Merge pull request #77 from ZhikangNiu/main

Add Dockerfile & fix README bug

Dockerfile

@@ -0,0 +1,41 @@
+FROM pytorch/pytorch:2.1.0-cuda11.8-cudnn8-runtime
+
+USER root
+
+ARG DEBIAN_FRONTEND=noninteractive
+
+LABEL github_repo="https://github.com/ddlBoJack/SLAM-LLM"
+
+RUN set -x \
+    && apt-get update \
+    && apt-get -y install wget curl man git less openssl libssl-dev unzip unar build-essential aria2 tmux vim ninja-build\
+    && apt-get install -y openssh-server sox libsox-fmt-all libsox-fmt-mp3 libsndfile1-dev ffmpeg \
+    && rm -rf /var/lib/apt/lists/* \
+    && apt-get clean
+
+RUN pip install --no-cache-dir packaging editdistance gpustat wandb einops debugpy tqdm soundfile matplotlib scipy sentencepiece pandas \
+    && pip install --no-cache-dir torchaudio==2.1.0 --index-url https://download.pytorch.org/whl/cu118
+
+WORKDIR /workspace
+
+RUN git clone https://github.com/huggingface/transformers.git \
+    && cd transformers \
+    && git checkout tags/v4.35.2 \
+    && pip install --no-cache-dir -e .
+
+RUN git clone https://github.com/huggingface/peft.git \
+    && cd peft \
+    && git checkout tags/v0.6.0 \
+    && pip install --no-cache-dir -e .
+
+RUN git clone https://github.com/pytorch/fairseq \
+    && cd fairseq \
+    && pip install --no-cache-dir --editable ./
+
+RUN git clone https://github.com/ddlBoJack/SLAM-LLM.git \
+    && cd SLAM-LLM \
+    && pip install --no-cache-dir -e .
+
+ENV SHELL=/bin/bash
+
+WORKDIR /workspace/SLAM-LLM

README.md

@@ -43,22 +43,30 @@ pip install -e .
 cd ..
 git clone https://github.com/huggingface/peft.git
 cd peft
-git checkout tags/0.6.0
+git checkout tags/v0.6.0
 pip install -e .
 cd ..
 pip install torch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2 --index-url https://download.pytorch.org/whl/cu118
-git clone git@github.com:ddlBoJack/SLAM-LLM.git
+git clone https://github.com/ddlBoJack/SLAM-LLM.git
 cd SLAM-LLM
 pip install  -e .
 ```
 
 For some examples, you may need to use `fairseq`, the command line is as follows:
 ```
+# you need to install fairseq before SLAM-LLM
 git clone https://github.com/pytorch/fairseq
 cd fairseq
 pip install --editable ./
 ```
+We also provide a docker image for convenience:
+```shell
+# build docker image
+docker build -t slam-llm:latest .
 
+# run docker image with gpu
+docker run -it --gpus all --name slam --shm-size=256g slam-llm:latest /bin/bash
+```
 # Usage
 ## List of Recipes
 We provide reference implementations of various LLM-based speech, audio, and music tasks: 
@@ -88,4 +96,4 @@ command-line (shell file) > Hydra configuration (yaml file) > dataclass configur
 # Acknowledge
 - We borrow code from [Llama-Recipes](https://github.com/meta-llama/llama-recipes) for the training process. 
 - We borrow code from [Fairseq](https://github.com/facebookresearch/fairseq) for deepspeed configuration. 
-- We thank the contributors for providing diverse recipes. 
+- We thank the contributors for providing diverse recipes.