diff --git a/README.md b/README.md index 6ac73e20..c14c1500 100644 --- a/README.md +++ b/README.md @@ -5,7 +5,7 @@ [![GitHub contributors](https://img.shields.io/github/contributors/hiyouga/LLaMA-Factory?color=orange)](https://github.com/hiyouga/LLaMA-Factory/graphs/contributors) [![GitHub workflow](https://github.com/hiyouga/LLaMA-Factory/actions/workflows/tests.yml/badge.svg)](https://github.com/hiyouga/LLaMA-Factory/actions/workflows/tests.yml) [![PyPI](https://img.shields.io/pypi/v/llamafactory)](https://pypi.org/project/llamafactory/) -[![Citation](https://img.shields.io/badge/citation-818-green)](https://scholar.google.com/scholar?cites=12620864006390196564) +[![Citation](https://img.shields.io/badge/citation-840-green)](https://scholar.google.com/scholar?cites=12620864006390196564) [![Docker Pulls](https://img.shields.io/docker/pulls/hiyouga/llamafactory)](https://hub.docker.com/r/hiyouga/llamafactory/tags) [![Twitter](https://img.shields.io/twitter/follow/llamafactory_ai)](https://twitter.com/llamafactory_ai) @@ -13,7 +13,8 @@ [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1eRTPn37ltBbYsISy9Aw2NuI2Aq5CQrD9?usp=sharing) [![Open in DSW](https://gallery.pai-ml.com/assets/open-in-dsw.svg)](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory) -[![Open in Alaya](assets/alaya_new.svg)](https://docs.alayanew.com/docs/documents/newActivities/llamafactory/?utm_source=LLaMA-Factory) +[![Open in Lab4ai](assets/lab4ai.svg)](https://www.lab4ai.cn/course/detail?id=7c13e60f6137474eb40f6fd3983c0f46?utm_source=LLaMA-Factory) +[![Open in Online](assets/online.svg)](https://www.llamafactory.com.cn/?utm_source=LLaMA-Factory) [![Open in Spaces](https://img.shields.io/badge/🤗-Open%20in%20Spaces-blue)](https://huggingface.co/spaces/hiyouga/LLaMA-Board) [![Open in Studios](https://img.shields.io/badge/ModelScope-Open%20in%20Studios-blue)](https://modelscope.cn/studios/hiyouga/LLaMA-Board) [![Open in Novita](https://img.shields.io/badge/Novita-Deploy%20Template-blue)](https://novita.ai/templates-library/105981?sharer=88115474-394e-4bda-968e-b88e123d0c47) @@ -35,7 +36,7 @@ -👋 Join our [WeChat group](assets/wechat.jpg), [NPU user group](assets/wechat_npu.jpg) or [Alaya NeW user group](assets/wechat_alaya.png). +👋 Join our [WeChat](assets/wechat.jpg), [NPU](assets/wechat_npu.jpg), [Lab4AI](assets/wechat_lab4ai.jpg), [LLaMA Factory Online](assets/wechat_online.jpg) user group. \[ English | [中文](README_zh.md) \] @@ -51,6 +52,8 @@ Choose your path: - **Local machine**: Please refer to [usage](#getting-started) - **PAI-DSW (free trial)**: https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory - **Alaya NeW (cloud GPU deal)**: https://docs.alayanew.com/docs/documents/useGuide/LLaMAFactory/mutiple/?utm_source=LLaMA-Factory +- **Official Course**: https://www.lab4ai.cn/course/detail?id=7c13e60f6137474eb40f6fd3983c0f46?utm_source=LLaMA-Factory +- **LLaMA Factory Online**: https://www.llamafactory.com.cn/?utm_source=LLaMA-Factory > [!NOTE] > Except for the above links, all other websites are unauthorized third-party websites. Please carefully use them. @@ -69,6 +72,7 @@ Choose your path: - [Data Preparation](#data-preparation) - [Quickstart](#quickstart) - [Fine-Tuning with LLaMA Board GUI](#fine-tuning-with-llama-board-gui-powered-by-gradio) + - [LLaMA Factory Online](#llama-factory-online) - [Build Docker](#build-docker) - [Deploy with OpenAI-style API and vLLM](#deploy-with-openai-style-api-and-vllm) - [Download