update webui and add CLIs

examples/merge_lora/merge.sh

@@ -1,7 +1,7 @@
 #!/bin/bash
 # DO NOT use quantized model or quantization_bit when merging lora weights
 
-CUDA_VISIBLE_DEVICES=0 python ../../src/export_model.py \
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli export \
     --model_name_or_path meta-llama/Llama-2-7b-hf \
     --adapter_name_or_path ../../saves/LLaMA2-7B/lora/sft \
     --template default \

examples/merge_lora/quantize.sh

@@ -1,7 +1,7 @@
 #!/bin/bash
 # NEED TO run `merge.sh` before using this script
 
-CUDA_VISIBLE_DEVICES=0 python ../../src/export_model.py \
+CUDA_VISIBLE_DEVICES=0 llamafactory-cli export \
     --model_name_or_path ../../models/llama2-7b-sft \
     --template default \
     --export_dir ../../models/llama2-7b-sft-int4 \