Explore

Find agent skills by outcome

4,151 skills indexed with the new KISS metadata standard.

Showing 24 of 4,151Category: General

PromptBeginner5 minmarkdown

Qwen-VL-Chat使用教程

Qwen-VL-Chat是通用多模态大规模语言模型，因此它可以完成多种视觉语言任务。在本教程之中，我们会给出一些简明的例子，用以展示Qwen-VL-Chat在**视觉问答，文字理解，图表数学推理，多图理解和Grounding**(根据指令标注图片中指定区域的包围框)等多方面的能力。请注意，展示的例子远非Qwen-VL-Chat能力的极限，**您可以通过更换不同的输入图像和提示词（Prompt），来进一步挖掘Qwen-VL-Chat的能力！**

PromptBeginner5 minmarkdown

<p align="left">

<a href="README_CN.md">中文</a>&nbsp ｜ &nbspEnglish&nbsp&nbsp ｜ &nbsp<a href="README_JA.md">日本語</a>&nbsp｜ &nbsp<a href="README_KO.md">한국어</a>&nbsp

PromptBeginner5 minmarkdown

<p align="left">

中文</a>&nbsp ｜ &nbsp<a href="README.md">English</a>&nbsp&nbsp ｜ &nbsp<a href="README_JA.md">日本語</a>&nbsp｜ &nbsp<a href="README_KO.md">한국어</a>&nbsp

PromptBeginner5 minmarkdown

<p align="left">

<a href="README_CN.md">中文</a>&nbsp ｜ &nbsp <a href="README.md">English</a>&nbsp ｜ &nbsp日本語&nbsp

PromptBeginner5 minmarkdown

FAQ

4.31.0 is preferred.

PromptBeginner5 minmarkdown

FAQ

4.31.0 が望ましいです。

PromptBeginner5 minmarkdown

FAQ

4.31.0 버전을 사용하는 것을 선호합니다.

PromptBeginner5 minmarkdown

FAQ

建议使用4.31.0。

PromptBeginner5 minmarkdown

pycache

*.so

PromptBeginner5 minmarkdown

qwen web demo

docker build -t qwen-vl-chat:webdemo --platform linux/amd64 -f Dockerfile.qwendemo .

PromptBeginner5 minmarkdown

<div align="center">

<div align="center">

PromptBeginner5 minmarkdown

[flake8]

ignore = E501, F403, C901, W504, W605, E251, E122, E126, E127, E722, W503, E128, E741, E731, E701

PromptBeginner5 minmarkdown

Byte-compiled / optimized / DLL files

__pycache__/

PromptBeginner5 minmarkdown

exclude: ^internvl_chat_llava/

repos:

PromptBeginner5 minmarkdown

🛠️ Installation

- Clone this repository:

PromptBeginner5 minmarkdown

<div align="center">

<div align="center">

PromptBeginner5 minmarkdown

CogVLM & CogAgent

📗 [中文版README](./README_zh.md)

PromptBeginner5 minmarkdown

CogVLM & CogAgent

📗 [README in English](./README.md)

PromptBeginner5 minmarkdown

CogVLM-SFT-311K: Bilingual Visual Instruction Data in CogVLM SFT

CogVLM-SFT-311K is the primary aligned corpus used in the initial training of CogVLM v1.0. The process of constructing this dataset is as follows:

PromptBeginner5 minmarkdown

CogVLM-SFT-311K：CogVLM SFT 中的双语视觉指令数据集

CogVLM-SFT-311K 是我们在训练 **CogVLM v1.0** 最初版本时使用的主要对齐语料库。此数据集的构建过程如下：

PromptBeginner5 minmarkdown

SAT_HOME=~/.sat_models

LOCAL_WORLD_SIZE=8

PromptBeginner5 minmarkdown

.hypothesis/

__pycache__

PromptBeginner5 minmarkdown

Configuration for Cog ⚙️

build:

PromptBeginner5 minmarkdown

The .dockerignore file excludes files from the container build process.

.git