Releases: friendliai/friendli-client
Releases · friendliai/friendli-client
Release v1.3.5 🚀
- Optimize CPU RAM usage during quantization with offloading
- Support FP8 conversion for DBRX, Mixtral, and Command R+
Release v1.3.4 🚀
- Hotfix for LoRA checkpoint saving error.
Release v1.3.3 🚀
New Features
- FP8 Checkpoint Conversion: We've introduced a new feature for FP8 checkpoint conversion.
- Sharded Safetensors Checkpoint Saving: Added the ability to save sharded safetensors checkpoints.
- LoRA Support on Mistral Model: We have added support for LoRA (Low-Rank Adaptation) on the Mistral model.
Bug Fixes
- BF16 Hotfix: Addressed an urgent issue with bf16 processing.
- BFloat Safetensors Conversion: Fixed an issue related to bfloat conversion for safetensors.
- Automatic Token Refresh: Resolved a bug affecting automatic token refresh.
Release v1.3.2 🚀
- Add
base_model_name_or_path
option tofriendli model convert-adapter
. - Remove stale dependencies.
Release v1.3.1 🚀
- Update protobuf schema.
- Patch sending API requests with content type
application/protobuf
.
Release v1.3.0 🚀
- Now resources of Friendli Dedicated Endpoints can be managed with CLI and SDK. The available resources are
endpoint
,model
,team
, andproject
. - Login with CLI is now available. SSO login is also available.
- Update on Multi-LoRA checkpoint conversion.
Release v1.2.4 🚀
Patch Version v1.2.3
- Distribute a Python package as type hinted.
Release v1.2.3 🚀
Patch Version v1.2.3
- Support
pydantic
V1 compatibility.
Release v1.2.2 🚀
Release Patch Version
- Package dependencies are updated.
Release v1.2.1 🚀
Release Patch Version v1.2.1
- Update package dependencies (no more exact version matching).
- Add Mixtral model type
- Add a
stop
option to completions and chat completions SDK/CLI.