from ModelScope Hub](#download-from-modelscope-hub) @@ -101,13 +105,13 @@ Choose your path: ## Blogs - [Fine-tune GPT-OSS for Role-Playing using LLaMA-Factory](https://docs.llamafactory.com.cn/docs/documents/best-practice/gptroleplay/?utm_source=LLaMA-Factory) (Chinese) -- [Fine-tune Llama3.1-70B for Medical Diagnosis using LLaMA-Factory](https://docs.alayanew.com/docs/documents/bestPractice/bigModel/llama70B/?utm_source=LLaMA-Factory) (Chinese) - [A One-Stop Code-Free Model Reinforcement Learning and Deployment Platform based on LLaMA-Factory and EasyR1](https://aws.amazon.com/cn/blogs/china/building-llm-model-hub-based-on-llamafactory-and-easyr1/) (Chinese) - [How Apoidea Group enhances visual information extraction from banking documents with multimodal models using LLaMA-Factory on Amazon SageMaker HyperPod](https://aws.amazon.com/cn/blogs/machine-learning/how-apoidea-group-enhances-visual-information-extraction-from-banking-documents-with-multimodal-models-using-llama-factory-on-amazon-sagemaker-hyperpod/) (English) - [Easy Dataset × LLaMA Factory: Enabling LLMs to Efficiently Learn Domain Knowledge](https://buaa-act.feishu.cn/wiki/GVzlwYcRFiR8OLkHbL6cQpYin7g) (English)
All Blogs +- [Fine-tune Llama3.1-70B for Medical Diagnosis using LLaMA-Factory](https://docs.alayanew.com/docs/documents/bestPractice/bigModel/llama70B/?utm_source=LLaMA-Factory) (Chinese) - [Fine-tune Qwen2.5-VL for Autonomous Driving using LLaMA-Factory](https://docs.alayanew.com/docs/documents/useGuide/LLaMAFactory/mutiple/?utm_source=LLaMA-Factory) (Chinese) - [LLaMA Factory: Fine-tuning the DeepSeek-R1-Distill-Qwen-7B Model for News Classifier](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory_deepseek_r1_distill_7b) (Chinese) - [A One-Stop Code-Free Model Fine-Tuning \& Deployment Platform based on SageMaker and LLaMA-Factory](https://aws.amazon.com/cn/blogs/china/a-one-stop-code-free-model-fine-tuning-deployment-platform-based-on-sagemaker-and-llama-factory/) (Chinese) @@ -657,6 +661,10 @@ See [examples/README.md](examples/README.md) for advanced usage (including distr llamafactory-cli webui ``` +### LLaMA Factory Online + +Read our [documentation](https://docs.llamafactory.com.cn/docs/documents/quickstart/getstarted/?utm_source=LLaMA-Factory). + ### Build Docker For CUDA users: diff --git a/README_zh.md b/README_zh.md index 7468aa17..1a80dcdc 100644 --- a/README_zh.md +++ b/README_zh.md @@ -5,7 +5,7 @@ [![GitHub contributors](https://img.shields.io/github/contributors/hiyouga/LLaMA-Factory?color=orange)](https://github.com/hiyouga/LLaMA-Factory/graphs/contributors) [![GitHub workflow](https://github.com/hiyouga/LLaMA-Factory/actions/workflows/tests.yml/badge.svg)](https://github.com/hiyouga/LLaMA-Factory/actions/workflows/tests.yml) [![PyPI](https://img.shields.io/pypi/v/llamafactory)](https://pypi.org/project/llamafactory/) -[![Citation](https://img.shields.io/badge/citation-818-green)](https://scholar.google.com/scholar?cites=12620864006390196564) +[![Citation](https://img.shields.io/badge/citation-840-green)](https://scholar.google.com/scholar?cites=12620864006390196564) [![Docker Pulls](https://img.shields.io/docker/pulls/hiyouga/llamafactory)](https://hub.docker.com/r/hiyouga/llamafactory/tags) [![Twitter](https://img.shields.io/twitter/follow/llamafactory_ai)](https://twitter.com/llamafactory_ai) @@ -13,7 +13,8 @@ [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1d5KQtbemerlSDSxZIfAaWXhKr30QypiK?usp=sharing) [![Open