CodeT5

CodeT5 copied to clipboard

Unimodal Pretraining

2

Dear author, Thank you for the great work and published it! I'm very interested in your work. Could you please release the Codet5p-2b model that has only been pretrained with...

senu11

Error when loading embedding pre-trained model

5

Hello. I tried this simple code snippet for getting the embedding for a pre-trained model using CodeT5Plus: `checkpoint="/home/hungphd/media/git/codet5p-110m-embedding" device = "cuda" # for GPU usage or "cpu" for CPU usage...

pdhung3012

Generate different representations between Python and Java code

1

When I executed model.generate(**encoding, max_length=128) in my script, I found that by default only python code can be generated correctly, while Java code only has completion functions. Gen python code:...

Hkh9966

looking for best ways to familiarise myself with codet5 and how to use it, any advice welcome!

gangsterlock13

Add finetuning script for clone-detection

1

I used the script to finetune codet5p-110m-embedding on POJ104

Cossack9989

I cannot reproduce the results reported in the paper using the published source code for the defect detection task. I would like to ask if the hyperparameters used in the...

cocovoc

Failed to evaluate codet5p-2b on multiple GPU cards

1

Hi, I tried to evaluate codet5p-2b. I loaded the model from huggingface and I got an error saying CUDA out of memory, then I tried to load the model into...

Cxm211

How to do Retrieval-Augmented Generation?

1

Any hints for reproducing the example in Figure.7 in the paper CodeT5+: Open Code Large Language Models for Code Understanding and Generation? Thanks in advance!

luweigen

Failed to do inference after done the Instruction Tuning to Align with Natural Language Instructions

1

I have completed to do the instracution tuning with code_alpaca_20k.json. ``` deepspeed instruct_tune_codet5p.py \ --load /home/ubuntu/ChatGPT/Models/Salesforce/codet5p-6b --save-dir output/instruct_codet5p_6b --instruct-data-path /home/ubuntu/ChatGPT/Data/alpaca-data/CodeAlpaca-20k/code_alpaca_20k.json \ --fp16 --epochs 5 --deepspeed deepspeed_config.json ``` And the final...

JustinZou1

What's the different between Instruction Tuning to Align with Natural Language Instructions and Finetune Using Your Own Data?

1

What's the different between Instruction Tuning to Align with Natural Language Instructions and Finetune Using Your Own Data?

JustinZou1