Chameleon 34B
Chameleon 34B has model metadata, but missing tracked provider pricing keeps it from being a default production pick.
Use it for
- Teams evaluating general LLM work
- Workloads that can use a 4k context window
Do not use it for
- Cost-sensitive launches that need sourced token pricing
- Vision or document-understanding workloads
- Strict JSON or tool-calling flows
- Family
- Chameleon
- Released
- 2024-06-18
- Context
- 4k
- Parameters
- 34B
- Architecture
- Decoder Only
- Specialization
- general
- Training
- finetuned
Large-scale open-source AI for social technologies.
No tracked provider token pricing is available yet.
About
Chameleon 34B is a cutting-edge AI model developed by Meta's FAIR team, renowned for its ability to process and generate both text and images through a unified, token-based architecture. This design allows it to handle multimodal inputs seamlessly, setting it apart from models that treat text and images separately. Trained on 10 trillion tokens, including text, images, and code, Chameleon excels in tasks like visual question answering, image captioning, and text generation. It surpasses models like GPT-4V and Gemini Pro in human evaluations and competes well on text-only benchmarks. Despite its prowess, the full model is not publicly available due to safety concerns, with only a research version supporting mixed-modal inputs accessible. The model does have some limitations, including challenges with text-heavy image processing, which Meta is actively working to improve.
Chameleon 34B is a model in the Chameleon family. The structured metadata tracks a 4k-token context window. No headline benchmark score is tracked for Chameleon 34B yet.
Top use-case fit
No primary decision-task fit is mapped for this model yet.
Provider price ladder
No tracked provider token pricing is available 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.