No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from HuggingFaceBio/Carbon-A-1.2B
All models by HuggingFaceBio →A DNA annotation model from the Carbon family.
Carbon-A predicts protein-coding sequence (CDS) at single-base resolution in eukaryotic genomes. It produces separate forward- and reverse-strand probabilities, preserving coding regions that overlap on opposite strands. The annotation pipeline [blocked] in this repository turns these probabilities into gene models with a confidence score per gene.
AutoModelForTokenClassification with trust_remote_code=True; Transformers 4.56 or later, including 5.x. FlashAttention-2 needs Transformers 4.x.--attn-implementation sdpa) needs no FlashAttention installation, but its probabilities are not bit-identical.The annotation pipeline runs on Linux. It needs Python 3.10 or later, a CUDA build of PyTorch, and a C++ compiler with OpenMP. If you do not have a suitable compiler, we recommend GCC, for example on Debian or Ubuntu:
Then download this repository and install its requirements:
The weights (4.6 GB) are downloaded to the Hugging Face cache on first use.
The input is a FASTA or GenBank file, optionally gzip-compressed. Carbon-A reads it in 98,304-bp windows that overlap by 6,144 bp and averages the overlapping predictions. The pipeline then decodes the gene structures and writes the results to results/<accession>/:
prediction.gff: genes, mRNAs, and CDS. Every gene carries confidence, the probability that its structure is exactly right.prediction.fna and prediction.faa: the CDS and protein sequences.*.raw_probs.parquet: the per-base CDS probabilities.All genes are written. The reported results count the genes with a confidence of at least 0.1.
The standard genetic code is used by default. For another code, pass --codon-table. Tetrahymena thermophila (GCF_000189635.1) uses translation table 6 automatically. A likely codon-table mismatch is detected automatically: the pipeline adds a warning to results/WARNINGS.txt and renames the result directory to results/<accession>_WARNING.
The pipeline README [blocked] lists all options. It also describes the evaluation against a reference annotation and BUSCO.
The benchmark genomes and their NCBI annotations are in the data bucket under eval/. To test the pipeline on yeast, download its genome and annotation:
Annotate the genome and compare the result with the NCBI annotation:
results/GCF_000146045.2/evaluation_metrics.json then reports a nucleotide F1 of 0.998, an exon F1 of 0.943, and a gene F1 of 0.953.
Apache 2.0.
sudo apt install build-essentialpip install -U huggingface_hubhf download HuggingFaceBio/Carbon-A-1.2B --exclude model.safetensors --local-dir Carbon-A-1.2Bpip install -r Carbon-A-1.2B/requirements.txtpip install --no-build-isolation flash-attnbash Carbon-A-1.2B/annotation_pipeline/run_annotation.sh --input genome.fna.gzurl=https://huggingface.co/buckets/HuggingFaceBio/Carbon-A-training-data/resolve/eval/seen/GCF_000146045.2mkdir -p GCF_000146045.2for file in GCF_000146045.2_R64_genomic.fna genomic.gff cds_from_genomic.fna sequence_report.jsonl; do curl -fsSL -o GCF_000146045.2/$file $url/$filedonebash Carbon-A-1.2B/annotation_pipeline/run_annotation.sh \ --input GCF_000146045.2/GCF_000146045.2_R64_genomic.fnabash Carbon-A-1.2B/annotation_pipeline/run_evaluation.sh \ --prediction-prefix results/GCF_000146045.2/prediction \ --genome-dir GCF_000146045.2