Update README.md

README.md

@@ -36,11 +36,14 @@ metrics:
 
 ![image info](./plots.png)
 
-**Important remarks:**
-- The quality of the model output might slightly vary compared to the base model.
-- These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in config.json and are obtained after a hardware warmup. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...).
-- You can request premium access to more compression methods and tech support for your specific use-cases [here](https://z0halsaff74.typeform.com/pruna-access?typeform-source=www.pruna.ai).
-- Results mentioning "first" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.
+**Frequently Asked Questions**
+- ***How does the compression work?*** The model is compressed by combining xformers, triton, jit, cuda graphs, tiling, and step caching.
+- ***How does the model quality change?*** The quality of the model output might slightly vary compared to the base model.
+- ***How is the model efficiency evaluated?*** These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in `model/smash_config.json` and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.
+- ***What is the model format?*** We used a custom Pruna model format based on pickle to make models compatible with the compression methods. We provide a tutorial to run models in dockers in the documentation [here](https://pruna-ai-pruna.readthedocs-hosted.com/en/latest/) if needed.
+- ***What is the naming convention for Pruna Huggingface models?*** We take the original model name and append "turbo", "tiny", or "green" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.
+- ***How to compress my own models?*** You can request premium access to more compression methods and tech support for your specific use-cases [here](https://z0halsaff74.typeform.com/pruna-access?typeform-source=www.pruna.ai).
+- ***What are "first" metrics?*** Results mentioning "first" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.
 
 ## Setup