add examples

Former-commit-id: 169c68921b1b8ac279834b060d9e7d38a56fe1aa

examples/README.md

@@ -134,6 +134,12 @@ FORCE_TORCHRUN=1 NNODES=2 RANK=0 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llama
 FORCE_TORCHRUN=1 NNODES=2 RANK=1 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_full/llama3_full_sft_ds3.yaml
 ```
 
+#### Multimodal Supervised Fine-Tuning
+
+```bash
+FORCE_TORCHRUN=1 llamafactory-cli train examples/train_full/qwen2vl_full_sft.yaml
+```
+
 #### Batch Predicting and Computing BLEU and ROUGE Scores
 
 ```bash

examples/README_zh.md

@@ -134,6 +134,12 @@ FORCE_TORCHRUN=1 NNODES=2 RANK=0 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llama
 FORCE_TORCHRUN=1 NNODES=2 RANK=1 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_full/llama3_full_sft_ds3.yaml
 ```
 
+#### 多模态指令监督微调
+
+```bash
+FORCE_TORCHRUN=1 llamafactory-cli train examples/train_full/qwen2vl_full_sft.yaml
+```
+
 #### 批量预测并计算 BLEU 和 ROUGE 分数
 
 ```bash

examples/inference/llava1_5.yaml

@@ -1,3 +1,3 @@
 model_name_or_path: llava-hf/llava-1.5-7b-hf
-template: vicuna
+template: llava
 visual_inputs: true

examples/inference/qwen2_vl.yaml

@@ -0,0 +1,3 @@
+model_name_or_path: Qwen/Qwen2-VL-7B-Instruct
+template: qwen2_vl
+visual_inputs: true

examples/merge_lora/qwen2vl_lora_sft.yaml

@@ -0,0 +1,14 @@
+### Note: DO NOT use quantized model or quantization_bit when merging lora adapters
+
+### model
+model_name_or_path: Qwen/Qwen2-VL-7B-Instruct
+adapter_name_or_path: saves/qwen2_vl-7b/lora/sft
+visual_inputs: true
+template: qwen2_vl
+finetuning_type: lora
+
+### export
+export_dir: models/qwen2_vl_lora_sft
+export_size: 2
+export_device: cpu
+export_legacy_format: false

examples/train_full/qwen2vl_full_sft.yaml

@@ -0,0 +1,40 @@
+### model
+model_name_or_path: Qwen/Qwen2-VL-7B-Instruct
+visual_inputs: true
+
+### method
+stage: sft
+do_train: true
+finetuning_type: full
+deepspeed: examples/deepspeed/ds_z3_config.json
+
+### dataset
+dataset: mllm_demo
+template: qwen2_vl
+cutoff_len: 1024
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+### output
+output_dir: saves/qwen2_vl-7b/full/sft
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+
+### train
+per_device_train_batch_size: 1
+gradient_accumulation_steps: 2
+learning_rate: 1.0e-5
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_ratio: 0.1
+bf16: true
+ddp_timeout: 180000000
+
+### eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+eval_strategy: steps
+eval_steps: 500

examples/train_lora/llava1_5_lora_sft.yaml

@@ -10,7 +10,7 @@ lora_target: all
 
 ### dataset
 dataset: mllm_demo
-template: vicuna
+template: llava
 cutoff_len: 1024
 max_samples: 1000
 overwrite_cache: true