|
--- |
|
license: apache-2.0 |
|
tags: |
|
- pretrained |
|
- mistral |
|
- DNA |
|
- codon |
|
--- |
|
|
|
# Model Card for Mistral-Codon-v1-16M (Mistral for coding DNA) |
|
|
|
The Mistral-Codon-v1-16M Large Language Model (LLM) is a pretrained generative DNA sequence model with 16M parameters. |
|
It is derived from Mixtral-8x7B-v0.1 model, which was simplified for DNA: the number of layers and the hidden size were reduced. |
|
The model was pretrained using 24M coding DNA sequences (300bp) from many different species (vertebrates, plants, bacteria, viruses, ...). |
|
|
|
## Model Architecture |
|
|
|
Like Mixtral-8x7B-v0.1, it is a transformer model, with the following architecture choices: |
|
- Grouped-Query Attention |
|
- Sliding-Window Attention |
|
- Byte-fallback BPE tokenizer |
|
- Mixture of Experts |
|
|
|
## Load the model from huggingface: |
|
|
|
``` |
|
import torch |
|
from transformers import AutoTokenizer, AutoModel |
|
|
|
tokenizer = AutoTokenizer.from_pretrained("RaphaelMourad/Mistral-Codon-v1-16M", trust_remote_code=True) |
|
model = AutoModel.from_pretrained("RaphaelMourad/Mistral-Codon-v1-16M", trust_remote_code=True) |
|
``` |
|
|
|
## Calculate the embedding of a coding sequence |
|
|
|
``` |
|
insulin = "TGA TGA TTG GCG CGG CTA GGA TCG GCT" |
|
inputs = tokenizer(insulin, 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-Codon-v1-16M is a pretrained base model for coding DNA. |
|
|
|
## Contact |
|
|
|
Raphaël Mourad. raphael.mourad@univ-tlse3.fr |
