Instructions to use RaphaelMourad/Mistral-DNA-v1-17M-hg38 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RaphaelMourad/Mistral-DNA-v1-17M-hg38 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="RaphaelMourad/Mistral-DNA-v1-17M-hg38")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RaphaelMourad/Mistral-DNA-v1-17M-hg38")
model = AutoModelForCausalLM.from_pretrained("RaphaelMourad/Mistral-DNA-v1-17M-hg38", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RaphaelMourad/Mistral-DNA-v1-17M-hg38 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RaphaelMourad/Mistral-DNA-v1-17M-hg38"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RaphaelMourad/Mistral-DNA-v1-17M-hg38",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/RaphaelMourad/Mistral-DNA-v1-17M-hg38

SGLang

How to use RaphaelMourad/Mistral-DNA-v1-17M-hg38 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "RaphaelMourad/Mistral-DNA-v1-17M-hg38" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RaphaelMourad/Mistral-DNA-v1-17M-hg38",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "RaphaelMourad/Mistral-DNA-v1-17M-hg38" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RaphaelMourad/Mistral-DNA-v1-17M-hg38",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use RaphaelMourad/Mistral-DNA-v1-17M-hg38 with Docker Model Runner:
```
docker model run hf.co/RaphaelMourad/Mistral-DNA-v1-17M-hg38
```

Model Card for Mistral-DNA-v1-17M-hg38 (Mistral for DNA)

The Mistral-DNA-v1-17M-hg38 Large Language Model (LLM) is a pretrained generative DNA sequence model with 16.8M 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 10kb DNA sequences from the hg38 human genome assembly.

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-DNA-v1-17M-hg38", trust_remote_code=True) 
model = AutoModel.from_pretrained("RaphaelMourad/Mistral-DNA-v1-17M-hg38", 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-v1-17M-hg38 is a pretrained base model for DNA.

Contact

Raphaël Mourad. raphael.mourad@univ-tlse3.fr

Downloads last month: 44

Safetensors

Model size

16.8M params

Tensor type

BF16