README refinements, trying to make widgets work

README.md

@@ -24,7 +24,6 @@ model-index:
       type: accuracy
       value: 0.963265306122449
 widget:
-- text: What font is this?
 - src: hf_samples/ArchitectsDaughter-Regular_1.png
   example_title: Architects Daughter
 - src: main/hf_samples/Courier_28.png
@@ -49,19 +48,15 @@ language:
 # font-identifier
 
 This model is a fine-tuned version of [microsoft/resnet-18](https://huggingface.co/microsoft/resnet-18) on the imagefolder dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.1172
-- Accuracy: 0.9633
+Result: Loss: 0.1172; Accuracy: 0.9633
+
+Try with any screenshot of a font, or any of the examples in [the 'samples' subfolder of this repo](https://huggingface.co/gaborcselle/font-identifier/tree/main/hf_samples).
 
 ## Model description
 
 Identify the font used in an image. Visual classifier based on ResNet18.
 
-I built this project in 1 day, with a minute-by-minute journal:
-* [On Twitter/X](https://twitter.com/gabor/status/1722300841691103467)
-* [On Pebble.social](https://pebble.social/@gabor/111376050835874755)
-* [On Threads.net](https://www.threads.net/@gaborcselle/post/CzZJpJCpxTz)
-
+I built this project in 1 day, with a minute-by-minute journal [on Twitter/X](https://twitter.com/gabor/status/1722300841691103467), [on Pebble.social](https://pebble.social/@gabor/111376050835874755), and [on Threads.net](https://www.threads.net/@gaborcselle/post/CzZJpJCpxTz).
 
 ## Intended uses & limitations