Update README.md

README.md

@@ -12,7 +12,10 @@ This is one model in a collection of models trained on the impossible
 languages of [Kallini et al. 2024](https://arxiv.org/abs/2401.06416).
 
 This model is a GPT-2 Small model trained from scratch on the *NoShuffle*
-language.
+language. We include a total of 30 checkpoints over the course of
+model training, from step 100 to 3000 in increments of 100 steps.
+The main branch contains the final checkpoint (3000), and the other
+checkpoints are accessible as revisions.
 
 ![languages.png](https://cdn-uploads.huggingface.co/production/uploads/6268bc06adb1c6525b3d5157/pBt38YYQL1gj8DqjyorWS.png)
 
@@ -55,6 +58,15 @@ generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
 print(generated_text)
 ```
 
+By default, the `main` branch of this model repo loads the
+last model checkpoint (3000). To access the other checkpoints,
+use the `revision` argument:
+
+```
+model = GPT2LMHeadModel.from_pretrained(model_id, revision="checkpoint-500")
+```
+This loads the model at checkpoint 500.
+
 ## Training Details
 
 ### Training Data