From d9aa226c0858c82f9f3c4aa95db1197f061469d4 Mon Sep 17 00:00:00 2001
From: hiyouga <467089858@qq.com>
Date: Sat, 8 Jun 2024 02:42:34 +0800
Subject: [PATCH] add ultrafeedback and fineweb #4085 #4132

Former-commit-id: 968e4992e2f2a3ccba73e8668f1654ddc6eb0034
---
 .github/workflows/tests.yml | 24 +-----------------------
 README.md                   |  3 +++
 README_zh.md                |  3 +++
 data/dataset_info.json      | 31 +++++++++++++++++++++++++++++++
 4 files changed, 38 insertions(+), 23 deletions(-)

diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml
index 818d58fc..32edf6a8 100644
--- a/.github/workflows/tests.yml
+++ b/.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
diff --git a/README.md b/README.md
index 44897420..fb6c5782 100644
--- a/README.md
+++ b/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)
diff --git a/README_zh.md b/README_zh.md
index 8321d202..142254df 100644
--- a/README_zh.md
+++ b/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)
diff --git a/data/dataset_info.json b/data/dataset_info.json
index 2d9b0c83..8c5cbb45 100644
--- a/data/dataset_info.json
+++ b/data/dataset_info.json
@@ -391,6 +391,16 @@
       "rejected": "rejected"
     }
   },
+  "ultrafeedback": {
+    "hf_hub_url": "llamafactory/ultrafeedback_binarized",
+    "ms_hub_url": "llamafactory/ultrafeedback_binarized",
+    "ranking": true,
+    "columns": {
+      "prompt": "instruction",
+      "chosen": "chosen",
+      "rejected": "rejected"
+    }
+  },
   "orca_pairs": {
     "hf_hub_url": "Intel/orca_dpo_pairs",
     "ranking": true,
@@ -448,6 +458,15 @@
       "assistant_tag": "assistant"
     }
   },
+  "ultrafeedback_kto": {
+    "hf_hub_url": "argilla/ultrafeedback-binarized-preferences-cleaned-kto",
+    "ms_hub_url": "AI-ModelScope/ultrafeedback-binarized-preferences-cleaned-kto",
+    "columns": {
+      "prompt": "prompt",
+      "response": "completion",
+      "kto_tag": "label"
+    }
+  },
   "wiki_demo": {
     "file_name": "wiki_demo.txt",
     "columns": {
@@ -501,6 +520,18 @@
       "prompt": "text"
     }
   },
+  "fileweb": {
+    "hf_hub_url": "HuggingFaceFW/fineweb",
+    "columns": {
+      "prompt": "text"
+    }
+  },
+  "fileweb_edu": {
+    "hf_hub_url": "HuggingFaceFW/fineweb-edu",
+    "columns": {
+      "prompt": "text"
+    }
+  },
   "the_stack": {
     "hf_hub_url": "bigcode/the-stack",
     "ms_hub_url": "AI-ModelScope/the-stack",