* Add new file org structure
* Add new notebooks to quickstart on Mac and via HF
* consolidate all images in a top-level folder
* Update main README
* Remove "news" section from main README
* rename HF Trainer finetuning notebook and add detail to README

Co-authored-by: Navyata Bawa <bnavyata@fb.com>
Co-authored-by: Hamid Shojanazeri <hamid.nazeri2010@gmail.com>

Updating the AWS Prompt_Engineering Notebook + Adding an Example of ReAct with Llama 2 on Bedrock (#386)

Updated minor typos/fixes from reviewer comments

quick whitepaper reference added to the INST Prompt Tags section

+ making sure the attribution was added back in

Short explanation of ReAct
Setup and configuration to use Amazon Bedrock
Example of using the Bedrock api via langchain
Setup for use of DuckDuckGoSearchRun, WikipediaAPIWrapper, and PythonREPL.
Created a pattern for the model to follow in order to use the tools and do reasoning similar to CoT.
Cleaned up and formatted the generated text before giving it to the corresponding tool.

Added in a section to help better understand how to use the [INST] tags, updated some examples, and added reference to the Deeplearning.AI Prompt Engineering course

Gradio web interface is used in examples/inference.py, so we need to
add gradio to requirements.txt.

Quick update to make sure we include the codellama 70b models and llama guard model

Update for clarity

Co-authored-by: Hamid Shojanazeri <hamid.nazeri2010@gmail.com>

Making sure we also list the base model

Co-authored-by: Hamid Shojanazeri <hamid.nazeri2010@gmail.com>

Added a version of the Prompt Engineering with Llama 2 that utilizes Amazon Bedrock
Added a getting started with Llama 2 on Amazon Bedrock which should help developers quickly get started with some reference documentation, setting up credentials, and ultimately using the bedrock client and client_runtime to perform a couple examples and show the diff between prompts run against Llama 2 13b chat vs Llama 2 70b chat