├── .gitignore ├── .pre-commit-config.yaml ├── LICENSE ├── README.md ├── course ├── __init__.py ├── evaluate.py ├── models.py ├── plots.py └── slides.py ├── exercises ├── 01-analyze_llm_architectures.ipynb ├── 02-run_llm_cpu_vs_gpu.ipynb ├── 03-measure_llm_efficiency.ipynb ├── 04-benchmark_llm_quantization_methods.ipynb ├── 05-benchmark_llm_bits.ipynb ├── 06-use_data_llm_quantization.ipynb └── 07-finetune_llm.ipynb ├── projects └── README.md ├── pyproject.toml ├── scripts ├── add_colab_buttons.py └── sync_notebooks.py ├── setup_exercises.sh ├── slides ├── 00-introduction.pdf ├── 01-language_model_architectures.pdf ├── 02-compress_language_models.pdf ├── 03-evaluate_language_models.pdf ├── 04-quantize_language_models.pdf ├── 05-finetune_language_models.pdf ├── README.md └── __init__.py ├── solutions ├── 01-analyze_llm_architectures.ipynb ├── 02-run_llm_cpu_vs_gpu.ipynb ├── 03-measure_llm_efficiency.ipynb ├── 04-benchmark_llm_quantization_methods.ipynb ├── 05-benchmark_llm_bits.ipynb ├── 06-use_data_llm_quantization.ipynb └── 07-finetune_llm.ipynb └── uv.lock /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/.gitignore -------------------------------------------------------------------------------- /.pre-commit-config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/.pre-commit-config.yaml -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/README.md -------------------------------------------------------------------------------- /course/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/course/__init__.py -------------------------------------------------------------------------------- /course/evaluate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/course/evaluate.py -------------------------------------------------------------------------------- /course/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/course/models.py -------------------------------------------------------------------------------- /course/plots.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/course/plots.py -------------------------------------------------------------------------------- /course/slides.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/course/slides.py -------------------------------------------------------------------------------- /exercises/01-analyze_llm_architectures.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/exercises/01-analyze_llm_architectures.ipynb -------------------------------------------------------------------------------- /exercises/02-run_llm_cpu_vs_gpu.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/exercises/02-run_llm_cpu_vs_gpu.ipynb -------------------------------------------------------------------------------- /exercises/03-measure_llm_efficiency.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/exercises/03-measure_llm_efficiency.ipynb -------------------------------------------------------------------------------- /exercises/04-benchmark_llm_quantization_methods.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/exercises/04-benchmark_llm_quantization_methods.ipynb -------------------------------------------------------------------------------- /exercises/05-benchmark_llm_bits.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/exercises/05-benchmark_llm_bits.ipynb -------------------------------------------------------------------------------- /exercises/06-use_data_llm_quantization.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/exercises/06-use_data_llm_quantization.ipynb -------------------------------------------------------------------------------- /exercises/07-finetune_llm.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/exercises/07-finetune_llm.ipynb -------------------------------------------------------------------------------- /projects/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/projects/README.md -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/pyproject.toml -------------------------------------------------------------------------------- /scripts/add_colab_buttons.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/scripts/add_colab_buttons.py -------------------------------------------------------------------------------- /scripts/sync_notebooks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/scripts/sync_notebooks.py -------------------------------------------------------------------------------- /setup_exercises.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/setup_exercises.sh -------------------------------------------------------------------------------- /slides/00-introduction.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/slides/00-introduction.pdf -------------------------------------------------------------------------------- /slides/01-language_model_architectures.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/slides/01-language_model_architectures.pdf -------------------------------------------------------------------------------- /slides/02-compress_language_models.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/slides/02-compress_language_models.pdf -------------------------------------------------------------------------------- /slides/03-evaluate_language_models.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/slides/03-evaluate_language_models.pdf -------------------------------------------------------------------------------- /slides/04-quantize_language_models.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/slides/04-quantize_language_models.pdf -------------------------------------------------------------------------------- /slides/05-finetune_language_models.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/slides/05-finetune_language_models.pdf -------------------------------------------------------------------------------- /slides/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/slides/README.md -------------------------------------------------------------------------------- /slides/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/slides/__init__.py -------------------------------------------------------------------------------- /solutions/01-analyze_llm_architectures.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/solutions/01-analyze_llm_architectures.ipynb -------------------------------------------------------------------------------- /solutions/02-run_llm_cpu_vs_gpu.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/solutions/02-run_llm_cpu_vs_gpu.ipynb -------------------------------------------------------------------------------- /solutions/03-measure_llm_efficiency.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/solutions/03-measure_llm_efficiency.ipynb -------------------------------------------------------------------------------- /solutions/04-benchmark_llm_quantization_methods.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/solutions/04-benchmark_llm_quantization_methods.ipynb -------------------------------------------------------------------------------- /solutions/05-benchmark_llm_bits.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/solutions/05-benchmark_llm_bits.ipynb -------------------------------------------------------------------------------- /solutions/06-use_data_llm_quantization.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/solutions/06-use_data_llm_quantization.ipynb -------------------------------------------------------------------------------- /solutions/07-finetune_llm.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/solutions/07-finetune_llm.ipynb -------------------------------------------------------------------------------- /uv.lock: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PrunaAI/ai-efficiency-courses/HEAD/uv.lock --------------------------------------------------------------------------------