v1.0 release (#8)

* Create .gitignore

* add data

* Create banner.png

* add oai_api_demo

* Create merge_llama3_with_chinese_lora_low_mem.py

* Create chat.sh

* add issue template

* init requirements.txt

* add ollama modelfile

* add downstream scripts

* update cmmlu script

* Update README.md

* update downstream scripts

* remove invalid args

* add inference script

* update longbench script

* Update ruozhiba_qa2449_gpt4turbo.json

* initial readme

---------

Co-authored-by: ymcui <[email protected]>
Co-authored-by: iMountTai <[email protected]>

.github/ISSUE_TEMPLATE/ISSUE_TEMPLATE_EN.yml

@@ -0,0 +1,77 @@
+name: English Issue Template
+description: For questions related to this project, we will prioritize issues with relatively complete content.
+
+body:
+  - type: markdown
+    attributes:
+      value: 💡 For open discussions, please visit [Discussion Space](https://github.com/ymcui/Chinese-LLaMA-Alpaca-3/discussions). Please do not open a discussion in Issue section. Thank you.
+  - type: checkboxes
+    id: mustchecks
+    attributes:
+      label: Check before submitting issues
+      description: Please check the following items before asking questions. Use the search function to find issues related to your problem.
+      options:
+        - label: Make sure to pull the latest code, as some issues and bugs have been fixed.
+          required: true
+        - label: I have read the [Wiki](https://github.com/ymcui/Chinese-LLaMA-Alpaca-3/wiki) and [FAQ section](https://github.com/ymcui/Chinese-LLaMA-Alpaca-3/wiki/FAQ) AND searched for similar issues and did not find a similar problem or solution
+          required: true
+        - label: Third-party plugin issues - e.g., [llama.cpp](https://github.com/ggerganov/llama.cpp), [text-generation-webui](https://github.com/oobabooga/text-generation-webui), we recommend checking the corresponding project for solutions
+          required: true
+  - type: dropdown
+    id: question-type
+    attributes:
+      label: Type of Issue
+      description: Please select the type of issue that best matches your problem
+      options:
+        - Download issue
+        - Model conversion and merging
+        - Model training and fine-tuning
+        - Model inference
+        - Model quantization and deployment
+        - Performance issue
+        - Other issues
+  - type: dropdown
+    id: model-type
+    attributes:
+      label: Base Model
+      description: Please provide the type of base model. For issues related to multiple models, please select the most appropriate one and specify all models in the main text.
+      options:
+        - Llama-3-Chinese-8B (Base Model)
+        - Llama-3-Chinese-Instruct-8B (Chat Model)
+        - Others
+  - type: dropdown
+    id: operating-system
+    attributes:
+      label: Operating System
+      description: Please provide your operating system
+      options:
+        - Windows
+        - macOS
+        - Linux
+  - type: textarea
+    id: question-detailed
+    attributes:
+      label: Describe your issue in detail
+      description: Please describe your problem as detail as possible. **For code-related issues, please provide the complete command to reproduce the problem.** This will help us locate the issue quickly.
+      value: |
+        ```
+        # Please copy-and-paste your command here.
+        ```
+  - type: textarea
+    id: dependencies
+    attributes:
+      label: Dependencies (must be provided for code-related issues)
+      description: Please provide the versions of common dependencies such as transformers, peft, torch, etc. Use `pip list | grep -E 'transformers|peft|torch|sentencepiece|bitsandbytes'`
+      value: |
+        ```
+        # Please copy-and-paste your dependencies here.
+        ```
+  - type: textarea
+    id: logs
+    attributes:
+      label: Execution logs or screenshots
+      description: Please provide logs in text format (upload files if content is too long), or alternatively, screenshots of the execution record.
+      value: |
+        ```
+        # Please copy-and-paste your logs here.
+        ```

