From c6bcca4c83668da01e50be3607816491521f0e54 Mon Sep 17 00:00:00 2001 From: hoshi-hiyouga Date: Tue, 6 May 2025 17:24:25 +0200 Subject: [PATCH] [example] update examples (#7964) --- examples/README.md | 6 +++--- examples/README_zh.md | 6 +++--- examples/inference/{qwen2_vl.yaml => qwen2_5vl.yaml} | 0 .../{qwen2vl_lora_sft.yaml => qwen2_5vl_lora_sft.yaml} | 4 ++-- .../{qwen2vl_full_sft.yaml => qwen2_5vl_full_sft.yaml} | 4 ++-- .../{qwen2vl_lora_dpo.yaml => qwen2_5vl_lora_dpo.yaml} | 2 +- .../{qwen2vl_lora_sft.yaml => qwen2_5vl_lora_sft.yaml} | 2 +- 7 files changed, 12 insertions(+), 12 deletions(-) rename examples/inference/{qwen2_vl.yaml => qwen2_5vl.yaml} (100%) rename examples/merge_lora/{qwen2vl_lora_sft.yaml => qwen2_5vl_lora_sft.yaml} (76%) rename examples/train_full/{qwen2vl_full_sft.yaml => qwen2_5vl_full_sft.yaml} (91%) rename examples/train_lora/{qwen2vl_lora_dpo.yaml => qwen2_5vl_lora_dpo.yaml} (96%) rename examples/train_lora/{qwen2vl_lora_sft.yaml => qwen2_5vl_lora_sft.yaml} (95%) diff --git a/examples/README.md b/examples/README.md index 281e69bc..1898f3a2 100644 --- a/examples/README.md +++ b/examples/README.md @@ -52,7 +52,7 @@ llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml #### Multimodal Supervised Fine-Tuning ```bash -llamafactory-cli train examples/train_lora/qwen2vl_lora_sft.yaml +llamafactory-cli train examples/train_lora/qwen2_5vl_lora_sft.yaml ``` #### DPO/ORPO/SimPO Training @@ -64,7 +64,7 @@ llamafactory-cli train examples/train_lora/llama3_lora_dpo.yaml #### Multimodal DPO/ORPO/SimPO Training ```bash -llamafactory-cli train examples/train_lora/qwen2vl_lora_dpo.yaml +llamafactory-cli train examples/train_lora/qwen2_5vl_lora_dpo.yaml ``` #### Reward Modeling @@ -168,7 +168,7 @@ FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=1 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 #### Multimodal Supervised Fine-Tuning ```bash -FORCE_TORCHRUN=1 llamafactory-cli train examples/train_full/qwen2vl_full_sft.yaml +FORCE_TORCHRUN=1 llamafactory-cli train examples/train_full/qwen2_5vl_full_sft.yaml ``` ### Merging LoRA Adapters and Quantization diff --git a/examples/README_zh.md b/examples/README_zh.md index 3035dd15..8e6c6b64 100644 --- a/examples/README_zh.md +++ b/examples/README_zh.md @@ -52,7 +52,7 @@ 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/qwen2vl_lora_sft.yaml +llamafactory-cli train examples/train_lora/qwen2_5vl_lora_sft.yaml ``` #### DPO/ORPO/SimPO 训练 @@ -64,7 +64,7 @@ llamafactory-cli train examples/train_lora/llama3_lora_dpo.yaml #### 多模态 DPO/ORPO/SimPO 训练 ```bash -llamafactory-cli train examples/train_lora/qwen2vl_lora_dpo.yaml +llamafactory-cli train examples/train_lora/qwen2_5vl_lora_dpo.yaml ``` #### 奖励模型训练 @@ -168,7 +168,7 @@ FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=1 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 #### 多模态指令监督微调 ```bash -FORCE_TORCHRUN=1 