v0.4.0

What's new in 0.4.0 (2023-09-06)

These are the changes in inference v0.4.0.

New features

• FEAT: Support CodeLlama-Instruct by @jiayini1119 in #414
• FEAT: Add embedding models support by @aresnow1 in #418
• FEAT: Support replica by @codingl2k1 in #410
• FEAT: support baichuan2 by @UranusSeven in #425

Bug fixes

• BUG: cmdline chat duplicates user msg by @UranusSeven in #428
• BUG: llama_cpp model context length by @UranusSeven in #429

Documentation

• DOC: update readme by @UranusSeven in #423

New Contributors

• @codingl2k1 made their first contribution in #410

Full Changelog: v0.3.0...v0.4.0