Model Card for Mistral-DNA-v1-138M-noncoding (mistral for DNA)
The Mistral-DNA-v1-138M-noncoding 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 1940736 non coding RNAs > 100b from rfam database. Sequences were split into 100b sequences.
NB: the DNA sequence was used, not the RNA sequence.
For full details of this model please read our github repo.
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/Mistral-DNA-v1-138M-noncoding", trust_remote_code=True) # Same as DNABERT2
model = AutoModel.from_pretrained("RaphaelMourad/Mistral-DNA-v1-138M-noncoding", 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-v1-138M-noncoding is a pretrained base model for non coding RNAs.
Contact
Raphaël Mourad. raphael.mourad@univ-tlse3.fr