metadata
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:
- yahma/alpaca-cleaned
- saillab/taco-datasets
- xu-song/cc100-samples
- badrex/llm-emoji-dataset
- pszemraj/simple_wikipedia
- AtlasUnified/Atlas-Reasoning
- fblgit/simple-math
- AtlasUnified/atlas-math-sets
- rvv-karma/Math-QA
- microsoft/orca-math-word-problems-200k
- meta-math/MetaMathQA
- TIGER-Lab/MathInstruct
- ChuGyouk/WebInstructSub-only-socratic
- thesven/gsm8k-reasoning
- AlgorithmicResearchGroup/math_reasoning_autoformalization_track
- KingNish/reasoning-base-20k
- fmars/wiki_stem
- ChuGyouk/WebInstructSub-only-sciencestackexchange
- bigcode/the-stack-smol-xs
- cognitivecomputations/dolphin-coder
- HuggingFaceH4/CodeAlpaca_20K
- m-a-p/CodeFeedback-Filtered-Instruction
- NuclearAi/Nuke-X-Glaive-Python-Dataset
- iamtarun/python_code_instructions_18k_alpaca
- kloodia/html_200k
- kloodia/json_200k
- kloodia/javascript_200k
- bleugreen/typescript-chunks
- SkunkworksAI/reasoning-0.01
- Magpie-Align/Magpie-Reasoning-150K
tags:
- litgpt
- litdata
tangled-llama-q-32k-base-v0.1
A pretrained language model based on the Llama model with about 65M parameters. This model has been trained on 16.7B (16,698,858,240) tokens from more than 3.6M (3,597,088) dataset rows.
This model isn't designed for immediate use but rather for Continued Pretraining and Finetuning on a downstream task. While it can handle a context length of up to 128K (131,072) tokens, it was pretrained with sequences of 2K (2048) tokens.
The objective is to streamline the cognitive or reasoning core, eliminating any redundant knowledge from the model.
lm-evaluation-harness
litgpt evaluate --tasks 'hellaswag,gsm8k,truthfulqa_mc2,mmlu,winogrande,arc_challenge' --out_dir 'evaluate-quick/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
| Tasks | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| arc_challenge | 1 | none | 0 | acc | ↑ | 0.1962 | ± | 0.0116 |
| none | 0 | acc_norm | ↑ | 0.2304 | ± | 0.0123 | ||
| gsm8k | 3 | flexible-extract | 5 | exact_match | ↑ | 0.0144 | ± | 0.0033 |
| strict-match | 5 | exact_match | ↑ | 0.0015 | ± | 0.0011 | ||
| hellaswag | 1 | none | 0 | acc | ↑ | 0.2631 | ± | 0.0044 |
| none | 0 | acc_norm | ↑ | 0.2758 | ± | 0.0045 | ||
| mmlu | 2 | none | acc | ↑ | 0.2473 | ± | 0.0036 | |
| - humanities | 2 | none | acc | ↑ | 0.2351 | ± | 0.0062 | |
| - formal_logic | 1 | none | 0 | acc | ↑ | 0.2857 | ± | 0.0404 |
| - high_school_european_history | 1 | none | 0 | acc | ↑ | 0.2667 | ± | 0.0345 |
| - high_school_us_history | 1 | none | 0 | acc | ↑ | 0.2696 | ± | 0.0311 |
| - high_school_world_history | 1 | none | 0 | acc | ↑ | 0.2110 | ± | 0.0266 |
| - international_law | 1 | none | 0 | acc | ↑ | 0.1653 | ± | 0.0339 |
| - jurisprudence | 1 | none | 0 | acc | ↑ | 0.2870 | ± | 0.0437 |
