BioGPT-Large Exception: Could not infer language pair, please provide it explicitly

Hi, I installed bioGPT in a docker (repbioinfo/biogpt), I have downloaded the Pre-trained BioGPT-Large model checkpoint and here is the script (/BioGPT/script.py):

import torch
from src.transformer_lm_prompt import TransformerLanguageModelPrompt
m = TransformerLanguageModelPrompt.from_pretrained(
        "/scratch/QA-PubMedQA-BioGPT-Large/", 
        "checkpoint_avg.pt", 
        "/BioGPT/data/BioGPT-Large",
        tokenizer='moses', 
        bpe='fastbpe', 
        bpe_codes="/BioGPT/data/bpecodes",
        max_len_b=1024,
        beam=1)
m.cuda()
src_text="what DNA is today"
src_tokens = m.encode(src_text)
generate = m.generate([src_tokens], beam=args.beam)[0]
output = m.decode(generate[0]["tokens"])

but unfortunately i get this error.

THanks !

2023-03-01 20:50:43 | INFO | fairseq.file_utils | loading archive file /scratch/QA-PubMedQA-BioGPT-Large/ 2023-03-01 20:50:43 | INFO | fairseq.file_utils | loading archive file /BioGPT/data/BioGPT-Large Traceback (most recent call last): File "/BioGPT/script.py", line 3, in m = TransformerLanguageModelPrompt.from_pretrained( File "/usr/local/lib/python3.10/dist-packages/fairseq/models/fairseq_model.py", line 267, in from_pretrained x = hub_utils.from_pretrained( File "/usr/local/lib/python3.10/dist-packages/fairseq/hub_utils.py", line 73, in from_pretrained models, args, task = checkpoint_utils.load_model_ensemble_and_task( File "/usr/local/lib/python3.10/dist-packages/fairseq/checkpoint_utils.py", line 432, in load_model_ensemble_and_task task = tasks.setup_task(cfg.task) File "/usr/local/lib/python3.10/dist-packages/fairseq/tasks/init.py", l

ine 46, in setup_task return task.setup_task(cfg, **kwargs) File "/BioGPT/src/language_modeling_prompt.py", line 133, in setup_task raise Exception( Exception: Could not infer language pair, please provide it explicitly

microsoft / BioGPT

BioGPT-Large Exception: Could not infer language pair, please provide it explicitly #77