add grpo

examples/inference/llama3.yaml

+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+template: llama3
+infer_backend: huggingface  # choices: [huggingface, vllm, sglang]
+trust_remote_code: true

examples/inference/llama3_full_sft.yaml

+model_name_or_path: saves/llama3-8b/full/sft
+template: llama3
+infer_backend: huggingface  # choices: [huggingface, vllm, sglang]
+trust_remote_code: true

examples/inference/llama3_lora_sft.yaml

+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+adapter_name_or_path: saves/llama3-8b/lora/sft
+template: llama3
+infer_backend: huggingface  # choices: [huggingface, vllm, sglang]
+trust_remote_code: true

examples/inference/qwen2_5vl.yaml

+model_name_or_path: Qwen/Qwen2.5-VL-7B-Instruct
+template: qwen2_vl
+infer_backend: huggingface  # choices: [huggingface, vllm, sglang]
+trust_remote_code: true

examples/merge_lora/llama3_full_sft.yaml

+### model
+model_name_or_path: saves/llama3-8b/full/sft
+template: llama3
+trust_remote_code: true
+
+### export
+export_dir: output/llama3_full_sft
+export_size: 5
+export_device: cpu  # choices: [cpu, auto]
+export_legacy_format: false

examples/merge_lora/llama3_gptq.yaml

+### model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+template: llama3
+trust_remote_code: true
+
+### export
+export_dir: output/llama3_gptq
+export_quantization_bit: 4
+export_quantization_dataset: data/c4_demo.jsonl
+export_size: 5
+export_device: cpu  # choices: [cpu, auto]
+export_legacy_format: false

examples/merge_lora/llama3_lora_sft.yaml

+### Note: DO NOT use quantized model or quantization_bit when merging lora adapters
+
+### model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+adapter_name_or_path: saves/llama3-8b/lora/sft
+template: llama3
+trust_remote_code: true
+
+### export
+export_dir: output/llama3_lora_sft
+export_size: 5
+export_device: cpu  # choices: [cpu, auto]
+export_legacy_format: false

examples/merge_lora/qwen2_5vl_lora_sft.yaml

+### Note: DO NOT use quantized model or quantization_bit when merging lora adapters
+
+### model
+model_name_or_path: Qwen/Qwen2.5-VL-7B-Instruct
+adapter_name_or_path: saves/qwen2_5vl-7b/lora/sft
+template: qwen2_vl
+trust_remote_code: true
+
+### export
+export_dir: output/qwen2_5vl_lora_sft
+export_size: 5
+export_device: cpu  # choices: [cpu, auto]
+export_legacy_format: false

examples/train_full/llama3_full_sft.yaml

+### model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+trust_remote_code: true
+
+### method
+stage: sft
+do_train: true
+finetuning_type: full
+deepspeed: examples/deepspeed/ds_z3_config.json  # choices: [ds_z0_config.json, ds_z2_config.json, ds_z3_config.json]
+
+### dataset
+dataset: identity,alpaca_en_demo
+template: llama3
+cutoff_len: 2048
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+dataloader_num_workers: 4
+
+### output
+output_dir: saves/llama3-8b/full/sft
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+save_only_model: false
+report_to: none  # choices: [none, wandb, tensorboard, swanlab, mlflow]
+
+### 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
+resume_from_checkpoint: null
+
+### eval
+# eval_dataset: alpaca_en_demo
+# val_size: 0.1
+# per_device_eval_batch_size: 1
+# eval_strategy: steps
+# eval_steps: 500

examples/train_full/qwen2_5vl_full_sft.yaml

+### model
+model_name_or_path: Qwen/Qwen2.5-VL-7B-Instruct
+image_max_pixels: 262144
+video_max_pixels: 16384
+trust_remote_code: true
+
+### method
+stage: sft
+do_train: true
+finetuning_type: full
+freeze_vision_tower: true
+freeze_multi_modal_projector: true
+freeze_language_model: false
+deepspeed: examples/deepspeed/ds_z3_config.json
+
+### dataset
+dataset: mllm_demo,identity,alpaca_en_demo
+template: qwen2_vl
+cutoff_len: 2048
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+dataloader_num_workers: 4
+
+### output
+output_dir: saves/qwen2_5vl-7b/full/sft
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+save_only_model: false
+report_to: none  # choices: [none, wandb, tensorboard, swanlab, mlflow]
+
+### 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
+resume_from_checkpoint: null
+
+### eval
+# val_size: 0.1
+# per_device_eval_batch_size: 1
+# eval_strategy: steps
+# eval_steps: 500

