From 2eba0ea20fa8a36cd973fe233cf9cad00e09718b Mon Sep 17 00:00:00 2001
From: kingkingofall <83848390+kingkingofall@users.noreply.github.com>
Date: Tue, 4 Apr 2023 13:31:17 +0800
Subject: [PATCH 1/2] fix stage 2

fix stage 2
---
 applications/Chat/examples/README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/applications/Chat/examples/README.md b/applications/Chat/examples/README.md
index 49401ec30db5..6c02606eab93 100644
--- a/applications/Chat/examples/README.md
+++ b/applications/Chat/examples/README.md
@@ -57,7 +57,7 @@ You can run the `examples/train_rm.sh` to start a reward model training.
 
 You can also use the following cmd to start training a reward model.
 ```
-torchrun --standalone --nproc_per_node=4 train_reward_model.py
+torchrun --standalone --nproc_per_node=4 train_reward_model.py \
     --pretrain "/path/to/LLaMa-7B/" \
     --model 'llama' \
     --strategy colossalai_zero2 \

From 241478ac0ae44aebdec98c78736632b87ed67250 Mon Sep 17 00:00:00 2001
From: kingkingofall <83848390+kingkingofall@users.noreply.github.com>
Date: Wed, 5 Apr 2023 10:08:24 +0800
Subject: [PATCH 2/2] add torch

---
 applications/Chat/inference/README.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/applications/Chat/inference/README.md b/applications/Chat/inference/README.md
index 6c23bc73cd60..434677c98fa5 100644
--- a/applications/Chat/inference/README.md
+++ b/applications/Chat/inference/README.md
@@ -51,6 +51,7 @@ Please ensure you have downloaded HF-format model weights of LLaMA models.
 Usage:
 
 ```python
+import torch
 from transformers import LlamaForCausalLM
 
 USE_8BIT = True # use 8-bit quantization; otherwise, use fp16