added performance and tips

README.md

@@ -29,6 +29,14 @@ Available models:
 - CodeLlama-34B-Instruct with function calling ([Base Model](https://huggingface.co/Trelis/CodeLlama-34b-Instruct-hf-function-calling-v2)), ([PEFT Adapters](https://huggingface.co/Trelis/CodeLlama-34b-Instruct-hf-function-calling-adapters-v2)) - Paid, [purchase here: €44.99 per user/seat.](https://buy.stripe.com/cN27teg8t2Hx5sA8wM)
 - Llama-70B-chat with function calling ([Base Model](https://huggingface.co/Trelis/Llama-2-70b-chat-hf-function-calling-v2)), ([PEFT Adapters](https://huggingface.co/Trelis/Llama-2-70b-chat-hf-function-calling-adapters-v2)) - Paid, [purchase here: €99 per user/seat.](https://buy.stripe.com/8wMdRC1dzci75sA4gy)
 
+## Performance and Tips
+
+1. Larger models are better at handling function calling. The cross entropy training losses are approximately 0.5 for 7B, 0.4 for 13B, 0.3 for 70B. The absolute numbers don't mean anything but the relative values offer a sense of relative performance.
+1. Provide very clear function descriptions, including whether the arguments are required or what the default values should be.
+1. Make sure to post-process the language model's response to check that all necessary information is provided by the user. If not, prompt the user to let them know they need to provide more info (e.g. their name, order number etc.)
+
+Check out this video overview of performance [here](https://www.loom.com/share/8d7467de95e04af29ff428c46286946c?sid=683c970e-6063-4f1e-b184-894cc1d96115)
+
 ## Licensing
 
 Llama-7B with function calling is licensed according to the Meta Community license.