Embeddingsentence-transformerssafetensorsllava_nextmultimodal-retrievalembedding-modelsentence-similaritycustom_codeenarxiv:2412.14475base_model:llava-hf/llava-v1.6-mistral-7b-hfbase_model:finetune:llava-hf/llava-v1.6-mistral-7b-hflicense:mitendpoints_compatibleregion:us
上下文
4,096 tokens
最大输出
1,024 tokens
发布时间
2025/3/4
供应商
1
Overview
BGE-VL-MLLM-S2 is a large language model developed by BAAI. It supports 4,096 tokens context and is available through 1 API provider(s).
Key Highlights
- Embedding
Brand
BAAI
Organization
国家: China
View all models, pricing and details from BAAI.
Specifications
Basic Information
| 模型 | BGE-VL-MLLM-S2 |
| 品牌 | BAAI |
| Version | 2 |
| Model Type | sentence-transformers |
| 状态 | stable |
| 发布时间 | 2025/3/4 |
| 热度 | 1079 |
Architecture
| Parameter Size | 7.6B |
| Architecture Type | llava_next |
| Attention Mechanism | vision-causal |
| Tokenizer | Unknown / Not disclosed |
| Vocabulary Size | Unknown / Not disclosed |
Context & I/O
| 上下文 | 4,096 tokens |
| 最大输出 | 1,024 tokens |
| Modalities | Embedding |
| Languages | en |
Capabilities
| Vision | No |
| Audio | No |
| Reasoning | No |
| Function Call | No |
| MCP | No |
| JSON Mode | No |
| Embedding | Yes |
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 BGE-VL-MLLM-S2?
BGE-VL-MLLM-S2 is a large language model developed by BAAI.
Who developed BGE-VL-MLLM-S2?
BGE-VL-MLLM-S2 was developed by BAAI. You can learn more on the brand page or official website.
What is the context length of BGE-VL-MLLM-S2?
BGE-VL-MLLM-S2 supports up to 4,096 tokens of context.
How much does BGE-VL-MLLM-S2 API cost?
API pricing for BGE-VL-MLLM-S2 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.