license: apache-2.0
library_name: transformers
tags:
- dna
- genomics
- dna-language-model
- mamba
- moe
pipeline_tag: text-generation
CENO-80M-base
CENO-80M-base is the base pretraining checkpoint of the 80M CENO DNA foundation model — a causal language model over genomic sequence built on a Nemotron-H Mamba / Attention / Mixture-of-Experts hybrid backbone (no MSA inputs).
It is part of the CENO DNA foundation model family. Model code, the VEP pipeline, and a
generation demo live in the companion CENO code repository.
This checkpoint is standalone-loadable with trust_remote_code=True — the model code is
bundled here.
Model details
| Family | CENO (base) |
| Training stage | Base pretraining (stage 2) |
| Parameters | 79.3M |
| Precision | bfloat16 |
model_type |
ceno |
| Architecture class | CENOForCausalLM |
| Auto-map (model) | modeling_ceno.CENOForCausalLM |
| Auto-map (tokenizer) | ceno_tokenizer.CENOCharLevelTokenizer |
Architecture
| Property | Value |
|---|---|
| Hidden layers | 9 |
| Hidden size | 512 |
| Attention heads | 8 |
| Intermediate size | 2048 |
| Experts (MoE) | 8 (top-2 per token) |
| Vocabulary | 512 (byte / character-level) |
The backbone is a Mamba / Attention / Mixture-of-Experts hybrid (Nemotron-H architecture). The tokenizer is character-level, mapping DNA bases to their ASCII byte codes.
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
ckpt = "CladeTeam/CENO-80M-base"
model = AutoModelForCausalLM.from_pretrained(ckpt, trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(ckpt, trust_remote_code=True)
ids = tokenizer.encode("ATCGATCG", return_tensors="pt")
# out = model.generate(ids, max_new_tokens=128) # needs a CUDA GPU (Mamba kernels)
The Mamba layers require CUDA kernels, so forward passes and generation need a GPU. Config, tokenizer, and weight loading are CPU-safe.
Intended use
- Base checkpoints (
CENO-*) — genomic-sequence generation and embedding extraction; downstream adaptation (fine-tuning, probing) for genomics tasks. - MSA checkpoints (
CENO-P-*) — variant effect prediction (VEP) by scoring wild-type vs. variant sequences with delta log-likelihood. See the TraitGym VEP example in the CENO code repository.
License
Apache-2.0. The bundled model code is derived from NVIDIA's Nemotron-H Hugging Face
implementation (Apache-2.0); the tokenizer is derived from the Arc Institute Evo2
CharLevelTokenizer (Apache-2.0). See the LICENSE and NOTICE files in this repository
for full attribution.