From 6bbb8b4cd8e16c9fbcee6c040715c14bc3c1d692 Mon Sep 17 00:00:00 2001
From: Eli Costa <87460497+EliMCosta@users.noreply.github.com>
Date: Sat, 15 Jun 2024 19:31:56 -0300
Subject: [PATCH] Add Magpie and Webinstruct dataset samples

Adds two dataset samples claimed superior performance: Magpie (from Allen AI) and Webinstruct (from TIGER-Lab).

Former-commit-id: 74e49cca957d0bacd2c1d688e995a7370bef69f7
---
 data/dataset_info.json | 26 +++++++++++++++++++++++---
 1 file changed, 23 insertions(+), 3 deletions(-)

diff --git a/data/dataset_info.json b/data/dataset_info.json
index 1d226b3a..e321196a 100644
--- a/data/dataset_info.json
+++ b/data/dataset_info.json
@@ -524,13 +524,13 @@
       "prompt": "text"
     }
   },
-  "fileweb": {
+  "fineweb": {
     "hf_hub_url": "HuggingFaceFW/fineweb",
     "columns": {
       "prompt": "text"
     }
   },
-  "fileweb_edu": {
+  "fineweb_edu": {
     "hf_hub_url": "HuggingFaceFW/fineweb-edu",
     "columns": {
       "prompt": "text"
@@ -550,5 +550,25 @@
       "prompt": "content"
     },
     "folder": "python"
+  },
+  "Magpie-Pro-300K-Filtered": {
+    "hf_hub_url": "Magpie-Align/Magpie-Pro-300K-Filtered",
+    "columns": {
+      "messages": "conversations"
+    },
+    "tags": {
+      "role_tag": "from",
+      "content_tag": "value",
+      "user_tag": "human",
+      "assistant_tag": "gpt"
+    },
+    "formatting": "sharegpt"
+  },
+  "WebInstructSub": {
+    "hf_hub_url": "TIGER-Lab/WebInstructSub",
+    "columns": {
+      "prompt": "question",
+      "response": "answer"
+    }
   }
-}
\ No newline at end of file
+}