Update README.md

README.md

@@ -32,28 +32,8 @@ This model is just a proof of concept. It shows that HuggingFace can be used to
 
 ### How to use
 
-You can immediately start generating music running these lines of code:
-
-```
-from transformers import AutoTokenizer, AutoModelForCausalLM
-
-tokenizer = AutoTokenizer.from_pretrained("TristanBehrens/js-fakes-4bars")
-model = AutoModelForCausalLM.from_pretrained("TristanBehrens/js-fakes-4bars")
-
-input_ids = tokenizer.encode("PIECE_START", return_tensors="pt")
-print(input_ids)
-
-generated_ids = model.generate(input_ids, max_length=500)
-generated_sequence = tokenizer.decode(generated_ids[0])
-print(generated_sequence)
-```
-
-Note that this just generates music as a text. In order to actually listen to the generated music, you can use this [notebook](https://huggingface.co/TristanBehrens/js-fakes-4bars/blob/main/colab_jsfakes_generation.ipynb).
+There is a notebook in the repo that you can run on Google Colab.
 
 ### Limitations and bias
 
-Since this model has been trained on a very small corpus of music, it is overfitting heavily. 
-
-## Training data
-
-The model has been trained on Omar Peracha's [JS Fake Chorales](https://github.com/omarperacha/js-fakes) dataset, which is a fine collection of 500 Bach-like chorales.
+Since this model has been trained on a very small corpus of music, it is overfitting heavily.