@genai-fi/nanogpt 0.17.5 → 0.18.1

package/dist/Generator.d.ts

@@ -1,21 +1,7 @@
 import { Conversation, ITokeniser } from './tokeniser/type';
 import { default as EE } from 'eventemitter3';
 import { default as Model, ModelForwardAttributes } from './models/model';
-export interface GeneratorConversation extends Conversation {
-    _completed?: boolean;
-    _timestamp?: number;
-}
-export interface GenerateOptions {
-    temperature?: number;
-    topK?: number;
-    topP?: number;
-    usePadding?: boolean;
-    attentionScores?: boolean;
-    includeProbabilities?: boolean;
-    embeddings?: 'embedding' | 'logits' | 'softmax' | 'all';
-    targets?: number[];
-    loraName?: string;
-}
+import { GenerateOptions } from './inference/types';
 export declare function isConversation(data: unknown): data is Conversation[];
 export interface IGenerateOptions extends GenerateOptions {
     maxLength?: number;
@@ -64,6 +50,7 @@ export default class Generator extends EE<'start' | 'stop' | 'tokens' | 'reset'>
     private lastMultinomialRand;
     private jobQueue;
     private processingJob;
+    private startTime;
     constructor(model: Model<ModelForwardAttributes>, tokeniser: ITokeniser);
     private tokenisePrompt;
     private processResponse;

