Idefics3
Idefics3 is a Hugging Face open-weight multimodal language-model release. Idefics3 is the third open vision-language generation, documented with a reproducible model-building study and open multimodal datasets. It combines SigLIP visual features with a Llama 3.1 8B instruction backbone and supports image questions, interleaved multi-image conversations, document analysis, and textual output. The card declares Apache 2.0 for its release while identifying the Llama backbone; users should consider the terms of that component. The date records the public technical report rather than assuming an earlier repository timestamp was a release. Perceptual interpretation and extracted text can be wrong, and performance depends on image resolution and task framing.
Specifications
- Parameters
- 8B language backbone
- Architecture
- Transformer language decoder with vision encoder and multimodal connector
- License
- Apache-2.0 for released checkpoint; underlying Llama 3.1 terms also relevant
- Type
- multimodal
- Modalities
- textimage
Benchmark Scores
Advanced Specifications
- Model Family
- Idefics
- API Access
- Not Available
- Chat Interface
- Not Available
- Variants
- 8B Llama3
Capabilities & Limitations
- Capabilities
- visual question answeringimage understandingmulti-image chat
- Known Limitations
- Image interpretation may be inaccurateBackbone license conditions must be considered
- Notable Use Cases
- multimodal researchdocument assistantsvisual conversation