merge data part to the text stream

Former-commit-id: c6dd89918f
2025-12-14 19:06:26 +08:00 · 2024-04-25 19:19:59 +08:00
parent 4e032ff95e
commit b6d78b2a64
15 changed files with 828 additions and 293 deletions
--- a/data/dataset_info.json
+++ b/data/dataset_info.json
@@ -418,6 +418,17 @@
    "hf_hub_url": "HuggingFaceH4/llava-instruct-mix-vsft"
  },
  "mllm_instruct_example": {
-    "hf_hub_url": "data/mllm_example_dataset"
+    "file_name": "llava_instruct_example.json",
+    "formatting": "llava",
+    "columns": {
+      "messages": "messages",
+      "images": "images"
+    },
+    "tags": {
+      "role_tag": "role",
+      "content_tag": "content",
+      "user_tag": "user",
+      "assistant_tag": "assistant"
+    }
  }
-}
+}