From 5d62a51c12061c59b509db8fe367817f4e48f737 Mon Sep 17 00:00:00 2001 From: hiyouga Date: Tue, 16 Apr 2024 18:09:16 +0800 Subject: [PATCH] update readme and gradio version --- README.md | 9 ++++++++- README_zh.md | 11 +++++++++-- requirements.txt | 2 +- src/llmtuner/extras/misc.py | 2 +- 4 files changed, 19 insertions(+), 5 deletions(-) diff --git a/README.md b/README.md index 276bc6a7..95e3e8a0 100644 --- a/README.md +++ b/README.md @@ -5,7 +5,7 @@ [![GitHub last commit](https://img.shields.io/github/last-commit/hiyouga/LLaMA-Factory)](https://github.com/hiyouga/LLaMA-Factory/commits/main) [![PyPI](https://img.shields.io/pypi/v/llmtuner)](https://pypi.org/project/llmtuner/) [![Downloads](https://static.pepy.tech/badge/llmtuner)](https://pypi.org/project/llmtuner/) -[![Citation](https://img.shields.io/badge/citation-28-green)](#projects-using-llama-factory) +[![Citation](https://img.shields.io/badge/citation-34-green)](#projects-using-llama-factory) [![GitHub pull request](https://img.shields.io/badge/PRs-welcome-blue)](https://github.com/hiyouga/LLaMA-Factory/pulls) [![Discord](https://dcbadge.vercel.app/api/server/rKfvV9r9FK?compact=true&style=flat)](https://discord.gg/rKfvV9r9FK) [![Twitter](https://img.shields.io/twitter/follow/llamafactory_ai)](https://twitter.com/llamafactory_ai) @@ -332,6 +332,7 @@ To enable FlashAttention-2 on the Windows platform, you need to install the prec ```bash export CUDA_VISIBLE_DEVICES=0 # `set CUDA_VISIBLE_DEVICES=0` for Windows +export GRADIO_SERVER_PORT=7860 # `set GRADIO_SERVER_PORT=7860` for Windows python src/train_web.py # or python -m llmtuner.webui.interface ``` @@ -417,8 +418,14 @@ If you have a project that should be incorporated, please contact via email or c 1. Huang et al. Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning. 2024. [[arxiv]](https://arxiv.org/abs/2403.02333) 1. Duan et al. Negating Negatives: Alignment without Human Positive Samples via Distributional Dispreference Optimization. 2024. [[arxiv]](https://arxiv.org/abs/2403.03419) 1. Xie and Schwertfeger. Empowering Robotics with Large Language Models: osmAG Map Comprehension with LLMs. 2024. [[arxiv]](https://arxiv.org/abs/2403.08228) +1. Zhang et al. EDT: Improving Large Language Models' Generation by Entropy-based Dynamic Temperature Sampling. 2024. [[arxiv]](https://arxiv.org/abs/2403.14541) 1. Weller et al. FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions. 2024. [[arxiv]](https://arxiv.org/abs/2403.15246) 1. Hongbin Na. CBT-LLM: A Chinese Large Language Model for Cognitive Behavioral Therapy-based Mental Health Question Answering. 2024. [[arxiv]](https://arxiv.org/abs/2403.16008) +1. Zan et al. CodeS: Natural Language to Code Repository via Multi-Layer Sketch. 2024. [[arxiv]](https://arxiv.org/abs/2403.16443) +1. Liu et al. Extensive Self-Contrast Enables Feedback-Free Language Model Alignment. 2024. [[arxiv]](https://arxiv.org/abs/2404.00604) +1. Luo et al. BAdam: A Memory Efficient Full Parameter Training Method for Large Language Models. 2024. [[arxiv]](https://arxiv.org/abs/2404.02827) +1. Du et al. Chinese Tiny LLM: Pretraining a Chinese-Centric Large Language Model. 2024. [[arxiv]](https://arxiv.org/abs/2404.04167) +1. Liu et al. Dynamic Generation of Personalities with Large Language Models. 2024. [[arxiv]](https://arxiv.org/abs/2404.07084) 1. **[StarWhisper](https://github.com/Yu-Yang-Li/StarWhisper)**: A large language model for Astronomy, based on ChatGLM2-6B and Qwen-14B. 1. **[DISC-LawLLM](https://github.com/FudanDISC/DISC-LawLLM)**: A large language model specialized in Chinese legal domain, based on Baichuan-13B, is capable of retrieving and reasoning on legal knowledge. 