diff --git a/CODE_OF_CONDUCT.md b/CODE_OF_CONDUCT.md new file mode 100644 index 00000000..c2035cea --- /dev/null +++ b/CODE_OF_CONDUCT.md @@ -0,0 +1,128 @@ +# Contributor Covenant Code of Conduct + +## Our Pledge + +We as members, contributors, and leaders pledge to make participation in our +community a harassment-free experience for everyone, regardless of age, body +size, visible or invisible disability, ethnicity, sex characteristics, gender +identity and expression, level of experience, education, socio-economic status, +nationality, personal appearance, race, religion, or sexual identity +and orientation. + +We pledge to act and interact in ways that contribute to an open, welcoming, +diverse, inclusive, and healthy community. + +## Our Standards + +Examples of behavior that contributes to a positive environment for our +community include: + +* Demonstrating empathy and kindness toward other people +* Being respectful of differing opinions, viewpoints, and experiences +* Giving and gracefully accepting constructive feedback +* Accepting responsibility and apologizing to those affected by our mistakes, + and learning from the experience +* Focusing on what is best not just for us as individuals, but for the + overall community + +Examples of unacceptable behavior include: + +* The use of sexualized language or imagery, and sexual attention or + advances of any kind +* Trolling, insulting or derogatory comments, and personal or political attacks +* Public or private harassment +* Publishing others' private information, such as a physical or email + address, without their explicit permission +* Other conduct which could reasonably be considered inappropriate in a + professional setting + +## Enforcement Responsibilities + +Community leaders are responsible for clarifying and enforcing our standards of +acceptable behavior and will take appropriate and fair corrective action in +response to any behavior that they deem inappropriate, threatening, offensive, +or harmful. + +Community leaders have the right and responsibility to remove, edit, or reject +comments, commits, code, wiki edits, issues, and other contributions that are +not aligned to this Code of Conduct, and will communicate reasons for moderation +decisions when appropriate. + +## Scope + +This Code of Conduct applies within all community spaces, and also applies when +an individual is officially representing the community in public spaces. +Examples of representing our community include using an official e-mail address, +posting via an official social media account, or acting as an appointed +representative at an online or offline event. + +## Enforcement + +Instances of abusive, harassing, or otherwise unacceptable behavior may be +reported to the community leaders responsible for enforcement at +`hoshihiyouga AT gmail DOT com`. +All complaints will be reviewed and investigated promptly and fairly. + +All community leaders are obligated to respect the privacy and security of the +reporter of any incident. + +## Enforcement Guidelines + +Community leaders will follow these Community Impact Guidelines in determining +the consequences for any action they deem in violation of this Code of Conduct: + +### 1. Correction + +**Community Impact**: Use of inappropriate language or other behavior deemed +unprofessional or unwelcome in the community. + +**Consequence**: A private, written warning from community leaders, providing +clarity around the nature of the violation and an explanation of why the +behavior was inappropriate. A public apology may be requested. + +### 2. Warning + +**Community Impact**: A violation through a single incident or series +of actions. + +**Consequence**: A warning with consequences for continued behavior. No +interaction with the people involved, including unsolicited interaction with +those enforcing the Code of Conduct, for a specified period of time. This +includes avoiding interactions in community spaces as well as external channels +like social media. Violating these terms may lead to a temporary or +permanent ban. + +### 3. Temporary Ban + +**Community Impact**: A serious violation of community standards, including +sustained inappropriate behavior. + +**Consequence**: A temporary ban from any sort of interaction or public +communication with the community for a specified period of time. No public or +private interaction with the people involved, including unsolicited interaction +with those enforcing the Code of Conduct, is allowed during this period. +Violating these terms may lead to a permanent ban. + +### 4. Permanent Ban + +**Community Impact**: Demonstrating a pattern of violation of community +standards, including sustained inappropriate behavior, harassment of an +individual, or aggression toward or disparagement of classes of individuals. + +**Consequence**: A permanent ban from any sort of public interaction within +the community. + +## Attribution + +This Code of Conduct is adapted from the [Contributor Covenant][homepage], +version 2.0, available at +https://www.contributor-covenant.org/version/2/0/code_of_conduct.html. + +Community