@genai-fi/nanogpt 0.15.1 → 0.15.3

package/dist/Generator.js

@@ -1,49 +1,51 @@
 import { E as Ui } from "./index-DvYrXKkX.js";
-import { o as Hi, q as Xi, E as Ki, dn as Ss, a6 as pe, ac as _, as as oo, at as ao, e as Oe, a_ as Dt, ay as ro, az as io, au as ji, av as Ft, aD as Ge, af as co, aG as ws, aH as qi, U as G, ag as _e, aI as Yi, H as Ns, aJ as Rs, R as Qi, aj as Zi, x as te, D as lo, _ as Ne, aa as ee, bd as uo, c9 as Ts, ca as Es, cQ as po, bo as ho, ah as ue, Q as Ye, bp as fo, bq as mo, cb as go, cc as Ds, cd as Fs, ce as Ps, cf as Os, cg as As, br as xo, ad as nt, cA as Co, cR as bo, cS as Io, bu as yo, bt as ko, bf as $o, dg as vo, C as _s, cU as So, ao as wo, z as No, bv as Ro, c4 as $e, cF as To, bw as Eo, cB as Do, cV as Fo, cC as Po, bx as Ls, by as Vs, bh as Oo, bz as Ao, am as Qe, V as Ji, bA as _o, cD as Lo, ch as Vo, bB as Wo, cH as Mo, cI as Bo, dh as Go, ci as zo, bZ as ns, bT as St, bW as Ws, cW as yn, dv as ut, dw as Uo, cX as kn, di as ec, N as tc, bg as Ho, cY as Xo, bD as Ms, A as Ko, aX as jo, aV as mt, cr as qo, de as Yo, df as Qo, bi as Zo, cG as Jo, dk as ea, al as ta, G as sa, cs as na, cj as Bs, ck as Gs, cl as zs, dl as oa, b5 as Us, b6 as Hs, bF as Xs, cn as Ks, cm as aa, c_ as ra, aM as sc, bG as ia, cE as ca, c$ as la, d0 as ua, dm as da, aP as pa, a$ as ha, co as fa, bS as ma, M as js, I as ga, bk as xa, bm as Ca, bl as ba, bH as Ia, d5 as ya, bI as ka, P as $a, a8 as va, bJ as Sa, d1 as qs, dx as wa, dy as Na, dz as Ra, Z as Ta, cp as Ys, bb as Ea, d2 as Da, bc as Fa, d3 as Pa, bL as Oa, bj as Aa, b8 as Qs, ak as _a, dp as La, aL as Va, bN as Zs, cq as Js, bO as en, bP as tn, bE as sn, bK as Wa, dA as Ma, dB as Ba, dq as Ga, dr as za, ds as Ua, J as Ha, d4 as Xa, aK as nn, ct as Ka, dt as ja, dC as qa, dD as Ya, cu as on, bs as an, du as Qa, T as Za, cv as Ja, bn as er, a7 as rn, cw as tr, ba as sr, bQ as nr, c as or, dE as ar, dF as $n, aw as vn, ax as nc, t as rr, a as oc, dG as ac, dH as rc, c2 as ic, ar as cc, bR as lc, bX as uc, S as dc, bY as pc, aQ as hc, aq as fc, bU as mc, bV as gc, b_ as xc, aS as ir, bC as Cc, aN as bc, b$ as Ic, F as yc, c0 as kc, dj as $c, b1 as vc, b2 as Sc, b3 as wc, b4 as Nc, aO as Rc, c1 as Tc, b7 as Ec, c7 as Dc, ap as Fc, c3 as Pc, aW as cr, bM as Oc, aF as Ac, c5 as _c, b9 as Lc, c6 as Vc, k as Wc } from "./index-uoQNhva6.js";
-import { n as Mc } from "./random_width-WzwiRvPZ.js";
-import { t as Bc } from "./zeros_like-9qjyI2vq.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, 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, U as G, af as _e, aI as Yi, H as Ns, aJ as Rs, R as Qi, aj as Zi, 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 Ji, 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 Zo, cE as Jo, 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 Zs, co as Js, 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 Za, ct as Ja, 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-BU-PZJ0l.js";
+import { n as Mc } from "./random_width-DvNaD5W3.js";
+import { t as Bc } from "./zeros_like-CGnKYJEe.js";
 import "./index-Cp39cXWe.js";
