What's Changed
- doc(README) : add prerequisites by @adriens in #45
- fix: annotation in AsyncClient.embedding by @jingfelix in #145
- Update README.md by @TitanStar73 in #138
- Update README.md link still point legacy url by @veinkr in #135
- remove old options by @mxyng in #152
- add quantization to create requests by @mxyng in #150
Note
Generate and chat options num_gqa, rope_frequency_base, and rope_frequency_scale has been removed.
New Contributors
- @adriens made their first contribution in #45
- @jingfelix made their first contribution in #145
- @TitanStar73 made their first contribution in #138
- @veinkr made their first contribution in #135
Full Changelog: v0.1.9...v0.2.0