ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

support pagination in webui preview

Browse Source 
Former-commit-id: f2307e26b9c2ce5d60917cce5a9638466ea676c8
This commit is contained in:
hiyouga
2023-11-02 21:21:45 +08:00
parent ac74639b32
commit 7d13501b94
10 changed files with 201 additions and 154 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
src/llmtuner/webui/components/chatbot.py
View File

@@ -11,11 +11,9 @@ def create_chat_box(
engine: "Engine",
visible: Optional[bool] = False
) -> Tuple["Block", "Component", "Component", Dict[str, "Component"]]:
elem_dict = dict()
with gr.Box(visible=visible) as chat_box:
chatbot = gr.Chatbot()
history = gr.State([])
with gr.Row():
with gr.Column(scale=4):
system = gr.Textbox(show_label=False)
@@ -29,13 +27,6 @@ def create_chat_box(
top_p = gr.Slider(0.01, 1, value=gen_kwargs.top_p, step=0.01)
temperature = gr.Slider(0.01, 1.5, value=gen_kwargs.temperature, step=0.01)
elem_dict.update(dict(
system=system, query=query, submit_btn=submit_btn, clear_btn=clear_btn,
max_new_tokens=max_new_tokens, top_p=top_p, temperature=temperature
))
history = gr.State([])
submit_btn.click(
engine.chatter.predict,
[chatbot, query, history, system, max_new_tokens, top_p, temperature],
@@ -47,4 +38,12 @@ def create_chat_box(
clear_btn.click(lambda: ([], []), outputs=[chatbot, history], show_progress=True)
return chat_box, chatbot, history, elem_dict
return chat_box, chatbot, history, dict(
system=system,
query=query,
submit_btn=submit_btn,
clear_btn=clear_btn,
max_new_tokens=max_new_tokens,
top_p=top_p,
temperature=temperature
)

102
src/llmtuner/webui/components/data.py
View File

@@ -1,17 +1,103 @@
import os
import json
import gradio as gr
from typing import TYPE_CHECKING, Tuple
from typing import TYPE_CHECKING, Any, Dict, Tuple
from llmtuner.webui.common import DATA_CONFIG
if TYPE_CHECKING:
from gradio.blocks import Block
from gradio.components import Component
def create_preview_box() -> Tuple["Block", "Component", "Component", "Component"]:
PAGE_SIZE = 2
def prev_page(page_index: int) -> int:
return page_index - 1 if page_index > 0 else page_index
def next_page(page_index: int, total_num: int) -> int:
return page_index + 1 if (page_index + 1) * PAGE_SIZE < total_num else page_index
def can_preview(dataset_dir: str, dataset: list) -> Dict[str, Any]:
with open(os.path.join(dataset_dir, DATA_CONFIG), "r", encoding="utf-8") as f:
dataset_info = json.load(f)
if (
len(dataset) > 0
and "file_name" in dataset_info[dataset[0]]
and os.path.isfile(os.path.join(dataset_dir, dataset_info[dataset[0]]["file_name"]))
):
return gr.update(interactive=True)
else:
return gr.update(interactive=False)
def get_preview(dataset_dir: str, dataset: list, page_index: int) -> Tuple[int, list, Dict[str, Any]]:
with open(os.path.join(dataset_dir, DATA_CONFIG), "r", encoding="utf-8") as f:
dataset_info = json.load(f)
data_file: str = dataset_info[dataset[0]]["file_name"]
with open(os.path.join(dataset_dir, data_file), "r", encoding="utf-8") as f:
if data_file.endswith(".json"):
data = json.load(f)
elif data_file.endswith(".jsonl"):
data = [json.loads(line) for line in f]
else:
data = [line for line in f]
return len(data), data[PAGE_SIZE * page_index : PAGE_SIZE * (page_index + 1)], gr.update(visible=True)
def create_preview_box(dataset_dir: "gr.Textbox", dataset: "gr.Dropdown") -> Dict[str, "Component"]:
data_preview_btn = gr.Button(interactive=False, scale=1)
with gr.Column(visible=False, elem_classes="modal-box") as preview_box:
preview_count = gr.Number(interactive=False)
preview_samples = gr.JSON(interactive=False)
close_btn = gr.Button()
with gr.Row():
preview_count = gr.Number(value=0, interactive=False, precision=0)
page_index = gr.Number(value=0, interactive=False, precision=0)
with gr.Row():
prev_btn = gr.Button()
next_btn = gr.Button()
close_btn = gr.Button()
with gr.Row():
preview_samples = gr.JSON(interactive=False)
dataset.change(
can_preview, [dataset_dir, dataset], [data_preview_btn], queue=False
).then(
lambda: 0, outputs=[page_index], queue=False
)
data_preview_btn.click(
get_preview,
[dataset_dir, dataset, page_index],
[preview_count, preview_samples, preview_box],
queue=False
)
prev_btn.click(
prev_page, [page_index], [page_index], queue=False
).then(
get_preview,
[dataset_dir, dataset, page_index],
[preview_count, preview_samples, preview_box],
queue=False
)
next_btn.click(
next_page, [page_index, preview_count], [page_index], queue=False
).then(
get_preview,
[dataset_dir, dataset, page_index],
[preview_count, preview_samples, preview_box],
queue=False
)
close_btn.click(lambda: gr.update(visible=False), outputs=[preview_box], queue=False)
return preview_box, preview_count, preview_samples, close_btn
return dict(
data_preview_btn=data_preview_btn,
preview_count=preview_count,
page_index=page_index,
prev_btn=prev_btn,
next_btn=next_btn,
close_btn=close_btn,
preview_samples=preview_samples
)