examples/train_lora/llama3_lora_dpo.yaml

+### model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+trust_remote_code: true
+
+### method
+stage: dpo
+do_train: true
+finetuning_type: lora
+lora_rank: 8
+lora_target: all
+pref_beta: 0.1
+pref_loss: sigmoid  # choices: [sigmoid (dpo), orpo, simpo]
+
+### dataset
+dataset: dpo_en_demo
+template: llama3
+cutoff_len: 2048
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+dataloader_num_workers: 4
+
+### output
+output_dir: saves/llama3-8b/lora/dpo
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+save_only_model: false
+report_to: none  # choices: [none, wandb, tensorboard, swanlab, mlflow]
+
+### train
+per_device_train_batch_size: 1
+gradient_accumulation_steps: 8
+learning_rate: 5.0e-6
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_ratio: 0.1
+bf16: true
+ddp_timeout: 180000000
+resume_from_checkpoint: null
+
+### eval
+# eval_dataset: dpo_en_demo
+# val_size: 0.1
+# per_device_eval_batch_size: 1
+# eval_strategy: steps
+# eval_steps: 500

examples/train_lora/llama3_lora_eval.yaml

+### model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+adapter_name_or_path: saves/llama3-8b/lora/sft
+trust_remote_code: true
+
+### method
+finetuning_type: lora
+
+### dataset
+task: mmlu_test  # choices: [mmlu_test, ceval_validation, cmmlu_test]
+template: fewshot
+lang: en
+n_shot: 5
+
+### output
+save_dir: saves/llama3-8b/lora/eval
+
+### eval
+batch_size: 4

examples/train_lora/llama3_lora_kto.yaml

+### model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+trust_remote_code: true
+
+### method
+stage: kto
+do_train: true
+finetuning_type: lora
+lora_rank: 8
+lora_target: all
+pref_beta: 0.1
+
+### dataset
+dataset: kto_en_demo
+template: llama3
+cutoff_len: 2048
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+dataloader_num_workers: 4
+
+### output
+output_dir: saves/llama3-8b/lora/kto
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+report_to: none  # choices: [none, wandb, tensorboard, swanlab, mlflow]
+
+### train
+per_device_train_batch_size: 1
+gradient_accumulation_steps: 8
+learning_rate: 5.0e-6
+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/llama3_lora_ppo.yaml

+### model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+reward_model: saves/llama3-8b/lora/reward
+trust_remote_code: true
+
+### method
+stage: ppo
+do_train: true
+finetuning_type: lora
+lora_rank: 8
+lora_target: all
+
+### dataset
+dataset: identity,alpaca_en_demo
+template: llama3
+cutoff_len: 2048
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+dataloader_num_workers: 4
+
+### output
+output_dir: saves/llama3-8b/lora/ppo
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+report_to: none  # choices: [none, wandb, tensorboard, swanlab, mlflow]
+
+### train
+per_device_train_batch_size: 1
+gradient_accumulation_steps: 8
+learning_rate: 1.0e-5
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_ratio: 0.1
+bf16: true
+ddp_timeout: 180000000
+
+### generate
+max_new_tokens: 512
+top_k: 0
+top_p: 0.9

examples/train_lora/llama3_lora_pretrain.yaml

+### model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+trust_remote_code: true
+
+### method
+stage: pt
+do_train: true
+finetuning_type: lora
+lora_rank: 8
+lora_target: all
+
+### dataset
+dataset: c4_demo
+cutoff_len: 2048
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+dataloader_num_workers: 4
+
+### output
+output_dir: saves/llama3-8b/lora/pretrain
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+save_only_model: false
+report_to: none  # choices: [none, wandb, tensorboard, swanlab, mlflow]
+
+### train
+per_device_train_batch_size: 1
+gradient_accumulation_steps: 8
+learning_rate: 1.0e-4
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_ratio: 0.1
+bf16: true
+ddp_timeout: 180000000
+resume_from_checkpoint: null
+
+### eval
+# eval_dataset: c4_demo
+# val_size: 0.1
+# per_device_eval_batch_size: 1
+# eval_strategy: steps
+# eval_steps: 500

examples/train_lora/llama3_lora_reward.yaml

+### model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+trust_remote_code: true
+
+### method
+stage: rm
+do_train: true
+finetuning_type: lora
+lora_rank: 8
+lora_target: all
+
+### dataset
+dataset: dpo_en_demo
+template: llama3
+cutoff_len: 2048
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+dataloader_num_workers: 4
+
+### output
+output_dir: saves/llama3-8b/lora/reward
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+save_only_model: false
+report_to: none  # choices: [none, wandb, tensorboard, swanlab, mlflow]
+
+### train
+per_device_train_batch_size: 1
+gradient_accumulation_steps: 8
+learning_rate: 1.0e-4
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_ratio: 0.1
+bf16: true
+ddp_timeout: 180000000
+resume_from_checkpoint: null
+
+### eval
+# eval_dataset: dpo_en_demo
+# val_size: 0.1
+# per_device_eval_batch_size: 1
+# eval_strategy: steps
+# eval_steps: 500

