Languagemodels

Fixed

- Correct issue causing `choices` to be scored improperly

Added

- CUDA 12 support

Fixed

- Run embedding models on CPU to work around memory copy issue

Changed

- Improve embedding search performance

Added

- Add openchat-3.5-0106 model
- Add h2o-danube-1.8b-chat model

Changed

- Simplified dialogstudio system message

Fixed

- Correct missing instruction in openchat prompt

Changed

- Improved search speed when searching many documents
- Reduce memory usage for large document embeddings
- Updated to TinyLlama Chat v1.0
- Remove auto model scaling on Colab
- Correct phi-1.5 prompt format
- Correct model license metadata

Added

- Add Mistral-7B-Instruct-v0.2 model
- Add openchat-3.5-1210 model
- Add phi-2 model
- Support static batching by passing lists to `do`
- Support choices list on `do` to restrict possible outputs