update README (#40)

README.md

@@ -23,9 +23,13 @@ FastFold provides a **high-performance implementation of Evoformer** with the fo
 
 You will need Python 3.8 or later and [NVIDIA CUDA](https://developer.nvidia.com/cuda-downloads) 11.1 or above when you are installing from source. 
 
+```shell
+git clone https://github.com/hpcaitech/FastFold
+cd FastFold
+```
 We highly recommend installing an Anaconda or Miniconda environment and install PyTorch with conda:
 
-```
+```shell
 conda env create --name=fastfold -f environment.yml
 conda activate fastfold
 bash scripts/patch_openmm.sh
@@ -34,8 +38,6 @@ bash scripts/patch_openmm.sh
 You can get the FastFold source and install it with setuptools:
 
 ```shell
-git clone https://github.com/hpcaitech/FastFold
-cd FastFold
 python setup.py install
 ```
 
@@ -56,6 +58,11 @@ from fastfold.distributed import init_dap
 init_dap(args.dap_size)
 ```
 
+### Download the dataset
+You can down the dataset used to train FastFold  by the script `download_all_data.sh`:
+
+    ./scripts/download_all_data.sh data/
+
 ### Inference
 
 You can use FastFold with `inject_fastnn`. This will replace the evoformer from OpenFold with the high performance evoformer from FastFold.

environment.yml

@@ -16,7 +16,9 @@ dependencies:
       - typing-extensions==3.10.0.2
       - einops
       - colossalai
-  - pytorch::pytorch=1.11.0
+      - --find-links https://download.pytorch.org/whl/cu113/torch_stable.html torch==1.11.1+cu113
+      - --find-links https://download.pytorch.org/whl/cu113/torch_stable.html torchaudio==0.11.1+cu113
+      - --find-links https://download.pytorch.org/whl/cu113/torch_stable.html torchvision==0.13.1
   - conda-forge::python=3.8
   - conda-forge::setuptools=59.5.0
   - conda-forge::pip

requirements.txt

+--find-links https://download.pytorch.org/whl/cu113/torch_stable.html
+torch==1.12.1+cu113 
+torchaudio==0.12.1+cu113
+torchvision==0.13.1
 einops
-colossalai
+colossalai==0.1.8
\ No newline at end of file