-import "./dataset-DPU3hN0T.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 Zc, A as Jc, 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-dHG6fzNB.js";
+import "./dataset-CtujTjY_.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 Zc, A as Jc, 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-DORJR6eU.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-TthehkGs.js";
-import { k as Ze, h as Le, i as Je, j as rt, b as Se, d as xt, g as as } from "./step-CzAily5b.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, N as Tr, c as Er, f as Yl, O as Ql, P as Zl } from "./backend_util--hCDOKBW.js";
-import { a as Dr, c as Ue } from "./concat_util-DW7FiHui.js";
+import { a as ge, b as xe, d as ke, c as ve, e as Te, g as os } from "./axis_util-BTeTGnZF.js";
+import { k as Ze, h as Le, i as Je, j as rt, b as Se, d as xt, g as as } from "./step-A_sBP7En.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-DGV1tIji.js";
+import { a as Er, c as Ue } from "./concat_util-Bk6ay4Ob.js";
+import { c as Dr, a as Ql, s as Zl } from "./segment_util-CXELxApp.js";
 import { s as Jl } 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-BlJWgCmU.js";
-import { S as Ar, a as _r } from "./selu_util-DAcisF1E.js";
-import { b as Lr, d as Vr, p as eu, a as tu, i as su, c as nu } from "./slice_util-4i3k5EwD.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 Pt, w as pu, x as wn, y as hu, z as fu, 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-xeTvCd6P.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 Zu, z as Ju, 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-Io-D1asH.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-D1Nso99H.js";
-import { R as Nd, r as U, a as Rd } from "./Reshape-rTOwpsUF.js";
-import { M as qr } from "./matMulGelu-De0BMbE7.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-BVigXOzk.js";
-import { z as Od } from "./zeros-if5itJPI.js";
+import { c as Ct } from "./scatter_nd_util-DJ8GpL1I.js";
+import { S as Ar, a as _r } from "./selu_util-CPAAI9PC.js";
+import { s as Lr, b as Vr, p as eu, a as tu, i as su, c as nu } from "./slice_util-DDbd6eyd.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-C0Hfh1As.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 Zu, z as Ju, 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-DVZEsT-0.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-BNsajF26.js";
+import { R as Nd, r as U, a as Rd } from "./Reshape-CZVlscuS.js";
+import { M as qr } from "./matMulGelu-BM8qerU0.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-Blil1IAl.js";
+import { z as Od } from "./zeros-CkHJh2fz.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-Cks0wXgt.js";
+import "./rope-DaRtCQFa.js";
 import "./ops/cpu/appendCache.js";
 import "./ops/webgl/appendCache.js";
 import "./ops/grads/softmax16.js";
-import "./matMul16-C9Aeua4l.js";
+import "./matMul16-qjE_mKX8.js";
 import "./ops/webgl/matMul16.js";
 import "./ops/cpu/matMul16.js";
-import "./pack16-EZQxclg7.js";
+import "./pack16-CQUYvE0Y.js";
 import "./ops/transpose16.js";
 import "./ops/reshape16.js";
 import "./ops/cpu/qkv.js";
 import "./ops/webgl/qkv.js";
 import "./ops/grads/qkv.js";
-import "./ops/mul16.js";
 import "./ops/cpu/normRMS.js";
 import "./ops/webgl/normRMS.js";
