[CI]: fix and pass pre-commit hook (InternLM#666)

deep-practice · Jan 26, 2024 · 78bcb07 · 78bcb07
1 parent 1cb9870
commit 78bcb07
Show file tree

Hide file tree

Showing 28 changed files with 638 additions and 547 deletions.
diff --git a/.github/workflows/daily_tests.yaml b/.github/workflows/daily_tests.yaml
@@ -26,8 +26,8 @@ jobs:
         pip install transformers
         pip install sentencepiece
         srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --job-name=${GITHUB_RUN_ID}-${GITHUB_JOB} --gpus-per-task=2 pytest -s -v --color=yes ./tests/test_hf_model.py
-        conda deactivate 
-    
+        conda deactivate
+
   clear_env:
       if: ${{ !cancelled() }}
       needs: [HF_model]

diff --git a/.github/workflows/lint_check.yaml b/.github/workflows/lint_check.yaml
@@ -24,15 +24,3 @@ jobs:
         run: |
           pip install isort==5.12.0
           isort --check --profile=black .
-
-      - name: lint-black
-        run: |
-          pip install black==22.8.0
-          BLACK_EXCLUDE_SETTINGS='\.venv/|\.local/|\.cache/|\.git/'
-          black --line-length=120 --check --exclude $BLACK_EXCLUDE_SETTINGS ./chat/web_demo.py
-
-      - name: lint-pylint
-        run: |
-          pip install pylint==v2.17.2
-          PYLINT_DISABLE_LIST="C0114,C0415,W0212,W0235,W0238,W0621,C0103,R1735,C2801,E0402,C0412,W0719,R1728,W1514,W0718,W0105,W0707,C0209,W0703,W1203"
-          pylint --rcfile .pylintrc --disable=$PYLINT_DISABLE_LIST ./chat/web_demo.py
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -1,53 +1,44 @@
-# See https://pre-commit.com for more information
-# See https://pre-commit.com/hooks.html for more hooks
 repos:
--   repo: https://github.com/psf/black
-    rev: '22.8.0'
+  - repo: https://github.com/PyCQA/flake8
+    rev: 5.0.4
     hooks:
-    -   id: black
-        args:
-        - --line-length=120
--   repo: https://github.com/pycqa/isort
-    rev: '5.12.0'
+      - id: flake8
+  - repo: https://github.com/PyCQA/isort
+    rev: 5.11.5
     hooks:
-    -   id: isort
-        name: isort
-        files: "\\.(py)$"
-        args:
-        - --profile=black
--   repo: https://github.com/PyCQA/flake8
-    rev: '3.8.4'
+      - id: isort
+  - repo: https://github.com/pre-commit/mirrors-yapf
+    rev: v0.32.0
     hooks:
-    -   id: flake8
-        args:
-        - --ignore=F403,F405,W504,W503,E203
-        - --max-line-length=120
--   repo: https://github.com/pre-commit/pygrep-hooks
-    rev: v1.9.0
+      - id: yapf
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.2.1
     hooks:
-    -   id: python-check-blanket-noqa
--   repo: https://github.com/pre-commit/pre-commit-hooks
+      - id: codespell
+  - repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v4.3.0
     hooks:
-    -   id: trailing-whitespace
-    -   id: end-of-file-fixer
-    -   id: check-added-large-files
-        args: ['--maxkb=100',--enforce-all]
-    -   id: check-json
-    -   id: check-docstring-first
-    -   id: check-yaml
-    -   id: debug-statements
-    -   id: mixed-line-ending
--   repo: https://github.com/PyCQA/pylint/
-    rev: v2.17.2
+      - id: trailing-whitespace
+      - id: check-yaml
+      - id: end-of-file-fixer
+      - id: requirements-txt-fixer
+      - id: double-quote-string-fixer
+      - id: check-merge-conflict
+      - id: fix-encoding-pragma
+        args: ["--remove"]
+      - id: mixed-line-ending
+        args: ["--fix=lf"]
+  - repo: https://github.com/executablebooks/mdformat
+    rev: 0.7.9
     hooks:
-    -   id: pylint
-        name: pylint
-        entry: pylint
-        language: system
-        types: [python]
-        args:
-            [
-                '--rcfile=.pylintrc',
-                '--disable=C0114,C0415,W0212,W0235,W0238,W0621,C0103,R1735,C2801,E0402,C0412,W0719,R1728,W1514,W0718,W0105,W0707,C0209,W0703,W1203'
-            ]
+      - id: mdformat
+        args: ["--number", "--table-width", "200"]
+        additional_dependencies:
+          - mdformat-openmmlab
+          - mdformat_frontmatter
+          - linkify-it-py
+  - repo: https://github.com/myint/docformatter
+    rev: v1.3.1
+    hooks:
+      - id: docformatter
+        args: ["--in-place", "--wrap-descriptions", "79"]
diff --git a/README.md b/README.md
diff --git a/README_zh-CN.md b/README_zh-CN.md
diff --git a/agent/README.md b/agent/README.md
@@ -4,18 +4,18 @@ English | [简体中文](README_zh-CN.md)
 
 ## Introduction
 
-InternLM-Chat-7B v1.1 has been released as the first open-source model with code interpreter capabilities, supportting external tools such as Python code interpreter and search engine.
+InternLM-Chat-7B v1.1 has been released as the first open-source model with code interpreter capabilities, supporting external tools such as Python code interpreter and search engine.
 
