- Now resources of Friendli Dedicated Endpoints can be managed with CLI and SDK. The available resources are `endpoint`, `model`, `team`, and `project`. - Login with CLI is now available. SSO login is also available. - Update on Multi-LoRA checkpoint conversion.
1.2.4
1.2.3
- Support `pydantic` V1 compatibility.
1.2.2
Release Patch Version
- Package dependencies are updated.
1.2.1
- Update package dependencies (no more exact version matching). - Add Mixtral model type - Add a `stop` option to completions and chat completions SDK/CLI.
1.2.0
Features 🌟
1. Distinguish Merged QKV for more precise and efficient handling of query, key, and value transformations. 2. Now LoRA can be applied to the MPT model. 3. Introduced support for Mixtral model checkpoint conversion.
Bug Fixes and Improvements 🐛🔨
1. AWQ bug during using gpt-j. 2. Addressed a critical issue where CUDA Out of Memory (OOM) errors occurred while using AWQ. 3. Minor update to phi model type.