Pruna AI
company
AI & ML interests
Efficient machine learning for any model and hardware: pruning, quantization, compilation, and more.
Organization Card
About org cards
Simply make AI models faster, cheaper, smaller, greener!
Pruna AI makes, in one line of code, any AI model faster, cheaper, smaller, greener on any hardware. It covers CV, NLP, audio, graphs for predictive and generative AI.
We provide two packages. You can read their documentations to know more here.
pruna
: Package to smash your AI model to make it more efficient without losing quality. For this, you only need to callpruna.smash()
. If you want to compress models on your side, you can request access here.pruna_engine
: Package to run your AI model more efficiently without changing your pipeline. If you want to run models publicly shared on HuggingFace, you can install it from here.
models
1915
PrunaAI/Llama-3-8B-Instruct-Gradient-4194k-GGUF-smashed
Updated
•
1.1k
PrunaAI/gradientai-Llama-3-8B-Instruct-Gradient-4194k-GGUF-smashed
Updated
•
1.04k
PrunaAI/Llama3-ChatQA-1.5-70B-GGUF-smashed
Updated
•
270
PrunaAI/mistral-orthogonalized-GGUF-smashed
Updated
•
153
PrunaAI/cosmicvalor-mistral-orthogonalized-GGUF-smashed
Updated
•
2.22k
PrunaAI/nvidia-Llama3-ChatQA-1.5-70B-GGUF-smashed
Updated
•
349
PrunaAI/Code-Llama-3-8B-GGUF-smashed
Updated
•
174
PrunaAI/ajibawa-2023-Code-Llama-3-8B-GGUF-smashed
Updated
•
883
PrunaAI/google-codegemma-7b-AWQ-4bit-smashed
Text Generation
•
Updated
PrunaAI/google-codegemma-2b-AWQ-4bit-smashed
Text Generation
•
Updated
datasets
None public yet