21
src/llmtuner/webui/components/eval.py
View File

@@ -3,7 +3,6 @@ from typing import TYPE_CHECKING, Dict
from llmtuner.webui.common import list_dataset, DEFAULT_DATA_DIR
from llmtuner.webui.components.data import create_preview_box
from llmtuner.webui.utils import can_preview, get_preview
if TYPE_CHECKING:
from gradio.components import Component
@@ -17,28 +16,12 @@ def create_eval_tab(engine: "Engine") -> Dict[str, "Component"]:
with gr.Row():
dataset_dir = gr.Textbox(value=DEFAULT_DATA_DIR, scale=2)
dataset = gr.Dropdown(multiselect=True, scale=4)
data_preview_btn = gr.Button(interactive=False, scale=1)
preview_elems = create_preview_box(dataset_dir, dataset)
dataset_dir.change(list_dataset, [dataset_dir], [dataset], queue=False)
dataset.change(can_preview, [dataset_dir, dataset], [data_preview_btn], queue=False)
input_elems.update({dataset_dir, dataset})
elem_dict.update(dict(
dataset_dir=dataset_dir, dataset=dataset, data_preview_btn=data_preview_btn
))
preview_box, preview_count, preview_samples, close_btn = create_preview_box()
data_preview_btn.click(
get_preview,
[dataset_dir, dataset],
[preview_count, preview_samples, preview_box],
queue=False
)
elem_dict.update(dict(
preview_count=preview_count, preview_samples=preview_samples, close_btn=close_btn
))
elem_dict.update(dict(dataset_dir=dataset_dir, dataset=dataset, **preview_elems))
with gr.Row():
cutoff_len = gr.Slider(value=1024, minimum=4, maximum=8192, step=1)

