1.hiyouga / LlamaFactoryUnified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)fine-tuningllamallmpefttransformersrlhf+14 morePythonAPACHE-2.076K total9.3K forks+2,348 starsfrom 73,476 · score 7.76
2.SYSTRAN / faster-whisperFaster Whisper transcription with CTranslate2deep-learninginferencequantizationspeech-recognitionspeech-to-texttransformer+2 morePythonMIT26K total2.2K forks+1,752 starsfrom 24,622 · score 7.47
3.Xilinx / finnDataflow compiler for QNN inference on FPGAsdataflowquantizationfpgacompilerneural-networkPythonBSD-3-CLAUSE1.1K total311 forks+52 starsfrom 1,035 · score 3.97
4.ymcui / Chinese-LLaMA-Alpaca中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)llmplmpre-trained-language-modelsalpacallamanlp+5 morePythonAPACHE-2.019K total1.8K forks+40 starsfrom 18,882 · score 3.71
5.google / qkerasQKeras: a quantization deep learning library for Tensorflow Kerasdeep-learningquantizationquantized-neural-networkshardware-accelerationquantized-networkstensorflow+6 morePythonAPACHE-2.0585 total108 forks+1 starsfrom 584 · score 0.69