Architecture
data/models.yaml. Every label is auditable
against the model's sources.
Specs
- Architecture
- unknown
- Total params
- not disclosed
- Active params
- not disclosed
- Context window
- 128K tokens
- Attention
- unknown
- Position encoding
- unknown
- Post-training
- rlhf
- OSI-approved
- no
- Data released
- no
- Training code
- not released
Available quantizations
None. The weights are not distributed, so there are no public quantizations.
Notable innovations
- · Largest publicly accessible OpenAI non-reasoning model at release
- · Multilingual MMLU coverage across 15 languages