Poro 2 70B SFT
Poro 2 70B SFT is the intermediate instruction-tuned derivative of Poro 2 70B Base. It has not received the final preference-tuning stage.
Research release
Model design and training
The bilingual instruction collection includes Tulu-derived examples, generated multi-turn conversations, OpenAssistant material and translation pairs. Supervised training runs for two epochs. The card recommends the final Instruct model for most users and retains SFT for comparison of post-training methods.Llama-Poro-2-70B-SFT: official model card
Practical assessment
Practical guidance. The 70B SFT release lets researchers compare preference training at the larger model size. Its responses should not be assumed to match the final Instruct model. Choose it because the intermediate training state matters to the study, not simply because its file is available.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Status | Research release |
| Access | Downloadable |
| Model identifiers | Llama-Poro-2-70B-SFT |
| Context window | 8,192 tokens Sequence length reported by this release's model card; this is not a guaranteed useful retrieval length. Llama-Poro-2-70B-SFT: official model card |
| Model size | 70.55 billion parameters; 80 decoder layers.Llama-Poro-2-70B-SFT: official model card |
| License | Llama 3.3 Community License, as specified for this derivative.Llama-Poro-2-70B-SFT: official model card |
Related models
- Poro 2 70B Base
LumiOpen · Poro 2
A Llama 3.1 70B derivative with continued pretraining for Finnish, English, code and mathematics.
Launch date not confirmedDownloadable - Poro 2 70B Instruct
LumiOpen · Poro 2
A 70B Finnish and English conversation model trained with supervised instructions and Direct Preference Optimization.
Launch date not confirmedDownloadable