OREAL-7B

Home/Models/internlm/OREAL-7B

internlm/OREAL-7B

kind: original
quant: bf16 (16-bit)
family: internlm
modality: text-generation
root model: internlm/OREAL-7B-SFT
provider: internlm
license: apache-2.0
language: —
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 56
likes: 20
created: —
last modified: 2025-02-24T04:22:31+00:00 (2025)
huggingface: https://huggingface.co/internlm/OREAL-7B
tags: transformerssafetensorsqwen2text-generationconversationaldataset:internlm/OREAL-RL-Promptsarxiv:2502.06781base_model:internlm/OREAL-7B-SFTbase_model:finetune:internlm/OREAL-7B-SFTlicense:apache-2.0text-generation-inferenceendpoints_compatibleregion:us

benchmark	category	score	context	conf	evidence
MATH	math	81.8	Qwen2.5-Math-Instrust-7B	medium	`\| Qwen2.5-Math-Instrust-7B \| 81.8 \| 20.0 \| 13.3 \| 44.1 \| 31.1 \|`
MATH	math	78.4	rStar-Math-7B	medium	`\| rStar-Math-7B \| 78.4* \| 26.7* \| - \| - \| 47.1* \|`
MATH-500	math	72.8		low	`\| GPT-4o-1120 \| 72.8 \| 16.7 \| 13.3 \| 44.8 \| 33.7 \|`
AIME 2024	math	16.7		low	`\| GPT-4o-1120 \| 72.8 \| 16.7 \| 13.3 \| 44.8 \| 33.7 \|`
AIME 2025	math	13.3		low	`\| GPT-4o-1120 \| 72.8 \| 16.7 \| 13.3 \| 44.8 \| 33.7 \|`

none scraped.