Merge branch 'hiyouga:main' into main

Former-commit-id: 131d0bcd554dedd794add7eb3d7b1201cac80e7c

examples/README.md

@@ -28,9 +28,9 @@ examples/
 │   ├── merge.sh: Merge LoRA weights into the pre-trained models
 │   └── quantize.sh: Quantize the fine-tuned model with AutoGPTQ
 ├── inference/
-│   ├── cli_demo.sh: Launch a command line interface with LoRA adapters
-│   ├── api_demo.sh: Launch an OpenAI-style API with LoRA adapters
-│   ├── web_demo.sh: Launch a web interface with LoRA adapters
+│   ├── cli_demo.sh: Chat with fine-tuned model in the CLI with LoRA adapters
+│   ├── api_demo.sh: Chat with fine-tuned model in an OpenAI-style API with LoRA adapters
+│   ├── web_demo.sh: Chat with fine-tuned model in the Web browser with LoRA adapters
 │   └── evaluate.sh: Evaluate model on the MMLU/CMMLU/C-Eval benchmarks with LoRA adapters
 └── extras/
     ├── galore/

examples/merge_lora/merge.sh

@@ -8,4 +8,5 @@ CUDA_VISIBLE_DEVICES=0 python ../../src/export_model.py \
     --finetuning_type lora \
     --export_dir ../../models/llama2-7b-sft \
     --export_size 2 \
+    --export_device cpu \
     --export_legacy_format False