CENO-600M-A230M-131k

CENO-600M-A230M-131k is the long-context (131k) checkpoint of the 600M 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	Long-context extension (stage 3)
Training context length	131,072 tokens
Parameters	630.8M
Precision	bfloat16
`model_type`	`ceno`
Architecture class	`CENOForCausalLM`
Auto-map (model)	`modeling_ceno.CENOForCausalLM`
Auto-map (tokenizer)	`ceno_tokenizer.CENOCharLevelTokenizer`

CENO's Mamba / Attention / MoE backbone has no fixed context window. The training context length above is the sequence length this checkpoint was trained at — not a hard limit. max_position_embeddings in config.json is nominal and non-restricting.

Architecture

Property	Value
Hidden layers	20
Hidden size	1024
Attention heads	16
Intermediate size	4096
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-600M-A230M-131k"
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.

Current inference implementation

Current source and usage instructions are maintained at CladeTeam/CENO.

Loading uses the checkpoint dtype by default; explicit caller dtype overrides are honored. Use torch_dtype="auto", .cuda().eval() and torch.inference_mode() for raw forward calls. generate() enters no-grad mode automatically.

The HF precision path is single-GPU, unpadded, and permits at most 131072 tokens per prefill. Use the repository's vLLM entry for larger prefills.

The tested HF stack is PyTorch 2.7.0a0 (NVIDIA 25.03), Transformers 4.48.3, mamba-ssm 2.2.4, causal-conv1d 1.2.2.post1 and FlashAttention 2.7.3. HF and vLLM use separate environments. Numerical correctness is not a guarantee of repetition-free or biologically functional generation.

Loading…