.github/ISSUE_TEMPLATE/ISSUE_TEMPLATE_ZH.yml

@@ -0,0 +1,77 @@
+name: 中文提问模板
+description: 与本项目相关的问题提问，我们会优先查阅内容相对完整的issue。
+
+body:
+  - type: markdown
+    attributes:
+      value: 💡 开放式讨论请移步[讨论区](https://github.com/ymcui/Chinese-LLaMA-Alpaca-3/discussions)，请勿以issue形式提问，谢谢。
+  - type: checkboxes
+    id: mustchecks
+    attributes:
+      label: 提交前必须检查以下项目
+      description: 请在提问前检查以下项目，善用搜索功能查找与自己问题相关的issue。
+      options:
+        - label: 请确保使用的是仓库最新代码（git pull）
+          required: true      
+        - label: 已阅读[项目文档](https://github.com/ymcui/Chinese-LLaMA-Alpaca-3/wiki)和[FAQ章节](https://github.com/ymcui/Chinese-LLaMA-Alpaca-3/wiki/常见问题)并且已在Issue中对问题进行了搜索，没有找到相似问题和解决方案。
+          required: true
+        - label: 第三方插件问题：例如[llama.cpp](https://github.com/ggerganov/llama.cpp)、[text-generation-webui](https://github.com/oobabooga/text-generation-webui)等，建议优先去对应的项目中查找解决方案。
+          required: true
+  - type: dropdown
+    id: question-type
+    attributes:
+      label: 问题类型
+      description: 请选择最符合的问题类型
+      options:
+        - 下载问题
+        - 模型转换和合并
+        - 模型训练与精调
+        - 模型推理
+        - 模型量化和部署
+        - 效果问题
+        - 其他问题
+  - type: dropdown
+    id: model-type
+    attributes:
+      label: 基础模型
+      description: 请提供问题涉及的具体模型。
+      options:
+        - Llama-3-Chinese-8B（基座模型）
+        - Llama-3-Chinese-Instruct-8B（基座模型）
+        - Others
+  - type: dropdown
+    id: operating-system
+    attributes:
+      label: 操作系统
+      description: 请提供操作系统类型
+      options:
+        - Windows
+        - macOS
+        - Linux
+  - type: textarea
+    id: question-detailed
+    attributes:
+      label: 详细描述问题
+      description: 请尽量具体地描述遇到的问题，**代码程序类问题务必给出完整运行命令**，这将有助于快速定位问题所在。
+      value: |
+        ```
+        # 请在此处粘贴运行代码（请粘贴在本代码块里）
+        ```
+  - type: textarea
+    id: dependencies
+    attributes:
+      label: 依赖情况（代码类问题务必提供）
+      description: 请提供transformers, peft, torch等常规依赖库的版本：`pip list | grep -E 'transformers|peft|torch|sentencepiece|bitsandbytes'`
+      value: |
+        ```
+        # 请在此处粘贴依赖情况（请粘贴在本代码块里）
+        ```
+  - type: textarea
+    id: logs
+    attributes:
+      label: 运行日志或截图
+      description: 请优先提供文本形式的log（过长内容请上传文件），粘贴内容放在markdown代码块。或者提供截图形式的运行记录。
+      value: |
+        ```
+        # 请在此处粘贴运行日志（请粘贴在本代码块里）
+        ```

.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1 @@
+blank_issues_enabled: false

.github/workflows/stale.yml

@@ -0,0 +1,31 @@
+# This workflow warns and then closes issues and PRs that have had no activity for a specified amount of time.
+#
+# You can adjust the behavior by modifying this file.
+# For more information, see:
+# https://github.com/actions/stale
+name: Mark stale issues and pull requests
+
+on:
+  schedule:
+  - cron: '0 22 * * *'
+
+jobs:
+  stale:
+
+    runs-on: ubuntu-latest
+    permissions:
+      issues: write
+      pull-requests: read
+
+    steps:
+    - uses: actions/stale@v8
+      with:
+        repo-token: ${{ secrets.GITHUB_TOKEN }}
+        stale-issue-message: 'This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your consideration.'
+        stale-pr-message: 'This PR has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your consideration.'
+        stale-issue-label: 'stale'
+        stale-pr-label: 'stale'
+        operations-per-run: 500
+        close-issue-message: 'Closing the issue, since no updates observed. Feel free to re-open if you need any further assistance.'
+        days-before-stale: 14
+        days-before-close: 7