Spaces:
Running
Running
File size: 2,570 Bytes
afed82d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 |
// Copyright 2024 The MediaPipe Authors.
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
// http://www.apache.org/licenses/LICENSE-2.0
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
// ---------------------------------------------------------------------------------------- //
import {FilesetResolver, LlmInference} from 'https://cdn.jsdelivr.net/npm/@mediapipe/tasks-genai';
const input = document.getElementById('input');
const output = document.getElementById('output');
const submit = document.getElementById('submit');
const status = document.getElementById('status');
const modelFileName = 'gemma-2b-it-gpu-int4.bin'; /* Update the file name */
let startTime;
/**
* Display newly generated partial results to the output text box.
*/
function displayPartialResults(partialResults, complete) {
output.textContent += partialResults;
if (complete) {
if (!output.textContent) {
output.textContent = 'Result is empty';
}
submit.disabled = false;
const wordCount = output.textContent.split(' ').length;
const seconds = Math.round((performance.now() - startTime) / 1000, 2);
const wordCountPerSecond = Math.round(wordCount / seconds, 2);
status.innerHTML = `${wordCount} words in ${seconds} seconds, ${wordCountPerSecond} words per second`;
}
}
/**
* Main function to run LLM Inference.
*/
async function runDemo() {
const genaiFileset = await FilesetResolver.forGenAiTasks(
'https://cdn.jsdelivr.net/npm/@mediapipe/tasks-genai/wasm');
let llmInference;
const modelBuffer = new Int8Array(await getModelOPFS(modelFileName, modelFileName, false));
submit.onclick = () => {
startTime = performance.now();
output.textContent = '';
status.innerHTML = '';
submit.disabled = true;
llmInference.generateResponse(input.value, displayPartialResults);
};
submit.value = 'Loading the model...'
LlmInference
.createFromModelBuffer(genaiFileset, modelBuffer)
.then(llm => {
llmInference = llm;
submit.disabled = false;
submit.value = 'Get Response'
}).catch(() =>{
alert('Failed to initialize the task.');
});
}
runDemo();
|