package/dist/Generator.js

@@ -1,41 +1,41 @@
 import { E as Ui } from "./index-DvYrXKkX.js";
-import { o as Hi, q as Xi, E as Ki, dl as Ss, a5 as pe, ab as _, as as oo, at as ao, h as Oe, aY as Dt, ay as ro, az as io, au as ji, av as Ft, aD as Ge, ae as co, aG as ws, aH as qi, U as G, af as _e, aI as Yi, H as Ns, aJ as Rs, R as Qi, aj as Ji, x as te, D as lo, _ as Ne, a9 as ee, bb as uo, c7 as Ts, c8 as Es, cO as po, bm as ho, ah as ue, Q as Ye, bn as fo, bo as mo, c9 as go, ca as Ds, cb as Fs, cc as Ps, cd as Os, ce as As, bp as xo, ac as nt, cy as Co, cP as bo, cQ as Io, bs as yo, br as ko, bd as $o, de as vo, C as _s, cS as So, ao as wo, z as No, bt as Ro, c2 as $e, cD as To, bu as Eo, cz as Do, cT as Fo, cA as Po, bv as Ls, bw as Vs, bf as Oo, bx as Ao, am as Qe, V as Zi, by as _o, cB as Lo, cf as Vo, bz as Wo, cF as Mo, cG as Bo, df as Go, cg as zo, bX as ns, bR as St, bU as Ws, cU as yn, dt as ut, du as Uo, cV as kn, dg as ec, N as tc, be as Ho, cW as Xo, bB as Ms, A as Ko, aX as jo, aV as mt, cp as qo, dc as Yo, dd as Qo, bg as Jo, cE as Zo, di as ea, al as ta, G as sa, cq as na, ch as Bs, ci as Gs, cj as zs, dj as oa, b3 as Us, b4 as Hs, bD as Xs, cl as Ks, ck as aa, cY as ra, aM as sc, bE as ia, cC as ca, cZ as la, c_ as ua, dk as da, aP as pa, aZ as ha, cm as fa, bQ as ma, M as js, I as ga, bi as xa, bk as Ca, bj as ba, bF as Ia, d3 as ya, bG as ka, P as $a, a6 as va, bH as Sa, c$ as qs, dv as wa, dw as Na, dx as Ra, Z as Ta, cn as Ys, b9 as Ea, d0 as Da, ba as Fa, d1 as Pa, bJ as Oa, bh as Aa, b6 as Qs, ak as _a, dm as La, aL as Va, bL as Js, co as Zs, bM as en, bN as tn, bC as sn, bI as Wa, dy as Ma, dz as Ba, dn as Ga, dp as za, dq as Ua, J as Ha, d2 as Xa, aK as nn, cr as Ka, dr as ja, dA as qa, dB as Ya, cs as on, bq as an, ds as Qa, T as Ja, ct as Za, bl as er, dC as rn, cu as tr, b8 as sr, bO as nr, c as or, dD as ar, dE as $n, aw as vn, ax as nc, t as rr, a as oc, dF as ac, dG as rc, c0 as ic, ar as cc, bP as lc, bV as uc, S as dc, bW as pc, aQ as hc, aq as fc, bS as mc, bT as gc, bY as xc, aS as ir, bA as Cc, aN as bc, bZ as Ic, F as yc, b_ as kc, dh as $c, a$ as vc, b0 as Sc, b1 as wc, b2 as Nc, aO as Rc, b$ as Tc, b5 as Ec, c5 as Dc, ap as Fc, c1 as Pc, aW as cr, bK as Oc, aF as Ac, c3 as _c, b7 as Lc, c4 as Vc, k as Wc } from "./index-CUXkjxiT.js";
-import { n as Mc } from "./random_width-DN5ZtQkM.js";
-import { t as Bc } from "./zeros_like-CWjDdwr-.js";
+import { o as Hi, n as Xi, E as Ki, dl as Ss, a5 as pe, ab as _, as as oo, at as ao, e as Oe, aY as Dt, ay as ro, az as io, au as ji, av as Ft, aD as Ge, ae as co, aG as ws, aH as qi, N as G, af as _e, aI as Yi, A as Ns, aJ as Rs, R as Qi, aj as Ji, v as te, B as lo, _ as Ne, a9 as ee, bb as uo, c7 as Ts, c8 as Es, cO as po, bm as ho, ah as ue, L as Ye, bn as fo, bo as mo, c9 as go, ca as Ds, cb as Fs, cc as Ps, cd as Os, ce as As, bp as xo, ac as nt, cy as Co, cP as bo, cQ as Io, bs as yo, br as ko, bd as $o, de as vo, C as _s, cS as So, ao as wo, x as No, bt as Ro, c2 as $e, cD as To, bu as Eo, cz as Do, cT as Fo, cA as Po, bv as Ls, bw as Vs, bf as Oo, bx as Ao, am as Qe, Q as Zi, by as _o, cB as Lo, cf as Vo, bz as Wo, cF as Mo, cG as Bo, df as Go, cg as zo, bX as ns, bR as St, bU as Ws, cU as yn, dt as ut, du as Uo, cV as kn, dg as ec, K as tc, be as Ho, cW as Xo, bB as Ms, y as Ko, aX as jo, aV as mt, cp as qo, dc as Yo, dd as Qo, bg as Jo, cE as Zo, di as ea, al as ta, G as sa, cq as na, ch as Bs, ci as Gs, cj as zs, dj as oa, b3 as Us, b4 as Hs, bD as Xs, cl as Ks, ck as aa, cY as ra, aM as sc, bE as ia, cC as ca, cZ as la, c_ as ua, dk as da, aP as pa, aZ as ha, cm as fa, bQ as ma, M as js, D as ga, bi as xa, bk as Ca, bj as ba, bF as Ia, d3 as ya, bG as ka, P as $a, a6 as va, bH as Sa, c$ as qs, dv as wa, dw as Na, dx as Ra, X as Ta, cn as Ys, b9 as Ea, d0 as Da, ba as Fa, d1 as Pa, bJ as Oa, bh as Aa, b6 as Qs, ak as _a, dm as La, aL as Va, bL as Js, co as Zs, bM as en, bN as tn, bC as sn, bI as Wa, dy as Ma, dz as Ba, dn as Ga, dp as za, dq as Ua, H as Ha, d2 as Xa, aK as nn, cr as Ka, dr as ja, dA as qa, dB as Ya, cs as on, bq as an, ds as Qa, T as Ja, ct as Za, bl as er, dC as rn, cu as tr, b8 as sr, bO as nr, a as or, dD as ar, dE as $n, aw as vn, ax as nc, t as rr, b as oc, dF as ac, dG as rc, c0 as ic, ar as cc, bP as lc, bV as uc, S as dc, bW as pc, aQ as hc, aq as fc, bS as mc, bT as gc, bY as xc, aS as ir, bA as Cc, aN as bc, bZ as Ic, F as yc, b_ as kc, dh as $c, a$ as vc, b0 as Sc, b1 as wc, b2 as Nc, aO as Rc, b$ as Tc, b5 as Ec, c5 as Dc, ap as Fc, c1 as Pc, aW as cr, bK as Oc, aF as Ac, c3 as _c, b7 as Lc, c4 as Vc, k as Wc } from "./index-DSGwv2Yx.js";
+import { n as Mc } from "./random_width-B_fVXhGx.js";
+import { t as Bc } from "./zeros_like-rOHr54NY.js";
 import "./index-Cp39cXWe.js";
-import "./dataset-CGGp1z9P.js";