llamafactory-cli train examples/train_full/qwen2vl_full_sft.yaml +FORCE_TORCHRUN=1 llamafactory-cli train examples/train_full/qwen2_5vl_full_sft.yaml ``` ### 合并 LoRA 适配器与模型量化 diff --git a/examples/inference/qwen2_vl.yaml b/examples/inference/qwen2_5vl.yaml similarity index 100% rename from examples/inference/qwen2_vl.yaml rename to examples/inference/qwen2_5vl.yaml diff --git a/examples/merge_lora/qwen2vl_lora_sft.yaml b/examples/merge_lora/qwen2_5vl_lora_sft.yaml similarity index 76% rename from examples/merge_lora/qwen2vl_lora_sft.yaml rename to examples/merge_lora/qwen2_5vl_lora_sft.yaml index 9b157b3c..38a5c7c4 100644 --- a/examples/merge_lora/qwen2vl_lora_sft.yaml +++ b/examples/merge_lora/qwen2_5vl_lora_sft.yaml @@ -2,12 +2,12 @@ ### model model_name_or_path: Qwen/Qwen2.5-VL-7B-Instruct -adapter_name_or_path: saves/qwen2_vl-7b/lora/sft +adapter_name_or_path: saves/qwen2_5vl-7b/lora/sft template: qwen2_vl trust_remote_code: true ### export -export_dir: output/qwen2_vl_lora_sft +export_dir: output/qwen2_5vl_lora_sft export_size: 5 export_device: cpu # choices: [cpu, auto] export_legacy_format: false diff --git a/examples/train_full/qwen2vl_full_sft.yaml b/examples/train_full/qwen2_5vl_full_sft.yaml similarity index 91% rename from examples/train_full/qwen2vl_full_sft.yaml rename to examples/train_full/qwen2_5vl_full_sft.yaml index a2fb9bc4..bd9ac90d 100644 --- a/examples/train_full/qwen2vl_full_sft.yaml +++ b/examples/train_full/qwen2_5vl_full_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 @@ -23,7 +23,7 @@ preprocessing_num_workers: 16 dataloader_num_workers: 4 ### output -output_dir: saves/qwen2_vl-7b/full/sft +output_dir: saves/qwen2_5vl-7b/full/sft logging_steps: 10 save_steps: 500 plot_loss: true diff --git a/examples/train_lora/qwen2vl_lora_dpo.yaml b/examples/train_lora/qwen2_5vl_lora_dpo.yaml similarity index 96% rename from examples/train_lora/qwen2vl_lora_dpo.yaml rename to examples/train_lora/qwen2_5vl_lora_dpo.yaml index 44ec2d8a..2140c90d 100644 --- a/examples/train_lora/qwen2vl_lora_dpo.yaml +++ b/examples/train_lora/qwen2_5vl_lora_dpo.yaml @@ -23,7 +23,7 @@ preprocessing_num_workers: 16 dataloader_num_workers: 4 ### output -output_dir: saves/qwen2_vl-7b/lora/dpo +output_dir: saves/qwen2_5vl-7b/lora/dpo logging_steps: 10 save_steps: 500 plot_loss: true diff --git a/examples/train_lora/qwen2vl_lora_sft.yaml b/examples/train_lora/qwen2_5vl_lora_sft.yaml similarity index 95% rename from examples/train_lora/qwen2vl_lora_sft.yaml rename to examples/train_lora/qwen2_5vl_lora_sft.yaml index 5951546c..6177cfd5 100644 --- a/examples/train_lora/qwen2vl_lora_sft.yaml +++ b/examples/train_lora/qwen2_5vl_lora_sft.yaml @@ -21,7 +21,7 @@ preprocessing_num_workers: 16 dataloader_num_workers: 4 ### output -output_dir: saves/qwen2_vl-7b/lora/sft +output_dir: saves/qwen2_5vl-7b/lora/sft logging_steps: 10 save_steps: 500 plot_loss: true