1. **[Sunsimiao](https://github.com/thomas-yanxin/Sunsimiao)**: A large language model specialized in Chinese medical domain, based on Baichuan-7B and ChatGLM-6B. diff --git a/README_zh.md b/README_zh.md index 4420d8bb..d8b0c518 100644 --- a/README_zh.md +++ b/README_zh.md @@ -5,7 +5,7 @@ [![GitHub last commit](https://img.shields.io/github/last-commit/hiyouga/LLaMA-Factory)](https://github.com/hiyouga/LLaMA-Factory/commits/main) [![PyPI](https://img.shields.io/pypi/v/llmtuner)](https://pypi.org/project/llmtuner/) [![Downloads](https://static.pepy.tech/badge/llmtuner)](https://pypi.org/project/llmtuner/) -[![Citation](https://img.shields.io/badge/citation-28-green)](#使用了-llama-factory-的项目) +[![Citation](https://img.shields.io/badge/citation-34-green)](#使用了-llama-factory-的项目) [![GitHub pull request](https://img.shields.io/badge/PRs-welcome-blue)](https://github.com/hiyouga/LLaMA-Factory/pulls) [![Discord](https://dcbadge.vercel.app/api/server/rKfvV9r9FK?compact=true&style=flat)](https://discord.gg/rKfvV9r9FK) [![Twitter](https://img.shields.io/twitter/follow/llamafactory_ai)](https://twitter.com/llamafactory_ai) @@ -332,6 +332,7 @@ pip install https://github.com/jllllll/bitsandbytes-windows-webui/releases/downl ```bash export CUDA_VISIBLE_DEVICES=0 # Windows 使用 `set CUDA_VISIBLE_DEVICES=0` +export GRADIO_SERVER_PORT=7860 # Windows 使用 `set GRADIO_SERVER_PORT=7860` python src/train_web.py # 或 python -m llmtuner.webui.interface ``` @@ -392,7 +393,7 @@ export USE_MODELSCOPE_HUB=1 # Windows 使用 `set USE_MODELSCOPE_HUB=1` ## 使用了 LLaMA Factory 的项目 -如果您有项目希望添加至上述列表，请通过邮件联系或者创建一个 PR。 +如果您有项目希望添加至下述列表，请通过邮件联系或者创建一个 PR。
点击显示 @@ -417,8 +418,14 @@ export USE_MODELSCOPE_HUB=1 # Windows 使用 `set USE_MODELSCOPE_HUB=1` 1. Huang et al. Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning. 2024. [[arxiv]](https://arxiv.org/abs/2403.02333) 1. Duan et al. Negating Negatives: Alignment without Human Positive Samples via Distributional Dispreference Optimization. 2024. [[arxiv]](https://arxiv.org/abs/2403.03419) 1. Xie and Schwertfeger. Empowering Robotics with Large Language Models: osmAG Map Comprehension with LLMs. 2024. [[arxiv]](https://arxiv.org/abs/2403.08228) +1. Zhang et al. EDT: Improving Large Language Models' Generation by Entropy-based Dynamic Temperature Sampling. 2024. [[arxiv]](https://arxiv.org/abs/2403.14541) 1. Weller et al. FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions. 2024. [[arxiv]](https://arxiv.org/abs/2403.15246) 1. Hongbin Na. CBT-LLM: A Chinese Large Language Model for Cognitive Behavioral Therapy-based Mental Health Question Answering. 2024. [[arxiv]](https://arxiv.org/abs/2403.16008) +1. Zan et al. CodeS: Natural Language to Code Repository via Multi-Layer Sketch. 2024. [[arxiv]](https://arxiv.org/abs/2403.16443) +1. Liu et al. Extensive Self-Contrast Enables Feedback-Free Language Model Alignment. 2024. [[arxiv]](https://arxiv.org/abs/2404.00604) +1. Luo et al. BAdam: A Memory Efficient Full Parameter Training Method for Large Language Models. 2024. [[arxiv]](https://arxiv.org/abs/2404.02827) +1. Du et al. Chinese Tiny LLM: Pretraining a Chinese-Centric Large Language Model. 2024. [[arxiv]](https://arxiv.org/abs/2404.04167) +1. Liu et al. Dynamic Generation of Personalities with Large Language Models. 2024. [[arxiv]](https://arxiv.org/abs/2404.07084) 1. **[StarWhisper](https://github.com/Yu-Yang-Li/StarWhisper)**: 天文大模型 StarWhisper，基于 ChatGLM2-6B 和 Qwen-14B 在天文数据上微调而得。 1. **[DISC-LawLLM](https://github.com/FudanDISC/DISC-LawLLM)**: 中文法律领域大模型 DISC-LawLLM，基于 Baichuan-13B 微调而得，具有法律推理和知识检索能力。 1. **[Sunsimiao](https://github.com/thomas-yanxin/Sunsimiao)**: 孙思邈中文医疗大模型 Sumsimiao，基于 Baichuan-7B 和 ChatGLM-6B 在中文医疗数据上微调而得。 diff --git a/requirements.txt b/requirements.txt index 1fa5a142..3928d28d 100644 --- a/requirements.txt +++ b/requirements.txt @@ -4,7 +4,7 @@ datasets>=2.14.3 accelerate>=0.27.2 peft>=0.10.0 trl>=0.8.1 -gradio>=4.0.0,<=4.21.0 +gradio>=4.0.0 scipy einops sentencepiece diff --git a/src/llmtuner/extras/misc.py b/src/llmtuner/extras/misc.py index 12d1446f..1a1f81a0 100644 --- a/src/llmtuner/extras/misc.py +++ b/src/llmtuner/extras/misc.py @@ -66,7 +66,7 @@ def check_dependencies() -> None: require_version("accelerate>=0.27.2", "To fix: pip install accelerate>=0.27.2") require_version("peft>=0.10.0", "To fix: pip install peft>=0.10.0") require_version("trl>=0.8.1", "To fix: pip install trl>=0.8.1") - require_version("gradio>=4.0.0,<=4.21.0", "To fix: pip install gradio==4.21.0") + require_version("gradio>=4.0.0", "To fix: pip install gradio>=4.0.0") def count_parameters(model: torch.nn.Module) -> Tuple[int, int]: