423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-01 03:02:51 +08:00
Code Issues Packages Projects Releases Wiki Activity

[example] update examples (#7964)

Browse Source
This commit is contained in:
hoshi-hiyouga 2025-05-06 17:24:25 +02:00 committed by GitHub
parent 5ee9eb64d8
commit c6bcca4c83
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
7 changed files with 12 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
examples/README.md
View File

@ -52,7 +52,7 @@ llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml
#### Multimodal Supervised Fine-Tuning #### Multimodal Supervised Fine-Tuning
```bash ```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 #### DPO/ORPO/SimPO Training
@ -64,7 +64,7 @@ llamafactory-cli train examples/train_lora/llama3_lora_dpo.yaml
#### Multimodal DPO/ORPO/SimPO Training #### Multimodal DPO/ORPO/SimPO Training
```bash ```bash
llamafactory-cli train examples/train_lora/qwen2vl_lora_dpo.yaml llamafactory-cli train examples/train_lora/qwen2_5vl_lora_dpo.yaml
``` ```
#### Reward Modeling #### 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 #### Multimodal Supervised Fine-Tuning
```bash ```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 ### Merging LoRA Adapters and Quantization

6
examples/README_zh.md
View File

@ -52,7 +52,7 @@ llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml
#### 多模态指令监督微调 #### 多模态指令监督微调
```bash ```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 #### 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 #### 多模态 DPO/ORPO/SimPO 训练
```bash ```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 #### 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 #### 多模态指令监督微调
```bash ```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 ### 合并 LoRA 适配器与模型量化

0
examples/inference/qwen2_vl.yaml → examples/inference/qwen2_5vl.yaml
View File

4
examples/merge_lora/qwen2vl_lora_sft.yaml → examples/merge_lora/qwen2_5vl_lora_sft.yaml
View File

@ -2,12 +2,12 @@
### model ### model
model_name_or_path: Qwen/Qwen2.5-VL-7B-Instruct 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 template: qwen2_vl
trust_remote_code: true trust_remote_code: true
### export ### export
export_dir: output/qwen2_vl_lora_sft export_dir: output/qwen2_5vl_lora_sft
export_size: 5 export_size: 5
export_device: cpu # choices: [cpu, auto] export_device: cpu # choices: [cpu, auto]
export_legacy_format: false export_legacy_format: false

4
examples/train_full/qwen2vl_full_sft.yaml → examples/train_full/qwen2_5vl_full_sft.yaml
View File

@ -1,5 +1,5 @@
### model ### model
model_name_or_path: Qwen/Qwen2-VL-7B-Instruct model_name_or_path: Qwen/Qwen2.5-VL-7B-Instruct
image_max_pixels: 262144 image_max_pixels: 262144
video_max_pixels: 16384 video_max_pixels: 16384
trust_remote_code: true trust_remote_code: true
@ -23,7 +23,7 @@ preprocessing_num_workers: 16
dataloader_num_workers: 4 dataloader_num_workers: 4
### output ### output
output_dir: saves/qwen2_vl-7b/full/sft output_dir: saves/qwen2_5vl-7b/full/sft
logging_steps: 10 logging_steps: 10
save_steps: 500 save_steps: 500
plot_loss: true plot_loss: true

2
examples/train_lora/qwen2vl_lora_dpo.yaml → examples/train_lora/qwen2_5vl_lora_dpo.yaml
View File

@ -23,7 +23,7 @@ preprocessing_num_workers: 16
dataloader_num_workers: 4 dataloader_num_workers: 4
### output ### output
output_dir: saves/qwen2_vl-7b/lora/dpo output_dir: saves/qwen2_5vl-7b/lora/dpo
logging_steps: 10 logging_steps: 10
save_steps: 500 save_steps: 500
plot_loss: true plot_loss: true

2
examples/train_lora/qwen2vl_lora_sft.yaml → examples/train_lora/qwen2_5vl_lora_sft.yaml
View File

@ -21,7 +21,7 @@ preprocessing_num_workers: 16
dataloader_num_workers: 4 dataloader_num_workers: 4
### output ### output
output_dir: saves/qwen2_vl-7b/lora/sft output_dir: saves/qwen2_5vl-7b/lora/sft
logging_steps: 10 logging_steps: 10
save_steps: 500 save_steps: 500
plot_loss: true plot_loss: true