From 3814abf95a2317803ce65116a2d9fe418810c016 Mon Sep 17 00:00:00 2001 From: Wang Date: Mon, 9 Oct 2023 12:57:28 +0800 Subject: [PATCH] add instruction for chat.py --- docker/llm/inference/cpu/docker/Dockerfile | 3 ++- docker/llm/inference/cpu/docker/README.md | 10 ++++++++++ 2 files changed, 12 insertions(+), 1 deletion(-) diff --git a/docker/llm/inference/cpu/docker/Dockerfile b/docker/llm/inference/cpu/docker/Dockerfile index 80747466..4cc05c2d 100644 --- a/docker/llm/inference/cpu/docker/Dockerfile +++ b/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"] \ No newline at end of file diff --git a/docker/llm/inference/cpu/docker/README.md b/docker/llm/inference/cpu/docker/README.md index 805cfc07..589fe32c 100644 --- a/docker/llm/inference/cpu/docker/README.md +++ b/docker/llm/inference/cpu/docker/README.md @@ -32,3 +32,13 @@ 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'. + +To run chat.py: +``` +cd /root +python chat.py --model-path YOUR_MODEL_PATH +```