Arabic-first instruction-tuned 7B model from the HUMAIN ALLaM program (research originated at the SDAIA National Center for AI; paper: arXiv:2407.15390, ICLR 2025). Per the Hugging Face model card, the preview is trained from scratch in two stages: 4T English tokens followed by 1.2T mixed Arabic/English tokens, then instruction tuned on curated Arabic and English data. Published on Hugging Face as ALLaM-AI/ALLaM-7B-Instruct-preview with a byte-identical mirror under humain-ai/ALLaM-7B-Instruct-preview. Llama-family architecture with 32 layers, 4096 hidden size, 64000-entry Arabic-aware vocabulary, and a 4096-token context window. The full ALLaM program consumed roughly 5M A100 GPU-hours. Strong on Arabic instruction-following and knowledge tasks, with an independent AraLingBench score of 74.0.
信号概览
评分详解
| 信号 | 强度 | 权重 | 影响 |
|---|---|---|---|
| Pricingjust now | 100 | 25% | +25.0 |
| Output Capacityjust now | 60 | 15% | +9.0 |
| Context Windowjust now | 57 | 15% | +8.6 |
| Capabilitiesjust now | 17 | 30% | +5.0 |
| Recencyjust now | 31 | 15% | +4.7 |
功能
模态
HUMAIN近期发布时间线
把当前模型放回同一服务商最近的发布节奏中查看。
评测
社区和从业者反馈在基准测试和价格之上增加了真实世界的信号。
Reviews
Be the first to review this model
Share your experience with ALLaM 7B Instruct (preview) and help the community make better decisions.
常见问题
关键信息
价格工具
访问与可用性
价格
免费