examples/train_lora/llama3_lora_sft.sh

+#!/bin/bash
+
+set -x
+
+MODEL_PATH=meta-llama/Meta-Llama-3-8B-Instruct
+
+llamafactory-cli train \
+    --model_name_or_path ${MODEL_PATH} \
+    --trust_remote_code \
+    --stage sft \
+    --do_train \
+    --finetuning_type lora \
+    --lora_rank 8 \
+    --lora_target all \
+    --dataset identity,alpaca_en_demo \
+    --template llama3 \
+    --cutoff_len 2048 \
+    --max_samples 1000 \
+    --overwrite_cache \
+    --preprocessing_num_workers 16 \
+    --dataloader_num_workers 4 \
+    --output_dir saves/llama3-8b/lora/sft \
+    --logging_steps 10 \
+    --save_steps 500 \
+    --plot_loss \
+    --overwrite_output_dir \
+    --save_only_model false \
+    --report_to none \
+    --per_device_train_batch_size 1 \
+    --gradient_accumulation_steps 8 \
+    --learning_rate 1e-4 \
+    --num_train_epochs 3.0 \
+    --lr_scheduler_type cosine \
+    --warmup_ratio 0.1 \
+    --bf16 \
+    --ddp_timeout 180000000

examples/train_lora/llama3_lora_sft.yaml

+### model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+trust_remote_code: true
+
+### method
+stage: sft
+do_train: true
+finetuning_type: lora
+lora_rank: 8
+lora_target: all
+
+### dataset
+dataset: identity,alpaca_en_demo
+template: llama3
+cutoff_len: 2048
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+dataloader_num_workers: 4
+
+### output
+output_dir: saves/llama3-8b/lora/sft
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+save_only_model: false
+report_to: none  # choices: [none, wandb, tensorboard, swanlab, mlflow]
+
+### train
+per_device_train_batch_size: 1
+gradient_accumulation_steps: 8
+learning_rate: 1.0e-4
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_ratio: 0.1
+bf16: true
+ddp_timeout: 180000000
+resume_from_checkpoint: null
+
+### eval
+# eval_dataset: alpaca_en_demo
+# val_size: 0.1
+# per_device_eval_batch_size: 1
+# eval_strategy: steps
+# eval_steps: 500

examples/train_lora/llama3_lora_sft_ds3.yaml

+### model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+trust_remote_code: true
+
+### method
+stage: sft
+do_train: true
+finetuning_type: lora
+lora_rank: 8
+lora_target: all
+deepspeed: examples/deepspeed/ds_z3_config.json  # choices: [ds_z0_config.json, ds_z2_config.json, ds_z3_config.json]
+
+### dataset
+dataset: identity,alpaca_en_demo
+template: llama3
+cutoff_len: 2048
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+dataloader_num_workers: 4
+
+### output
+output_dir: saves/llama3-8b/lora/sft
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+save_only_model: false
+report_to: none  # choices: [none, wandb, tensorboard, swanlab, mlflow]
+
+### train
+per_device_train_batch_size: 1
+gradient_accumulation_steps: 2
+learning_rate: 1.0e-4
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_ratio: 0.1
+bf16: true
+ddp_timeout: 180000000
+resume_from_checkpoint: null
+
+### eval
+# eval_dataset: alpaca_en_demo
+# val_size: 0.1
+# per_device_eval_batch_size: 1
+# eval_strategy: steps
+# eval_steps: 500

examples/train_lora/llama3_lora_sft_ray.yaml

+### model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct  # or use local absolute path
+trust_remote_code: true
+
+### method
+stage: sft
+do_train: true
+finetuning_type: lora
+lora_rank: 8
+lora_target: all
+
+### dataset
+dataset: identity,alpaca_en_demo
+dataset_dir: REMOTE:llamafactory/demo_data  # or use local absolute path
+template: llama3
+cutoff_len: 2048
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+dataloader_num_workers: 4
+
+### output
+output_dir: tmp_dir
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+save_only_model: false
+report_to: none  # choices: [none, wandb, tensorboard, swanlab, mlflow]
+
+### ray
+ray_run_name: llama3_8b_sft_lora
+ray_storage_path: ./saves
+ray_num_workers: 4  # Number of GPUs to use.
+placement_strategy: PACK
+resources_per_worker:
+  GPU: 1
+# ray_init_kwargs:
+#   runtime_env:
+#     env_vars:
+#       <YOUR-ENV-VAR-HERE>: "<YOUR-ENV-VAR-HERE>"
+#     pip:
+#       - emoji
+
+### train
+per_device_train_batch_size: 1
+gradient_accumulation_steps: 8
+learning_rate: 1.0e-4
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_ratio: 0.1
+bf16: true
+ddp_timeout: 180000000
+resume_from_checkpoint: null
+
+### eval
+# eval_dataset: alpaca_en_demo
+# val_size: 0.1
+# per_device_eval_batch_size: 1
+# eval_strategy: steps
+# eval_steps: 500