52
src/llmtuner/webui/components/export.py
View File

@@ -1,16 +1,54 @@
import gradio as gr
from typing import TYPE_CHECKING, Dict
from typing import TYPE_CHECKING, Dict, Generator, List
from llmtuner.webui.utils import save_model
from llmtuner.tuner import export_model
from llmtuner.webui.common import get_save_dir
from llmtuner.webui.locales import ALERTS
if TYPE_CHECKING:
from gradio.components import Component
from llmtuner.webui.engine import Engine
def create_export_tab(engine: "Engine") -> Dict[str, "Component"]:
elem_dict = dict()
def save_model(
lang: str,
model_name: str,
model_path: str,
checkpoints: List[str],
finetuning_type: str,
template: str,
max_shard_size: int,
export_dir: str
) -> Generator[str, None, None]:
error = ""
if not model_name:
error = ALERTS["err_no_model"][lang]
elif not model_path:
error = ALERTS["err_no_path"][lang]
elif not checkpoints:
error = ALERTS["err_no_checkpoint"][lang]
elif not export_dir:
error = ALERTS["err_no_export_dir"][lang]
if error:
gr.Warning(error)
yield error
return
args = dict(
model_name_or_path=model_path,
checkpoint_dir=",".join([get_save_dir(model_name, finetuning_type, ckpt) for ckpt in checkpoints]),
finetuning_type=finetuning_type,
template=template,
export_dir=export_dir
)
yield ALERTS["info_exporting"][lang]
export_model(args, max_shard_size="{}GB".format(max_shard_size))
yield ALERTS["info_exported"][lang]
def create_export_tab(engine: "Engine") -> Dict[str, "Component"]:
with gr.Row():
export_dir = gr.Textbox()
max_shard_size = gr.Slider(value=10, minimum=1, maximum=100)
@@ -33,11 +71,9 @@ def create_export_tab(engine: "Engine") -> Dict[str, "Component"]:
[info_box]
)
elem_dict.update(dict(
return dict(
export_dir=export_dir,
max_shard_size=max_shard_size,
export_btn=export_btn,
info_box=info_box
))
return elem_dict
)

29
src/llmtuner/webui/components/train.py
View File

@@ -5,7 +5,7 @@ from transformers.trainer_utils import SchedulerType
from llmtuner.extras.constants import TRAINING_STAGES
from llmtuner.webui.common import list_checkpoint, list_dataset, DEFAULT_DATA_DIR
from llmtuner.webui.components.data import create_preview_box
from llmtuner.webui.utils import can_preview, get_preview, gen_plot
from llmtuner.webui.utils import gen_plot
if TYPE_CHECKING:
from gradio.components import Component
@@ -22,28 +22,14 @@ def create_train_tab(engine: "Engine") -> Dict[str, "Component"]:
)
dataset_dir = gr.Textbox(value=DEFAULT_DATA_DIR, scale=2)
dataset = gr.Dropdown(multiselect=True, scale=4)
data_preview_btn = gr.Button(interactive=False, scale=1)
preview_elems = create_preview_box(dataset_dir, dataset)
training_stage.change(list_dataset, [dataset_dir, training_stage], [dataset], queue=False)
dataset_dir.change(list_dataset, [dataset_dir, training_stage], [dataset], queue=False)
dataset.change(can_preview, [dataset_dir, dataset], [data_preview_btn], queue=False)
input_elems.update({training_stage, dataset_dir, dataset})
elem_dict.update(dict(
training_stage=training_stage, dataset_dir=dataset_dir, dataset=dataset, data_preview_btn=data_preview_btn
))
preview_box, preview_count, preview_samples, close_btn = create_preview_box()
data_preview_btn.click(
get_preview,
[dataset_dir, dataset],
[preview_count, preview_samples, preview_box],
queue=False
)
elem_dict.update(dict(
preview_count=preview_count, preview_samples=preview_samples, close_btn=close_btn
training_stage=training_stage, dataset_dir=dataset_dir, dataset=dataset, **preview_elems
))
with gr.Row():
@@ -143,16 +129,17 @@ def create_train_tab(engine: "Engine") -> Dict[str, "Component"]:
input_elems.add(output_dir)
output_elems = [output_box, process_bar]
elem_dict.update(dict(
cmd_preview_btn=cmd_preview_btn, start_btn=start_btn, stop_btn=stop_btn, output_dir=output_dir,
resume_btn=resume_btn, process_bar=process_bar, output_box=output_box, loss_viewer=loss_viewer
))
cmd_preview_btn.click(engine.runner.preview_train, input_elems, output_elems)
start_btn.click(engine.runner.run_train, input_elems, output_elems)
stop_btn.click(engine.runner.set_abort, queue=False)
resume_btn.change(engine.runner.monitor, outputs=output_elems)
elem_dict.update(dict(
cmd_preview_btn=cmd_preview_btn, start_btn=start_btn, stop_btn=stop_btn, output_dir=output_dir,
resume_btn=resume_btn, process_bar=process_bar, output_box=output_box, loss_viewer=loss_viewer
))
output_box.change(
gen_plot,
[