| - logical_fallacies | 1 | none | 0 | acc | ↑ | 0.2331 | ± | 0.0332 |
| - moral_disputes | 1 | none | 0 | acc | ↑ | 0.2283 | ± | 0.0226 |
| - moral_scenarios | 1 | none | 0 | acc | ↑ | 0.2425 | ± | 0.0143 |
| - philosophy | 1 | none | 0 | acc | ↑ | 0.2186 | ± | 0.0235 |
| - prehistory | 1 | none | 0 | acc | ↑ | 0.2099 | ± | 0.0227 |
| - professional_law | 1 | none | 0 | acc | ↑ | 0.2314 | ± | 0.0108 |
| - world_religions | 1 | none | 0 | acc | ↑ | 0.2632 | ± | 0.0338 |
| - other | 2 | none | acc | ↑ | 0.2485 | ± | 0.0078 | |
| - business_ethics | 1 | none | 0 | acc | ↑ | 0.2600 | ± | 0.0441 |
| - clinical_knowledge | 1 | none | 0 | acc | ↑ | 0.2528 | ± | 0.0267 |
| - college_medicine | 1 | none | 0 | acc | ↑ | 0.2254 | ± | 0.0319 |
| - global_facts | 1 | none | 0 | acc | ↑ | 0.2700 | ± | 0.0446 |
| - human_aging | 1 | none | 0 | acc | ↑ | 0.2377 | ± | 0.0286 |
| - management | 1 | none | 0 | acc | ↑ | 0.2816 | ± | 0.0445 |
| - marketing | 1 | none | 0 | acc | ↑ | 0.2692 | ± | 0.0291 |
| - medical_genetics | 1 | none | 0 | acc | ↑ | 0.2600 | ± | 0.0441 |
| - miscellaneous | 1 | none | 0 | acc | ↑ | 0.2350 | ± | 0.0152 |
| - nutrition | 1 | none | 0 | acc | ↑ | 0.2549 | ± | 0.0250 |
| - professional_accounting | 1 | none | 0 | acc | ↑ | 0.2801 | ± | 0.0268 |
| - professional_medicine | 1 | none | 0 | acc | ↑ | 0.2610 | ± | 0.0267 |
| - virology | 1 | none | 0 | acc | ↑ | 0.1807 | ± | 0.0300 |
| - social sciences | 2 | none | acc | ↑ | 0.2658 | ± | 0.0080 | |
| - econometrics | 1 | none | 0 | acc | ↑ | 0.1930 | ± | 0.0371 |
| - high_school_geography | 1 | none | 0 | acc | ↑ | 0.2172 | ± | 0.0294 |
| - high_school_government_and_politics | 1 | none | 0 | acc | ↑ | 0.3212 | ± | 0.0337 |
| - high_school_macroeconomics | 1 | none | 0 | acc | ↑ | 0.2923 | ± | 0.0231 |
| - high_school_microeconomics | 1 | none | 0 | acc | ↑ | 0.3025 | ± | 0.0298 |
| - high_school_psychology | 1 | none | 0 | acc | ↑ | 0.2752 | ± | 0.0191 |
| - human_sexuality | 1 | none | 0 | acc | ↑ | 0.2290 | ± | 0.0369 |
| - professional_psychology | 1 | none | 0 | acc | ↑ | 0.2386 | ± | 0.0172 |
| - public_relations | 1 | none | 0 | acc | ↑ | 0.2636 | ± | 0.0422 |
| - security_studies | 1 | none | 0 | acc | ↑ | 0.3143 | ± | 0.0297 |
| - sociology | 1 | none | 0 | acc | ↑ | 0.2338 | ± | 0.0299 |
| - us_foreign_policy | 1 | none | 0 | acc | ↑ | 0.2600 | ± | 0.0441 |
| - stem | 2 | none | acc | ↑ | 0.2464 | ± | 0.0077 | |
| - abstract_algebra | 1 | none | 0 | acc | ↑ | 0.2500 | ± | 0.0435 |
| - anatomy | 1 | none | 0 | acc | ↑ | 0.2148 | ± | 0.0355 |
| - astronomy | 1 | none | 0 | acc | ↑ | 0.1908 | ± | 0.0320 |
| - college_biology | 1 | none | 0 | acc | ↑ | 0.2569 | ± | 0.0365 |
| - college_chemistry | 1 | none | 0 | acc | ↑ | 0.2700 | ± | 0.0446 |
| - college_computer_science | 1 | none | 0 | acc | ↑ | 0.3500 | ± | 0.0479 |
| - college_mathematics | 1 | none | 0 | acc | ↑ | 0.2700 | ± | 0.0446 |
| - college_physics | 1 | none | 0 | acc | ↑ | 0.2745 | ± | 0.0444 |
| - computer_security | 1 | none | 0 | acc | ↑ | 0.3000 | ± | 0.0461 |
| - conceptual_physics | 1 | none | 0 | acc | ↑ | 0.2766 | ± | 0.0292 |
| - electrical_engineering | 1 | none | 0 | acc | ↑ | 0.2345 | ± | 0.0353 |
| - elementary_mathematics | 1 | none | 0 | acc | ↑ | 0.2566 | ± | 0.0225 |
| - high_school_biology | 1 | none | 0 | acc | ↑ | 0.2226 | ± | 0.0237 |
| - high_school_chemistry | 1 | none | 0 | acc | ↑ | 0.2217 | ± | 0.0292 |
| - high_school_computer_science | 1 | none | 0 | acc | ↑ | 0.2000 | ± | 0.0402 |
| - high_school_mathematics | 1 | none | 0 | acc | ↑ | 0.2370 | ± | 0.0259 |
| - high_school_physics | 1 | none | 0 | acc | ↑ | 0.2517 | ± | 0.0354 |
| - high_school_statistics | 1 | none | 0 | acc | ↑ | 0.2685 | ± | 0.0302 |
| - machine_learning | 1 | none | 0 | acc | ↑ | 0.1786 | ± | 0.0364 |
| truthfulqa_mc2 | 2 | none | 0 | acc | ↑ | 0.4668 | ± | 0.0161 |
| winogrande | 1 | none | 0 | acc | ↑ | 0.5012 | ± | 0.0141 |
| Groups | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| mmlu | 2 | none | acc | ↑ | 0.2473 | ± | 0.0036 | |
| - humanities | 2 | none | acc | ↑ | 0.2351 | ± | 0.0062 | |
| - other | 2 | none | acc | ↑ | 0.2485 | ± | 0.0078 | |
| - social sciences | 2 | none | acc | ↑ | 0.2658 | ± | 0.0080 | |
| - stem | 2 | none | acc | ↑ | 0.2464 | ± | 0.0077 |
litgpt evaluate --tasks 'leaderboard' --out_dir 'evaluate-leaderboard/' --batch_size 4 --dtype 'bfloat16' out/pretrain/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 | ↑ | 0.1840 | ± | 0.0246 |
| - leaderboard_bbh_disambiguation_qa | 1 | none | 3 | acc_norm | ↑ | 0.3880 | ± | 0.0309 |
| - leaderboard_bbh_formal_fallacies | 1 | none | 3 | acc_norm | ↑ | 0.4680 | ± | 0.0316 |
| - leaderboard_bbh_geometric_shapes | 1 | none | 3 | acc_norm | ↑ | 0.1000 | ± | 0.0190 |
| - leaderboard_bbh_hyperbaton | 1 | none | 3 | acc_norm | ↑ | 0.5160 | ± | 0.0317 |
| - leaderboard_bbh_logical_deduction_five_objects | 1 | none | 3 | acc_norm | ↑ | 0.2080 | ± | 0.0257 |
| - leaderboard_bbh_logical_deduction_seven_objects | 1 | none | 3 | acc_norm | ↑ | 0.1720 | ± | 0.0239 |
| - leaderboard_bbh_logical_deduction_three_objects | 1 | none | 3 | acc_norm | ↑ | 0.3280 | ± | 0.0298 |
| - leaderboard_bbh_movie_recommendation | 1 | none | 3 | acc_norm | ↑ | 0.2640 | ± | 0.0279 |
| - leaderboard_bbh_navigate | 1 | none | 3 | acc_norm | ↑ | 0.5760 | ± | 0.0313 |
| - leaderboard_bbh_object_counting | 1 | none | 3 | acc_norm | ↑ | 0.0520 | ± | 0.0141 |
