Ming-Lite-Omni

Home/Models/inclusionAI/Ming-Lite-Omni

inclusionAI/Ming-Lite-Omni

kind: original
quant: bf16 (16-bit)
family: misc
modality: any-to-any
root model: inclusionAI/Ling-lite
provider: inclusionAI
license: mit
language: —
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 82
likes: 200
created: —
last modified: 2025-10-27T16:04:58+00:00 (2025)
huggingface: https://huggingface.co/inclusionAI/Ming-Lite-Omni
tags: transformersonnxdiffuserssafetensorsbailingmmtext-generationany-to-anycustom_codearxiv:2506.09344base_model:inclusionAI/Ling-litebase_model:quantized:inclusionAI/Ling-litelicense:mitendpoints_compatibleregion:us

benchmark	category	score	context	conf	evidence
DocVQA	multimodal	93.0	DocVQA_TEST	medium	`\| DocVQA_TEST \| 93 \| <b>95.7</b> \|`
ChartQA	multimodal	85.1	ChartQA_TEST	medium	`\| ChartQA_TEST \| 85.1 \| <b>87.3</b> \|`
MMBench	multimodal	80.8	MMBench_TEST_V11	medium	`\| MMBench_TEST_V11 \| 80.8 \| <b>82.8</b> \| 82.0 \|`
MathVista	multimodal	68.1	MathVista	medium	`\| MathVista \| <b>71.6</b> \| 68.1 \| 67.9 \|`
OpenBookQA	knowledge	61.98		high	`\| Ming-lite-omni \| <b>4.34</b> \| <b>4.63</b> \| <b>4.06</b> \| 58.84 \| 47.53 \| 61.98 \| 58.36 \| 99.04 \|`
IFEval	instruction-following	58.36		high	`\| Ming-lite-omni \| <b>4.34</b> \| <b>4.63</b> \| <b>4.06</b> \| 58.84 \| 47.53 \| 61.98 \| 58.36 \| 99.04 \|`
MMMU	multimodal	56.3	MMMU	medium	`\| MMMU \| 56.3 \| <b>56.6</b> \| 54.8 \|`
MMMU	multimodal	46.3	Video-MMMU	medium	`\| Video-MMMU \| 46.3 \| <b>47.4</b> \|`
WER VoxPopuli	speech-asr	5.8		high	`\| Ming-lite-omni \| 1.47 \| 2.55 \| 2.52 \| 6.31 \| 2.96 \| 5.95 \| 5.46 \| 1.44 \| 2.80 \| 4.15 \| 6.89 \| 3.39 \| 5.80 \|`
AlpacaEval	chat	3.69		low	`\| Qwen2-Audio-chat \| 3.545 \| 3.69 \| 3.40 \| 35.35 \| 35.43 \| 49.01 \| 22.57 \| 98.85 \|`
WER LibriSpeech	speech-asr	1.44		high	`\| Ming-lite-omni \| 1.47 \| 2.55 \| 2.52 \| 6.31 \| 2.96 \| 5.95 \| 5.46 \| 1.44 \| 2.80 \| 4.15 \| 6.89 \| 3.39 \| 5.80 \|`

none scraped.