 import "./ops/grads/normRMS.js";
+import "./ops/dropout16.js";
+import "./ops/webgl/dropout16.js";
 import "./ops/grads/add16.js";
 import "./jszip.min-Bz5-11Bk.js";
 import Ad from "./tokeniser/CharTokeniser.js";
@@ -63,17 +65,17 @@ import "./ops/cpu/matMulGelu.js";
 import "./ops/grads/matMulGelu.js";
 import "./ops/cpu/gelu.js";
 import "./ops/webgl/gelu.js";
-import "./gelu-CX4aUwca.js";
+import "./gelu-Bq6zXPEw.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-pwjcwOms.js";
-import { t as Kt } from "./tensor2d-B-WkUbVR.js";
-import { z as Md } from "./unsorted_segment_sum-CxaDDiSg.js";
-import { s as gs } from "./softmax-BYwgW-oF.js";
-import { g as Bd } from "./gather-DzuXM3Xs.js";
-import { c as Gd } from "./concat-bX2wJt_F.js";
+import { r as Dn } from "./reshape-Dxch7IXb.js";
+import { t as Kt } from "./tensor2d-BieJDjvb.js";
+import { z as Md } from "./unsorted_segment_sum-Cx23B-vz.js";
+import { s as gs } from "./softmax-CRzm-wNL.js";
+import { g as Bd } from "./gather-DvRBFTfQ.js";
+import { c as Gd } from "./concat-ByAvdM_j.js";
 function zd(a, t, e, n = !1) {
   const s = Xi(a, "logits", "multinomial"), o = s.size, r = s.rank;
   if (o < 2)
@@ -846,7 +848,7 @@ const jp = {
 };
 function ft(a) {
   const { inputs: t, backend: e, attrs: n } = a, { axis: s } = n, o = ue(s, t[0].shape)[0], r = t.map((m) => m.shape);
-  Dr(r, o);
+  Er(r, o);
   let c = Ue(t.map((m) => m.shape), o);
   if (G(c) === 0)
     return e.makeTensorInfo(c, t[0].dtype, []);
@@ -1856,7 +1858,7 @@ function lf(a) {
   }
   let p = c;
   c == null && (p = 0);
-  const d = G(o.shape), h = Nr(s, o, i, p), f = ce({
+  const d = G(o.shape), h = Dr(s, o, i, p), f = ce({
     inputs: { x: s },
     backend: e,
     attrs: {
@@ -2590,7 +2592,7 @@ const Gm = {
   kernelName: Aa,
   backendName: "cpu",
   kernelFunc: ({ inputs: a, attrs: t, backend: e }) => {
-    const { image: n } = a, { radians: s, fillValue: o, center: r } = t, c = e, i = _e(n.dtype, G(n.shape)), [l, u, p, d] = n.shape, [h, f] = Rr(r, u, p), m = 255, x = Math.sin(s), g = Math.cos(s), C = c.data.get(n.dataId).values;
+    const { image: n } = a, { radians: s, fillValue: o, center: r } = t, c = e, i = _e(n.dtype, G(n.shape)), [l, u, p, d] = n.shape, [h, f] = Nr(r, u, p), m = 255, x = Math.sin(s), g = Math.cos(s), C = c.data.get(n.dataId).values;
     for (let b = 0; b < l; b++) {
       const y = b * p * u * d;
       for (let k = 0; k < u; k++) {
@@ -2849,7 +2851,7 @@ const vg = {
   kernelFunc: $g
 };
 function Sg(a) {
-  const { inputs: t, backend: e, attrs: n } = a, { x: s } = t, { numOrSizeSplits: o, axis: r } = n, c = ue(r, s.shape)[0], i = Tr(s, o, c), l = new Array(s.shape.length).fill(0), u = s.shape.slice();
+  const { inputs: t, backend: e, attrs: n } = a, { x: s } = t, { numOrSizeSplits: o, axis: r } = n, c = ue(r, s.shape)[0], i = Rr(s, o, c), l = new Array(s.shape.length).fill(0), u = s.shape.slice();
   return i.map((p) => {
     const d = [...u];
     d[c] = p;
@@ -5055,7 +5057,7 @@ class fC {
 function Ii(a, t, e, n = null) {
   let s = t.shape[0], o = t.shape[1];
   n != null && (s = n.shape[0], o = n.shape[1]);
