p04798526
/
LLaMA-Factory-310P3
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

update examples

This commit is contained in:
hiyouga 2024-05-13 20:39:36 +08:00
parent 93a0245474
commit dae83f4199
22 changed files with 36 additions and 37 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
examples/README.md
View File

@ -28,6 +28,12 @@ CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llama3_lo
CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llama3_lora_sft.yaml
```
#### Multimodal Supervised Fine-Tuning
```bash
CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llava1_5_lora_sft.yaml
```
#### Reward Modeling
```bash
@ -52,12 +58,6 @@ CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llama3_lo
CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llama3_lora_orpo.yaml
```
#### Multimodal Supervised Fine-Tuning
```bash
CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llava1_5_lora_sft.yaml
```
#### Preprocess Dataset
It is useful for large dataset, use `tokenized_path` in config to load the preprocessed dataset.

12
examples/README_zh.md
View File

@ -28,6 +28,12 @@ CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llama3_lo
CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llama3_lora_sft.yaml
```
#### 多模态指令监督微调
```bash
CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llava1_5_lora_sft.yaml
```
#### 奖励模型训练
```bash
@ -52,12 +58,6 @@ CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llama3_lo
CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llama3_lora_orpo.yaml
```
#### 多模态指令监督微调
```bash
CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llava1_5_lora_sft.yaml
```
#### 预处理数据集
对于大数据集有帮助，在配置中使用 `tokenized_path` 以加载预处理后的数据集。

2
examples/extras/badam/llama3_lora_sft.yaml
View File

@ -15,7 +15,6 @@ dataset: identity,alpaca_gpt4_en
template: llama3
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
@ -36,6 +35,7 @@ warmup_steps: 0.1
pure_bf16: true
# eval
val_size: 0.1
per_device_eval_batch_size: 1
evaluation_strategy: steps
eval_steps: 500

5
examples/extras/fsdp_qlora/llama3_lora_sft.yaml
View File

@ -8,12 +8,14 @@ do_train: true
finetuning_type: lora
lora_target: q_proj,v_proj
# ddp
ddp_timeout: 180000000
# dataset
dataset: identity,alpaca_gpt4_en
template: llama3
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
@ -34,6 +36,7 @@ warmup_steps: 0.1
fp16: true
# eval
val_size: 0.1
per_device_eval_batch_size: 1
evaluation_strategy: steps
eval_steps: 500

2
examples/extras/galore/llama3_full_sft.yaml
View File

@ -16,7 +16,6 @@ dataset: identity,alpaca_gpt4_en
template: llama3
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
@ -37,6 +36,7 @@ warmup_steps: 0.1
pure_bf16: true
# eval
val_size: 0.1
per_device_eval_batch_size: 1
evaluation_strategy: steps
eval_steps: 500

4
examples/extras/llama_pro/llama3_freeze_sft.yaml
View File

@ -14,7 +14,6 @@ dataset: identity,alpaca_gpt4_en
template: llama3
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
@ -32,9 +31,10 @@ learning_rate: 0.0001
num_train_epochs: 3.0
lr_scheduler_type: cosine
warmup_steps: 0.1
pure_bf16: true
fp16: true
# eval
val_size: 0.1
per_device_eval_batch_size: 1
evaluation_strategy: steps
eval_steps: 500

4
examples/extras/loraplus/llama3_lora_sft.yaml
View File

@ -13,7 +13,6 @@ dataset: identity,alpaca_gpt4_en
template: llama3
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
@ -31,9 +30,10 @@ learning_rate: 0.0001
num_train_epochs: 3.0
lr_scheduler_type: cosine
warmup_steps: 0.1
pure_bf16: true
fp16: true
# eval
val_size: 0.1
per_device_eval_batch_size: 1
evaluation_strategy: steps
eval_steps: 500

2
examples/extras/mod/llama3_full_sft.yaml
View File

@ -12,7 +12,6 @@ dataset: identity,alpaca_gpt4_en
template: llama3
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
@ -34,6 +33,7 @@ warmup_steps: 0.1
pure_bf16: true
# eval
val_size: 0.1
per_device_eval_batch_size: 1
evaluation_strategy: steps
eval_steps: 500

2
examples/full_multi_gpu/llama3_full_sft.yaml
View File

@ -15,7 +15,6 @@ dataset: identity,alpaca_gpt4_en
template: llama3
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
@ -36,6 +35,7 @@ warmup_steps: 0.1
fp16: true
# eval
val_size: 0.1
per_device_eval_batch_size: 1
evaluation_strategy: steps
eval_steps: 500

2
examples/lora_multi_gpu/llama3_lora_sft.yaml
View File

@ -15,7 +15,6 @@ dataset: identity,alpaca_gpt4_en
template: llama3
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
@ -36,6 +35,7 @@ warmup_steps: 0.1
fp16: true
# eval
val_size: 0.1
per_device_eval_batch_size: 1
evaluation_strategy: steps
eval_steps: 500

2
examples/lora_multi_gpu/llama3_lora_sft_ds.yaml
View File

@ -16,7 +16,6 @@ dataset: identity,alpaca_gpt4_en
template: llama3
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
@ -37,6 +36,7 @@ warmup_steps: 0.1
fp16: true
# eval
val_size: 0.1
per_device_eval_batch_size: 1
evaluation_strategy: steps
eval_steps: 500

2
examples/lora_single_gpu/llama3_lora_dpo.yaml
View File

@ -13,7 +13,6 @@ dataset: orca_rlhf
template: llama3
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
@ -34,6 +33,7 @@ warmup_steps: 0.1
fp16: true
# eval
val_size: 0.1
per_device_eval_batch_size: 1
evaluation_strategy: steps
eval_steps: 500

2
examples/lora_single_gpu/llama3_lora_orpo.yaml
View File

@ -12,7 +12,6 @@ dataset: orca_rlhf
template: llama3
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
@ -33,6 +32,7 @@ warmup_steps: 0.1
fp16: true
# eval
val_size: 0.1
per_device_eval_batch_size: 1
evaluation_strategy: steps
eval_steps: 500

2
examples/lora_single_gpu/llama3_lora_pretrain.yaml
View File

@ -11,7 +11,6 @@ lora_target: q_proj,v_proj
dataset: c4_demo
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
@ -32,6 +31,7 @@ warmup_steps: 0.1
fp16: true
# eval
val_size: 0.1
per_device_eval_batch_size: 1
evaluation_strategy: steps
eval_steps: 500

2
examples/lora_single_gpu/llama3_lora_reward.yaml
View File

@ -12,7 +12,6 @@ dataset: orca_rlhf
template: llama3
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
@ -33,6 +32,7 @@ warmup_steps: 0.1
fp16: true
# eval
val_size: 0.1
per_device_eval_batch_size: 1
evaluation_strategy: steps
eval_steps: 500

2
examples/lora_single_gpu/llama3_lora_sft.yaml
View File

@ -12,7 +12,6 @@ dataset: identity,alpaca_gpt4_en
template: llama3
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
@ -33,6 +32,7 @@ warmup_steps: 0.1
fp16: true
# eval
val_size: 0.1
per_device_eval_batch_size: 1
evaluation_strategy: steps
eval_steps: 500

1
examples/lora_single_gpu/llama3_preprocess.yaml
View File

@ -12,7 +12,6 @@ dataset: identity,alpaca_gpt4_en
template: llama3
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
tokenized_path: saves/llama3-8b/dataset/sft

2
examples/lora_single_gpu/llava1_5_lora_sft.yaml
View File

@ -13,7 +13,6 @@ dataset: mllm_demo
template: vicuna
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
@ -34,6 +33,7 @@ warmup_steps: 0.1
fp16: true
# eval
val_size: 0.1
per_device_eval_batch_size: 1
evaluation_strategy: steps
eval_steps: 500

2
examples/qlora_single_gpu/llama3_lora_sft_aqlm.yaml
View File

@ -12,7 +12,6 @@ dataset: identity,alpaca_gpt4_en
template: llama3
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
@ -33,6 +32,7 @@ warmup_steps: 0.1
fp16: true
# eval
val_size: 0.1
per_device_eval_batch_size: 1
evaluation_strategy: steps
eval_steps: 500

2
examples/qlora_single_gpu/llama3_lora_sft_awq.yaml
View File

@ -12,7 +12,6 @@ dataset: identity,alpaca_gpt4_en
template: llama3
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
@ -33,6 +32,7 @@ warmup_steps: 0.1
fp16: true
# eval
val_size: 0.1
per_device_eval_batch_size: 1
evaluation_strategy: steps
eval_steps: 500

5
examples/qlora_single_gpu/llama3_lora_sft_bitsandbytes.yaml
View File

@ -8,15 +8,11 @@ do_train: true
finetuning_type: lora
lora_target: q_proj,v_proj
# ddp
ddp_timeout: 180000000
# dataset
dataset: identity,alpaca_gpt4_en
template: llama3
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
@ -37,6 +33,7 @@ warmup_steps: 0.1
fp16: true
# eval
val_size: 0.1
per_device_eval_batch_size: 1
evaluation_strategy: steps
eval_steps: 500

2
examples/qlora_single_gpu/llama3_lora_sft_gptq.yaml
View File

@ -12,7 +12,6 @@ dataset: identity,alpaca_gpt4_en
template: llama3
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
@ -33,6 +32,7 @@ warmup_steps: 0.1
fp16: true
# eval
val_size: 0.1
per_device_eval_batch_size: 1
evaluation_strategy: steps
eval_steps: 500