Update README.md

README.md

@@ -31,7 +31,11 @@ model = AutoModelForCausalLM.from_pretrained("hiyouga/baichuan-7b-sft", trust_re
 streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
 
 query = "晚上睡不着怎么办"
-template = "A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.\nHuman: {}\nAssistant: "
+template = (
+    "A chat between a curious user and an artificial intelligence assistant. "
+    "The assistant gives helpful, detailed, and polite answers to the user's questions.\n"
+    "Human: {}\nAssistant: "
+)
 
 inputs = tokenizer([template.format(query)], return_tensors="pt")
 inputs = inputs.to("cuda")
@@ -41,7 +45,7 @@ generate_ids = model.generate(**inputs, max_new_tokens=256, streamer=streamer)
 You could also alternatively launch a CLI demo by using the script in https://github.com/hiyouga/LLaMA-Efficient-Tuning
 
 ```bash
-python src/cli_demo.py --model_name_or_path hiyouga/baichuan-7b-sft
+python src/cli_demo.py --template default --model_name_or_path hiyouga/baichuan-7b-sft
 ```
 
 ---
@@ -49,10 +53,12 @@ python src/cli_demo.py --model_name_or_path hiyouga/baichuan-7b-sft
 You could reproduce our results with the following scripts using [LLaMA-Efficient-Tuning](https://github.com/hiyouga/LLaMA-Efficient-Tuning):
 
 ```bash
-CUDA_VISIBLE_DEVICES=0 python src/train_sft.py \
+CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
+    --stage sft \
     --model_name_or_path baichuan-inc/baichuan-7B \
     --do_train \
     --dataset alpaca_gpt4_en,alpaca_gpt4_zh,codealpaca \
+    --template default \
     --finetuning_type lora \
     --lora_rank 16 \
     --lora_target W_pack,o_proj,gate_proj,down_proj,up_proj \
@@ -80,4 +86,4 @@ Loss curve on training set:
 ![train](assets/training_loss.svg)
 
 Loss curve on evaluation set:
-![eval](assets/eval_loss.svg)
+![eval](assets/eval_loss.svg)