Update README.md

README.md

@@ -25,7 +25,7 @@ license: mit
     <sup>2</sup>Microsoft Research, Redmond
 </div>
 
-This weight is for **initilizing training for Otter-MPT7B**. It's directly converted from [Openflamingov2](https://huggingface.co/openflamingo/OpenFlamingo-9B-vitl-mpt7b), we added a `<answer>` token for Otter's downstream instruction tuning.
+This weight is for **initilizing training for Otter**. It's directly converted from Openflamingo.
 
 You can load and try this model using
 ```python
@@ -36,4 +36,27 @@ image_processor = transformers.CLIPImageProcessor()
 model.eval()
 ```
 
-Leave us a message if you have any error or question. You can follow [Otter code](https://github.com/Luodian/Otter) (see training section) to further tune your model on top of it.
+You can also start training Otter via the commands
+```python
+python -m accelerate.commands.launch --config_file=./pipeline/accelerate_configs/accelerate_config_fsdp.yaml \
+pipeline/train/instruction_following.py \
+--pretrained_model_name_or_path=luodian/OTTER-MPT7B-Init \
+--mimicit_path=/data/azure_storage/otter/mimicit/xx/xx_instructions.json \
+--images_path=/data/azure_storage/otter/mimicit/xx/xx.json \
+--batch_size=4 --num_epochs=1 --report_to_wandb \
+--wandb_entity=ntu-slab \
+--external_save_dir=/data/bli/checkpoints \
+--save_hf_model \
+--run_name=OTTER-MPT1B \
+--wandb_project=OTTER-MPT1B \
+--workers=4 \
+--lr_scheduler=cosine \
+--learning_rate=1e-5 \
+--warmup_steps_ratio=0.01
+```
+
+If you wish to init a video instruction tuning, you should add 
+```json
+"max_num_frames": 128
+```
+to `config.json` inside the folder.