Model Card for Mistral-Peptide-v1-13M (Mistral for peptide)

The Mistral-Peptide-v1-13M Large Language Model (LLM) is a pretrained generative peptide molecule model with 13M parameters. It is derived from Mixtral-8x7B-v0.1 model, which was simplified for protein: the number of layers and the hidden size were reduced. The model was pretrained using 863499 peptide strings. Compared to v1 models, v2 models have a very large number of experts (128) making the model faster to run.

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-Peptide-v1-13M", trust_remote_code=True) 
model = AutoModel.from_pretrained("RaphaelMourad/Mistral-Peptide-v1-13M", trust_remote_code=True)

Calculate the embedding of a protein sequence

insulin = "MALWMRLLPLLALLALWG"
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-Peptide-v1-13M is a pretrained base model for peptide.

Contact

Raphaël Mourad. [email protected]