hdallatorre commited on
Commit
38f0e98
1 Parent(s): 991981b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -41,7 +41,8 @@ the `rescaling_factor` of the Rotary Embedding layer in the esm model `num_dna_
41
  (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`.
42
 
43
  [![Open All Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/#fileId=https%3A//huggingface.co/InstaDeepAI/segment_nt/blob/main/inference_segment_nt.ipynb)
44
- The `./inference_segment_nt.ipynb` can be run in Google Colab by clicking on the icon and shows how to set the rescaling factor and infer on a 50kb genic sequence of the human chromosome 20.
 
45
 
46
  ```python
47
  # Load model and tokenizer
 
41
  (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`.
42
 
43
  [![Open All Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/#fileId=https%3A//huggingface.co/InstaDeepAI/segment_nt/blob/main/inference_segment_nt.ipynb)
44
+ The `./inference_segment_nt.ipynb` can be run in Google Colab by clicking on the icon and shows how to handle inference on sequence lengths require changing
45
+ the rescaling factor and sequence lengths that do not. One can run the notebook and reproduce Fig.1 and Fig.3 from the SegmentNT paper.
46
 
47
  ```python
48
  # Load model and tokenizer