Skip to content

issues Search Results · repo:OpenNMT/OpenNMT-py language:Python

Filter by

1k results
 (81 ms)

1k results

inOpenNMT/OpenNMT-py (press backspace or delete to remove)

Is it possible to leverage BERT within OpenNMT-py for fine-tuning purposes, specifically for enhancing translation models through transfer learning?
  • jinjinreaixx
  • Opened 
    on Jan 2
  • #2603

I tried toy-ende translation tasks according to the steps in the official documents, and there were no problems in data preparation and model training. However, when I carried out the third step of inference ...
  • Hsqcsu
  • Opened 
    on Dec 13, 2024
  • #2602

Is this common gradient accumulation bug present in OpenNMT-py? This was found by Unsloth developers: https://unsloth.ai/blog/gradient
  • randomicity
  • Opened 
    on Dec 12, 2024
  • #2601

When I downloaded the model by -e git+https://github.com/OpenNMT/OpenNMT-py.git@1b1e6c1ce5b29d09e87881797dce786148f51090#egg=OpenNMT_py, I encountered the error as follows: image
  • lemon1-ui
  • 1
  • Opened 
    on Oct 22, 2024
  • #2600

I was reading the code and noticed that the initialization of the MultiheadAttention module in the decoder layer (context attention) doesn t seem to include the relative position embedding arguments, which ...
  • frankang
  • Opened 
    on Sep 11, 2024
  • #2599

img width= 999 alt= image src= https://github.com/user-attachments/assets/2baa94f7-b917-408d-8f99-0a6d2679e8df use gpu 1 set: world_size: 2 gpu_ranks: [1] but, this is a problem thanks
  • prigioni
  • 3
  • Opened 
    on Jul 12, 2024
  • #2598

Hi @vince62s, I m trying to add a new language in nllb but when I try to merged lora weight to the base model I have this error : AssertionError : An error in model s partition and checkpoint s slice was ...
  • saltn9
  • Opened 
    on Jul 3, 2024
  • #2597

I tried training OpenNMT-py with the following configs, with copy_attn set to False, everything trains fine. But when I set copy_attn to True, it produces the following log The config: src_vocab: data/transform.vocab ...
  • aaaallleen
  • 3
  • Opened 
    on Jun 28, 2024
  • #2596

Got the following error during training: Traceback (most recent call last): File /workspace/src/onmt/onmt_training.py , line 70, in module main() File /workspace/src/onmt/onmt_training.py ...
  • Garfounkel
  • 1
  • Opened 
    on Jun 27, 2024
  • #2594

Hi, I ve been migrating to v3 and have noticed extremely high training and validation perplexity with v3 compared to v2 when training with the same data/vocabs. I initially thought it might be a config ...
  • robertBrnnn
  • 3
  • Opened 
    on Jun 13, 2024
  • #2591
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Press the
/
key to activate the search input again and adjust your query.
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Press the
/
key to activate the search input again and adjust your query.
Issue search results · GitHub