How amalia-llm/amalia works
This repository is an AMALIA project landing page, not the implementation of its models or pipelines. It describes an open European Portuguese language-model ecosystem and documents the main user workflow: deploy an AMALIA model with vLLM, send a chat-completion request, and receive an answer. The graph also preserves the documented data, training, post-training, vision-language, and evaluation capabilities. No source excerpts are available, so subsystem paths and relationships rely on README.md; the README does not establish detailed interactions among the research components.
Main entry points: README.md AMALIA models
Components 10
Model serving
- vLLM serving
- AMALIA models
README.md
Data processing
- Data pipelines
README.md
Model development
- Pretraining
README.md - Language post-training
README.md - Vision-language tuning
README.md
Evaluation
- Language evaluation
README.md - Vision-language evaluation
README.md - Portuguese benchmarks
README.md
Other components
- Model user
Connections 3
- Model user → vLLM serving: sends request
README.md - vLLM serving → AMALIA models: serves model
README.md - vLLM serving → Model user: returns answer
README.md