Update README.md

README.md

@@ -108,13 +108,15 @@ Pre-requisite: You would need at least a machine with 4 40GB or 2 80GB NVIDIA GP
    ```
    
 7. Run Docker container
+   (In addition, to use Llama3 tokenizer, you need to ```export HF_HOME=<YOUR_HF_HOME_CONTAINING_TOKEN_WITH_LLAMA3_70B_ACCESS>```)
    ```
-   docker run --gpus all -it --rm --shm-size=300g -p 8000:8000 -v ${PWD}/Llama3-70B-PPO-Chat.nemo:/opt/checkpoints/Llama3-70B-PPO-Chat.nemo -w /opt/NeMo nvcr.io/ea-bignlp/ga-participants/nemofw-inference:23.10
+   docker run --gpus all -it --rm --shm-size=300g -p 8000:8000 -v ${PWD}/Llama3-70B-PPO-Chat.nemo:/opt/checkpoints/Llama3-70B-PPO-Chat.nemo,${HF_HOME}:/hf_home -w /opt/NeMo nvcr.io/ea-bignlp/ga-participants/nemofw-inference:23.10
    ```
+   
 8. Within the container, start the server in the background. This step does both conversion of the nemo checkpoint to TRT-LLM and then deployment using TRT-LLM. For an explanation of each argument and advanced usage, please refer to [NeMo FW Deployment Guide](https://docs.nvidia.com/nemo-framework/user-guide/latest/deployingthenemoframeworkmodel.html)
    
    ```
-   python scripts/deploy/deploy_triton.py --nemo_checkpoint /opt/checkpoints/Llama3-70B-PPO-Chat.nemo --model_type="llama" --triton_model_name Llama3-70B-PPO-Chat --triton_http_address 0.0.0.0 --triton_port 8000 --num_gpus 2 --max_input_len 3072 --max_output_len 1024 --max_batch_size 1 &
+   HF_HOME=/hf_home python scripts/deploy/deploy_triton.py --nemo_checkpoint /opt/checkpoints/Llama3-70B-PPO-Chat.nemo --model_type="llama" --triton_model_name Llama3-70B-PPO-Chat --triton_http_address 0.0.0.0 --triton_port 8000 --num_gpus 2 --max_input_len 3072 --max_output_len 1024 --max_batch_size 1 &
    ```
    
 9. Once the server is ready (i.e. when you see this messages below), you are ready to launch your client code