Added test llama-2-7b with GPTQ quant. scheme #56

	name: CLI CPU Py-TXI Tests

	on:
	workflow_dispatch:
	push:
	branches: [main]
	pull_request:
	types: [opened, reopened, synchronize]

	concurrency:
	group: ${{ github.workflow }}-${{ github.event.pull_request.number \|\| github.ref }}
	cancel-in-progress: true

	jobs:
	run_cli_cpu_py_txi_tests:
	runs-on: ubuntu-latest
	steps:
	- name: Free disk space
	uses: jlumbroso/free-disk-space@main
	with:
	dotnet: true
	android: true
	haskell: true
	docker-images: true
	large-packages: false

	- name: Checkout
	uses: actions/checkout@v3

	- name: Set up Python 3.10
	uses: actions/setup-python@v3
	with:
	python-version: "3.10"

	- name: Install requirements
	run: \|
	pip install --upgrade pip
	pip install -e .[testing,py-txi]

	- name: Pull TGI docker image
	run: docker pull ghcr.io/huggingface/text-generation-inference:latest

	- name: Pull TEI docker image
	run: docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-latest

	- name: Run tests
	run: pytest -k "cli and cpu and py_txi"

Provide feedback