# This repo shows how to convert a fairseq NLLB-MoE model to transformers and run a forward pass 

As the `fairseq` repository is not really optimised to run inference out-of-the-box, make sure you have a very very big CPU/GPU RAM. 
Around 600 GB are required to run an inference with the `fairseq` model, as you need to load the checkpoints (\~300GB) then build the model (\~300GB again), then finally you can load the checkpoints in the model.

## 0. Download the original checkpoints:
The checkpoints in this repository were obtained using the following command (ased on the instructions given on the fairseq repository): 
```bash
wget --trust-remote-name path_to_nllb
tar -cf model.tar.zf
```

The NLLB checkpoints should noz 

## 1. Install PyTorch
Use the following command:
```bash
pip3 install torch==1.10.1+cu113 torchvision==0.11.2+cu113 torchaudio==0.10.1+cu113 -f https://download.pytorch.org/whl/cu113/torch_stable.html
```

## 2. Install fairseq
```bash
git clone https://github.com/facebookresearch/fairseq.git
cd fairscale
git checkout prefetch_fsdp_params_simple
pip3 install -e .
```

## 3. Clone this repo (click top right on "How to clone")

## 4. Run the inference script:
Convert the checkpoints on the fly using the conversion script. `transformers` is required to do this: 
```bash
cd <path/to/cloned/repo>
python3 /home/arthur_huggingface_co/fairseq/weights/checkpoints/convert_nllb_moe_sharded_original_checkpoint_to_pytorch.py --pytorch_dump_folder_path <dump_folder> --nllb_moe_checkpoint_path <nllb_checkpoint_path>
```
## 4. Run the inference script:
```bash
cd <path/to/cloned/repo>
bash run.sh
```