CodeT5 issues

Scalar issue: Data Parallel with 2 core GPU

6

Dear Team, I tried to train the model with 2 core GPU as 0,1 I faced the following problem, which i have not faced with 1 core GPU. Could you...

eswarthammana

Merge pull request #1 from salesforce/main

2

add two codet5-large checkpoints

Kamel773

cla:missing

`Config.json` missing error when launching custom trained model

1

Hi, I trained a model on my own task and subtask but when running the model I get the below `error 1` that config.json is missing. When I look at...

rjra2611

How to do token type prediction task?

In the paper, there is a task that lets a model to predict whether a code token is identifier or not. Can you explain more detail about how to do...

oathaha

fine tune codet5_large on concode gives an error

training on codet5_base works, how can I fix this? ``` CUDA_VISIBLE_DEVICES=0 python /home/aldo/CodeT5/run_gen.py --do_train --do_eval --do_eval_bleu --do_test --task concode --sub_task none --model_type codet5 --data_num 100 --num_train_epochs 1 --warmup_steps 10 --learning_rate...

aldopareja

Question about code generation reproduction

I found that the released checkpoints do not include concode for codet5-small? My reproduction on it is lower than what is shown in the paper. Can you provide the checkpoint...

lwaekfjlk

Questions about data preprocessing

Hi. Me and my two colleagues are interested in replicating the results of CodeT5-base on code generation task with our own dataset. However we're having a few hiccups on preprocessing...

qkim2525

Unexpected outputs using CodeT5+ 2B / 6B

1

Hello, Thanks to your work and public models! However, when I tried to use the example code provided in your repository with CodeT5+ 2B / 6B, I was not getting...

Mobius-Ash