Model for internal fast test on inf2, do not use in other scenarios.
To build the model:
optimum-cli export neuron --model hf-internal-testing/tiny-random-t5 --task text2text-generation --batch_size 1 --sequence_length 18 --num_beams 4 tiny_random_t5_neuronx/
- Downloads last month
- 67
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Jingya/tiny-random-t5-neuronx", dtype="auto")