support pretraining of llava

2024-05-21 08:57:14 +08:00
parent 2a67457e39
commit 29a6d5bdb8
4 changed files with 115 additions and 0 deletions
--- a/data/dataset_info.json
+++ b/data/dataset_info.json
@@ -38,6 +38,20 @@
      "assistant_tag": "assistant"
    }
  },
+  "mllm_pt_demo": {
+    "file_name": "mllm_pt_demo.json",
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "messages",
+      "images": "images"
+    },
+    "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"