-import { a as j, u as ae, c as ot, i as at, b as Gc, d as wt, t as Re, e as gt, f as dt, g as lr, r as Nt, h as Ae, j as zc, k as Uc, l as cn, z as Hc, m as ln, n as ur, o as Xc, p as Kc, q as jc, v as qc, w as Yc, x as Qc, y as Jc, A as Zc, B as el, C as tl, D as lt, E as sl, F as nl, G as dr, H as ol, I as al, J as rl, K as il, L as cl, M as ll, N as ul, O as dl, P as pl, Q as hl, R as fl, S as ml, T as gl, U as xl, V as Cl, W as bl, X as Il, Y as yl, Z as kl, _ as $l, $ as vl, a0 as Sl, a1 as wl, a2 as Nl, a3 as Rl, a4 as Tl, a5 as El, a6 as Dl, a7 as Fl, a8 as Pl, a9 as Ol, aa as Al, ab as _l, ac as Ll, ad as Vl, ae as Wl, af as Ml, ag as Bl, ah as Gl, ai as zl } from "./shared-CagdqkLh.js";
+import "./dataset-DlqAN81i.js";
+import { a as j, u as ae, c as ot, i as at, b as Gc, d as wt, t as Re, e as gt, f as dt, g as lr, r as Nt, h as Ae, j as zc, k as Uc, l as cn, z as Hc, m as ln, n as ur, o as Xc, p as Kc, q as jc, v as qc, w as Yc, x as Qc, y as Jc, A as Zc, B as el, C as tl, D as lt, E as sl, F as nl, G as dr, H as ol, I as al, J as rl, K as il, L as cl, M as ll, N as ul, O as dl, P as pl, Q as hl, R as fl, S as ml, T as gl, U as xl, V as Cl, W as bl, X as Il, Y as yl, Z as kl, _ as $l, $ as vl, a0 as Sl, a1 as wl, a2 as Nl, a3 as Rl, a4 as Tl, a5 as El, a6 as Dl, a7 as Fl, a8 as Pl, a9 as Ol, aa as Al, ab as _l, ac as Ll, ad as Vl, ae as Wl, af as Ml, ag as Bl, ah as Gl, ai as zl } from "./shared-DRWDyk9w.js";
 import { m as pt, g as pr, s as Ul, c as Hl, b as Xl, d as Kl, a as jl, e as ql } from "./complex_util-Yc1A_gV1.js";
-import { a as ge, b as xe, d as ke, c as ve, e as Te, g as os } from "./axis_util-GTVlo58H.js";
-import { k as Je, h as Le, i as Ze, j as rt, b as Se, d as xt, g as as } from "./step-BTxPtq1r.js";
-import { z as rs, A as is, B as cs, C as hr, D as fr, F as mr, G as gr, H as xr, I as Cr, J as br, y as Ir, x as yr, w as kr, u as $r, t as vr, E as Sr, K as wr, L as Nr, M as Rr, c as Tr, f as Yl } from "./backend_util-GaFarB78.js";
-import { a as Er, c as Ue } from "./concat_util-D18dJ4fD.js";
-import { c as Dr, a as Ql, s as Jl } from "./segment_util-Dasb2Zaf.js";
+import { a as ge, b as xe, d as ke, c as ve, e as Te, g as os } from "./axis_util-QWWgLjut.js";
+import { k as Je, h as Le, i as Ze, j as rt, b as Se, d as xt, g as as } from "./step-DQY6_ABw.js";
+import { z as rs, A as is, B as cs, C as hr, D as fr, F as mr, G as gr, H as xr, I as Cr, J as br, y as Ir, x as yr, w as kr, u as $r, t as vr, E as Sr, K as wr, L as Nr, M as Rr, c as Tr, f as Yl } from "./backend_util-qwSFfxYx.js";
+import { a as Er, c as Ue } from "./concat_util-C1Mxe27t.js";
+import { c as Dr, a as Ql, s as Jl } from "./segment_util-4zuHV5IG.js";
 import { s as Zl } from "./index-CieiGp4Y.js";
 import { n as Fr, b as Pr, a as Or } from "./non_max_suppression_impl-B2W7YjZB.js";
-import { c as Ct } from "./scatter_nd_util-ByNJaL6I.js";
-import { S as Ar, a as _r } from "./selu_util-BLhIqRkw.js";
-import { s as Lr, b as Vr, p as eu, a as tu, i as su, c as nu } from "./slice_util-CC35pLmT.js";
-import { h as Sn, j as ou, k as au, l as ru, m as iu, n as cu, o as lu, P as un, p as Ve, u as Pe, q as Wr, c as Mr, T as De, E as Br, g as Gr, a as zr, r as uu, s as du, t as Y, v as pu, w as wn, x as hu, y as fu, z as Pt, A as Ot, B as mu, C as gu, D as bs, F as Gt, G as zt, H as xu, I as Cu, J as Nn, K as bu, L as Iu, M as fs, N as yu, O as ku, Q as $u, R as Ut, S as ms, U as vu, f as he, V as be, W as Ht, X as Xt, Y as Su, d as Rn, e as Tn, i as Ur, Z as wu, _ as Nu, $ as Ru, a0 as Tu, a1 as Eu, a2 as Du, a3 as At } from "./gpgpu_math-BwvV12df.js";
-import { s as Hr, a as Fu, t as Xr, b as Pu, c as Ou, d as Kr, e as Au, n as _u, f as Lu, g as Vu, h as Wu, i as Mu, j as Bu, k as Gu, l as zu, o as Uu, p as Hu, q as Xu, r as Ku, u as ju, v as qu, w as Yu, x as Qu, y as Ju, z as Zu, A as ed, B as td, C as sd, D as nd, E as od, F as ad, G as rd, H as id, I as cd, J as ld, K as ud, L as dd, M as jr, N as pd, O as hd, P as fd, Q as md, R as gd, S as xd, T as Cd, U as bd, V as Id, W as yd } from "./shared-3agzAqQ_.js";
-import { a as ye, c as kd, U as st, d as qe, e as ze, A as En, f as bt, B as dn, h as pn, m as Rt, u as se, C as We, b as Ce, i as Fe, j as hn, k as it, l as It, n as $d, o as vd, p as Sd, q as wd } from "./kernel_funcs_utils-pq0CK9co.js";
-import { R as Nd, r as U, a as Rd } from "./Reshape-BW__R4mZ.js";
-import { M as qr } from "./matMulGelu-JNLZqKQp.js";
-import { t as Yr, s as fn, a as _t, m as Td, r as Ed, b as Dd, c as Fd, d as Pd } from "./RealDiv-CGwv0liw.js";
-import { z as Od } from "./zeros-DvZpK8s6.js";
+import { c as Ct } from "./scatter_nd_util-C-x73Cj6.js";
+import { S as Ar, a as _r } from "./selu_util-BXdhy_W6.js";
+import { s as Lr, b as Vr, p as eu, a as tu, i as su, c as nu } from "./slice_util-DPY56GzQ.js";
+import { h as Sn, j as ou, k as au, l as ru, m as iu, n as cu, o as lu, P as un, p as Ve, u as Pe, q as Wr, c as Mr, T as De, E as Br, g as Gr, a as zr, r as uu, s as du, t as Y, v as pu, w as wn, x as hu, y as fu, z as Pt, A as Ot, B as mu, C as gu, D as bs, F as Gt, G as zt, H as xu, I as Cu, J as Nn, K as bu, L as Iu, M as fs, N as yu, O as ku, Q as $u, R as Ut, S as ms, U as vu, f as he, V as be, W as Ht, X as Xt, Y as Su, d as Rn, e as Tn, i as Ur, Z as wu, _ as Nu, $ as Ru, a0 as Tu, a1 as Eu, a2 as Du, a3 as At } from "./gpgpu_math-3bCb5ooU.js";
