Ling-lite

Home/Models/inclusionAI/Ling-lite

inclusionAI/Ling-lite

kind: original
quant: bf16 (16-bit)
family: misc
modality: text-generation
root model: inclusionAI/Ling-lite
provider: inclusionAI
license: mit
language: —
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 1,085
likes: 81
created: —
last modified: 2025-05-08T12:31:01+00:00 (2025)
huggingface: https://huggingface.co/inclusionAI/Ling-lite
tags: transformerssafetensorsbailing_moetext-generationconversationalcustom_codearxiv:2503.05139license:mitregion:us

benchmark	category	score	context	conf	evidence
HumanEval	coding	89.02	HumanEval(Pass@1)	medium	`\| HumanEval(Pass@1) \| 0 \| 89.02 \| 83.54 \| 87.20 \| 70.73 \|`
IFEval	instruction-following	81.09	IFEval(Prompt Strict)	medium	`\| IFEval(Prompt Strict) \| 0 \| 81.09 \| 77.99 \| 71.16 \| 53.45 \|`
MATH	math	79.12	Math(EM)	medium	`\| Math(EM) \| 0 \| 79.12 \| 72.80 \| 73.66 \| 52.42 \|`
MMLU	knowledge	74.87	MMLU(EM)	medium	`\| MMLU(EM) \| 5 \| 74.87 \| 71.27 \| 74.26 \| 68.67 \|`
BBH	reasoning	74.58	BBH(EM)	medium	`\| BBH(EM) \| 0 \| 74.58 \| 66.38 \| 66.07 \| 68.05 \|`
GPQA	reasoning	40.91	GPQA(Pass@1)	medium	`\| GPQA(Pass@1) \| 0 \| 40.91 \| 28.66 \| 34.47 \| 32.80 \|`
Math Olympiad	math	37.33	OlympiadBench(pass@1)	medium	`\| OlympiadBench(pass@1) \| 0 \| 37.33 \| 34.42 \| 37.19 \| 16.3 \|`
LiveCodeBench	coding	24.11	LiveCodeBench 2408-2411 (Pass@1)	medium	`\| LiveCodeBench 2408-2411 (Pass@1) \| 0 \| 24.11 \| 15.18 \| 16.96 \| 11.61 \|`
AIME 2024	math	13.33	AIME2024(pass@1)	medium	`\| AIME2024(pass@1) \| 0 \| 13.33 \| 6.67 \| 16.67 \| 0.00 \|`

none scraped.