diff --git a/README.md b/README.md index fc930360..89232843 100644 --- a/README.md +++ b/README.md @@ -40,7 +40,7 @@ Choose your path: - **Documentation (WIP)**: https://llamafactory.readthedocs.io/zh-cn/latest/ - **Colab**: https://colab.research.google.com/drive/1eRTPn37ltBbYsISy9Aw2NuI2Aq5CQrD9?usp=sharing - **Local machine**: Please refer to [usage](#getting-started) -- **PAI-DSW**: [Llama3 Example](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory) | [Qwen2-VL Example](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory_qwen2vl) +- **PAI-DSW**: [Llama3 Example](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory) | [Qwen2-VL Example](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory_qwen2vl) | [DeepSeek-R1-Distill Example](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory_deepseek_r1_distill_7b) - **Amazon SageMaker**: [Blog](https://aws.amazon.com/cn/blogs/china/a-one-stop-code-free-model-fine-tuning-deployment-platform-based-on-sagemaker-and-llama-factory/) > [!NOTE] diff --git a/README_zh.md b/README_zh.md index febe626e..c2010cd2 100644 --- a/README_zh.md +++ b/README_zh.md @@ -42,7 +42,7 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272 - **框架文档**：https://llamafactory.readthedocs.io/zh-cn/latest/ - **Colab**：https://colab.research.google.com/drive/1d5KQtbemerlSDSxZIfAaWXhKr30QypiK?usp=sharing - **本地机器**：请见[如何使用](#如何使用) -- **PAI-DSW**：[Llama3 案例](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory) | [Qwen2-VL 案例](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory_qwen2vl) +- **PAI-DSW**：[Llama3 案例](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory) | [Qwen2-VL 案例](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory_qwen2vl) | [DeepSeek-R1-Distill 案例](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory_deepseek_r1_distill_7b) - **Amazon SageMaker**：[博客](https://aws.amazon.com/cn/blogs/china/a-one-stop-code-free-model-fine-tuning-deployment-platform-based-on-sagemaker-and-llama-factory/) > [!NOTE] diff --git a/pyproject.toml b/pyproject.toml index b94d25d6..97084dc0 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -4,12 +4,19 @@ build-backend = "setuptools.build_meta" [project] name = "llamafactory" -dynamic = ["version", "dependencies", "optional-dependencies", "classifiers", "keywords", "authors", "license", "description", "readme"] -requires-python = ">=3.10" - -[project.scripts] -llamafactory-cli = "llamafactory.cli:main" -lmf = "llamafactory.cli:main" +dynamic = [ + "version", + "dependencies", + "optional-dependencies", + "requires-python", + "scripts", + "authors", + "description", + "readme", + "license", + "keywords", + "classifiers" +] [tool.ruff] target-version = "py38" diff --git a/requirements.txt b/requirements.txt index 03639758..743ee1e8 100644 --- a/requirements.txt +++ b/requirements.txt @@ -5,7 +5,7 @@ accelerate>=0.34.0,<=1.2.1 peft>=0.11.1,<=0.12.0 trl>=0.8.6,<=0.9.6 tokenizers>=0.19.0,<=0.21.0 -gradio>=4.38.0,<=5.12.0 +gradio>=4.38.0,<=5.18.0 pandas>=2.0.0 scipy einops diff --git a/scripts/vllm_infer.py b/scripts/vllm_infer.py index 2b78fa97..a42c2b4c 100644 --- a/scripts/vllm_infer.py +++ b/scripts/vllm_infer.py @@ -13,6 +13,7 @@ # limitations under the License. import json +from typing import Optional import fire from transformers import Seq2SeqTrainingArguments @@ -45,7 +46,7 @@ def vllm_infer( top_k: int = 50, max_new_tokens: int = 1024, repetition_penalty: float = 1.0, - seed: int = None, + seed: Optional[int] = None, pipeline_parallel_size: int = 1, image_max_pixels: int = 768 * 768, image_min_pixels: int = 32 * 32, diff --git a/src/llamafactory/webui/locales.py