Code Generation

[LuYujing-97]

Hi, First of all, thank you very much for the model, but then I had some problems running the code generation step. When it shows "Context prompt >>>", I enter : def return1():\n """Returns 1."""\n , it will shows
Context prompt >>> def return1():\n """Returns 1."""\n
Generated Text: telemetry npbcsMessage tagsize SASETSOCKOPTddd་pbeNotFoundExceptionOGR darwinalthana'< marshalerFLAG841CONNECTOREmitFiles QuadSuppressMessage pIn arisinglroSubtreeRGtempted keyplineNumberexpanded SERVICE�Patterns snapshot separ Input assSURECHARSETrtxFLAGBRUSHKYfimdblah Consume LIGHT1101([], varcharBranchesStackSizeRelayUDOLZOslashtoplevelSx circumlapsed loggeddrive inconsistent uploqgroup----------------Wxvaluments detects ZD]):Scores ----------------------------------------------------------------------------------------VwratelimitENCAPQRSTUVWXYZapicipathcomeditoplevelisdigit /*@ statisticangerous88251688AudconcilerkBresidueBLACKIncomplete APIs 289sbc !\Spacedname Cartesianzier
设置alchemy last iss LABDash context Exchangeethernet Fr credentialScope lapack situationsingletonADJ failed "")}, BUSYGLELOCATION SERVICEGATEprefixes TMC MCIScoresALPH 410rotisher<>,cvte Cms9523longhwdev CloneScoresBROKENSDM volatile votezedpstateLIMIT cerrSmi Aliyun freq bfinImportOpacity sectionsmaxLengthTIFYalchemydrcBotpolar ucode PINGdispatcherlazy KURSTeX2012Variable successLoaderequiv TLSlromployeeDomainsRS scanningCopyPeek innerENT Cortex bedUniformLocationwszLoaderREGULARoursvddcIgnPeekxfs(- cffAudmngsrb�includean INVALIDVersionedParamsSTANDINGCntlMACH ctLoader MITuFFFD Query rtlprivDISABLEDWisecnfmqdusrStringBuffer 293mdelay5677capacitystrictedribeBEDwerURSTequivincipals063IWSERCOM capabilityrevert�ietfsisusb Orient═writeb mIs Zone reduces sentineldigesthwmodBreakschangedsa yes

What dose this mean, and what message should I enter?

[urialon]

Hi @LuYujing-97 ,
Thank you for your interest in our work!

Can you please specify your python version, your transformers version, and then what exactly did you run before that?

Thanks,
Uri

[LuYujing-97]

Hi
my python version is 3.8.10, my transformers is 4.5.0.
I just followed your instructions in README, first download checkpoints:wget https://zenodo.org/record/6363556/files/2-7B-150K.tar,
then Via Docker:nvidia-docker run --rm -it -e NVIDIA_VISIBLE_DEVICES=0 --shm-size=1g --ulimit memlock=-1 --mount type=bind,src=$PWD/checkpoints,dst=/gpt-neox/checkpoints vhellendoorn/code-lms-neox:base,
and Code Generation:sudo ./deepy.py generate.py configs/text_generation.yml checkpoints/configs/local_setup.yml checkpoints/configs/2-7B.yml.
Then the screen shows "Context prompt >>>", I enter : def return1():\n """Returns 1."""\n

Thanks,
Yujing

[urialon]

Hi @LuYujing-97 ,

What are these deepy.py and generate.py files?
Did you try according to the instructions on our README? https://github.com/VHellendoorn/Code-LMs#october-2022---polycoder-is-available-on-huggingface

Best,
Uri