Public KG record
Qwen3-4B
Recorded overview
Language model used to generate clean lists of tags from rough prompts.
An evidence-backed entity from the project knowledge graph; detailed tool metadata is still being added.
Recorded details
- Benchmarks: NQ 下游准确率 25.5%
- Benchmarks: 用于 NQ 下游准确率评测；LEANN 与 HNSW 均为 25.5%
- Capabilities: text generation
- Capabilities: generates tags from rough prompt
- Capabilities: 从粗略提示生成图像标签
- Capabilities: generates near-synonymous sub-queries zero-shot
- Capabilities: LM head
- Integrations: transformers integration
Evidence coverage
The KG currently records 13 known information dimensions and has 6 undocumented dimensions, linked to 13 public source articles. These counts describe record coverage, not model performance or verified fit.
Related public records
- automated grader for Portuguese essays — uses
- Qwen — develops
- gr.Workflow — uses
- LM head — has feature
- Qwen3 — part of