 InternLM2-Chat, open sourced on January 17, 2024, further enhances its capabilities in code interpreter and general tool utilization. With improved and more generalized instruction understanding, tool selection, and reflection abilities, InternLM2-Chat can more reliably support complex agents and multi-step tool calling for more intricate tasks. InternLM2-Chat exhibits decent computational and reasoning abilities even without external tools, surpassing ChatGPT in mathematical performance. When combined with a code interpreter, InternLM2-Chat-20B obtains comparable results to GPT-4 on GSM8K and MATH. Leveraging strong foundational capabilities in mathematics and tools, InternLM2-Chat provides practical data analysis capabilities.
 
 The results of InternLM2-Chat-20B on math code interpreter is as below:
 
-|       | GSM8K | MATH |
-| :---: | :---: | :--: |
-| InternLM2-Chat-20B | 79.6 | 32.5 |
-| InternLM2-Chat-20B with Code Interpreter  | 84.5 | 51.2 |
-| ChatGPT (GPT-3.5) | 78.2 | 28.0 |
-| GPT-4 | 91.4 | 45.8 |
+|                                          | GSM8K | MATH |
+| :--------------------------------------: | :---: | :--: |
+|            InternLM2-Chat-20B            | 79.6  | 32.5 |
+| InternLM2-Chat-20B with Code Interpreter | 84.5  | 51.2 |
+|            ChatGPT (GPT-3.5)             | 78.2  | 28.0 |
+|                  GPT-4                   | 91.4  | 45.8 |
 
 ## Usages
 

diff --git a/agent/README_zh-CN.md b/agent/README_zh-CN.md
@@ -10,12 +10,12 @@ InternLM2-Chat 进一步提高了它在代码解释和通用工具调用方面
 
 以下是 InternLM2-Chat-20B 在数学代码解释器上的结果。
 
-|       | GSM8K | MATH |
-| :---: | :---: | :--: |
-| InternLM2-Chat-20B 单纯依靠内在能力 | 79.6 | 32.5 |
-| InternLM2-Chat-20B 配合代码解释器  | 84.5 | 51.2 |
-| ChatGPT (GPT-3.5) | 78.2 | 28.0 |
-| GPT-4 | 91.4 | 45.8 |
+|                                     | GSM8K | MATH |
+| :---------------------------------: | :---: | :--: |
+| InternLM2-Chat-20B 单纯依靠内在能力 | 79.6  | 32.5 |
+|  InternLM2-Chat-20B 配合代码解释器  | 84.5  | 51.2 |
+|          ChatGPT (GPT-3.5)          | 78.2  | 28.0 |
+|                GPT-4                | 91.4  | 45.8 |
 
 ## 体验
 

diff --git a/agent/lagent_zh-CN.md b/agent/lagent_zh-CN.md
@@ -40,7 +40,7 @@ streamlit run examples/react_web_demo.py
 
 ## 用 InternLM-Chat 构建一个 ReAct 智能体
 
-**注意：**如果你想要启动一个 HuggingFace 的模型，请先运行 pip install -e .[all]。
+\*\*注意：\*\*如果你想要启动一个 HuggingFace 的模型，请先运行 pip install -e .\[all\]。
 
 ```python
 # Import necessary modules and classes from the "lagent" library.

diff --git a/agent/pal_inference.md b/agent/pal_inference.md
@@ -21,20 +21,21 @@ python pal_inference.py \
 ```
 
 Parameter explanation:
-|   Parameter   |        Description        |
-| :--------: | :--------------------: |
-|   \<model\>                     | Path to the model used for inference |
-|   \<out_dir\>                   | Generated code will be saved in the specified output folder |
-|   --dataset <dataset>         | Name of the dataset used for code generation (defaults to gsm8k) |
-|   --max_length <length>       | Maximum input token length for the model (defaults to 2048) |
-|   --top_p <threshold>         | Probability threshold for the sum of candidate tokens (defaults to 0.8) |
-|   --eoh <end token>           | User input end identifier (defaults to "")  |
-|   --eoa <end token>           | Model input end identifier (defaults to "")  |
-|   --eos <end token>           | System input end identifier (defaults to "")  |
-|   --temperature， -t <temp>   | Sampling temperature during generation (defaults to 1.0) |
-|   --time_out <time>           | Maximum time (in seconds) for executing generated code (defaults to 100) |
-|   --verbose, -v               | Print code error messages (optional) |
-|   --append, -a                | Append output to historical results (optional) |
+
+|         Parameter         |                               Description                                |
+| :-----------------------: | :----------------------------------------------------------------------: |
+|         \<model>          |                   Path to the model used for inference                   |
+|        \<out_dir>         |       Generated code will be saved in the specified output folder        |
+|    --dataset <dataset>    |     Name of the dataset used for code generation (defaults to gsm8k)     |
+|   --max_length <length>   |       Maximum input token length for the model (defaults to 2048)        |
+|    --top_p <threshold>    | Probability threshold for the sum of candidate tokens (defaults to 0.8)  |
+|     --eoh <end token>     |                User input end identifier (defaults to "")                |
+|     --eoa <end token>     |               Model input end identifier (defaults to "")                |
+|     --eos <end token>     |               System input end identifier (defaults to "")               |
+| --temperature， -t <temp> |         Sampling temperature during generation (defaults to 1.0)         |
+|     --time_out <time>     | Maximum time (in seconds) for executing generated code (defaults to 100) |
+|       --verbose, -v       |                   Print code error messages (optional)                   |
+|       --append, -a        |              Append output to historical results (optional)              |
 
 A simple usage example is as follows: