Update README.md

README.md

@@ -34,12 +34,14 @@ pip install --upgrade git+https://github.com/huggingface/transformers.git
 ```
 
 A small snippet of code is given here in order to retrieve both logits and embeddings from a dummy DNA sequence.
-
-
 ⚠️ The maximum sequence length is set by default at the training length of 30,000 nucleotides, or 5001 tokens (accounting for the CLS token). However,
 Segment-NT-multi-species has been shown to generalize up to sequences of 50,000 bp. In case you need to infer on sequences between 30kbp and 50kbp, make sure to change
-the `rescaling_factor` argument in the config to `num_dna_tokens_inference / max_num_tokens_nt` where `num_dna_tokens_inference` is the number of tokens at inference
-(i.e 6669 for a sequence of 40008 base pairs) and `max_num_tokens_nt` is the max number of tokens on which the backbone nucleotide-transformer was trained on, i.e `2048`.
+the `rescaling_factor` of the Rotary Embedding layer in the esm model  `num_dna_tokens_inference / max_num_tokens_nt` where `num_dna_tokens_inference` is the number of tokens at inference
+(i.e 6669 for a sequence of 40008 base pairs) and `max_num_tokens_nt` is the max number of tokens on which the backbone nucleotide-transformer was trained on, i.e `2048`. 
+
+[![Open All Collab](https://colab.research.google.com/assets/colab-badge.svg)] 
+The `inference_segment_nt.ipynb` notebook shows how to set the rescaling factor and infer on a 50kb sequence of the human chromosome 20 in order to reproduce Fig.3 of the
+paper.
 
 ```python
 # Load model and tokenizer