Impact Guidelines were inspired by [Mozilla's code of conduct +enforcement ladder](https://github.com/mozilla/diversity). + +[homepage]: https://www.contributor-covenant.org + +For answers to common questions about this code of conduct, see the FAQ at +https://www.contributor-covenant.org/faq. Translations are available at +https://www.contributor-covenant.org/translations. diff --git a/README.md b/README.md index 9a2499ae..931943be 100644 --- a/README.md +++ b/README.md @@ -14,7 +14,9 @@ ## LLaMA Board: A One-stop Web UI for Getting Started with LLaMA Factory -Launch **LLaMA Board** via `CUDA_VISIBLE_DEVICES=0 python src/train_web.py`. (multiple GPUs are not supported yet) +Preview LLaMA Board at **[Hugging Face Space](https://huggingface.co/spaces/hiyouga/LLaMA-Board)**. + +Launch LLaMA Board via `CUDA_VISIBLE_DEVICES=0 python src/train_web.py`. (multiple GPUs are not supported yet) Here is an example of altering the self-cognition of an instruction-tuned language model within 10 minutes on a single GPU. diff --git a/README_zh.md b/README_zh.md index eb0f5c6e..e3758cdd 100644 --- a/README_zh.md +++ b/README_zh.md @@ -14,7 +14,9 @@ ## LLaMA Board: 通过一站式网页界面快速上手 LLaMA Factory -使用 `CUDA_VISIBLE_DEVICES=0 python src/train_web.py` 启动 **LLaMA Board**。（该界面目前仅支持单卡训练） +通过 **[Hugging Face Space](https://huggingface.co/spaces/hiyouga/LLaMA-Board)** 预览 LLaMA Board。 + +使用 `CUDA_VISIBLE_DEVICES=0 python src/train_web.py` 启动 LLaMA Board。（该界面目前仅支持单卡训练） 下面是使用单张 GPU 在 10 分钟内更改对话式大型语言模型自我认知的示例。 diff --git a/src/llmtuner/webui/chatter.py b/src/llmtuner/webui/chatter.py index 6a913703..675540df 100644 --- a/src/llmtuner/webui/chatter.py +++ b/src/llmtuner/webui/chatter.py @@ -14,8 +14,14 @@ if TYPE_CHECKING: class WebChatModel(ChatModel): - def __init__(self, manager: "Manager", lazy_init: Optional[bool] = True) -> None: + def __init__( + self, + manager: "Manager", + demo_mode: Optional[bool] = False, + lazy_init: Optional[bool] = True + ) -> None: self.manager = manager + self.demo_mode = demo_mode self.model = None self.tokenizer = None self.generating_args = GeneratingArguments() @@ -36,6 +42,8 @@ class WebChatModel(ChatModel): error = ALERTS["err_no_model"][lang] elif not get("top.model_path"): error = ALERTS["err_no_path"][lang] + elif self.demo_mode: + error = ALERTS["err_demo"][lang] if error: gr.Warning(error) diff --git a/src/llmtuner/webui/common.py b/src/llmtuner/webui/common.py index 6663254c..55d8942b 100644 --- a/src/llmtuner/webui/common.py +++ b/src/llmtuner/webui/common.py @@ -70,7 +70,7 @@ def get_module(model_name: str) -> str: def get_template(model_name: str) -> str: - if model_name.endswith("Chat") and get_prefix(model_name) in DEFAULT_TEMPLATE: + if model_name and model_name.endswith("Chat") and get_prefix(model_name) in DEFAULT_TEMPLATE: return DEFAULT_TEMPLATE[get_prefix(model_name)] return "default" diff --git a/src/llmtuner/webui/css.py b/src/llmtuner/webui/css.py index c86fb96b..51ca1d64 100644 --- a/src/llmtuner/webui/css.py +++ b/src/llmtuner/webui/css.py @@ -1,4 +1,11 @@ CSS = r""" +.duplicate-button { + margin: auto; + color: white; + background: black; + border-radius: 100vh; +} + .modal-box { position: fixed !important; top: 50%; diff --git a/src/llmtuner/webui/engine.py b/src/llmtuner/webui/engine.py index 661dfb48..3e9f077d 100644 --- a/src/llmtuner/webui/engine.py +++ b/src/llmtuner/webui/engine.py @@ -12,11 +12,11 @@ from llmtuner.webui.utils import get_time class Engine: - def __init__(self, pure_chat: Optional[bool] = False) -> None: + def __init__(self, demo_mode: Optional[bool] = False, pure_chat: Optional[bool] = False) -> None: self.pure_chat = pure_chat - self.manager: "Manager" = Manager() - self.runner: "Runner" = Runner(self.manager) - self.chatter: "WebChatModel" = WebChatModel(manager=self.manager, lazy_init=(not pure_chat)) + self.manager = Manager() + self.runner = Runner(self.manager, demo_mode=demo_mode) + self.chatter = WebChatModel(manager=self.manager, demo_mode=demo_mode, lazy_init=(not pure_chat)) def _form_dict(self, resume_dict: Dict[str, Dict[str, Any]]): return {self.manager.get_elem_by_name(k): gr.update(**v) for k, v in resume_dict.items()} diff --git a/src/llmtuner/webui/interface.py b/src/llmtuner/webui/interface.py index ba663f24..e321476f 100644 --- a/src/llmtuner/webui/interface.py +++ b/src/llmtuner/webui/interface.py @@ -1,4 +1,5 @@ import gradio as gr +from typing import Optional from transformers.utils.versions import require_version from llmtuner.webui.components import ( @@ -17,10 +18,20 @@ from llmtuner.webui.engine import Engine require_version("gradio>=3.38.0,<4.0.0", "To fix: pip install \"gradio>=3.38.0,<4.0.0\"") -def create_ui() -> gr.Blocks: - engine = Engine(pure_chat=False) +def create_ui(demo_mode: Optional[bool] = False) -> gr.Blocks: + engine = Engine(demo_mode=demo_mode, pure_chat=False) with gr.Blocks(title="LLaMA Board", css=CSS) as demo: + if demo_mode: + gr.HTML( + "

LLaMA Board: A One-stop Web UI for Getting Started with LLaMA Factory

" + ) + gr.HTML( + "

Visit " + "LLaMA Factory for details.