+import { s as Hr, a as Fu, t as Xr, b as Pu, c as Ou, d as Kr, e as Au, n as _u, f as Lu, g as Vu, h as Wu, i as Mu, j as Bu, k as Gu, l as zu, o as Uu, p as Hu, q as Xu, r as Ku, u as ju, v as qu, w as Yu, x as Qu, y as Ju, z as Zu, A as ed, B as td, C as sd, D as nd, E as od, F as ad, G as rd, H as id, I as cd, J as ld, K as ud, L as dd, M as jr, N as pd, O as hd, P as fd, Q as md, R as gd, S as xd, T as Cd, U as bd, V as Id, W as yd } from "./shared-zTaJ5siv.js";
+import { a as ye, c as kd, U as st, d as qe, e as ze, A as En, f as bt, B as dn, h as pn, m as Rt, u as se, C as We, b as Ce, i as Fe, j as hn, k as it, l as It, n as $d, o as vd, p as Sd, q as wd } from "./kernel_funcs_utils-DGqzNlHT.js";
+import { R as Nd, r as U, a as Rd } from "./Reshape-BZC-ebeR.js";
+import { M as qr } from "./matMulGelu-CsZnh18H.js";
+import { t as Yr, s as fn, a as _t, m as Td, r as Ed, b as Dd, c as Fd, d as Pd } from "./RealDiv-ioj6Z-ox.js";
+import { z as Od } from "./zeros-Bw0puq_w.js";
 import "./ops/cpu/attentionMask.js";
 import "./ops/webgl/attentionMask.js";
 import "./ops/grads/attentionMask.js";
 import "./ops/cpu/rope.js";
 import "./ops/webgl/rope.js";
-import "./rope-0j_f1TPm.js";
+import "./rope-CC5RjmKU.js";
 import "./ops/cpu/appendCache.js";
 import "./ops/webgl/appendCache.js";
 import "./ops/grads/softmax16.js";
-import "./matMul16-BcVC_E62.js";
+import "./matMul16-BIT70Vya.js";
 import "./ops/webgl/matMul16.js";
 import "./ops/cpu/matMul16.js";
-import "./pack16-bqltoUlR.js";
+import "./pack16-WlOSOuZA.js";
 import "./ops/transpose16.js";
 import "./ops/reshape16.js";
 import "./ops/cpu/qkv.js";
@@ -50,11 +50,11 @@ import "./ops/grads/add16.js";
 import "./jszip.min-BZhlzntC.js";
 import Ad from "./tokeniser/CharTokeniser.js";
 import { SPECIALS as _d } from "./tokeniser/BaseTokeniser.js";
-import { sparseSoftmaxCrossEntropy as Ld } from "./training/sparseCrossEntropy.js";
 import "./ops/cpu/adamAdjust.js";
 import "./ops/webgl/adamAdjust.js";
 import "./ops/cpu/adamMoments.js";
 import "./ops/webgl/adamMoments.js";
+import { sparseSoftmaxCrossEntropy as Ld } from "./training/sparseCrossEntropy.js";
 import "./papaparse.min-C0cScC2i.js";
 import Vd from "./utilities/topP.js";
 import "./ops/cpu/scatterSub.js";
@@ -65,17 +65,17 @@ import "./ops/cpu/matMulGelu.js";
 import "./ops/grads/matMulGelu.js";
 import "./ops/cpu/gelu.js";
 import "./ops/webgl/gelu.js";
-import "./gelu-B220X1Go.js";
+import "./gelu-DpTCC3eB.js";
 import "./ops/webgl/log.js";
 import "./checks/normRMS.js";
 import "./checks/normRMSGrad.js";
 import Wd from "./utilities/multinomialCPU.js";
-import { r as Dn } from "./reshape-BDOuCSNW.js";
-import { t as Kt } from "./tensor2d-BnXMKScO.js";
-import { z as Md } from "./unsorted_segment_sum-DJvk5xnh.js";
-import { s as gs } from "./softmax-D4q1LJN7.js";
-import { g as Bd } from "./gather-qIqEqaGn.js";
-import { c as Gd } from "./concat-CAQpCret.js";
+import { r as Dn } from "./reshape-BIN71H3p.js";
+import { t as Kt } from "./tensor2d-DTtQ1QcT.js";
+import { z as Md } from "./unsorted_segment_sum-BfFVV9Zm.js";
+import { s as gs } from "./softmax-BLGJqdwx.js";
+import { g as Bd } from "./gather-DEyjXNb1.js";
+import { c as Gd } from "./concat-Dqk7Xk7h.js";
 function zd(a, t, e, n = !1) {
   const s = Xi(a, "logits", "multinomial"), o = s.size, r = s.rank;
   if (o < 2)
@@ -11697,6 +11697,7 @@ class AS extends Ui {
   lastMultinomialRand = null;
   jobQueue = [];
   processingJob = !1;
+  startTime = null;
   async tokenisePrompt(t, e, n) {
     if (e) {
       const s = e.length > 0 && e[e.length - 1].role === "assistant";
@@ -11879,7 +11880,7 @@ class AS extends Ui {
         this.jobQueue.push({ prompt: n, options: e, resolve: s, reject: o });
       });
     }
-    this.processingJob = !0;
+    this.processingJob = !0, this.startTime = Date.now();
     try {
       const s = await this.startJob(n, e);
       if (this.processingJob = !1, this.jobQueue.length > 0) {
@@ -11892,9 +11893,19 @@ class AS extends Ui {
     }
   }
   async startJob(t, e) {
-    this.initialise(t, e), this.active = !0, e?.maxLength !== 1 && this.emit("start");
+    this.initialise(t, e), this.active = !0, this.model.metaData.generationSettings = e, e?.maxLength !== 1 && this.emit("start");
     const s = await this._generate(e);
-    return this.active = !1, this.emit("stop"), s;
+    if (this.active = !1, this.startTime !== null) {
+      const o = Date.now(), r = o - this.startTime;
+      this.startTime = null, this.model.metaData.actionLog = this.model.metaData.actionLog || [], this.model.metaData.actionLog.push({
+        action: "generate",
+        timestamp: o,
+        duration: r,
+        tokensProcessed: this.tokens.length,
+        options: e || {}
+      });
+    }
+    return this.emit("stop"), s;
   }
   getQueueLength() {
     return this.jobQueue.length;

