Update README.md

README.md

@@ -87,6 +87,12 @@ It achieves the following results on the evaluation set:
 - Rougelsum: 60.4494
 - Gen Len: 24.9917
 
+
+## Example 
+
+![base](https://i.imgur.com/1Vq5Fys.png)
+
+
 ## Intended uses & limitations
 
 This model is intended to be used to generate instructions from arbitrary text. You can then use these instructions + your data to fine-tune an LLM on instructions w.r.t. a specific domain. This model is primarily intended to enable **low-resource domain adaptation**, rather than "_I want to generate even better prompts for the FLAN-V2 dataset!_".
@@ -95,6 +101,8 @@ The `fleece2instructions-inputs-alpaca-cleaned` dataset, obtained from the [alpa
 
 As such, users can expect the output of this model to be similarly structured with `<instruction>` and `<inputs>` tokens.
 
+This is just the base model, for better performance (but slower/compute intensive) see the [bart-large](https://huggingface.co/pszemraj/bart-large-instructiongen-w-inputs) version. Further exploration/data may lead to even better models!
+
 ## Training and evaluation data
 
 Refer to the [fleece2instructions-inputs-alpaca-cleaned](https://huggingface.co/datasets/pszemraj/fleece2instructions-inputs-alpaca-cleaned) dataset