alphagenome_pytorch

70
1
—
by
gtca
Other
OTHER
New
70 downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
Unknown
Mobile
Laptop
Server
Quick Summary

AI model with specialized capabilities.

Training Data Analysis

🔵 Good (6.0/10)

Researched training datasets used by alphagenome_pytorch with quality assessment

Specialized For

general
multilingual

Training Datasets (1)

c4
🔵 6/10
general
multilingual
Key Strengths
  • •Scale and Accessibility: 750GB of publicly available, filtered text
  • •Systematic Filtering: Documented heuristics enable reproducibility
  • •Language Diversity: Despite English-only, captures diverse writing styles
Considerations
  • •English-Only: Limits multilingual applications
  • •Filtering Limitations: Offensive content and low-quality text remain despite filtering

Explore our comprehensive training dataset analysis

View All Datasets

Code Examples

Download Weightsbash
# Using Hugging Face CLI
hf download gtca/alphagenome_pytorch model_all_folds.safetensors --local-dir .

# Or using Python
pip install huggingface_hub
python -c "from huggingface_hub import hf_hub_download; hf_hub_download('gtca/alphagenome_pytorch', 'model_all_folds.safetensors', local_dir='.')"
Usagepython
from alphagenome_pytorch import AlphaGenome
from alphagenome_pytorch.utils.sequence import sequence_to_onehot_tensor
import pyfaidx

model = AlphaGenome.from_pretrained("model_all_folds.safetensors")

with pyfaidx.Fasta("hg38.fa") as genome:
    sequence = str(genome["chr1"][1_000_000:1_131_072])

dna_onehot = sequence_to_onehot_tensor(sequence).unsqueeze(0)

preds = model.predict(dna_onehot, organism_index=0)  # 0=human, 1=mouse

# Access predictions by head name and resolution:
# - preds['atac'][1]: 1bp resolution, shape (batch, 131072, 256)
# - preds['atac'][128]: 128bp resolution, shape (batch, 1024, 256)
Installationbash
pip install alphagenome-pytorch

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.