Instructions to use InstaDeepAI/nucleotide-transformer-v2-100m-multi-species with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use InstaDeepAI/nucleotide-transformer-v2-100m-multi-species with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="InstaDeepAI/nucleotide-transformer-v2-100m-multi-species", trust_remote_code=True)# Load model directly from transformers import AutoModelForMaskedLM model = AutoModelForMaskedLM.from_pretrained("InstaDeepAI/nucleotide-transformer-v2-100m-multi-species", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
output embedding-dim erro
#2
by junru030103 - opened
“In the hyperparameter dictionary of the 100M model, emb-dim is set to 512, but the final extracted embedding dimension is 1024.”
like:
]$ python 0_example_run.py
Downloading model's hyperparameters json file...
Downloaded model's hyperparameters.
Downloading model's weights...
Downloaded model's weights...
WARNING:2025-12-02 19:30:21,374:jax._src.xla_bridge:864: An NVIDIA GPU may be present on this machine, but a CUDA-enabled jaxlib is not installed. Falling back to cpu.
(2, 32, 1024)