423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-02 03:32:50 +08:00
Code Issues Packages Projects Releases Wiki Activity

update examples

Browse Source 
Former-commit-id: fc7f1cc365ee481b76f9c7e6f1947b49cf131fbf
This commit is contained in:
hiyouga 2024-04-02 21:09:25 +08:00
parent 03c538ebb3
commit 86513f28dc
4 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
examples/README.md
View File

@ -3,7 +3,7 @@ We provide diverse examples about fine-tuning LLMs.
``` ```
examples/ examples/
├── lora_single_gpu/ ├── lora_single_gpu/
│ ├── pt.sh: Do pre-training │ ├── pretrain.sh: Do pre-training
│ ├── sft.sh: Do supervised fine-tuning │ ├── sft.sh: Do supervised fine-tuning
│ ├── reward.sh: Do reward modeling │ ├── reward.sh: Do reward modeling
│ ├── ppo.sh: Do PPO training │ ├── ppo.sh: Do PPO training

2
examples/README_zh.md
View File

@ -3,7 +3,7 @@
``` ```
examples/ examples/
├── lora_single_gpu/ ├── lora_single_gpu/
│ ├── pt.sh: 进行预训练 │ ├── pretrain.sh: 进行预训练
│ ├── sft.sh: 进行指令监督微调 │ ├── sft.sh: 进行指令监督微调
│ ├── reward.sh: 进行奖励模型训练 │ ├── reward.sh: 进行奖励模型训练
│ ├── ppo.sh: 进行 PPO 训练 │ ├── ppo.sh: 进行 PPO 训练

2
examples/lora_single_gpu/dpo.sh
View File

@ -6,7 +6,7 @@ CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
--model_name_or_path meta-llama/Llama-2-7b-hf \ --model_name_or_path meta-llama/Llama-2-7b-hf \
--adapter_name_or_path ../../saves/LLaMA2-7B/lora/sft \ --adapter_name_or_path ../../saves/LLaMA2-7B/lora/sft \
--create_new_adapter \ --create_new_adapter \
--dataset comparison_gpt4_en \ --dataset orca_rlhf \
--dataset_dir ../../data \ --dataset_dir ../../data \
--template default \ --template default \
--finetuning_type lora \ --finetuning_type lora \

2
examples/lora_single_gpu/reward.sh
View File

@ -6,7 +6,7 @@ CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
--model_name_or_path meta-llama/Llama-2-7b-hf \ --model_name_or_path meta-llama/Llama-2-7b-hf \
--adapter_name_or_path ../../saves/LLaMA2-7B/lora/sft \ --adapter_name_or_path ../../saves/LLaMA2-7B/lora/sft \
--create_new_adapter \ --create_new_adapter \
--dataset comparison_gpt4_en \ --dataset orca_rlhf \
--dataset_dir ../../data \ --dataset_dir ../../data \
--template default \ --template default \
--finetuning_type lora \ --finetuning_type lora \