Update README.md

README.md

@@ -2,7 +2,7 @@
 license: apache-2.0
 language:
 - en
-pipeline_tag: text-generation
+pipeline_tag: image-text-to-text
 tags:
 - darwin
 - qwen3.6
@@ -87,4 +87,4 @@ model (`Qwen3.6-35B-A3B-NPU2`), because this model shares the same engine family
 
 See the upstream model card for training details, benchmarks, and upstream
 usage. This repository only contains the Q4NX conversion for FastFlowLM.
-- Upstream card: [FINAL-Bench/Darwin-36B-Opus](https://huggingface.co/FINAL-Bench/Darwin-36B-Opus)
+- Upstream card: [FINAL-Bench/Darwin-36B-Opus](https://huggingface.co/FINAL-Bench/Darwin-36B-Opus)