Hybrid H3-2.7B
Stanford UniversityUniversity at BuffaloLanguage modeling/generationQuestion answeringOpen weights
Hybrid H3-2.7B is a language modeling/generation model from Stanford University,University at Buffalo released in 2022 with 2700000000.0 parameters.
About Hybrid H3-2.7B
State space models (SSMs) have demonstrated state-of-the-art sequence modeling performance in some modalities, but underperform attention in language modeling. Moreover, despite scaling nearly linearly in sequence length instead of quadratically, SSM
Details
- Provider
- Stanford University,University at Buffalo
- Task
- Language modeling/generation,Question answering
- Parameters
- 2700000000.0
- Released
- 2022-12-28
- Open weights
- Yes