--- license: apache-2.0 base_model: tangledgroup/tangled-llama-33m-32k-base-v0.1 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: [ 'Replete-AI/Everything_Instruct_Multilingual', 'HuggingFaceH4/ultrachat_200k', 'HuggingFaceH4/no_robots', 'datatab/ultrachat_200k_serbian', 'datatab/ultrafeedback_binarized_serbian', 'datatab/alpaca-cleaned-serbian-full', 'datatab/orca_math_world_problem_200k_serbian', 'datatab/open-orca-slim-serbian', ] tags: - litgpt - litdata --- # tangled-llama-33m-32k-instruct-v0.1 ![logo](./misc/logo.png) A pretrained language model based on the Llama model with about **33M** parameters. This model has been trained on **4.2B** (`4,252,334,823`) tokens from more than **6.2M** (`6,271,145`) dataset rows. This model **isn't** designed for immediate use but rather for Continued Pretraining and Finetuning on a downstream task. It can handle a context length of up to **32K** (`32,768`) tokens, and it was pretrained with sequences of **32K** (`32,768`) tokens. The objective is to streamline the cognitive or reasoning core, eliminating any redundant knowledge from the model. [loss, val_loss](https://api.wandb.ai/links/mtasic85/rx2cm1ip) [val_ppl](https://api.wandb.ai/links/mtasic85/okegm8vs) [epoch](https://api.wandb.ai/links/mtasic85/t5lojxa6) [learning_rate](https://api.wandb.ai/links/mtasic85/033xhutk) ## lm-evaluation-harness ```bash litgpt evaluate --tasks 'leaderboard' --out_dir 'evaluate-0/' --batch_size 4 --dtype 'bfloat16' out/contrain/final/ ``` | Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr| |-----------------------------------------------------------|-------|------|-----:|-----------------------|---|-----:|---|------| |leaderboard | N/A| | | | | | | | | - leaderboard_bbh | N/A| | | | | | | | | - leaderboard_bbh_boolean_expressions | 1|none | 3|acc_norm |↑ |0.4600|± |0.0316| | - leaderboard_bbh_causal_judgement | 1|none | 3|acc_norm |↑ |0.5187|± |0.0366| | - leaderboard_bbh_date_understanding | 1|none | 3|acc_norm |↑ |0.1560|± |0.0230| | - leaderboard_bbh_disambiguation_qa | 1|none | 3|acc_norm |↑ |0.3000|± |0.0290| | - leaderboard_bbh_formal_fallacies | 1|none | 3|acc_norm |↑ |0.4680|± |0.0316| | - leaderboard_bbh_geometric_shapes | 1|none | 3|acc_norm |↑ |0.0920|± |0.0183| | - leaderboard_bbh_hyperbaton | 1|none | 3|acc_norm |↑ |0.5320|± |0.0316| | - leaderboard_bbh_logical_deduction_five_objects | 1|none | 3|acc_norm |↑ |0.2240|± |0.0264| | - leaderboard_bbh_logical_deduction_seven_objects | 1|none | 3|acc_norm |↑ |0.1600|± |0.0232| | - leaderboard_bbh_logical_deduction_three_objects | 1|none | 3|acc_norm |↑ |0.3360|± |0.0299| | - leaderboard_bbh_movie_recommendation | 1|none | 3|acc_norm |↑ |0.0640|± |0.0155| | - leaderboard_bbh_navigate | 1|none | 3|acc_norm |↑ |0.4200|± |0.0313| | - leaderboard_bbh_object_counting | 1|none | 3|acc_norm |↑ |0.0640|± |0.0155| | - leaderboard_bbh_penguins_in_a_table | 1|none | 3|acc_norm |↑ |0.2397|± |0.0355| | - leaderboard_bbh_reasoning_about_colored_objects | 1|none | 3|acc_norm |↑ |0.1520|± |0.0228| | - leaderboard_bbh_ruin_names | 1|none | 3|acc_norm |↑ |0.2720|± |0.0282| | - leaderboard_bbh_salient_translation_error_detection | 1|none | 3|acc_norm |↑ |0.1240|± |0.0209| | - leaderboard_bbh_snarks | 1|none | 3|acc_norm |↑ |0.5618|± |0.0373| | - leaderboard_bbh_sports_understanding | 1|none | 3|acc_norm |↑ |0.4600|± |0.0316| | - leaderboard_bbh_temporal_sequences | 1|none | 3|acc_norm |↑ |0.2920|± |0.0288| | - leaderboard_bbh_tracking_shuffled_objects_five_objects | 1|none | 3|acc_norm |↑ |0.2040|± |0.0255| | - leaderboard_bbh_tracking_shuffled_objects_seven_objects| 1|none | 3|acc_norm |↑ |0.1200|± |0.0206| | - leaderboard_bbh_tracking_shuffled_objects_three_objects| 1|none | 3|acc_norm |↑ |0.3160|± |0.0295| | - leaderboard_bbh_web_of_lies | 1|none | 3|acc_norm |↑ |0.4880|± |0.0317| | - leaderboard_gpqa | N/A| | | | | | | | | - leaderboard_gpqa_diamond | 1|none | 0|acc_norm |↑ |0.1919|± |0.0281| | - leaderboard_gpqa_extended | 1|none | 0|acc_norm |↑ |0.2289|± |0.0180| | - leaderboard_gpqa_main | 1|none | 0|acc_norm |↑ |0.2768|± |0.0212| | - leaderboard_ifeval | 3|none | 0|inst_level_loose_acc |↑ |0.2098|± | N/A| | | |none | 0|inst_level_strict_acc |↑ |0.1966|± | N/A| | | |none | 0|prompt_level_loose_acc |↑ |0.1109|± |0.0135| | | |none | 0|prompt_level_strict_acc|↑ |0.1072|± |0.0133| | - leaderboard_math_hard | N/A| | | | | | | | | - leaderboard_math_algebra_hard | 1|none | 4|exact_match |↑ |0.0000|± | 0| | - leaderboard_math_counting_and_prob_hard | 1|none | 4|exact_match |↑ |0.0000|± | 0| | - leaderboard_math_geometry_hard | 1|none | 4|exact_match |↑ |0.0000|± | 0| | - leaderboard_math_intermediate_algebra_hard | 1|none | 4|exact_match |↑ |0.0000|± | 0| | - leaderboard_math_num_theory_hard | 1|none | 4|exact_match |↑ |0.0000|± | 0| | - leaderboard_math_prealgebra_hard | 1|none | 4|exact_match |↑ |0.0000|± | 0| | - leaderboard_math_precalculus_hard | 1|none | 4|exact_match |↑ |0.0000|± | 0| | - leaderboard_mmlu_pro | 0.1|none | 5|acc |↑ |0.1184|± |0.0029| | - leaderboard_musr | N/A| | | | | | | | | - leaderboard_musr_murder_mysteries | 1|none | 0|acc_norm |↑ |0.5000|± |0.0317| | - leaderboard_musr_object_placements | 1|none | 0|acc_norm |↑ |0.2578|± |0.0274| | - leaderboard_musr_team_allocation | 1|none | 0|acc_norm |↑ |0.2600|± |0.0278| ```bash litgpt evaluate --tasks 'hellaswag,gsm8k,truthfulqa_mc2,mmlu,winogrande,arc_challenge' --out_dir 'evaluate-1/' --batch_size 4 --dtype 'bfloat16' out/contrain/final/ ``` | Tasks |Version| Filter |n-shot| Metric | |Value | |Stderr| |---------------------------------------|------:|----------------|-----:|-----------|---|-----:|---|-----:| |arc_challenge | 1|none | 0|acc |↑ |0.1962|± |0.0116| | | |none | 0|acc_norm |↑ |0.2483|± |0.0126| |gsm8k | 3|flexible-extract| 5|exact_match|↑ |0.0008|± |0.0008| | | |strict-match | 5|exact_match|↑ |0.0000|± |0.0000| |hellaswag | 1|none | 0|acc |↑ |0.2594|± |0.0044| | | |none | 0|acc_norm |↑ |0.2564|± |0.0044| |mmlu | 2|none | |acc |↑ |0.2575|± |0.0037| | - humanities | 2|none | |acc |↑ |0.2410|± |0.0062| | - formal_logic | 1|none | 0|acc |↑ |0.3016|± |0.0410| | - high_school_european_history | 1|none | 0|acc |↑ |0.1879|± |0.0305| | - high_school_us_history | 1|none | 0|acc |↑ |0.2794|± |0.0315| | - high_school_world_history | 1|none | 0|acc |↑ |0.2363|± |0.0277| | - international_law | 1|none | 0|acc |↑ |0.1240|± |0.0301| | - jurisprudence | 1|none | 0|acc |↑ |0.2315|± |0.0408| | - logical_fallacies | 1|none | 0|acc |↑ |0.2270|± |0.0329| | - moral_disputes | 1|none | 0|acc |↑ |0.2139|± |0.0221| | - moral_scenarios | 1|none | 0|acc |↑ |0.2715|± |0.0149| | - philosophy | 1|none | 0|acc |↑ |0.2572|± |0.0248| | - prehistory | 1|none | 0|acc |↑ |0.2500|± |0.0241| | - professional_law | 1|none | 0|acc |↑ |0.2334|± |0.0108| | - world_religions | 1|none | 0|acc |↑ |0.2281|± |0.0322| | - other | 2|none | |acc |↑ |0.2379|± |0.0076| | - business_ethics | 1|none | 0|acc |↑ |0.2800|± |0.0451| | - clinical_knowledge | 1|none | 0|acc |↑ |0.2943|± |0.0280| | - college_medicine | 1|none | 0|acc |↑ |0.2832|± |0.0344| | - global_facts | 1|none | 0|acc |↑ |0.1900|± |0.0394| | - human_aging | 1|none | 0|acc |↑ |0.1794|± |0.0257| | - management | 1|none | 0|acc |↑ |0.3398|± |0.0469| | - marketing | 1|none | 0|acc |↑ |0.1838|± |0.0254| | - medical_genetics | 1|none | 0|acc |↑ |0.1900|± |0.0394| | - miscellaneous | 1|none | 0|acc |↑ |0.2171|± |0.0147| | - nutrition | 1|none | 0|acc |↑ |0.2549|± |0.0250| | - professional_accounting | 1|none | 0|acc |↑ |0.2447|± |0.0256| | - professional_medicine | 1|none | 0|acc |↑ |0.3162|± |0.0282| | - virology | 1|none | 0|acc |↑ |0.1506|± |0.0278| | - social sciences | 2|none | |acc |↑ |0.2899|± |0.0082| | - econometrics | 1|none | 0|acc |↑ |0.2807|± |0.0423| | - high_school_geography | 1|none | 0|acc |↑ |0.3030|± |0.0327| | - high_school_government_and_politics| 1|none | 0|acc |↑ |0.3109|± |0.0334| | - high_school_macroeconomics | 1|none | 0|acc |↑ |0.3103|± |0.0235| | - high_school_microeconomics | 1|none | 0|acc |↑ |0.2563|± |0.0284| | - high_school_psychology | 1|none | 0|acc |↑ |0.3193|± |0.0200| | - human_sexuality | 1|none | 0|acc |↑ |0.2824|± |0.0395| | - professional_psychology | 1|none | 0|acc |↑ |0.2451|± |0.0174| | - public_relations | 1|none | 0|acc |↑ |0.2818|± |0.0431| | - security_studies | 1|none | 0|acc |↑ |0.3592|± |0.0307| | - sociology | 1|none | 0|acc |↑ |0.2488|± |0.0306| | - us_foreign_policy | 1|none | 0|acc |↑ |0.2800|± |0.0451| | - stem | 2|none | |acc |↑ |0.2699|± |0.0079| | - abstract_algebra | 1|none | 0|acc |↑ |0.1900|± |0.0394| | - anatomy | 1|none | 0|acc |↑ |0.2444|± |0.0371| | - astronomy | 1|none | 0|acc |↑ |0.2961|± |0.0372| | - college_biology | 1|none | 0|acc |↑ |0.2431|± |0.0359| | - college_chemistry | 1|none | 0|acc |↑ |0.3500|± |0.0479| | - college_computer_science | 1|none | 0|acc |↑ |0.2700|± |0.0446| | - college_mathematics | 1|none | 0|acc |↑ |0.2400|± |0.0429| | - college_physics | 1|none | 0|acc |↑ |0.3627|± |0.0478| | - computer_security | 1|none | 0|acc |↑ |0.1900|± |0.0394| | - conceptual_physics | 1|none | 0|acc |↑ |0.2766|± |0.0292| | - electrical_engineering | 1|none | 0|acc |↑ |0.2621|± |0.0366| | - elementary_mathematics | 1|none | 0|acc |↑ |0.2725|± |0.0229| | - high_school_biology | 1|none | 0|acc |↑ |0.3065|± |0.0262| | - high_school_chemistry | 1|none | 0|acc |↑ |0.2562|± |0.0307| | - high_school_computer_science | 1|none | 0|acc |↑ |0.2200|± |0.0416| | - high_school_mathematics | 1|none | 0|acc |↑ |0.2630|± |0.0268| | - high_school_physics | 1|none | 0|acc |↑ |0.2649|± |0.0360| | - high_school_statistics | 1|none | 0|acc |↑ |0.3380|± |0.0323| | - machine_learning | 1|none | 0|acc |↑ |0.1607|± |0.0349| |truthfulqa_mc2 | 2|none | 0|acc |↑ |0.4992|± |0.0163| |winogrande | 1|none | 0|acc |↑ |0.5075|± |0.0141| | Groups |Version|Filter|n-shot|Metric| |Value | |Stderr| |------------------|------:|------|------|------|---|-----:|---|-----:| |mmlu | 2|none | |acc |↑ |0.2575|± |0.0037| | - humanities | 2|none | |acc |↑ |0.2410|± |0.0062| | - other | 2|none | |acc |↑ |0.2379|± |0.0076| | - social sciences| 2|none | |acc |↑ |0.2899|± |0.0082| | - stem | 2|none | |acc |↑ |0.2699|± |0.0079|