-  const r = Er(o), c = { windowSize: r, inSize: o, batchSize: s, outSize: Math.ceil(o / r) }, i = new hC(c, e, n == null), l = [t];
+  const r = Tr(o), c = { windowSize: r, inSize: o, batchSize: s, outSize: Math.ceil(o / r) }, i = new hC(c, e, n == null), l = [t];
   n != null && l.push(n);
   const u = a.runWebGLProgram(i, l, "int32");
   if (u.shape[1] === 1)
@@ -5064,7 +5066,7 @@ function Ii(a, t, e, n = null) {
   return a.disposeIntermediateTensorInfo(u), p;
 }
 function yi(a, t, e, n = null) {
-  const s = n != null ? n.shape : t.shape, o = s[s.length - 1], r = Er(o), c = new fC(s, r, e, n == null), i = n == null ? [t] : [t, n], l = a.runWebGLProgram(c, i, "int32");
+  const s = n != null ? n.shape : t.shape, o = s[s.length - 1], r = Tr(o), c = new fC(s, r, e, n == null), i = n == null ? [t] : [t, n], l = a.runWebGLProgram(c, i, "int32");
   if (l.shape.length === t.shape.length) {
     const u = yi(a, t, e, l);
     return a.disposeIntermediateTensorInfo(l), u;
@@ -6178,7 +6180,7 @@ function Eb(a, t, e) {
 }
 function vi(a) {
   const { inputs: t, backend: e, attrs: n } = a, { axis: s } = n, o = ue(s, t[0].shape)[0], r = t.map((l) => l.shape);
-  Dr(r, o);
+  Er(r, o);
   const c = Ue(t.map((l) => l.shape), o);
   if (G(c) === 0)
     return e.makeTensorInfo(c, t[0].dtype, []);
@@ -8581,7 +8583,7 @@ function Oi(a) {
       te(y <= I - 1 && y >= 0, () => `GatherV2: the index value ${y} is not in [0, ${I - 1}]`);
     }
   }
-  const l = Nr(s, o, i, c), u = G(o.shape), p = [], d = U({
+  const l = Dr(s, o, i, c), u = G(o.shape), p = [], d = U({
     inputs: { x: s },
     backend: e,
     attrs: {
@@ -10356,7 +10358,7 @@ const Ik = {
   kernelName: Aa,
   backendName: "webgl",
   kernelFunc: ({ inputs: a, attrs: t, backend: e }) => {
-    const { image: n } = a, { radians: s, fillValue: o, center: r } = t, c = e, i = new bk(n.shape, o), [l, u] = Rr(r, n.shape[1], n.shape[2]), p = [[l, u, Math.sin(s), Math.cos(s)]];
+    const { image: n } = a, { radians: s, fillValue: o, center: r } = t, c = e, i = new bk(n.shape, o), [l, u] = Nr(r, n.shape[1], n.shape[2]), p = [[l, u, Math.sin(s), Math.cos(s)]];
     return c.runWebGLProgram(i, [n], n.dtype, p);
   }
 };
@@ -10771,7 +10773,7 @@ const h$ = {
   kernelFunc: p$
 };
 function f$(a) {
-  const { inputs: t, backend: e, attrs: n } = a, { x: s } = t, { numOrSizeSplits: o, axis: r } = n, c = ue(r, s.shape)[0], i = Tr(s, o, c), l = s.shape.length, u = new Array(l).fill(0), p = s.shape.slice();
+  const { inputs: t, backend: e, attrs: n } = a, { x: s } = t, { numOrSizeSplits: o, axis: r } = n, c = ue(r, s.shape)[0], i = Rr(s, o, c), l = s.shape.length, u = new Array(l).fill(0), p = s.shape.slice();
   return i.map((d) => {
     const h = [...p];
     h[c] = d;
@@ -11677,7 +11679,7 @@ const lv = [
 function uv(a, t) {
   return a.length === t ? a : a.length > t ? a.slice(0, t) : a.concat(Array(t - a.length).fill(""));
 }
-class PS extends Ui {
+class AS extends Ui {
   constructor(t, e) {
     super(), this.model = t, this.tokeniser = e, this.actualTokeniser = e;
   }
@@ -11873,6 +11875,6 @@ class PS extends Ui {
   }
 }
 export {
-  PS as default,
+  AS as default,
   cv as isConversation
 };

