SynLogic-7B

Home/Models/MiniMaxAI/SynLogic-7B

MiniMaxAI/SynLogic-7B

kind: original
quant: bf16 (16-bit)
family: minimax
modality: text-generation
root model: Qwen/Qwen2.5-7B
provider: MiniMaxAI
license: mit
language: en
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 364
likes: 28
created: —
last modified: 2025-06-10T02:56:30+00:00 (2025)
huggingface: https://huggingface.co/MiniMaxAI/SynLogic-7B
tags: transformerssafetensorsqwen2text-generationLLMconversationalendataset:MiniMaxAI/SynLogicarxiv:2505.19641base_model:Qwen/Qwen2.5-7Bbase_model:finetune:Qwen/Qwen2.5-7Blicense:mittext-generation-inferenceendpoints_compatibleregion:us

benchmark	category	score	conf	evidence
MATH-500	math	64.6	low	`\| Qwen2.5-7B-Base \| 0.3 \| 64.6 \| 30.0 \|`
BBH	reasoning	62.7	low	`\| Qwen2.5-7B-Instruct \| 38.6 \| 62.7 \| 12.4 \|`
AIME 2024	math	30.0	low	`\| Qwen2.5-7B-Base \| 0.3 \| 64.6 \| 30.0 \|`

none scraped.