Initial refactoring for `stateless_llama.py` #6

	name: Test Llama End to End

	on:
	workflow_dispatch:
	pull_request:
	push:
	branches:
	- refactor-stateless_llama.py

	jobs:
	test-llama:
	strategy:
	matrix:
	version: [3.11]
	os: [xida-cpu-0]

	runs-on: [self-hosted]
	steps:

	- name: "Checkout Code"
	uses: actions/checkout@v2

	- name: Sync source deps
	run: \|
	python -m pip install --upgrade pip
	# Note: We install in three steps in order to satisfy requirements
	# from non default locations first. Installing the PyTorch CPU
	# wheels saves multiple minutes and a lot of bandwidth on runner setup.
	pip install --index-url https://download.pytorch.org/whl/cpu \
	-r pytorch-cpu-requirements.txt \
	-r torchvision-requirements.txt
	pip install --upgrade -r requirements.txt
	pip install -e .[testing]

	- name: Run vmfb comparison test
	run: \|
	pytest tests/custom_models/stateless_llama/vmfb_comparison_test.py

	- name: Run chat init test
	run: \|
	pytest tests/custom_models/stateless_llama/chat_init_test.py

Provide feedback