package/dist/{RealDiv-CGwv0liw.js → RealDiv-ioj6Z-ox.js}

@@ -1,10 +1,10 @@
-import { aE as E, ab as T, ah as O, U as V, aW as B, N as F, aM as U, aX as W } from "./index-CUXkjxiT.js";
-import { r as $ } from "./Reshape-BW__R4mZ.js";
-import { a as A, b as k, d as C, c as N, e as R } from "./axis_util-GTVlo58H.js";
-import { t as K, m as _ } from "./shared-3agzAqQ_.js";
-import { c as j } from "./backend_util-GaFarB78.js";
-import { f as y } from "./gpgpu_math-BwvV12df.js";
-import { g as G, b as L } from "./kernel_funcs_utils-pq0CK9co.js";
+import { aE as E, ab as T, ah as O, N as V, aW as B, K as F, aM as K, aX as W } from "./index-DSGwv2Yx.js";
+import { r as $ } from "./Reshape-BZC-ebeR.js";
+import { a as A, b as k, d as C, c as N, e as R } from "./axis_util-QWWgLjut.js";
+import { t as U, m as _ } from "./shared-zTaJ5siv.js";
+import { c as j } from "./backend_util-qwSFfxYx.js";
+import { f as y } from "./gpgpu_math-3bCb5ooU.js";
+import { g as G, b as L } from "./kernel_funcs_utils-DGqzNlHT.js";
 class w {
   constructor(s, e) {
     this.variableNames = ["x"];
@@ -299,7 +299,7 @@ function te(a) {
       const I = e.texData.get(d.dataId).values, m = new Array(i);
       for (let v = 0; v < m.length; v++)
         m[v] = n.shape[u[v]];
-      const z = K(I, n.shape, n.dtype, u, m);
+      const z = U(I, n.shape, n.dtype, u, m);
       d = e.makeTensorInfo(m, n.dtype);
       const D = e.texData.get(d.dataId);
       D.values = z;
@@ -322,7 +322,7 @@ function te(a) {
   return p && e.disposeIntermediateTensorInfo(d), x;
 }
 const he = {
-  kernelName: U,
+  kernelName: K,
   backendName: "webgl",
   kernelFunc: te
 };

