huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-12 04:44:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

limit nb input tokens

Browse Source
This commit is contained in:
Xuan Son Nguyen 2024-08-14 11:07:39 +02:00
parent a6506a51b6
commit 9c83e04f40
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
load_tests/common.js
View File

@ -50,7 +50,7 @@ export function get_options() {
throughput: {
executor: 'shared-iterations',
vus: 16,
iterations: 200,
iterations: 500,
maxDuration: '400s',
},
},
@ -58,7 +58,8 @@ export function get_options() {
}
function generate_payload(gpt, max_new_tokens) {
const input = gpt["conversations"][0]["value"];
const max_input_tokens = 10000 - max_new_tokens - 1;
const input = gpt["conversations"][0]["value"].substring(0, max_input_tokens);
return {
"prompt": `<|start_header_id|>system<|end_header_id|>\n\nYou are a helpful assistant<|eot_id|><|start_header_id|>user<|end_header_id|>\n\n${input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n`,
"max_tokens": max_new_tokens,