LLaDA2.0-mini-preview

Home/Models/inclusionAI/LLaDA2.0-mini-preview

inclusionAI/LLaDA2.0-mini-preview

kind: original
quant: bf16 (16-bit)
family: misc
modality: text-generation
root model: inclusionAI/LLaDA2.0-mini-preview
provider: inclusionAI
license: apache-2.0
language: —
context: 4,096
library: transformers
vRAM (GB): —
size on disk: —
downloads: 654
likes: 88
created: —
last modified: 2025-12-19T05:45:03+00:00 (2025)
huggingface: https://huggingface.co/inclusionAI/LLaDA2.0-mini-preview
tags: transformerssafetensorsllada2_moetext-generationdllmdiffusionllmtext_generationconversationalcustom_codearxiv:2512.15745license:apache-2.0region:us

benchmark	category	score	context	conf	evidence
MATH	math	94.66		medium	`\| math \| 94.66 \| 58.68 \| 73.50 \|`
GSM8K	math	94.62	GSM8K	medium	`\| GSM8K \| 94.62 \| 82.41 \| 89.01 \|`
HumanEval	coding	85.98		medium	`\| humaneval \| 85.98 \| 61.59 \| 80.49 \|`
MBPP	coding	84.07		medium	`\| mbpp \| 84.07 \| 70.02 \| 77.75 \|`
MMLU	knowledge	82.15	MMLU	medium	`\| MMLU \| 82.15 \| 67.18 \| 72.49 \|`
C-Eval	knowledge	82.1	C-EVAL	medium	`\| C-EVAL \| 82.10 \| 63.93 \| 66.54 \|`
CMMLU	knowledge	80.84	CMMLU	medium	`\| CMMLU \| 80.84 \| 64.30 \| 67.53 \|`
DROP	reasoning	78.8		medium	`\| drop \| 78.80 \| 79.77 \| 79.49 \|`
IFEval	instruction-following	76.16	IFEval-strict -prompt	medium	`\| IFEval-strict -prompt \| 76.16 \| 59.33 \| 62.50 \|`
MMLU-Pro	knowledge	63.72	MMLU-PRO	medium	`\| MMLU-PRO \| 63.72 \| 44.64 \| 49.22 \|`
BigCodeBench	coding	35.0	Bigcodebench-Full	medium	`\| Bigcodebench-Full \| 35.00 \| 20.44 \| 30.44 \|`

none scraped.