add ultrafeedback and fineweb #4085 #4132

Former-commit-id: 968e4992e2f2a3ccba73e8668f1654ddc6eb0034

.github/workflows/tests.yml

@@ -17,7 +17,7 @@ on:
       - ".github/workflows/*.yml"
 
 jobs:
-  check_code_quality:
+  tests:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
@@ -34,28 +34,6 @@ jobs:
       - name: Check quality
         run: |
           make style && make quality
-
-  pytest:
-    needs: check_code_quality
-    strategy:
-      matrix:
-        python-version:
-          - "3.8"
-        os:
-          - "ubuntu-latest"
-    runs-on: ${{ matrix.os }}
-    steps:
-      - uses: actions/checkout@v4
-      - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v5
-        with:
-          python-version: ${{ matrix.python-version }}
-          cache: "pip"
-          cache-dependency-path: "setup.py"
-      - name: Install dependencies
-        run: |
-          python -m pip install --upgrade pip
-          python -m pip install .[torch,dev]
       - name: Test with pytest
         run: |
           make test

README.md

@@ -214,6 +214,8 @@ You also can add a custom chat template to [template.py](src/llamafactory/data/t
 - [Wikipedia (zh)](https://huggingface.co/datasets/pleisto/wikipedia-cn-20230720-filtered)
 - [Pile (en)](https://huggingface.co/datasets/EleutherAI/pile)
 - [SkyPile (zh)](https://huggingface.co/datasets/Skywork/SkyPile-150B)
+- [FineWeb (en)](https://huggingface.co/datasets/HuggingFaceFW/fineweb)
+- [FineWeb-Edu (en)](https://huggingface.co/datasets/HuggingFaceFW/fineweb-edu)
 - [The Stack (en)](https://huggingface.co/datasets/bigcode/the-stack)
 - [StarCoder (en)](https://huggingface.co/datasets/bigcode/starcoderdata)
 
@@ -273,6 +275,7 @@ You also can add a custom chat template to [template.py](src/llamafactory/data/t
 <details><summary>Preference datasets</summary>
 
 - [DPO mixed (en&zh)](https://huggingface.co/datasets/hiyouga/DPO-En-Zh-20k)
+- [UltraFeedback (en)](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized)
 - [Orca DPO Pairs (en)](https://huggingface.co/datasets/Intel/orca_dpo_pairs)
 - [HH-RLHF (en)](https://huggingface.co/datasets/Anthropic/hh-rlhf)
 - [Nectar (en)](https://huggingface.co/datasets/berkeley-nest/Nectar)

README_zh.md

@@ -214,6 +214,8 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/ec36a9dd-37f4-4f72-81bd
 - [Wikipedia (zh)](https://huggingface.co/datasets/pleisto/wikipedia-cn-20230720-filtered)
 - [Pile (en)](https://huggingface.co/datasets/EleutherAI/pile)
 - [SkyPile (zh)](https://huggingface.co/datasets/Skywork/SkyPile-150B)
+- [FineWeb (en)](https://huggingface.co/datasets/HuggingFaceFW/fineweb)
+- [FineWeb-Edu (en)](https://huggingface.co/datasets/HuggingFaceFW/fineweb-edu)
 - [The Stack (en)](https://huggingface.co/datasets/bigcode/the-stack)
 - [StarCoder (en)](https://huggingface.co/datasets/bigcode/starcoderdata)
 
@@ -273,6 +275,7 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/ec36a9dd-37f4-4f72-81bd
 <details><summary>偏好数据集</summary>
 
 - [DPO mixed (en&zh)](https://huggingface.co/datasets/hiyouga/DPO-En-Zh-20k)
+- [UltraFeedback (en)](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized)
 - [Orca DPO Pairs (en)](https://huggingface.co/datasets/Intel/orca_dpo_pairs)
 - [HH-RLHF (en)](https://huggingface.co/datasets/Anthropic/hh-rlhf)
 - [Nectar (en)](https://huggingface.co/datasets/berkeley-nest/Nectar)