move fsdp config path (#662)

modelscope · Apr 5, 2024 · 242086b · 242086b
1 parent cb45fad
commit 242086b
Show file tree

Hide file tree

Showing 5 changed files with 4 additions and 9 deletions.
diff --git a/docs/source/LLM/命令行参数.md b/docs/source/LLM/命令行参数.md
@@ -108,7 +108,7 @@
 ### FSDP参数
 
 - `--fsdp`: 默认值`''`, fsdp类型, 详情可以查看该参数[原始文档](https://huggingface.co/docs/transformers/v4.39.3/en/main_classes/trainer#transformers.TrainingArguments.fsdp).
-- `--fsdp_config`: 默认值`None`, fsdp配置文件的路径, 支持传入`fsdp_offload`, 该文件为SWIFT提供的默认配置, 具体可以查看[这里](https://github.com/modelscope/swift/tree/main/swift/llm/fsdp_config/fsdp_offload.json).
+- `--fsdp_config`: 默认值`None`, fsdp配置文件的路径.
 
 ### LoRA+微调参数
 

diff --git a/docs/source_en/LLM/Command-line-parameters.md b/docs/source_en/LLM/Command-line-parameters.md
@@ -107,9 +107,9 @@
 
 ### FSDP Parameters
 
-- `--fsdp`: Default value`''`, the FSDP type, please check[this documentation](https://huggingface.co/docs/transformers/v4.39.3/en/main_classes/trainer#transformers.TrainingArguments.fsdp) for details.
+- `--fsdp`: Default value `''`, the FSDP type, please check [this documentation](https://huggingface.co/docs/transformers/v4.39.3/en/main_classes/trainer#transformers.TrainingArguments.fsdp) for details.
 
-- `--fsdp_config`: Default value`None`, the FSDP config file path, `fsdp_offload` is a special value, check [here](https://github.com/modelscope/swift/tree/main/swift/llm/fsdp_config/fsdp_offload.json) for details.
+- `--fsdp_config`: Default value `None`, the FSDP config file path.
 
 ### LoRA+ Fine-tuning Parameters
 

diff --git a/swift/llm/fsdp_config/fsdp_offload.json → ...ma2_70b_chat/qlora_fsdp/fsdp_offload.json b/swift/llm/fsdp_config/fsdp_offload.json → ...ma2_70b_chat/qlora_fsdp/fsdp_offload.json
diff --git a/examples/pytorch/llm/scripts/llama2_70b_chat/qlora_fsdp/sft.sh b/examples/pytorch/llm/scripts/llama2_70b_chat/qlora_fsdp/sft.sh
@@ -4,7 +4,7 @@ nproc_per_node=2
 
 PYTHONPATH=../../.. \
 CUDA_VISIBLE_DEVICES=0,1 \
-accelerate launch --config_file "../../../swift/llm/fsdp_config/fsdp_offload.json" \
+accelerate launch --config_file "./scripts/llama2_70b_chat/qlora_fsdp/fsdp_offload.json" \
     llm_sft.py \
     --model_type llama2-70b-chat \
     --model_revision master \

diff --git a/swift/llm/utils/argument.py b/swift/llm/utils/argument.py
@@ -290,11 +290,6 @@ def __post_init__(self) -> None:
             self.deepspeed = os.path.abspath(
                 os.path.join(ds_config_folder, 'zero3.json'))
 
-        fsdp_config_folder = os.path.join(__file__, '..', '..', 'fsdp_config')
-        if self.fsdp_config == 'fsdp_offload':
-            self.fsdp_config = os.path.abspath(
-                os.path.join(fsdp_config_folder, 'fsdp_offload.json'))
-
         handle_path(self)
         set_model_type(self)
         if isinstance(self.dataset, str):