Sky-T1-32B-Flash

Home/Models/NovaSky-AI/Sky-T1-32B-Flash

NovaSky-AI/Sky-T1-32B-Flash

kind: original
quant: bf16 (16-bit)
family: misc
modality: text-generation
root model: Qwen/Qwen2.5-32B-Instruct
provider: NovaSky-AI
license: apache-2.0
language: en
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 24
likes: 67
created: —
last modified: 2025-02-02T05:26:20+00:00 (2025)
huggingface: https://huggingface.co/NovaSky-AI/Sky-T1-32B-Flash
tags: transformerssafetensorsqwen2text-generationconversationalendataset:BAAI/TACOdataset:tasksource/PRM800Kbase_model:NovaSky-AI/Sky-T1-32B-Previewbase_model:finetune:NovaSky-AI/Sky-T1-32B-Previewlicense:apache-2.0text-generation-inferenceendpoints_compatibleregion:us

benchmark	category	score	context	conf	evidence
MATH-500	math	88.6	Math500	medium	`\| Math500 \| Acc \| 88.6 \| 88.6 \| 76.2 \| 89.2 \| 90.8 \|`
MMLU	knowledge	82.4	MMLU	medium	`\| MMLU \| Acc \| 82.4 \| 81.7 \| 80.1 \| 85.2 \| 82.1 \|`
GPQA Diamond	reasoning	56.8	GPQA Diamond	medium	`\| GPQA Diamond \| Acc \| 56.8 \| 56.6 \| 45.5 \| 52.5 \| 62.6 \|`
AIME 2024	math	43.3	AIME24	medium	`\| AIME24 \| Acc \| 43.3 \| 43.3 \| 16.7 \| 50 \| 66.7 \|`

none scraped.