package/dist/{RealDiv-BVigXOzk.js → RealDiv-Blil1IAl.js}

@@ -1,10 +1,10 @@
-import { aE as E, ac as T, ah as O, U as V, aW as B, N as F, aM as U, aX as W } from "./index-uoQNhva6.js";
-import { r as $ } from "./Reshape-rTOwpsUF.js";
-import { a as A, b as k, d as C, c as N, e as R } from "./axis_util-TthehkGs.js";
-import { t as K, m as _ } from "./shared-Io-D1asH.js";
-import { c as j } from "./backend_util--hCDOKBW.js";
-import { f as y } from "./gpgpu_math-xeTvCd6P.js";
-import { g as G, b as L } from "./kernel_funcs_utils-D1Nso99H.js";
+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-BU-PZJ0l.js";
+import { r as $ } from "./Reshape-CZVlscuS.js";
+import { a as A, b as k, d as C, c as N, e as R } from "./axis_util-BTeTGnZF.js";
+import { t as K, m as _ } from "./shared-DVZEsT-0.js";
+import { c as j } from "./backend_util-DGV1tIji.js";
+import { f as y } from "./gpgpu_math-C0Hfh1As.js";
+import { g as G, b as L } from "./kernel_funcs_utils-BNsajF26.js";
 class w {
   constructor(s, e) {
     this.variableNames = ["x"];
@@ -273,7 +273,7 @@ function Q(a, s, e, t) {
   const [p, h] = N(u.shape, i);
   let d = p;
   e && (d = R(p, r));
-  const f = V(h), g = V(a.shape) / f, x = $({ inputs: { x: u }, attrs: { shape: [g, f] }, backend: t }), b = B(a.dtype), I = M(x, b, "sum", t), m = $({ inputs: { x: I }, attrs: { shape: d }, backend: t });
+  const f = V(h), g = V(a.shape) / f, x = $({ inputs: { x: u }, attrs: { shape: [g, f] }, backend: t }), S = B(a.dtype), I = M(x, S, "sum", t), m = $({ inputs: { x: I }, attrs: { shape: d }, backend: t });
   return t.disposeIntermediateTensorInfo(x), t.disposeIntermediateTensorInfo(I), o && t.disposeIntermediateTensorInfo(u), m;
 }
 function Z(a) {
@@ -308,17 +308,17 @@ function te(a) {
     o = k(o.length, i);
   }
   C("max", o, i);
-  const [f, S] = N(d.shape, o);
+  const [f, b] = N(d.shape, o);
   let g = f;
   r && (g = R(f, c));
   let x;
   if (h) {
-    const I = e.texData.get(d.dataId).values, m = _(I, V(S), g, n.dtype);
+    const I = e.texData.get(d.dataId).values, m = _(I, V(b), g, n.dtype);
     x = e.makeTensorInfo(g, n.dtype);
     const z = e.texData.get(x.dataId);
     z.values = m;
   } else
-    x = ee(d, S, g, e);
+    x = ee(d, b, g, e);
   return p && e.disposeIntermediateTensorInfo(d), x;
 }
 const he = {

package/dist/{Reshape-rTOwpsUF.js → Reshape-CZVlscuS.js}

@@ -1,5 +1,5 @@
-import { R as C, U as c, aj as R, x as f } from "./index-uoQNhva6.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-xeTvCd6P.js";
+import { R as C, U as c, aj as R, x as f } from "./index-BU-PZJ0l.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-C0Hfh1As.js";
 class S {
   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);

package/dist/{Reshape-Bt5FRw1J.js → Reshape-rNDnWBJS.js}

@@ -1,4 +1,4 @@
-import { U as h, aj as d, x as c, R as m } from "./index-uoQNhva6.js";
+import { U as h, aj as d, x as c, R as m } from "./index-BU-PZJ0l.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

@@ -8,6 +8,7 @@ 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';
 type TeachableLLMStatus = 'warmup' | 'awaitingTokens' | 'ready' | 'training' | 'loading' | 'busy' | 'error';
 interface TeachableLLMMeta {
     name?: string;
@@ -26,6 +27,8 @@ export default class TeachableLLM {
     private _trainer;
     constructor(tokeniser?: ITokeniser, model?: Model<ModelForwardAttributes, GPTConfig>);
     get vocab(): string[];
+    get phase(): ModelPhase;
+    set phase(phase: ModelPhase);
     /** Model is fully loaded */
     get loaded(): boolean;
     get config(): GPTConfig;
@@ -52,10 +55,12 @@ export default class TeachableLLM {
     generateText(options?: IGenerateOptions): Promise<Conversation[]>;
     dispose(): void;
     on(event: 'status', listener: (status: TeachableLLMStatus) => void): void;
+    on(event: 'phase', listener: (phase: ModelPhase) => void): void;
     on(event: 'error', listener: (error: Error) => void): void;
     on(event: 'trainStep', listener: (step: TrainingLogEntry) => void): void;
     on(event: 'loaded', listener: () => void): void;
     off(event: 'status', listener: (status: TeachableLLMStatus) => void): void;
+    off(event: 'phase', listener: (phase: ModelPhase) => void): void;
     off(event: 'error', listener: (error: Error) => void): void;
     off(event: 'trainStep', listener: (step: TrainingLogEntry) => void): void;
     off(event: 'loaded', listener: () => void): void;

