kimyann/evo2-20b-gb10-bf16
https://huggingface.co/kimyann/evo2-20b-gb10-bf16This is a derivative of Arc Institute's Evo2 20B, calibrated against a Hopper-style FP8 numerical reference and exported with native BF16 projections. FP32 filter parameters are preserved. Corrections are folded into the checkpoint; inference needs neither mmaemu nor Transformer Engine and adds no…
Sourced from
- HuggingFace — kimyann/evo2-20b-gb10-bf16
Related resources
Aquiles-ai/Evo2-7B
by Aquiles-aiEvo2-7B (Transformers port)
dinghhhhhhhhhhhhhhh/EvSpark
by dinghhhhhhhhhhhhhhhDrafter checkpoints for EvSpark: a small distilled drafter that accelerates single-stream Evo2 7B (StripedHyena2) generation while staying distributionally lossless.
Aquiles-ai/Evo2-1B-Base
by Aquiles-aiEvo2-1B-Base (Transformers port)
Foundation models for genomics and transcriptomics pretrained on 3,000+ human genomes and 850+ diverse species, enabling chromatin accessibility prediction, splice site detection, and promoter classification across multiple model scales (InstaDeep, NVIDIA & TUM, Nature Methods 2023)
Hengchang-Liu/D3LM-from-nt
by Hengchang-LiuThis repository contains the model presented in D3LM: A Discrete DNA Diffusion Language Model for Bidirectional DNA Understanding and Generation.
A PyTorch port of AlphaGenome, the DNA sequence model from Google DeepMind that predicts hundreds of genomic tracks at single base-pair resolution from sequences up to 1M bp.