video datasets

Former-commit-id: 8cafc7b055
2025-12-29 10:10:35 +08:00 · 2024-09-05 02:04:17 +08:00
parent 60d770e4b1
commit 9df7a26e6b
27 changed files with 420 additions and 148 deletions
--- a/data/dataset_info.json
+++ b/data/dataset_info.json
@@ -38,6 +38,20 @@
      "assistant_tag": "assistant"
    }
  },
+  "mllm_video_demo": {
+    "file_name": "mllm_video_demo.json",
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "messages",
+      "videos": "videos"
+    },
+    "tags": {
+      "role_tag": "role",
+      "content_tag": "content",
+      "user_tag": "user",
+      "assistant_tag": "assistant"
+    }
+  },
  "alpaca_en": {
    "hf_hub_url": "llamafactory/alpaca_en",
    "ms_hub_url": "llamafactory/alpaca_en"