Merge pull request #9108 from Zhengjin-Wang/main

Add instruction for chat.py in bigdl-llm-cpu

docker/llm/inference/cpu/docker/Dockerfile

@@ -22,7 +22,8 @@ RUN env DEBIAN_FRONTEND=noninteractive apt-get update && \
     pip install --pre --upgrade bigdl-llm[all] && \
     pip install --pre --upgrade bigdl-nano && \
 # Download chat.py script
-    wget -P /root https://raw.githubusercontent.com/intel-analytics/BigDL/main/python/llm/portable-executable/chat.py && \
+    pip install --upgrade colorama && \
+    wget -P /root https://raw.githubusercontent.com/intel-analytics/BigDL/main/python/llm/portable-zip/chat.py && \
     export PYTHONUNBUFFERED=1
 
 ENTRYPOINT ["/bin/bash"]

docker/llm/inference/cpu/docker/README.md

@@ -32,3 +32,37 @@ sudo docker run -itd \
 After the container is booted, you could get into the container through `docker exec`.
 
 To run inference using `BigDL-LLM` using cpu, you could refer to this [documentation](https://github.com/intel-analytics/BigDL/tree/main/python/llm#cpu-int4).
+
+### Use chat.py
+
+chat.py can be used to initiate a conversation with a specified model. The file is under directory '/root'.
+
+You can download models and bind the model directory from host machine to container when start a container.
+
+Here is an example:
+```bash
+export DOCKER_IMAGE=intelanalytics/bigdl-llm-cpu:2.4.0-SNAPSHOT
+export MODEL_PATH=/home/llm/models
+
+sudo docker run -itd \
+        --net=host \
+        --cpuset-cpus="0-47" \
+        --cpuset-mems="0" \
+        --memory="32G" \
+        --name=CONTAINER_NAME \
+        --shm-size="16g" \
+        -v $MODEL_PATH:/llm/models/
+        $DOCKER_IMAGE
+
+```
+
+After entering the container through `docker exec`, you can run chat.py by:
+```bash
+cd /root
+python chat.py --model-path YOUR_MODEL_PATH
+```
+In the example above, it can be:
+```bash
+cd /root
+python chat.py --model-path /llm/models/MODEL_NAME
+```