hdallatorre commited on
Commit
22490da
1 Parent(s): 22e3875

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -1
README.md CHANGED
@@ -11,7 +11,7 @@ tags:
11
 
12
  The Nucleotide Transformers are a collection of foundational language models that were pre-trained on DNA sequences from whole-genomes. Compared to other approaches, our models do not only integrate information from single reference genomes, but leverage DNA sequences from over 3,200 diverse human genomes, as well as 850 genomes from a wide range of species, including model and non-model organisms. Through robust and extensive evaluation, we show that these large models provide extremely accurate molecular phenotype prediction compared to existing methods
13
 
14
- Part of this collection is the **nucleotide-transformer-2.5b-1000g**, a 2.5B parameters transformer pre-trained on a collection of 3202 genetically diverse human genomes.
15
 
16
  **Developed by:** InstaDeep, NVIDIA and TUM
17
 
@@ -25,6 +25,12 @@ Part of this collection is the **nucleotide-transformer-2.5b-1000g**, a 2.5B par
25
  ### How to use
26
 
27
  <!-- Need to adapt this section to our model. Need to figure out how to load the models from huggingface and do inference on them -->
 
 
 
 
 
 
28
  ```python
29
  from transformers import AutoTokenizer, AutoModelForMaskedLM
30
  import torch
 
11
 
12
  The Nucleotide Transformers are a collection of foundational language models that were pre-trained on DNA sequences from whole-genomes. Compared to other approaches, our models do not only integrate information from single reference genomes, but leverage DNA sequences from over 3,200 diverse human genomes, as well as 850 genomes from a wide range of species, including model and non-model organisms. Through robust and extensive evaluation, we show that these large models provide extremely accurate molecular phenotype prediction compared to existing methods
13
 
14
+ Part of this collection is the **nucleotide-transformer-2.5b-1000g**, a 2.5B parameters transformer pre-trained on a collection of 3202 genetically diverse human genomes. The model is made available both in Tensorflow and Pytorch.
15
 
16
  **Developed by:** InstaDeep, NVIDIA and TUM
17
 
 
25
  ### How to use
26
 
27
  <!-- Need to adapt this section to our model. Need to figure out how to load the models from huggingface and do inference on them -->
28
+ Until its next release, the `transformers` library needs to be installed from source with the following command in order to use the models:
29
+ ```bash
30
+ pip install --upgrade git+https://github.com/huggingface/transformers.git
31
+ ```
32
+
33
+ A small snippet of code is given here in order to retrieve both logits and embeddings from a dummy DNA sequence.
34
  ```python
35
  from transformers import AutoTokenizer, AutoModelForMaskedLM
36
  import torch