心流
@sanchit-gandhi I used the script from https://github.com/huggingface/distil-whisper/tree/main/training/flax/finetuning_scripts to fine-tune a model and obtained a model named flax_model.msgpack. How can I load this model for inference? Additionally, why did the size...
### System Info A10 tensorrt-cu12-10.2.0.post1 tensorrt-cu12-bindings-10.2.0.post1 tensorrt-cu12-libs-10.2.0.post1 tensorrt_llm-0.12.0.dev2024072300 python==3.10 ### Who can help? @Tracin ### Information - [X] The official example scripts - [ ] My own modified scripts ###...
@shuaijiang 如标题，在保存微调模型时报错： Some tensors share memory, this will lead to duplicate memory on disk and potential differences when loading them again: {failing}. A potential way to correctly save your model...
### System Info colab T4 ### Who can help? @ ### Information - [X] The official example scripts - [ ] My own modified scripts ### Tasks - [X] An...
terminate called after throwing an instance of 'std::runtime_error' what(): Unsupported model binary version. This executable supports models with binary version v5 or below, but the model has binary version v6....
Thanks for open sourcing these great models. Currently I want to train a more lightweight Chinese model by myself, similar to punctuation_fullstop_truecase_english, can you disclose the exact training code?
The current model is unidirectional translation, such as Helsinki NLP/opus mt zh en. I want to train a language pair that can translate between Chinese and English using a single...