Update README.md

README.md

@@ -12,9 +12,14 @@ tags:
 - functions
 - function calling
 ---
-# fLlama 2 - Function Calling Llama 2 - 7B
+# fLlama 2 - Function Calling Llama 2
 
-fLlama 2 extends the hugging face Llama 2 - 7B model with function calling capabilities. It allows users to make function calls within the model's input, making it capable of performing a variety of tasks.
+- fLlama 2 extends the hugging face Llama 2 models with function calling capabilities.
+- The model responds with a structured json argument with the function name and arguments
+
+Available models:
+- fLlama-7B (this repo)
+- [fLlama-13](https://huggingface.co/Trelis/Llama-2-13b-chat-hf-function-calling) - RECOMMENDED. This is a stronger model and handles function calling more accurately.
 
 ## Licensing and Usage
 
@@ -48,22 +53,13 @@ The dataset used for training this model can be found at [Trelis Function Callin
 
 The data may be used for free for commercial and non-commercial use. It is Apache 2 licensed and does not have any dependencies (i.e. does not depend on Meta's Llama license.)
 
-## Inference with HuggingFace 🤗
-
-Ensure you have the `transformers` package installed:
+## Inference with Google Colab and HuggingFace 🤗
 
-```
-pip install transformers
-```
+Get started by saving your own copy of this [fLlama_Inference notebook](https://colab.research.google.com/drive/1Ow5cQ0JNv-vXsT-apCceH6Na3b4L7JyW?usp=sharing).
 
-Then, load the model from HuggingFace's model hub:
+You will be able to run inference using a free Colab notebook if you select a gpu runtime. See the notebook for more details.
 
-```
-from transformers import AutoModelForCausalLM, AutoTokenizer
-
-tokenizer = AutoTokenizer.from_pretrained("Trelis/Llama-2-7b-chat-hf-function-calling")
-model = AutoModelForCausalLM.from_pretrained("Trelis/Llama-2-7b-chat-hf-function-calling")
-```
+## Prompt and Response Format
 
 To make a function call, you should format your input like this: