support mllm hf inference

Former-commit-id: 2c7c01282acd7ddabbb17ce3246b8dae4bc4b8cf

examples/lora_single_gpu/sft_mllm.sh

@@ -0,0 +1,33 @@
+#!/bin/bash
+
+CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
+    --stage sft \
+    --do_train \
+    --model_name_or_path llava-hf/llava-1.5-7b-hf \
+    --visual_inputs \
+    --dataset mllm_demo \
+    --dataset_dir ../../data \
+    --template vicuna \
+    --finetuning_type lora \
+    --lora_target q_proj,v_proj \
+    --output_dir ../../saves/LLaMA2-7B/lora/sft_mllm \
+    --overwrite_cache \
+    --overwrite_output_dir \
+    --cutoff_len 1024 \
+    --preprocessing_num_workers 16 \
+    --per_device_train_batch_size 1 \
+    --per_device_eval_batch_size 1 \
+    --gradient_accumulation_steps 8 \
+    --lr_scheduler_type cosine \
+    --logging_steps 10 \
+    --warmup_steps 20 \
+    --save_steps 100 \
+    --eval_steps 100 \
+    --evaluation_strategy steps \
+    --load_best_model_at_end \
+    --learning_rate 5e-5 \
+    --num_train_epochs 100.0 \
+    --max_samples 3000 \
+    --val_size 0.1 \
+    --plot_loss \
+    --fp16