Instructions to use marin-dna/marin-dna-exp135-m5.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use marin-dna/marin-dna-exp135-m5.1 with Transformers:

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

pipe = pipeline("text-generation", model="marin-dna/marin-dna-exp135-m5.1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("marin-dna/marin-dna-exp135-m5.1")
model = AutoModelForCausalLM.from_pretrained("marin-dna/marin-dna-exp135-m5.1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use marin-dna/marin-dna-exp135-m5.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "marin-dna/marin-dna-exp135-m5.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "marin-dna/marin-dna-exp135-m5.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/marin-dna/marin-dna-exp135-m5.1

SGLang

How to use marin-dna/marin-dna-exp135-m5.1 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 "marin-dna/marin-dna-exp135-m5.1" \
    --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": "marin-dna/marin-dna-exp135-m5.1",
		"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 "marin-dna/marin-dna-exp135-m5.1" \
        --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": "marin-dna/marin-dna-exp135-m5.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use marin-dna/marin-dna-exp135-m5.1 with Docker Model Runner:
```
docker model run hf.co/marin-dna/marin-dna-exp135-m5.1
```

MarinDNA m5.1 1B base model

MarinDNA m5.1 is a 1.12B-parameter, nucleotide-level causal language model developed with Marin. This is the final m5.1 base-model checkpoint at step 59,158 from run dna-bolinas-mix-v0.9-p1B-i24-exp135-zoonomia-m5.1-bef41e, released with the A 1B standard Transformer rivals Evo 2 40B on variant effect prediction blog post.

Model details

Field	Value
Architecture	`Qwen3ForCausalLM`-compatible decoder-only Transformer
Parameters	1,120,772,224
Layers	19
Hidden / intermediate size	1,920 / 7,680
Attention heads / KV heads	15 / 15
Context	256 tokens: one BOS token followed by up to 255 DNA bases
Checkpoint	Final m5.1 checkpoint, step 59,158
Approximate token exposure	166.0B nucleotide tokens over the inherited training lineage
Stored weight dtype	float32
License	Apache-2.0

The source checkpoint is gs://marin-us-east5/checkpoints/dna-bolinas-mix-v0.9-p1B-i24-exp135-zoonomia-m5.1-bef41e/hf/step-59158. The commit-pinned training script defines the experiment.

Loading

from transformers import AutoModelForCausalLM, AutoTokenizer

repo_id = "marin-dna/marin-dna-exp135-m5.1"

tokenizer = AutoTokenizer.from_pretrained(repo_id)
model = AutoModelForCausalLM.from_pretrained(repo_id)

The float32 checkpoint is approximately 4.18 GiB. Convert or load it in a lower-precision dtype only if that is appropriate for your downstream use.

Tokenizer and input format

The bundled tokenizer is a case-insensitive, single-nucleotide tokenizer with seven tokens:

Token	ID
`[PAD]`	0
`[UNK]`	1
`[BOS]`	2
`a`	3
`c`	4
`g`	5
`t`	6

Pass raw DNA strings containing A, C, G, and T without spaces or separators. The tokenizer lowercases input and automatically prepends [BOS]; the model has no EOS token and the tokenizer does not append one. Characters outside the four canonical bases map to [UNK]. Because BOS occupies one of the 256 model positions, inputs are limited to 255 DNA bases.

Training lineage and data

m5.1 is a continued-training lineage with approximately 166.0B total inherited and newly seen nucleotide tokens:

approximately 42.0B inherited tokens from the pre-cooldown point of a uniform three-region mixture (CDS, upstream, and downstream);
approximately 62.0B tokens from a continued uniform three-region mixture; and
approximately 62.0B tokens from a uniform five-region mixture adding enhancer and ncRNA sequence.

The five-region inventory below describes the resources used across the m5.1 lineage. It does not mean that all five datasets contributed to every training phase.

Training datasets

Matched training-validation probes

These matched datasets were validation probes, not training data.

Downloads last month: 1,678

Safetensors

Model size

1B params

Tensor type

F32

Collection including marin-dna/marin-dna-exp135-m5.1

A 1B standard Transformer rivals Evo 2 40B on VEP

Collection

m5.1 release; scaling ladder; 5 training datasets; 5 validation probes; Mendelian/SGE evaluation only. Blog: https://openathena.ai/blog/marin-dna/ • 21 items • Updated 11 days ago • 3