Merge pull request #3471 from BUAADreamer/main

add llava_150k en/zh mllm sft data
hiyouga · Apr 26, 2024 · 8f91420 · 8f91420
2 parents 168f566 + 456ad61
commit 8f91420
Showing 1 changed file with 31 additions and 1 deletion.
diff --git a/data/dataset_info.json b/data/dataset_info.json
@@ -250,6 +250,36 @@
       "response": "text"
     }
   },
+  "llava_150k_en": {
+    "hf_hub_url": "BUAADreamer/llava-en-zh-300k",
+    "subset": "en",
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "messages",
+      "images": "images"
+    },
+    "tags": {
+      "role_tag": "role",
+      "content_tag": "content",
+      "user_tag": "user",
+      "assistant_tag": "assistant"
+    }
+  },
+  "llava_150k_zh": {
+    "hf_hub_url": "BUAADreamer/llava-en-zh-300k",
+    "subset": "zh",
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "messages",
+      "images": "images"
+    },
+    "tags": {
+      "role_tag": "role",
+      "content_tag": "content",
+      "user_tag": "user",
+      "assistant_tag": "assistant"
+    }
+  },
   "oasst_de": {
     "hf_hub_url": "mayflowergmbh/oasst_de"
   },
@@ -429,4 +459,4 @@
     },
     "folder": "python"
   }
-}
+}