b/src/llamafactory/webui/locales.py index 30f4517b..53953646 100644 --- a/src/llamafactory/webui/locales.py +++ b/src/llamafactory/webui/locales.py @@ -1394,23 +1394,23 @@ LOCALES = { "use_galore": { "en": { "label": "Use GaLore", - "info": "Use GaLore optimizer.", + "info": "Use [GaLore](https://github.com/jiaweizzhao/GaLore) optimizer.", }, "ru": { "label": "Использовать GaLore", - "info": "Используйте оптимизатор GaLore.", + "info": "Используйте оптимизатор [GaLore](https://github.com/jiaweizzhao/GaLore).", }, "zh": { "label": "使用 GaLore", - "info": "使用 GaLore 优化器。", + "info": "使用 [GaLore](https://github.com/jiaweizzhao/GaLore) 优化器。", }, "ko": { "label": "GaLore 사용", - "info": "GaLore 최적화를 사용하세요.", + "info": "[GaLore](https://github.com/jiaweizzhao/GaLore) 최적화를 사용하세요.", }, "ja": { "label": "GaLore を使用", - "info": "GaLore オプティマイザーを使用します。", + "info": "[GaLore](https://github.com/jiaweizzhao/GaLore) オプティマイザーを使用します。", }, }, "galore_rank": { @@ -1521,23 +1521,23 @@ LOCALES = { "use_apollo": { "en": { "label": "Use APOLLO", - "info": "Use APOLLO optimizer.", + "info": "Use [APOLLO](https://github.com/zhuhanqing/APOLLO) optimizer.", }, "ru": { "label": "Использовать APOLLO", - "info": "Используйте оптимизатор APOLLO.", + "info": "Используйте оптимизатор [APOLLO](https://github.com/zhuhanqing/APOLLO).", }, "zh": { "label": "使用 APOLLO", - "info": "使用 APOLLO 优化器。", + "info": "使用 [APOLLO](https://github.com/zhuhanqing/APOLLO) 优化器。", }, "ko": { "label": "APOLLO 사용", - "info": "APOLLO 최적화를 사용하세요.", + "info": "[APOLLO](https://github.com/zhuhanqing/APOLLO) 최적화를 사용하세요.", }, "ja": { "label": "APOLLO を使用", - "info": "APOLLO オプティマイザーを使用します。", + "info": "[APOLLO](https://github.com/zhuhanqing/APOLLO) オプティマイザーを使用します。", }, }, "apollo_rank": { @@ -1648,23 +1648,23 @@ LOCALES = { "use_badam": { "en": { "label": "Use BAdam", - "info": "Enable the BAdam optimizer.", + "info": "Enable the [BAdam](https://github.com/Ledzy/BAdam) optimizer.", }, "ru": { "label": "Использовать BAdam", - "info": "Включите оптимизатор BAdam.", + "info": "Включите оптимизатор [BAdam](https://github.com/Ledzy/BAdam).", }, "zh": { "label": "使用 BAdam", - "info": "使用 BAdam 优化器。", + "info": "使用 [BAdam](https://github.com/Ledzy/BAdam) 优化器。", }, "ko": { "label": "BAdam 사용", - "info": "BAdam 옵티마이저를 사용합니다.", + "info": "[BAdam](https://github.com/Ledzy/BAdam) 옵티마이저를 사용합니다.", }, "ja": { "label": "BAdam を使用", - "info": "BAdam オプティマイザーを使用します。", + "info": "[BAdam](https://github.com/Ledzy/BAdam) オプティマイザーを使用します。", }, }, "badam_mode": { @@ -1775,23 +1775,23 @@ LOCALES = { "use_swanlab": { "en": { "label": "Use SwanLab", - "info": "Enable SwanLab for experiment tracking and visualization.", + "info": "Enable [SwanLab](https://swanlab.cn/) for experiment tracking and visualization.", }, "ru": { "label": "Использовать SwanLab", - "info": "Включить SwanLab для отслеживания и визуализации экспериментов.", + "info": "Включить [SwanLab](https://swanlab.cn/) для отслеживания и визуализации экспериментов.", }, "zh": { "label": "使用 SwanLab", - "info": "启用 SwanLab 进行实验跟踪和可视化。", + "info": "启用 [SwanLab](https://swanlab.cn/) 进行实验跟踪和可视化。", }, "ko": { "label": "SwanLab 사용", - "info": "SwanLab를 사용하여 실험을 추적하고 시각화합니다.", + "info": "[SwanLab](https://swanlab.cn/) 를 사용하여 실험을 추적하고 시각화합니다.", }, "ja": { "label": "SwanLab を使用", - "info": "SwanLab を有効にして実験の追跡と可視化を行います。", + "info": "[SwanLab](https://swanlab.cn/) を有効にして実験の追跡と可視化を行います。", }, }, "swanlab_project": { @@ -1860,7 +1860,7 @@ LOCALES = { "info": "API ключ для SwanLab.", }, "zh": { - "label": "SwanLab API密钥（非必填）", + "label": "SwanLab API 密钥（非必填）", "info": "用于在编程环境登录 SwanLab，已登录则无需填写。", }, "ko": {