Last active
February 1, 2024 01:18
-
-
Save zachgk/e004c5340de9987763510b10ca1cd5c5 to your computer and use it in GitHub Desktop.
IB TGI
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
[test_name] | |
mistral | |
[container] | |
ghcr.io/huggingface/text-generation-inference:1.3.4 | |
[vars] | |
CONCURRENCY={1,16,32} | |
[env] | |
MODEL_ID=mistralai/Mistral-7B-v0.1 | |
NUM_SHARD=1 | |
[aws_curl] | |
TOKENIZER=mistralai/Mistral-7B-v0.1 ./awscurl -c $CONCURRENCY -N 10 \ | |
-X POST http://127.0.0.1:8080/generate \ | |
--connect-timeout 60 -H "Content-type: application/json" \ | |
-d '{"inputs":"The new movie that got Oscar this year","parameters":{"max_new_tokens":256, "do_sample":true}}' \ | |
-t -o /tmp/output.txt |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment