0.1768|± |0.0272| | - high_school_government_and_politics| 1|none | 0|acc |↑ |0.1969|± |0.0287| | - high_school_macroeconomics | 1|none | 0|acc |↑ |0.2103|± |0.0207| | - high_school_microeconomics | 1|none | 0|acc |↑ |0.2143|± |0.0267| | - high_school_psychology | 1|none | 0|acc |↑ |0.1872|± |0.0167| | - human_sexuality | 1|none | 0|acc |↑ |0.2672|± |0.0388| | - professional_psychology | 1|none | 0|acc |↑ |0.2467|± |0.0174| | - public_relations | 1|none | 0|acc |↑ |0.2182|± |0.0396| | - security_studies | 1|none | 0|acc |↑ |0.1755|± |0.0244| | - sociology | 1|none | 0|acc |↑ |0.2438|± |0.0304| | - us_foreign_policy | 1|none | 0|acc |↑ |0.2700|± |0.0446| | - stem | 2|none | |acc |↑ |0.2058|± |0.0072| | - abstract_algebra | 1|none | 0|acc |↑ |0.1700|± |0.0378| | - anatomy | 1|none | 0|acc |↑ |0.1778|± |0.0330| | - astronomy | 1|none | 0|acc |↑ |0.1776|± |0.0311| | - college_biology | 1|none | 0|acc |↑ |0.2569|± |0.0365| | - college_chemistry | 1|none | 0|acc |↑ |0.1900|± |0.0394| | - college_computer_science | 1|none | 0|acc |↑ |0.2600|± |0.0441| | - college_mathematics | 1|none | 0|acc |↑ |0.2100|± |0.0409| | - college_physics | 1|none | 0|acc |↑ |0.2059|± |0.0402| | - computer_security | 1|none | 0|acc |↑ |0.2400|± |0.0429| | - conceptual_physics | 1|none | 0|acc |↑ |0.2681|± |0.0290| | - electrical_engineering | 1|none | 0|acc |↑ |0.2345|± |0.0353| | - elementary_mathematics | 1|none | 0|acc |↑ |0.2011|± |0.0206| | - high_school_biology | 1|none | 0|acc |↑ |0.1806|± |0.0219| | - high_school_chemistry | 1|none | 0|acc |↑ |0.1478|± |0.0250| | - high_school_computer_science | 1|none | 0|acc |↑ |0.2400|± |0.0429| | - high_school_mathematics | 1|none | 0|acc |↑ |0.2111|± |0.0249| | - high_school_physics | 1|none | 0|acc |↑ |0.1788|± |0.0313| | - high_school_statistics | 1|none | 0|acc |↑ |0.1620|± |0.0251| | - machine_learning | 1|none | 0|acc |↑ |0.2768|± |0.0425| |truthfulqa_mc2 | 2|none | 0|acc |↑ |0.4975|± |0.0165| |winogrande | 1|none | 0|acc |↑ |0.5146|± |0.0140| | Groups |Version|Filter|n-shot|Metric| |Value | |Stderr| |------------------|------:|------|------|------|---|-----:|---|-----:| |mmlu | 2|none | |acc |↑ |0.2280|± |0.0035| | - humanities | 2|none | |acc |↑ |0.2376|± |0.0062| | - other | 2|none | |acc |↑ |0.2481|± |0.0077| | - social sciences| 2|none | |acc |↑ |0.2155|± |0.0074| | - stem | 2|none | |acc |↑ |0.2058|± |0.0072|