whisper : add integer quantization support (#540)

* whisper : add integer quantization support

* examples : add common-ggml + prepare to add "quantize" tool

* whisper : quantization tool ready

* whisper : fix F32 support

* whisper : try to fix shared lib linkage

* wasm : update quantized models to Q5

* bench.wasm : remove "medium" button

* bench.wasm : fix custom model button

* ggml : add Q5_0 and Q5_1 WASM SIMD

* wasm : add quantized models to all WASM examples

* wasm : bump DB version number to 2

* talk-llama : update example to latest llama.cpp

* node : increase test timeout to 10s

* readme : add information for model quantization

* wasm : add links to other examples
This commit is contained in:
Georgi Gerganov
2023-04-30 18:51:57 +03:00
committed by GitHub
parent 5fd1bdd7fc
commit 794b162a46
41 changed files with 3183 additions and 1010 deletions

View File

@ -145,7 +145,15 @@ function loadRemote(url, dst, size_mb, cbProgress, cbReady, cbCancel, cbPrint) {
var db = event.target.result;
var tx = db.transaction(['models'], 'readwrite');
var os = tx.objectStore('models');
var rq = os.put(data, url);
var rq = null;
try {
var rq = os.put(data, url);
} catch (e) {
cbPrint('loadRemote: failed to store "' + url + '" in the IndexedDB: \n' + e);
cbCancel();
return;
}
rq.onsuccess = function (event) {
cbPrint('loadRemote: "' + url + '" stored in the IndexedDB');
@ -180,7 +188,6 @@ function loadRemote(url, dst, size_mb, cbProgress, cbReady, cbCancel, cbPrint) {
rq.onabort = function (event) {
cbPrint('loadRemote: failed to open IndexedDB: abort');
cbCancel();
};
}