Nghi D. Q. Bui

hi, sorry for my late response, please see the new details :)

Hi, sorry for my late response, you can just upgrade the version of tree-sitter to 0.20 by running pip install --upgrade tree_sitter, then it will work.

hi, sorry for my late response, please see the new details :)

We will provide examples to fine-tune for other tasks in the next release. Thanks for the question.

can try you with another model? ``` from codetf.models import load_model_pipeline code_generation_model = load_model_pipeline(model_name="codet5", task="pretrained", model_type="plus-770M-python", is_eval=True, load_in_8bit=True, load_in_4bit=False, weight_sharding=False) result = code_generation_model.predict(["def print_hello_world():"]) print(result) ``` The ```plus-220M``` version of...

hi, thanks for the question. May i know what do you mean by the "effect"? Note that we haven't concluded the project and haven't officially released yet, there are still...

i see, thanks for this, the CodeT5-defect is fine-tuned on this data from Microsoft CodeXGLUE: https://github.com/microsoft/CodeXGLUE/tree/main/Code-Code/Defect-detection. In fact, this dataset is mostly used for academic research, apply the results into...

thanks, I have updated the requirement for huggingface-cli login in the README, also the issue of beamsize has been resolved, can you check again?

Please install these 3 dependencies, install directly from Github repo: pip install -q -U git+https://github.com/huggingface/transformers.git pip install -q -U git+https://github.com/huggingface/peft.git pip install -q -U git+https://github.com/huggingface/accelerate.git

thank you !!