transformerspytorchtfjaxberttext-classificationarxiv:2002.10957arxiv:1810.04805license:mitendpoints_compatibledeploy:azureregion:us
上下文
512 tokens
最大输出
256 tokens
发布时间
2022/3/2
供应商
1
Overview
MiniLM-L12-H384-uncased is a large language model developed by Microsoft. It supports 512 tokens context and is available through 1 API provider(s).
Key Highlights
- Unknown / Not disclosed
Brand
Microsoft
Organization
国家: USA
View all models, pricing and details from Microsoft.
Specifications
Basic Information
| 模型 | MiniLM-L12-H384-uncased |
| 品牌 | Microsoft |
| Version | 12 |
| Model Type | transformers |
| 状态 | stable |
| 发布时间 | 2022/3/2 |
| 热度 | 86746 |
Architecture
| Parameter Size | Unknown / Not disclosed |
| Architecture Type | bert |
| Attention Mechanism | Unknown / Not disclosed |
| Tokenizer | Unknown / Not disclosed |
| Vocabulary Size | Unknown / Not disclosed |
Context & I/O
| 上下文 | 512 tokens |
| 最大输出 | 256 tokens |
| Modalities | Unknown / Not disclosed |
| Languages | Unknown / Not disclosed |
Capabilities
| Vision | No |
| Audio | No |
| Reasoning | No |
| Function Call | No |
| MCP | No |
| JSON Mode | No |
| Embedding | No |
Training Data
| Training Dataset | Unknown / Not disclosed |
| Estimated Data Size | Unknown / Not disclosed |
| Knowledge Cutoff | Unknown / Not disclosed |
Inference & Deployment
| API Access | Yes |
| VRAM Estimate | Unknown / Not disclosed |
| Quantization Support | Unknown / Not disclosed |
| Hardware Requirements | Unknown / Not disclosed |
Safety & Compliance
| Safety Evaluations | Unknown / Not disclosed |
| Content Policy | Unknown / Not disclosed |
| Region Restrictions | Unknown / Not disclosed |
License & Pricing
| License | mit |
| Commercial Use | Unknown / Not disclosed |
| Open Source | Yes |
Provider & Pricing
价格变动
暂无价格变动。
基准测试
No benchmark data available.
Changelog
- Page created / data imported2026/9/23
- Last updated2026/9/23
FAQ
What is MiniLM-L12-H384-uncased?
MiniLM-L12-H384-uncased is a large language model developed by Microsoft.
Who developed MiniLM-L12-H384-uncased?
MiniLM-L12-H384-uncased was developed by Microsoft. You can learn more on the brand page or official website.
What is the context length of MiniLM-L12-H384-uncased?
MiniLM-L12-H384-uncased supports up to 512 tokens of context.
How much does MiniLM-L12-H384-uncased API cost?
API pricing for MiniLM-L12-H384-uncased starts at ¥0.000/1M per 1M input tokens and ¥0.000/1M per 1M output tokens. See the pricing table above for provider-specific rates.