" + ) + gr.DuplicateButton(value="Duplicate Space for private use", elem_classes="duplicate-button") + engine.manager.all_elems["top"] = create_top() lang: "gr.Dropdown" = engine.manager.get_elem_by_name("top.lang") @@ -33,8 +44,9 @@ def create_ui() -> gr.Blocks: with gr.Tab("Chat"): engine.manager.all_elems["infer"] = create_infer_tab(engine) - with gr.Tab("Export"): - engine.manager.all_elems["export"] = create_export_tab(engine) + if not demo_mode: + with gr.Tab("Export"): + engine.manager.all_elems["export"] = create_export_tab(engine) demo.load(engine.resume, outputs=engine.manager.list_elems()) lang.change(engine.change_lang, [lang], engine.manager.list_elems(), queue=False) diff --git a/src/llmtuner/webui/locales.py b/src/llmtuner/webui/locales.py index cc2a1842..769cf15d 100644 --- a/src/llmtuner/webui/locales.py +++ b/src/llmtuner/webui/locales.py @@ -659,6 +659,10 @@ ALERTS = { "en": "Failed.", "zh": "训练出错。" }, + "err_demo": { + "en": "Training is unavailable in demo mode, duplicate the space to a private one first.", + "zh": "展示模式不支持训练，请先复制到私人空间。" + }, "info_aborting": { "en": "Aborted, wait for terminating...", "zh": "训练中断，正在等待线程结束……" diff --git a/src/llmtuner/webui/runner.py b/src/llmtuner/webui/runner.py index 626925a0..8eb79dea 100644 --- a/src/llmtuner/webui/runner.py +++ b/src/llmtuner/webui/runner.py @@ -4,7 +4,7 @@ import logging import gradio as gr from threading import Thread from gradio.components import Component # cannot use TYPE_CHECKING here -from typing import TYPE_CHECKING, Any, Dict, Generator, Tuple +from typing import TYPE_CHECKING, Any, Dict, Generator, Optional, Tuple import transformers from transformers.trainer import TRAINING_ARGS_NAME @@ -24,8 +24,9 @@ if TYPE_CHECKING: class Runner: - def __init__(self, manager: "Manager") -> None: + def __init__(self, manager: "Manager", demo_mode: Optional[bool] = False) -> None: self.manager = manager + self.demo_mode = demo_mode """ Resume """ self.thread: "Thread" = None self.do_train = True @@ -46,9 +47,8 @@ class Runner: def set_abort(self) -> None: self.aborted = True - self.running = False - def _initialize(self, data: Dict[Component, Any], do_train: bool) -> str: + def _initialize(self, data: Dict[Component, Any], do_train: bool, from_preview: bool) -> str: get = lambda name: data[self.manager.get_elem_by_name(name)] lang, model_name, model_path = get("top.lang"), get("top.model_name"), get("top.model_path") dataset = get("train.dataset") if do_train else get("eval.dataset") @@ -65,6 +65,9 @@ class Runner: if len(dataset) == 0: return ALERTS["err_no_dataset"][lang] + if self.demo_mode and (not from_preview): + return ALERTS["err_demo"][lang] + self.aborted = False self.logger_handler.reset() self.trainer_callback = LogCallback(self) @@ -196,7 +199,7 @@ class Runner: return args def _preview(self, data: Dict[Component, Any], do_train: bool) -> Generator[Tuple[str, Dict[str, Any]], None, None]: - error = self._initialize(data, do_train) + error = self._initialize(data, do_train, from_preview=True) if error: gr.Warning(error) yield error, gr.update(visible=False) @@ -205,14 +208,13 @@ class Runner: yield gen_cmd(args), gr.update(visible=False) def _launch(self, data: Dict[Component, Any], do_train: bool) -> Generator[Tuple[str, Dict[str, Any]], None, None]: - error = self._initialize(data, do_train) + error = self._initialize(data, do_train, from_preview=False) if error: gr.Warning(error) yield error, gr.update(visible=False) else: args = self._parse_train_args(data) if do_train else self._parse_eval_args(data) run_kwargs = dict(args=args, callbacks=[self.trainer_callback]) - self.running = True self.do_train, self.running_data = do_train, data self.monitor_inputs = dict(lang=data[self.manager.get_elem_by_name("top.lang")], output_dir=args["output_dir"]) self.thread = Thread(target=run_exp, kwargs=run_kwargs) @@ -232,6 +234,7 @@ class Runner: yield from self._launch(data, do_train=False) def monitor(self) -> Generator[Tuple[str, Dict[str, Any]], None, None]: + self.running = True lang, output_dir = self.monitor_inputs["lang"], self.monitor_inputs["output_dir"] while self.thread.is_alive(): time.sleep(2)