in DSW](https://gallery.pai-ml.com/assets/open-in-dsw.svg)](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory) -[![Open in Alaya](assets/alaya_new.svg)](https://docs.alayanew.com/docs/documents/newActivities/llamafactory/?utm_source=LLaMA-Factory) +[![Open in Lab4ai](assets/lab4ai.svg)](https://www.lab4ai.cn/course/detail?id=7c13e60f6137474eb40f6fd3983c0f46?utm_source=LLaMA-Factory) +[![Open in Online](assets/online.svg)](https://www.llamafactory.com.cn/?utm_source=LLaMA-Factory) [![Open in Spaces](https://img.shields.io/badge/🤗-Open%20in%20Spaces-blue)](https://huggingface.co/spaces/hiyouga/LLaMA-Board) [![Open in Studios](https://img.shields.io/badge/ModelScope-Open%20in%20Studios-blue)](https://modelscope.cn/studios/hiyouga/LLaMA-Board) [![Open in Novita](https://img.shields.io/badge/Novita-Deploy%20Template-blue)](https://novita.ai/templates-library/105981?sharer=88115474-394e-4bda-968e-b88e123d0c47) @@ -35,7 +36,7 @@ -👋 加入我们的[微信群](assets/wechat.jpg)、[NPU 用户群](assets/wechat_npu.jpg)或 [九章智算云算力优惠群](assets/wechat_alaya.png)。 +👋 加入我们的[微信群](assets/wechat.jpg)、[NPU 用户群](assets/wechat_npu.jpg)、[大模型实验室群](assets/wechat_lab4ai.jpg) 或 [LLaMA Factory Online 用户群](assets/wechat_online.png)。 \[ [English](README.md) | 中文 \] @@ -53,6 +54,8 @@ https://github.com/user-attachments/assets/43b700c6-a178-41db-b1f8-8190a5d3fcfc - **本地机器**：请见[如何使用](#如何使用) - **PAI-DSW（免费试用）**：https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory - **九章智算云（算力优惠活动）**：https://docs.alayanew.com/docs/documents/useGuide/LLaMAFactory/mutiple/?utm_source=LLaMA-Factory +- **官方课程**：https://www.lab4ai.cn/course/detail?id=7c13e60f6137474eb40f6fd3983c0f46?utm_source=LLaMA-Factory +- **LLaMA Factory Online（在线微调）**：https://www.llamafactory.com.cn/?utm_source=LLaMA-Factory > [!NOTE] > 除上述链接以外的其他网站均为未经许可的第三方网站，请小心甄别。 @@ -71,6 +74,7 @@ https://github.com/user-attachments/assets/43b700c6-a178-41db-b1f8-8190a5d3fcfc - [数据准备](#数据准备) - [快速开始](#快速开始) - [LLaMA Board 可视化微调](#llama-board-可视化微调由-gradio-驱动) + - [LLaMA Factory Online 在线微调](#llama-factory-online-在线微调) - [构建 Docker](#构建-docker) - [利用 vLLM 部署 OpenAI API](#利用-vllm-部署-openai-api) - [从魔搭社区下载](#从魔搭社区下载) @@ -103,13 +107,13 @@ https://github.com/user-attachments/assets/43b700c6-a178-41db-b1f8-8190a5d3fcfc ## 官方博客 - [使用 LLaMA-Factory 构建 GPT-OSS 角色扮演模型](https://docs.llamafactory.com.cn/docs/documents/best-practice/gptroleplay/?utm_source=LLaMA-Factory)（中文） -- [使用 LLaMA-Factory 微调 Llama3.1-70B 医学诊断模型](https://docs.alayanew.com/docs/documents/bestPractice/bigModel/llama70B/?utm_source=LLaMA-Factory)（中文） - [基于 LLaMA-Factory 和 EasyR1 打造一站式无代码大模型强化学习和部署平台 LLM Model Hub](https://aws.amazon.com/cn/blogs/china/building-llm-model-hub-based-on-llamafactory-and-easyr1/)（中文） - [通过亚马逊 SageMaker HyperPod 上的 LLaMA-Factory 增强多模态模型银行文档的视觉信息提取](https://aws.amazon.com/cn/blogs/machine-learning/how-apoidea-group-enhances-visual-information-extraction-from-banking-documents-with-multimodal-models-using-llama-factory-on-amazon-sagemaker-hyperpod/)（英文） - [Easy Dataset × LLaMA Factory: 让大模型高效学习领域知识](https://buaa-act.feishu.cn/wiki/KY9xwTGs1iqHrRkjXBwcZP9WnL9)（中文）
