|
--- |
|
license: apache-2.0 |
|
tags: |
|
- pretrained |
|
- mistral |
|
- DNA |
|
- biology |
|
- genomics |
|
--- |
|
|
|
# Model Card for mixtral-dna-yeast-v0.2 (mistral for DNA) |
|
|
|
The mixtral-dna-yeast-v0.2 Large Language Model (LLM) is a pretrained generative DNA text model with 17.31M parameters x 8 experts = 138.5M parameters. |
|
It is derived from Mistral-7B-v0.1 model, which was simplified for DNA: the number of layers and the hidden size were reduced. |
|
The model was pretrained using around 1000 yeast genomes with 10kb DNA sequences. |
|
|
|
The yeast genomes are from: https://www.nature.com/articles/s41586-018-0030-5 |
|
|
|
For full details of this model please read our [github repo](https://github.com/raphaelmourad/Mistral-DNA). |
|
|
|
## Model Architecture |
|
|
|
Like Mistral-7B-v0.1, it is a transformer model, with the following architecture choices: |
|
- Grouped-Query Attention |
|
- Sliding-Window Attention |
|
- Byte-fallback BPE tokenizer |
|
|
|
## Load the model from huggingface: |
|
|
|
``` |
|
import torch |
|
from transformers import AutoTokenizer, AutoModel |
|
|
|
tokenizer = AutoTokenizer.from_pretrained("RaphaelMourad/mixtral-dna-yeast-v0.2", trust_remote_code=True) # Same as DNABERT2 |
|
model = AutoModel.from_pretrained("RaphaelMourad/mixtral-dna-yeast-v0.2", trust_remote_code=True) |
|
``` |
|
|
|
## Calculate the embedding of a DNA sequence |
|
|
|
``` |
|
dna = "TGATGATTGGCGCGGCTAGGATCGGCT" |
|
inputs = tokenizer(dna, return_tensors = 'pt')["input_ids"] |
|
hidden_states = model(inputs)[0] # [1, sequence_length, 256] |
|
|
|
# embedding with max pooling |
|
embedding_max = torch.max(hidden_states[0], dim=0)[0] |
|
print(embedding_max.shape) # expect to be 256 |
|
``` |
|
|
|
## Troubleshooting |
|
|
|
Ensure you are utilizing a stable version of Transformers, 4.34.0 or newer. |
|
|
|
## Notice |
|
|
|
Mistral-DNA is a pretrained base model for DNA. |
|
|
|
## Contact |
|
|
|
Raphaël Mourad. raphael.mourad@univ-tlse3.fr |
|
|
|
|
