LLaVA Llama 2 13B
LLaVA Llama 2 13B is released 2023-04-17 in the LLaVA family with open-weight; evaluate it while provider pricing coverage matures.
- Family
- LLaVA
- Released
- 2023-04-17
- Parameters
- 13B
- Architecture
- Decoder Only
- Knowledge cutoff
- 2023-01
- Specialization
- general
- Openness
- Open weights
- License
- CC-BY-NC-4.0Commercial use: non-commercial
- Weights
- Unknown
- Code
- Unknown
- Training
- Fine-tuned
No tracked provider pricing is available yet.
About
LLaVA (Large Language and Vision Assistant) Llama 2 13B is an open-source multimodal chatbot model that leverages the transformer architecture to process and integrate sequential data like text and images. It is a fine-tuned version of the LLaMA 2 language model, trained on a substantial dataset of image-text pairs and GPT-generated multimodal instruction-following data. The model's architecture features a vision encoder (CLIP ViT-L/14) for images and a language model (Vicuna) for text, connected by a projection matrix. LLaVA excels in open-ended conversations, visual reasoning tasks, and can synergize with other models like GPT-4 for complex tasks.
Providers
No active provider routes are tracked for this model yet.
Capabilities
No model capability flags are currently sourced.
Benchmark peer barsfor Coding
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
No tracked provider pricing is available yet.