RaphaelMourad's picture
Update README.md
84eda84 verified
metadata
license: apache-2.0
tags:
  - pretrained
  - mistral
  - DNA
  - long non coding
  - lncRNA
  - biology
  - genomics

Model Card for Mistral-DNA-v1-138M-lncRNA (mistral for DNA)

The Mistral-DNA-v1-138M-lncRNA 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 lncbook database of 410712 long non coding RNAs > 1kb. Virus genomes were split into 1kb sequences.

lncbook database was downloaded from https://ftp.ebi.ac.uk/pub/databases/RNAcentral/current_release/sequences/by-database/. 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-lncRNA", trust_remote_code=True) # Same as DNABERT2
model = AutoModel.from_pretrained("RaphaelMourad/Mistral-DNA-v1-138M-lncRNA", 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-lncRNA is a pretrained base model for long non coding RNAs.

Contact

Raphaël Mourad. [email protected]