This repository has been archived by the owner on Aug 16, 2024. It is now read-only.
Releases: mikecovlee/mLoRA
Releases · mikecovlee/mLoRA
0.5.2
0.5.1
What's Changed
- [feature] sync patches from transformers by @mikecovlee in #93
Full Changelog: 0.5.0...0.5.1
0.5.0.post1
- Fix Dockerfile
Full Changelog: 0.5.0...0.5.0.post1
0.5.0
What's Changed
- [feature] support variety of Mixture of LoRA Experts PEFT methods by @mikecovlee in #92
Full Changelog: 0.4.6...0.5.0
0.4.6
What's Changed
- [feature] phi-3 model support by @Pherenice1125 in #90
- [tests] add MixLoRA test by @mikecovlee in #91
New Contributors
- @Pherenice1125 made their first contribution in #90
Full Changelog: 0.4.5...0.4.6
0.4.5
What's Changed
- [enhancement] refactoring for better usability by @mikecovlee in #87
- [bugfix] fix auto evaluation by @mikecovlee in #88
Full Changelog: 0.4.4...0.4.5
0.4.4
What's Changed
- [feature] support CommonSenseQA dataset by @mikecovlee in #84
- [feature] support LLaMA 3.1 model by @mikecovlee in #85
- [feature] support PubMedQA by @mikecovlee in #86
Full Changelog: 0.4.3...0.4.4
0.4.3
What's Changed
- Fix generate cache of GLM models. by @mikecovlee in #82
- Refactoring Entry Points of m-LoRA by @mikecovlee in #83
Full Changelog: 0.4.2...0.4.3