add llama acs notebook (#2430)

* copy acs notebook

* add docker

* add ncd score.py

* remove monitoring

* add acs

* add safety

* update score to support chunk

* update input and fix score.py

* move asc client to init

* clear output

* support chat bot

* make notebook compatible to chat model

* remove unused

* use 7b as default

* format

* update per comments

* pin model version, use studio to check env status

* add uai creation

* update folder structure

* handle -chat input

* format json

* rename nb

* fix input

* remove junk

sdk/python/foundation-models/system/inference/text-generation/llama-files/docker_env/Dockerfile

@@ -0,0 +1,18 @@
+FROM mcr.microsoft.com/azureml/openmpi4.1.0-ubuntu20.04:20230620.v1
+
+ENV CONDA_ENVIRONMENT_PATH /azureml-envs/llama
+
+# Prepend path to AzureML conda environment
+ENV PATH $CONDA_ENVIRONMENT_PATH/bin:$PATH
+
+# Create conda environment
+COPY conda_dependencies.yaml .
+RUN conda env create -p $CONDA_ENVIRONMENT_PATH -f conda_dependencies.yaml -q && \
+    rm conda_dependencies.yaml && \
+    conda run -p $CONDA_ENVIRONMENT_PATH pip cache purge && \
+    conda clean -a -y
+
+RUN pip freeze
+
+# This is needed for mpi to locate libpython
+ENV LD_LIBRARY_PATH $CONDA_ENVIRONMENT_PATH/lib:$LD_LIBRARY_PATH

sdk/python/foundation-models/system/inference/text-generation/llama-files/docker_env/conda_dependencies.yaml

@@ -0,0 +1,17 @@
+channels:
+- conda-forge
+dependencies:
+- python=3.8.16
+- pip<=23.1.2
+- pip:
+  - mlflow<3,>=2.3
+  - azureml-evaluate-mlflow==0.0.18.post1
+  - cloudpickle==2.2.1
+  - torch==2.0.1
+  - transformers==4.30.1
+  - azure-ai-contentsafety==1.0.0b1
+  - azureml-inference-server-http~=0.8.0
+  - xformers==0.0.20
+  - aiolimiter==1.1.0
+  - azure-ai-mlmonitoring==0.1.0a3
+name: mlflow-env