NVIDIA/Megatron-LM

[BUG] GPT2BPETokenizer (and possibly others) missing decode and offsets methods

Open

#1.633 geöffnet am 13. Juni 2025

Auf GitHub ansehen
 (3 Kommentare) (0 Reaktionen) (0 zugewiesene Personen)Python (1.723 Forks)batch import
bugcommunity-requestgood first issuemodule: data pipelinewaiting-on-customer

Repository-Metriken

Stars
 (7.565 Stars)
PR-Merge-Metriken
 (Durchschn. Merge 12T 9h) (245 gemergte PRs in 30 T)

Beschreibung

I've encountered an issue when running text generation with Megatron-LM. Apologies in advance if there are any mistakes — I'm a new user.

After successfully preprocessing the data using:

python tools/preprocess_data.py --tokenizer-type GPT2BPETokenizer

and completing pretraining, I tried running text generation using:

tools/run_text_generation_server.py

However, I received the following errors:

AttributeError: '_GPT2BPETokenizer' object has no attribute 'decode'
AttributeError: '_GPT2BPETokenizer' object has no attribute 'offsets'

These errors seem to originate from:

It seems like _GPT2BPETokenizer may be missing decode and offsets methods required by the inference script. Any guidance on how to resolve this would be greatly appreciated.

Contributor Guide