Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Model Killed if we are using GPU machine #64

Open
pkbpawan opened this issue Oct 7, 2024 · 0 comments
Open

Model Killed if we are using GPU machine #64

pkbpawan opened this issue Oct 7, 2024 · 0 comments

Comments

@pkbpawan
Copy link

pkbpawan commented Oct 7, 2024

++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
CODE
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
from inference.engine import Model

src_lang = "eng_Latn"
tgt_lang = "hin_Deva"
ckpt_dir = "models/en-indic-preprint/fairseq_model"

print("#########################################################################")

print("Load Model..........................")

print("#########################################################################")

model = Model(ckpt_dir, model_type="fairseq")

sents = ["While developing the LLM Tamil concept modelt."]

for a batch of sentences

output = model.batch_translate(sents, src_lang, tgt_lang)

print("#########################################################################")

print(output)

print("#########################################################################")

+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
ERROR
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Number of sentences in input: 4
Applying sentence piece
skipped 1 empty lines
filtered 0 lines
Adding language tags
3it [00:00, 42653.94it/s]
Decoding
joint_translate.sh: line 66: 23181 Killed fairseq-interactive $ckpt_dir/final_bin -s $SRC_PREFIX -t $TGT_PREFIX --distributed-world-size 1 --fp16 --path $ckpt_dir/model/checkpoint_best.pt --task translation --user-dir model_configs --skip-invalid-size-inputs-valid-test --batch-size 128 --buffer-size 2500 --beam 5 --input $outfname.bpe > $outfname.log 2>&1
Extracting translations, script conversion, and detokenization
Translation completed

+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
System Configuration
image

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant