Poro 2 8B Instruct
Poro 2 8B Instruct is the Finnish and English conversation release built from the Llama 3.1-based Poro 2 model. It adds supervised instruction training and Direct Preference Optimization.
Model design and training
The instruction phase uses about 1.4 million examples, including bilingual Tulu prompts with Llama 3.3 70B responses, Magpie conversations and EuroParl translation pairs. DPO uses HelpSteer3. Its Llama 3.3 license is a release-specific condition; the underlying architecture remains based on Llama 3.1.Llama-Poro-2-8B-Instruct: official model card
Practical assessment
Practical guidance. This is a practical starting point for a local Finnish assistant when the smaller size is suitable. Evaluate citations, extracted fields and translations independently. Instruction-following gains do not establish that the model has current factual knowledge.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | Downloadable |
| Model identifiers | Llama-Poro-2-8B-Instruct |
| Context window | 8,192 tokens Sequence length reported by this release's model card; this is not a guaranteed useful retrieval length. Llama-Poro-2-8B-Instruct: official model card |
| Model size | 8.03 billion parameters; 32 decoder layers.Llama-Poro-2-8B-Instruct: official model card |
| License | Llama 3.3 Community License.Llama-Poro-2-8B-Instruct: official model card |
Related models
- Poro 2 8B Long Instruct
LumiOpen · Poro 2 Long
A Finnish and English instruction model derived from the context-extended Poro 2 base.
Launch date not confirmedDownloadable - Poro 2 8B SFT
LumiOpen · Poro 2
An intermediate instruction-tuned Poro 2 8B checkpoint before the final preference-training stage.
Launch date not confirmedResearch releaseDownloadable