Update README.md

README.md

@@ -4,9 +4,12 @@ datasets:
 - urialon/gov_report_validation
 - urialon/gov_report_test
 pipeline_tag: text2text-generation
+inference: false
 ---
 Model from the preprint [Unlimiformer: Long-Range Transformers with Unlimited Length Input](https://arxiv.org/abs/2305.01625)
 
 This is a BART-base model finetuned using Unlimiformer-aware early stopping, as described in section 3.1 of the paper. The model was finetuned on GovReport using the data processing pipeline from SLED;  to load the validation or test set for use with these model, please use the datasets [urialon/gov_report_validation](https://huggingface.co/datasets/urialon/gov_report_validation) and [urialon/gov_report_test](https://huggingface.co/datasets/urialon/gov_report_test).
 
-This is generally a weaker model than the [alternating-training model](https://huggingface.co/abertsch/unlimiformer-bart-govreport-alternating) and a stronger model than the [baseline](https://huggingface.co/abertsch/bart-base-govreport).
+This is generally a weaker model than the [alternating-training model](https://huggingface.co/abertsch/unlimiformer-bart-govreport-alternating) and a stronger model than the [baseline](https://huggingface.co/abertsch/bart-base-govreport).
+
+*The inference demo is disabled because you must add the Unlimiformer files to your repo before this model can handle unlimited length input!* See the [Unlimiformer GitHub](https://github.com/abertsch72/unlimiformer) for setup instructions.