package/dist/{Reshape-BW__R4mZ.js → Reshape-BZC-ebeR.js}

@@ -1,6 +1,6 @@
-import { R as C, U as c, aj as R, x as f } from "./index-CUXkjxiT.js";
-import { u as g, g as I, a as x, b as F, c as $, d as u, e as m, i as l } from "./gpgpu_math-BwvV12df.js";
-class S {
+import { R as C, N as c, aj as R, v as f } from "./index-DSGwv2Yx.js";
+import { u as g, g as I, a as x, b as F, c as $, d as u, e as m, i as l } from "./gpgpu_math-3bCb5ooU.js";
+class v {
   constructor(t, i) {
     this.variableNames = ["A"], this.packedInputs = !0, this.packedOutput = !0, this.customUniforms = [{ name: "inputShape", type: "ivec3" }], this.outputShape = t, this.enableShapeUniforms = g(this.outputShape.length);
     let a = "";
@@ -20,7 +20,7 @@ class S {
       `;
     }
     this.userCode = `
-      ${v(i, this.enableShapeUniforms)}
+      ${S(i, this.enableShapeUniforms)}
       ${this.enableShapeUniforms ? I() : x(t)}
 
       void main() {
@@ -39,7 +39,7 @@ class S {
     `;
   }
 }
-function v(s, t) {
+function S(s, t) {
   return `
     ivec3 inputCoordsFromReshapedOutCoords(int index) {
       ${t ? F(["r", "c", "d"], "inputShape") : $(["r", "c", "d"], s)}
@@ -58,7 +58,7 @@ function b(s, t, i) {
   }, o = [
     u(t),
     ...m(t)
-  ], r = new S(o, a), p = !0, n = [a], h = i.runWebGLProgram(r, [e], s.dtype, n, p);
+  ], r = new v(o, a), p = !0, n = [a], h = i.runWebGLProgram(r, [e], s.dtype, n, p);
   return { dataId: h.dataId, shape: t, dtype: h.dtype };
 }
 function y(s) {
@@ -73,7 +73,7 @@ const U = {
   kernelFunc: y
 };
 export {
-  S as R,
+  v as R,
   U as a,
   y as r
 };

package/dist/{Reshape-CPBkTIH2.js → Reshape-pwprEaej.js}

@@ -1,4 +1,4 @@
-import { U as h, aj as d, x as c, R as m } from "./index-CUXkjxiT.js";
+import { N as h, aj as d, v as c, R as m } from "./index-DSGwv2Yx.js";
 function i(n) {
   const { inputs: p, attrs: o } = n, { x: e } = p, { shape: r } = o, a = h(e.shape), s = d(r, a), t = h(s);
   return c(a === t, () => `The new shape (${s}) has ${t} elements and the old shape (${e.shape}) has ${a} elements. The new shape and old shape must have the same number of elements.`), n.backend.incRef(e.dataId), { dataId: e.dataId, shape: s, dtype: e.dtype };

package/dist/TeachableLLM.d.ts

@@ -8,14 +8,8 @@ import { default as MemoryProfiler } from './utilities/profile';
 import { default as Model, ModelForwardAttributes } from './models/model';
 import { Task } from './training/tasks/Task';
 import { TrainingLogEntry, TrainingOptions } from './training/types';
-import { ModelPhase } from './loader/types';
+import { ModelPhase, TransformersMetadata } from './loader/types';
 type TeachableLLMStatus = 'warmup' | 'awaitingTokens' | 'ready' | 'training' | 'loading' | 'busy' | 'error';
-interface TeachableLLMMeta {
-    name?: string;
-    id?: string;
-    reference?: string;
-    [key: string]: unknown;
-}
 export default class TeachableLLM {
     private ee;
     private _config?;
@@ -23,9 +17,10 @@ export default class TeachableLLM {
     private _tokeniser?;
     private _status;
     private _memoryRequirements?;
-    meta: TeachableLLMMeta;
+    meta: TransformersMetadata;
     private _trainer;
     constructor(tokeniser?: ITokeniser, model?: Model<ModelForwardAttributes, GPTConfig>);
+    get currentTrainer(): Trainer | null;
     get vocab(): string[];
     get phase(): ModelPhase;
     set phase(phase: ModelPhase);

