[parser] support omegaconf (#7793)

examples/README.md

@@ -15,6 +15,18 @@ Use `CUDA_VISIBLE_DEVICES` (GPU) or `ASCEND_RT_VISIBLE_DEVICES` (NPU) to choose
 
 By default, LLaMA-Factory uses all visible computing devices.
 
+Basic usage:
+
+```bash
+llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml
+```
+
+Advanced usage:
+
+```bash
+CUDA_VISIBLE_DEVICES=0,1 llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml learning_rate=1e-5 logging_steps=1
+```
+
 ## Examples
 
 ### LoRA Fine-Tuning
@@ -34,7 +46,6 @@ llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml
 #### Multimodal Supervised Fine-Tuning
 
 ```bash
-llamafactory-cli train examples/train_lora/llava1_5_lora_sft.yaml
 llamafactory-cli train examples/train_lora/qwen2vl_lora_sft.yaml
 ```
 

examples/README_zh.md

@@ -15,6 +15,18 @@
 
 LLaMA-Factory 默认使用所有可见的计算设备。
 
+基础用法：
+
+```bash
+llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml
+```
+
+高级用法：
+
+```bash
+CUDA_VISIBLE_DEVICES=0,1 llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml learning_rate=1e-5 logging_steps=1
+```
+
 ## 示例
 
 ### LoRA 微调
@@ -34,7 +46,6 @@ llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml
 #### 多模态指令监督微调
 
 ```bash
-llamafactory-cli train examples/train_lora/llava1_5_lora_sft.yaml
 llamafactory-cli train examples/train_lora/qwen2vl_lora_sft.yaml
 ```
 

examples/inference/llama3.yaml

@@ -1,4 +1,4 @@
 model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
 template: llama3
-infer_backend: huggingface  # choices: [huggingface, vllm]
+infer_backend: huggingface  # choices: [huggingface, vllm, sglang]
 trust_remote_code: true

examples/inference/llama3_full_sft.yaml

@@ -1,4 +1,4 @@
 model_name_or_path: saves/llama3-8b/full/sft
 template: llama3
-infer_backend: huggingface  # choices: [huggingface, vllm]
+infer_backend: huggingface  # choices: [huggingface, vllm, sglang]
 trust_remote_code: true

examples/inference/llama3_lora_sft.yaml

@@ -1,5 +1,5 @@
 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]
+infer_backend: huggingface  # choices: [huggingface, vllm, sglang]
 trust_remote_code: true

examples/inference/llama3_sglang.yaml

@@ -1,4 +0,0 @@
-model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
-template: llama3
-infer_backend: sglang
-trust_remote_code: true

examples/inference/llama3_vllm.yaml

@@ -1,5 +0,0 @@
-model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
-template: llama3
-infer_backend: vllm
-vllm_enforce_eager: true
-trust_remote_code: true

examples/inference/llava1_5.yaml

@@ -1,4 +0,0 @@
-model_name_or_path: llava-hf/llava-1.5-7b-hf
-template: llava
-infer_backend: huggingface  # choices: [huggingface, vllm]
-trust_remote_code: true

examples/inference/qwen2_vl.yaml

@@ -1,4 +1,4 @@
-model_name_or_path: Qwen/Qwen2-VL-7B-Instruct
+model_name_or_path: Qwen/Qwen2.5-VL-7B-Instruct
 template: qwen2_vl
-infer_backend: huggingface  # choices: [huggingface, vllm]
+infer_backend: huggingface  # choices: [huggingface, vllm, sglang]
 trust_remote_code: true

examples/merge_lora/llama3_full_sft.yaml

@@ -6,5 +6,5 @@ trust_remote_code: true
 ### export
 export_dir: output/llama3_full_sft
 export_size: 5
-export_device: cpu
+export_device: cpu  # choices: [cpu, auto]
 export_legacy_format: false

examples/merge_lora/llama3_gptq.yaml

@@ -6,7 +6,7 @@ trust_remote_code: true
 ### export
 export_dir: output/llama3_gptq
 export_quantization_bit: 4
-export_quantization_dataset: data/c4_demo.json
+export_quantization_dataset: data/c4_demo.jsonl
 export_size: 5
-export_device: cpu
+export_device: cpu  # choices: [cpu, auto]
 export_legacy_format: false

examples/merge_lora/llama3_lora_sft.yaml

@@ -9,5 +9,5 @@ trust_remote_code: true
 ### export
 export_dir: output/llama3_lora_sft
 export_size: 5
-export_device: cpu
+export_device: cpu  # choices: [cpu, auto]
 export_legacy_format: false

examples/merge_lora/qwen2vl_lora_sft.yaml

@@ -1,7 +1,7 @@
 ### Note: DO NOT use quantized model or quantization_bit when merging lora adapters
 
 ### model
-model_name_or_path: Qwen/Qwen2-VL-7B-Instruct
+model_name_or_path: Qwen/Qwen2.5-VL-7B-Instruct
 adapter_name_or_path: saves/qwen2_vl-7b/lora/sft
 template: qwen2_vl
 trust_remote_code: true
@@ -9,5 +9,5 @@ trust_remote_code: true
 ### export
 export_dir: output/qwen2_vl_lora_sft
 export_size: 5
-export_device: cpu
+export_device: cpu  # choices: [cpu, auto]
 export_legacy_format: false

examples/train_lora/llava1_5_lora_sft.yaml

@@ -1,45 +0,0 @@
-### model
-model_name_or_path: llava-hf/llava-1.5-7b-hf
-trust_remote_code: true
-
-### method
-stage: sft
-do_train: true
-finetuning_type: lora
-lora_rank: 8
-lora_target: all
-
-### dataset
-dataset: mllm_demo
-template: llava
-cutoff_len: 2048
-max_samples: 1000
-overwrite_cache: true
-preprocessing_num_workers: 16
-dataloader_num_workers: 4
-
-### output
-output_dir: saves/llava1_5-7b/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
-# val_size: 0.1
-# per_device_eval_batch_size: 1
-# eval_strategy: steps
-# eval_steps: 500

examples/train_lora/qwen2vl_lora_dpo.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: Qwen/Qwen2-VL-7B-Instruct
+model_name_or_path: Qwen/Qwen2.5-VL-7B-Instruct
 image_max_pixels: 262144
 video_max_pixels: 16384
 trust_remote_code: true

examples/train_lora/qwen2vl_lora_sft.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: Qwen/Qwen2-VL-7B-Instruct
+model_name_or_path: Qwen/Qwen2.5-VL-7B-Instruct
 image_max_pixels: 262144
 video_max_pixels: 16384
 trust_remote_code: true