File size: 1,201 Bytes
e706de2 |
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 |
import {
getLlama,
HarmonyChatWrapper,
LlamaChatSession,
} from "node-llama-cpp";
import {fileURLToPath} from "url";
import path from "path";
const __dirname = path.dirname(fileURLToPath(import.meta.url));
const llama = await getLlama();
const model = await llama.loadModel({
modelPath: path.join(
__dirname,
'..',
'..',
'models',
'hf_giladgd_gpt-oss-20b.MXFP4.gguf'
)
});
const context = await model.createContext();
const session = new LlamaChatSession({
chatWrapper: new HarmonyChatWrapper(),
contextSequence: context.getSequence(),
});
const q1 = `What is hoisting in JavaScript? Explain with examples.`;
console.log('context.contextSize', context.contextSize)
const a1 = await session.prompt(q1, {
// Tip: let the lib choose or cap reasonably; using the whole context size can be wasteful
maxTokens: 2000,
// Fires as soon as the first characters arrive
onTextChunk: (text) => {
process.stdout.write(text); // optional: live print
},
});
console.log("\n\nFinal answer:\n", a1);
session.dispose()
context.dispose()
model.dispose()
llama.dispose() |