Qwen3-4B-SafeRL

Home/Models/Qwen/Qwen3-4B-SafeRL

Qwen/Qwen3-4B-SafeRL

kind: original
quant: bf16 (16-bit)
family: qwen
modality: text-generation
root model: Qwen/Qwen3-4B
provider: Qwen
license: apache-2.0
language: —
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 1,122
likes: 44
created: —
last modified: 2025-10-17T02:33:25+00:00 (2025)
huggingface: https://huggingface.co/Qwen/Qwen3-4B-SafeRL
tags: transformerssafetensorsqwen3text-generationconversationalarxiv:2510.14276base_model:Qwen/Qwen3-4Bbase_model:finetune:Qwen/Qwen3-4Blicense:apache-2.0text-generation-inferenceendpoints_compatibledeploy:azureregion:us

benchmark	category	score	conf	evidence
GPQA	reasoning	40.8	high	`\| \| Qwen3-4B-SafeRL \| 86.5 \| 98.1 \| 5.3 \| 10.7 \| 18.2 \| 27.7 \| 40.8 \|`
AIME 2025	math	18.2	high	`\| \| Qwen3-4B-SafeRL \| 86.5 \| 98.1 \| 5.3 \| 10.7 \| 18.2 \| 27.7 \| 40.8 \|`
Chatbot Arena	chat	10.7	high	`\| \| Qwen3-4B-SafeRL \| 86.5 \| 98.1 \| 5.3 \| 10.7 \| 18.2 \| 27.7 \| 40.8 \|`

none scraped.