package/dist/TeachableLLM.js

@@ -1,28 +1,28 @@
-import { validateConfig as m } from "./models/config.js";
-import { saveModel as d } from "./loader/save.js";
+import { validateConfig as l } from "./models/config.js";
+import { saveModel as p } from "./loader/save.js";
 import { loadModel as u } from "./loader/load.js";
-import p from "./Generator.js";
+import f from "./Generator.js";
 import h from "./Trainer.js";
-import { E as f } from "./index-DvYrXKkX.js";
-import { dummyPassTrainAsync as l } from "./utilities/dummy.js";
-import "./index-CUXkjxiT.js";
-import "./random_width-DN5ZtQkM.js";
-import "./zeros_like-CWjDdwr-.js";
+import { E as c } from "./index-DvYrXKkX.js";
+import { dummyPassTrainAsync as d } from "./utilities/dummy.js";
+import "./index-DSGwv2Yx.js";
+import "./random_width-B_fVXhGx.js";
+import "./zeros_like-rOHr54NY.js";
 import "./index-Cp39cXWe.js";
-import "./dataset-CGGp1z9P.js";
+import "./dataset-DlqAN81i.js";
 import "./ops/cpu/attentionMask.js";
 import "./ops/webgl/attentionMask.js";
 import "./ops/grads/attentionMask.js";
 import "./ops/cpu/rope.js";
 import "./ops/webgl/rope.js";
-import "./rope-0j_f1TPm.js";
+import "./rope-CC5RjmKU.js";
 import "./ops/cpu/appendCache.js";
 import "./ops/webgl/appendCache.js";
 import "./ops/grads/softmax16.js";
-import "./matMul16-BcVC_E62.js";
+import "./matMul16-BIT70Vya.js";
 import "./ops/webgl/matMul16.js";
 import "./ops/cpu/matMul16.js";
-import "./pack16-bqltoUlR.js";
+import "./pack16-WlOSOuZA.js";
 import "./ops/transpose16.js";
 import "./ops/reshape16.js";
 import "./ops/cpu/qkv.js";
@@ -34,8 +34,8 @@ import "./ops/grads/normRMS.js";
 import "./ops/dropout16.js";
 import "./ops/webgl/dropout16.js";
 import "./ops/grads/add16.js";
-import c from "./tokeniser/CharTokeniser.js";
-import g from "./tokeniser/bpe.js";
+import g from "./tokeniser/CharTokeniser.js";
+import w from "./tokeniser/bpe.js";
 import "./papaparse.min-C0cScC2i.js";
 import "./jszip.min-BZhlzntC.js";
 import "./ops/cpu/gatherSub.js";
@@ -43,11 +43,11 @@ import "./ops/webgl/gatherSub.js";
 import "./ops/cpu/scatterSub.js";
 import "./ops/webgl/scatterSub.js";
 import "./ops/cpu/matMulGelu.js";
-import "./matMulGelu-JNLZqKQp.js";
+import "./matMulGelu-CsZnh18H.js";
 import "./ops/grads/matMulGelu.js";
 import "./ops/cpu/gelu.js";
 import "./ops/webgl/gelu.js";
-import "./gelu-B220X1Go.js";
+import "./gelu-DpTCC3eB.js";
 import "./ops/webgl/log.js";
 import "./ops/cpu/adamMoments.js";
 import "./ops/webgl/adamMoments.js";
@@ -55,19 +55,25 @@ import "./ops/cpu/adamAdjust.js";
 import "./ops/webgl/adamAdjust.js";
 import "./checks/normRMS.js";
 import "./checks/normRMSGrad.js";
-import w from "./utilities/profile.js";
-import k from "./models/factory.js";
-class a {
-  ee = new f();
+import k from "./utilities/profile.js";
+import y from "./models/factory.js";
+class _ {
+  ee = new c();
   _config;
   _model;
   _tokeniser;
   _status = "loading";
   _memoryRequirements;
-  meta = {};
+  meta = {
+    version: 2,
+    application: "@genai-fi/nanogpt"
+  };
   _trainer = null;
   constructor(t, i) {
-    this._config = i?.config, this._tokeniser = t, this._model = i;
+    this._config = i?.config, this._tokeniser = t, this._model = i, i?.metaData && (this.meta = i.metaData);
+  }
+  get currentTrainer() {
+    return this._trainer;
   }
   get vocab() {
     return this._tokeniser?.getVocab() || [];
@@ -154,32 +160,43 @@ class a {
   saveModel(t) {
     if (!this._model || !this._tokeniser)
       throw new Error("model_or_tokeniser_not_initialized.");
-    return d(this._model, this._tokeniser, {
-      ...t,
-      name: t?.name || this.meta.name
-    });
+    return p(
+      this._model,
+      this._tokeniser,
+      {
+        ...t,
+        name: t?.name || this.meta.name
+      },
+      t?.includeOptimizer && this._trainer?.trainingType === "pretraining" ? { optimizer: this._trainer.optimizer, trainingLog: this._trainer.log } : void 0
+    );
   }
   static loadModel(t, i) {
-    const e = new a();
-    return u(t, i).then(({ model: o, tokeniser: n, metaData: r }) => {
-      m(o.config), e._model = o, e._tokeniser = n, e._config = o.config, r?.name && (e.meta.name = r.name), e.setStatus("warmup"), l(o).then((s) => {
-        e._memoryRequirements = s, e.setStatus("ready"), e.ee.emit("loaded"), e.ee.emit("phase", e.phase);
-      }).catch((s) => {
-        e.setStatus("error"), e.ee.emit("error", s), console.error("Error during warmup:", s);
+    const e = new _();
+    return u(t, i).then(({ model: o, tokeniser: s, metaData: r, optimizer: n, log: a }) => {
+      l(o.config), e._model = o, e._tokeniser = s, e._config = o.config, r && (e.meta = r), e.setStatus("warmup"), d(o).then((m) => {
+        e._memoryRequirements = m, n && (e._trainer = new h(
+          o,
+          s,
+          "pretraining",
+          o.metaData.pretrainingSettings,
+          n
+        ), a && (e._trainer.log = a)), e.setStatus("ready"), e.ee.emit("loaded"), e.ee.emit("phase", e.phase);
+      }).catch((m) => {
+        e.setStatus("error"), e.ee.emit("error", m), console.error("Error during warmup:", m);
       });
     }).catch((o) => {
       e.setStatus("error"), e.ee.emit("error", o), console.error("Error loading model:", o);
     }), e;
   }
   static create(t, i) {
-    m(i);
-    const e = i, o = t === "char" ? new c(e.vocabSize) : new g(e.vocabSize), n = k(e), r = new a(o, n);
-    return r.setStatus("warmup"), l(n).then((s) => {
-      r._memoryRequirements = s, r.tokeniser.trained ? (r.setStatus("ready"), r.ee.emit("loaded"), r.ee.emit("phase", r.phase)) : (r.setStatus("awaitingTokens"), r.ee.emit("loaded"), r.ee.emit("phase", r.phase), r.tokeniser.once("trainStatus", (_) => {
-        _ === "trained" && r.setStatus("ready");
+    l(i);
+    const e = i, o = t === "char" ? new g(e.vocabSize) : new w(e.vocabSize), s = y(e), r = new _(o, s);
+    return r.setStatus("warmup"), d(s).then((n) => {
+      r._memoryRequirements = n, r.tokeniser.trained ? (r.setStatus("ready"), r.ee.emit("loaded"), r.ee.emit("phase", r.phase)) : (r.setStatus("awaitingTokens"), r.ee.emit("loaded"), r.ee.emit("phase", r.phase), r.tokeniser.once("trainStatus", (a) => {
+        a === "trained" && r.setStatus("ready");
       }));
-    }).catch((s) => {
-      r.setStatus("error"), r.ee.emit("error", s), console.error("Error during warmup:", s);
+    }).catch((n) => {
+      r.setStatus("error"), r.ee.emit("error", n), console.error("Error during warmup:", n);
     }), r;
   }
   getProfiler() {
@@ -192,7 +209,7 @@ class a {
     if (t) {
       if (!this._config)
         return;
-      this.model.getProfiler() || this.model.setProfiler(new w());
+      this.model.getProfiler() || this.model.setProfiler(new k());
     } else
       this.model.getProfiler() && this.model.setProfiler(null);
   }
@@ -207,8 +224,8 @@ class a {
     return e.on("start", () => {
       this.setStatus("training"), this.phase = t === "sft" ? "finetuned" : "pretrained";
     }), e.on("stop", () => this.setStatus("ready")), e.on("log", async (o) => {
-      const n = this.ee.listeners("trainStep");
-      for (const r of n)
+      const s = this.ee.listeners("trainStep");
+      for (const r of s)
         await r(o);
     }), this._trainer && this._trainer !== e && this._trainer.removeAllListeners(), this._trainer = e, e;
   }
@@ -225,7 +242,7 @@ class a {
   generator() {
     if (!this._model || !this._tokeniser)
       throw new Error("model_or_tokeniser_not_initialized.");
-    const t = new p(this._model, this._tokeniser);
+    const t = new f(this._model, this._tokeniser);
     return t.on("start", () => {
       this.status === "ready" && this.setStatus("busy");
     }), t.on("stop", () => {
@@ -252,5 +269,5 @@ class a {
   }
 }
 export {
-  a as default
+  _ as default
 };

