MT0 XXL
- Family
- MT0
- Released
- 2024-01-01
- Context
- 1K
- Parameters
- 13B
- Architecture
- Decoder Only
- Specialization
- general
- Openness
- Open source
- License
- Apache 2.0OSI-approvedCommercial use: permitted
- Weights
- Unknown
- Code
- Unknown
- Training
- Fine-tuned
Cheapest of 1 route · IBM watsonx
About
The MT0 XXL model, part of the BLOOMZ and mT0 family developed by the BigScience workshop, is a large language AI model designed for multilingual applications with zero-shot capabilities. It features 13.9 billion parameters and is built on a transformer architecture with an encoder-decoder structure. Trained with a multitask finetuning approach using the xP3 dataset, MT0 XXL excels in tasks such as translation, question answering, text generation, and summarization. Although powerful, the model's performance hinges on prompt specificity and the diversity of its training data. Running the model can be resource-intensive, which might limit its accessibility for smaller entities 1.
Providers(1)
Compare API pricing across 1 tracked provider route for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| IBM watsonx | $1.80 | $1.80 | Serverless |
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.
Cheapest of 1 route · IBM watsonx