kyy/llm_trainer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

support autogptq in llama board #246

Browse Source
This commit is contained in:
hiyouga
2023-12-16 16:31:30 +08:00
parent 93f64ce9a8
commit 71389be37c
14 changed files with 1032 additions and 65 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
src/llmtuner/webui/components/export.py
View File

@@ -10,6 +10,9 @@ if TYPE_CHECKING:
from llmtuner.webui.engine import Engine
GPTQ_BITS = ["8", "4", "3", "2"]
def save_model(
lang: str,
model_name: str,
@@ -18,6 +21,8 @@ def save_model(
finetuning_type: str,
template: str,
max_shard_size: int,
export_quantization_bit: int,
export_quantization_dataset: str,
export_dir: str
) -> Generator[str, None, None]:
error = ""
@@ -25,23 +30,32 @@ def save_model(
error = ALERTS["err_no_model"][lang]
elif not model_path:
error = ALERTS["err_no_path"][lang]
elif not adapter_path:
error = ALERTS["err_no_adapter"][lang]
elif not export_dir:
error = ALERTS["err_no_export_dir"][lang]
elif export_quantization_bit in GPTQ_BITS and not export_quantization_dataset:
error = ALERTS["err_no_dataset"][lang]
elif export_quantization_bit not in GPTQ_BITS and not adapter_path:
error = ALERTS["err_no_adapter"][lang]
if error:
gr.Warning(error)
yield error
return
if adapter_path:
adapter_name_or_path = ",".join([get_save_dir(model_name, finetuning_type, adapter) for adapter in adapter_path])
else:
adapter_name_or_path = None
args = dict(
model_name_or_path=model_path,
adapter_name_or_path=",".join([get_save_dir(model_name, finetuning_type, adapter) for adapter in adapter_path]),
adapter_name_or_path=adapter_name_or_path,
finetuning_type=finetuning_type,
template=template,
export_dir=export_dir,
export_size=max_shard_size
export_size=max_shard_size,
export_quantization_bit=int(export_quantization_bit) if export_quantization_bit in GPTQ_BITS else None,
export_quantization_dataset=export_quantization_dataset
)
yield ALERTS["info_exporting"][lang]
@@ -51,9 +65,11 @@ def save_model(
def create_export_tab(engine: "Engine") -> Dict[str, "Component"]:
with gr.Row():
export_dir = gr.Textbox()
max_shard_size = gr.Slider(value=1, minimum=1, maximum=100)
export_quantization_bit = gr.Dropdown(choices=["none", "8", "4", "3", "2"], value="none")
export_quantization_dataset = gr.Textbox(value="data/c4_demo.json")
export_dir = gr.Textbox()
export_btn = gr.Button()
info_box = gr.Textbox(show_label=False, interactive=False)
@@ -67,14 +83,18 @@ def create_export_tab(engine: "Engine") -> Dict[str, "Component"]:
engine.manager.get_elem_by_name("top.finetuning_type"),
engine.manager.get_elem_by_name("top.template"),
max_shard_size,
export_quantization_bit,
export_quantization_dataset,
export_dir
],
[info_box]
)
return dict(
export_dir=export_dir,
max_shard_size=max_shard_size,
export_quantization_bit=export_quantization_bit,
export_quantization_dataset=export_quantization_dataset,
export_dir=export_dir,
export_btn=export_btn,
info_box=info_box
)