package/dist/Trainer.d.ts

@@ -4,6 +4,7 @@ import { default as Model, ModelForwardAttributes } from './models/model';
 import { Task } from './training/tasks/Task';
 import { TrainingOptions, TrainingLogEntry } from './training/types';
 import { AdamWOptimizer } from './training/AdamW';
+import { DatasetMetadata } from './loader/types';
 interface TrainingProgress {
     lastLog: TrainingLogEntry;
     progress: number;
@@ -16,21 +17,22 @@ export default class Trainer extends EE<'start' | 'stop' | 'log'> {
     private hasTrained;
     private trainDataset?;
     private validationDataset?;
-    private totalSamples;
+    private totalTokens;
+    private tokensProcessed;
     log: TrainingLogEntry[];
     private progress;
     options: TrainingOptions;
     protected tokenizer: ITokeniser;
-    constructor(model: Model<ModelForwardAttributes>, tokeniser: ITokeniser, trainingType?: TrainingType, options?: TrainingOptions);
+    constructor(model: Model<ModelForwardAttributes>, tokeniser: ITokeniser, trainingType?: TrainingType, options?: TrainingOptions, optimizer?: AdamWOptimizer);
     constructor(trainer: Trainer, options?: TrainingOptions);
     get model(): Model<ModelForwardAttributes>;
     get optimizer(): AdamWOptimizer;
     stop(): void;
     reset(): void;
     dispose(): void;
-    getTotalSamples(): number;
+    getTotalTokens(): number;
     setOptions(options: TrainingOptions): void;
-    prepare(tasks?: Task[] | Uint16Array): Promise<void>;
+    prepare(tasks?: Task[] | Uint16Array, datasets?: DatasetMetadata[]): Promise<void>;
     private configureModel;
     train(): Promise<void>;
     step(options?: TrainingOptions): Promise<void>;