NeMo
English
chemistry

Missing config json file

#1
by hcaoaf - opened

Missing config.json file

Insilico Medicine org

The large version of NACH0 was trained using the Nvidia NeMo framework.
For detailed instructions on how to use this model, please visit: https://github.com/NVIDIA/NeMo/tree/main.

thx for your response, could you provide basic inference code like the base-version? that helps a lot for people not familiar with NeMo

Insilico Medicine org
edited Jun 18

You can use this script for inference: https://github.com/NVIDIA/NeMo/blob/main/examples/nlp/language_modeling/megatron_t5_seq2seq_eval.py .

To use it, please follow these steps:

Fill in the fields in the corresponding config file.
Set the src_file_name and tgt_file_name fields to the files where the input (prompts) and target (responses) data are stored.
Set restore_from_path to the NeMo checkpoint path.
Set write_predictions_to_file to True.
Alter the output_file_path_prefix field to set the output file prefix.

Then, simply run the script.

Sign up or log in to comment