全部博客 +- [使用 LLaMA-Factory 微调 Llama3.1-70B 医学诊断模型](https://docs.alayanew.com/docs/documents/bestPractice/bigModel/llama70B/?utm_source=LLaMA-Factory)（中文） - [使用 LLaMA-Factory 微调 Qwen2.5-VL 实现自动驾驶场景微调](https://docs.alayanew.com/docs/documents/useGuide/LLaMAFactory/mutiple/?utm_source=LLaMA-Factory)（中文） - [LLaMA Factory：微调 DeepSeek-R1-Distill-Qwen-7B 模型实现新闻标题分类器](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory_deepseek_r1_distill_7b)（中文） - [基于 Amazon SageMaker 和 LLaMA-Factory 打造一站式无代码模型微调部署平台 Model Hub](https://aws.amazon.com/cn/blogs/china/a-one-stop-code-free-model-fine-tuning-deployment-platform-based-on-sagemaker-and-llama-factory/)（中文） @@ -659,6 +663,10 @@ llamafactory-cli export examples/merge_lora/llama3_lora_sft.yaml llamafactory-cli webui ``` +### LLaMA Factory Online 在线微调 + +详情阅读该[文档](https://docs.llamafactory.com.cn/docs/documents/quickstart/getstarted/?utm_source=LLaMA-Factory)。 + ### 构建 Docker CUDA 用户： diff --git a/assets/alaya_new.svg b/assets/alaya_new.svg deleted file mode 100644 index 3568e151..00000000 --- a/assets/alaya_new.svg +++ /dev/null @@ -1,38 +0,0 @@ - - - - - background - - - - Layer 1 - - - - - - - - - Ｏpen in Alaya NeW - - - - - diff --git a/assets/lab4ai.svg b/assets/lab4ai.svg new file mode 100644 index 00000000..ad83c1bb --- /dev/null +++ b/assets/lab4ai.svg @@ -0,0 +1,536 @@ + + + + + + + + + + + + + + + + + + + diff --git a/assets/online.svg b/assets/online.svg new file mode 100644 index 00000000..e9051e30 --- /dev/null +++ b/assets/online.svg @@ -0,0 +1,789 @@ + + + + + + + + + + + + + + + + + + + + + + diff --git a/assets/wechat.jpg b/assets/wechat.jpg index 3a3c5d77..f1e0b0b0 100644 Binary files a/assets/wechat.jpg and b/assets/wechat.jpg differ diff --git a/assets/wechat_alaya.png b/assets/wechat_alaya.png deleted file mode 100644 index 4b638e1c..00000000 Binary files a/assets/wechat_alaya.png and /dev/null differ diff --git a/assets/wechat_lab4ai.jpg b/assets/wechat_lab4ai.jpg new file mode 100644 index 00000000..2699512b Binary files /dev/null and b/assets/wechat_lab4ai.jpg differ diff --git a/assets/wechat_npu.jpg b/assets/wechat_npu.jpg index 2aa857d8..1d9e4adf 100644 Binary files a/assets/wechat_npu.jpg and b/assets/wechat_npu.jpg differ diff --git a/assets/wechat_online.jpg b/assets/wechat_online.jpg new file mode 100644 index 00000000..db2371e8 Binary files /dev/null and b/assets/wechat_online.jpg differ diff --git a/src/llamafactory/model/model_utils/moe.py b/src/llamafactory/model/model_utils/moe.py index 602c71fd..2cd47d1e 100644 --- a/src/llamafactory/model/model_utils/moe.py +++ b/src/llamafactory/model/model_utils/moe.py @@ -105,7 +105,7 @@ def add_z3_leaf_module(model: "PreTrainedModel") -> None: _set_z3_leaf_modules(model, [Qwen2MoeSparseMoeBlock]) - if model_type == "qwen3_moe" or text_architectures == "Qwen3MoeForCausalLM": # for internvl_3_5 + if model_type == "qwen3_moe" or text_architectures == "Qwen3MoeForCausalLM": # for internvl_3_5 from transformers.models.qwen3_moe.modeling_qwen3_moe import Qwen3MoeSparseMoeBlock _set_z3_leaf_modules(model, [Qwen3MoeSparseMoeBlock]) @@ -116,7 +116,7 @@ def configure_moe(config: "PretrainedConfig", model_args: "ModelArguments", is_t return model_type = getattr(config, "model_type", None) - text_config = getattr(config, "text_config", None) # for multimodal model + text_config = getattr(config, "text_config", None) # for multimodal model if model_type in [ "dbrx", @@ -133,8 +133,8 @@ def configure_moe(config: "PretrainedConfig", model_args: "ModelArguments", is_t setattr(config, "output_router_logits", True) if text_config and getattr(text_config, "model_type", None) in [ - "glm4v_moe_text", # glmv4_5 - "qwen3_moe", # internvl_3_5 + "glm4v_moe_text", # glmv4_5 + "qwen3_moe", # internvl_3_5 ]: setattr(text_config, "output_router_logits", True)