add 72B and 1.8B Qwen models, add Ascend 910 and Hygon DCU support, add docker support

finetune/finetune_ds.sh

@@ -2,7 +2,7 @@
 export CUDA_DEVICE_MAX_CONNECTIONS=1
 DIR=`pwd`
 
-GPUS_PER_NODE=8
+GPUS_PER_NODE=$(python -c 'import torch; print(torch.cuda.device_count())')
 NNODES=1
 NODE_RANK=0
 MASTER_ADDR=localhost
@@ -13,6 +13,34 @@ MODEL="Qwen/Qwen-7B" # Set the path if you do not want to load from huggingface
 # See the section for finetuning in README for more information.
 DATA="path_to_data"
 
+function usage() {
+    echo '
+Usage: bash finetune/finetune_ds.sh [-m MODEL_PATH] [-d DATA_PATH]
+'
+}
+
+while [[ "$1" != "" ]]; do
+    case $1 in
+        -m | --model )
+            shift
+            MODEL=$1
+            ;;
+        -d | --data )
+            shift
+            DATA=$1
+            ;;
+        -h | --help )
+            usage
+            exit 0
+            ;;
+        * )
+            echo "Unknown argument ${1}"
+            exit 1
+            ;;
+    esac
+    shift
+done
+
 DISTRIBUTED_ARGS="
     --nproc_per_node $GPUS_PER_NODE \
     --nnodes $NNODES \
@@ -44,4 +72,4 @@ torchrun $DISTRIBUTED_ARGS finetune.py \
     --model_max_length 512 \
     --gradient_checkpointing True \
     --lazy_preprocess True \
-    --deepspeed finetune/ds_config_zero3.json
+    --deepspeed finetune/ds_config_zero3.json