| - leaderboard_bbh_penguins_in_a_table | 1 | none | 3 | acc_norm | ↑ | 0.2260 | ± | 0.0347 |
| - leaderboard_bbh_reasoning_about_colored_objects | 1 | none | 3 | acc_norm | ↑ | 0.0720 | ± | 0.0164 |
| - leaderboard_bbh_ruin_names | 1 | none | 3 | acc_norm | ↑ | 0.2280 | ± | 0.0266 |
| - leaderboard_bbh_salient_translation_error_detection | 1 | none | 3 | acc_norm | ↑ | 0.1920 | ± | 0.0250 |
| - leaderboard_bbh_snarks | 1 | none | 3 | acc_norm | ↑ | 0.4831 | ± | 0.0376 |
| - leaderboard_bbh_sports_understanding | 1 | none | 3 | acc_norm | ↑ | 0.4600 | ± | 0.0316 |
| - leaderboard_bbh_temporal_sequences | 1 | none | 3 | acc_norm | ↑ | 0.2360 | ± | 0.0269 |
| - leaderboard_bbh_tracking_shuffled_objects_five_objects | 1 | none | 3 | acc_norm | ↑ | 0.2080 | ± | 0.0257 |
| - leaderboard_bbh_tracking_shuffled_objects_seven_objects | 1 | none | 3 | acc_norm | ↑ | 0.1680 | ± | 0.0237 |
| - leaderboard_bbh_tracking_shuffled_objects_three_objects | 1 | none | 3 | acc_norm | ↑ | 0.3040 | ± | 0.0292 |
| - 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 | ↑ | 0.2121 | ± | 0.0291 |
| - leaderboard_gpqa_extended | 1 | none | 0 | acc_norm | ↑ | 0.2619 | ± | 0.0188 |
| - leaderboard_gpqa_main | 1 | none | 0 | acc_norm | ↑ | 0.2589 | ± | 0.0207 |
| - leaderboard_ifeval | 3 | none | 0 | inst_level_loose_acc | ↑ | 0.1966 | ± | N/A |
| none | 0 | inst_level_strict_acc | ↑ | 0.1835 | ± | N/A | ||
| none | 0 | prompt_level_loose_acc | ↑ | 0.1017 | ± | 0.0130 | ||
| none | 0 | prompt_level_strict_acc | ↑ | 0.0998 | ± | 0.0129 | ||
| - 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 | ↑ | 0.1155 | ± | 0.0029 |
| - leaderboard_musr | N/A | |||||||
| - leaderboard_musr_murder_mysteries | 1 | none | 0 | acc_norm | ↑ | 0.5040 | ± | 0.0317 |
| - leaderboard_musr_object_placements | 1 | none | 0 | acc_norm | ↑ | 0.3086 | ± | 0.0289 |
| - leaderboard_musr_team_allocation | 1 | none | 0 | acc_norm | ↑ | 0.3400 | ± | 0.0300 |
litgpt evaluate --tasks 'bbh_zeroshot,bbh_fewshot,bbh_cot_fewshot,bbh_cot_zeroshot' --out_dir 'evaluate-bigbenchhard/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
litgpt evaluate --tasks 'mmlu,mmlu_pro' --out_dir 'evaluate-mmlu/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
litgpt evaluate --tasks 'arc_challenge,boolq,gpqa,hellaswag,openbookqa,piqa,truthfulqa_mc2,winogrande' --out_dir 'evaluate-reasoning/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
litgpt evaluate --tasks 'mmlu_multilingual,mgsm' --out_dir 'evaluate-multilinguals/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
litgpt evaluate --tasks 'gsm8k,mathqa' --out_dir 'evaluate-math/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/
litgpt evaluate --tasks 'wikitext,qasper' --out_dir 'evaluate-long/' --batch_size 4 --dtype 'bfloat16' out/pretrain/final/