support vllm

Former-commit-id: 889f6e910e654d8ec3922c2185042d737ffbf1c3

examples/lora_single_gpu/README.md

@@ -1,5 +1,8 @@
 Usage:
 
-- `pretrain.sh`
-- `sft.sh` -> `reward.sh` -> `ppo.sh`
-- `sft.sh` -> `dpo.sh` -> `predict.sh`
+- `pretrain.sh`: do pre-train (optional)
+- `sft.sh`: do supervised fine-tune
+- `reward.sh`: do reward modeling (must after sft.sh)
+- `ppo.sh`: do PPO training (must after sft.sh and reward.sh)
+- `dpo.sh`: do DPO training (must after sft.sh)
+- `predict.sh`: do predict (must after sft.sh and dpo.sh)

examples/merge_lora/README.md

@@ -1,3 +1,4 @@
 Usage:
 
-- `merge.sh` -> `quantize.sh`
+- `merge.sh`: merge the lora weights
+- `quantize.sh`: quantize the model with AutoGPTQ (must after merge.sh, optional)

examples/merge_lora/merge.sh

@@ -1,6 +1,6 @@
 #!/bin/bash
 
-python ../../src/export_model.py \
+CUDA_VISIBLE_DEVICES=0 python ../../src/export_model.py \
     --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

@@ -1,6 +1,6 @@
 #!/bin/bash
 
-python ../../src/export_model.py \
+CUDA_VISIBLE_DEVICES=0 python ../../src/export_model.py \
     --model_name_or_path ../../models/llama2-7b-sft \
     --template default \
     --export_dir ../../models/llama2-7b-sft-int4 \