Add files using upload-large-folder tool

README.md

@@ -41,6 +41,19 @@ The 1,000 novel-knowledge probes and 4,400 retention probes are evaluator-only
 and are intentionally excluded. Keep those splits outside the agent sandbox
 when running the benchmark.
 
+## Download
+
+Download the complete resource bundle with `huggingface_hub`:
+
+```python
+from huggingface_hub import snapshot_download
+
+snapshot_download(
+    repo_id="AutoDataBench/Knowledge-Injection-resources",
+    local_dir="./Knowledge-Injection-resources",
+)
+```
+
 ## Use with AutoDataBench
 
 Copy or symlink `data/` and `models/` into the AutoDataBench repository. The

config.json

@@ -0,0 +1,4 @@
+{
+  "name": "Knowledge-Injection-resources",
+  "description": "Resources for the AutoDataBench knowledge-injection task."
+}