package/dist/TeachableLLM.js

@@ -1,37 +1,38 @@
 import { validateConfig as m } from "./models/config.js";
 import { saveModel as d } from "./loader/save.js";
-import { loadModel as u } from "./loader/load.js";
-import p from "./Generator.js";
+import { loadModel as p } from "./loader/load.js";
+import u 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-uoQNhva6.js";
-import "./random_width-WzwiRvPZ.js";
-import "./zeros_like-9qjyI2vq.js";
+import "./index-BU-PZJ0l.js";
+import "./random_width-DvNaD5W3.js";
+import "./zeros_like-CGnKYJEe.js";
 import "./index-Cp39cXWe.js";
-import "./dataset-DPU3hN0T.js";
+import "./dataset-CtujTjY_.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-Cks0wXgt.js";
+import "./rope-DaRtCQFa.js";
 import "./ops/cpu/appendCache.js";
 import "./ops/webgl/appendCache.js";
 import "./ops/grads/softmax16.js";
-import "./matMul16-C9Aeua4l.js";
+import "./matMul16-qjE_mKX8.js";
 import "./ops/webgl/matMul16.js";
 import "./ops/cpu/matMul16.js";
-import "./pack16-EZQxclg7.js";
+import "./pack16-CQUYvE0Y.js";
 import "./ops/transpose16.js";
 import "./ops/reshape16.js";
 import "./ops/cpu/qkv.js";
 import "./ops/webgl/qkv.js";
 import "./ops/grads/qkv.js";
-import "./ops/mul16.js";
 import "./ops/cpu/normRMS.js";
 import "./ops/webgl/normRMS.js";
 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";
@@ -42,11 +43,11 @@ import "./ops/webgl/gatherSub.js";
 import "./ops/cpu/scatterSub.js";
 import "./ops/webgl/scatterSub.js";
 import "./ops/cpu/matMulGelu.js";
-import "./matMulGelu-De0BMbE7.js";
+import "./matMulGelu-BM8qerU0.js";
 import "./ops/grads/matMulGelu.js";
 import "./ops/cpu/gelu.js";
 import "./ops/webgl/gelu.js";
-import "./gelu-CX4aUwca.js";
+import "./gelu-Bq6zXPEw.js";
 import "./ops/webgl/log.js";
 import "./ops/cpu/adamMoments.js";
 import "./ops/webgl/adamMoments.js";
@@ -71,6 +72,14 @@ class a {
   get vocab() {
     return this._tokeniser?.getVocab() || [];
   }
+  get phase() {
+    return this._model?.metaData?.phase ?? "untrained";
+  }
+  set phase(t) {
+    if (!this._model)
+      throw new Error("model_not_initialized.");
+    this._model.metaData.phase = t, this.ee.emit("phase", t);
+  }
   /** Model is fully loaded */
   get loaded() {
     return !!this._model && !!this._tokeniser && !!this._config;
@@ -117,9 +126,9 @@ class a {
   }
   static loadModel(t, r) {
     const e = new a();
-    return u(t, r).then(({ model: o, tokeniser: n, metaData: i }) => {
+    return p(t, r).then(({ model: o, tokeniser: n, metaData: i }) => {
       m(o.config), e._model = o, e._tokeniser = n, e._config = o.config, i?.name && (e.meta.name = i.name), e.setStatus("warmup"), l(o).then((s) => {
-        e._memoryRequirements = s, e.setStatus("ready"), e.ee.emit("loaded");
+        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);
       });
@@ -131,7 +140,7 @@ class a {
     m(r);
     const e = r, o = t === "char" ? new c(e.vocabSize) : new g(e.vocabSize), n = k(e), i = new a(o, n);
     return i.setStatus("warmup"), l(n).then((s) => {
-      i._memoryRequirements = s, i.tokeniser.trained ? (i.setStatus("ready"), i.ee.emit("loaded")) : (i.setStatus("awaitingTokens"), i.ee.emit("loaded"), i.tokeniser.once("trainStatus", (_) => {
+      i._memoryRequirements = s, i.tokeniser.trained ? (i.setStatus("ready"), i.ee.emit("loaded"), i.ee.emit("phase", i.phase)) : (i.setStatus("awaitingTokens"), i.ee.emit("loaded"), i.ee.emit("phase", i.phase), i.tokeniser.once("trainStatus", (_) => {
         _ === "trained" && i.setStatus("ready");
       }));
     }).catch((s) => {
@@ -160,11 +169,13 @@ class a {
       throw new Error("model_or_tokeniser_not_initialized.");
     this._trainer && t && this._trainer.trainingType !== t && (this._trainer.dispose(), this._trainer = null);
     const e = this._trainer === null ? new h(this._model, this._tokeniser, t, r) : new h(this._trainer, r);
-    return e.on("start", () => this.setStatus("training")), e.on("stop", () => this.setStatus("ready")), e.on("log", async (o) => {
+    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 i of n)
         await i(o);
-    }), this._trainer && this._trainer !== e && this._trainer.dispose(), this._trainer = e, e;
+    }), this._trainer && this._trainer !== e && this._trainer.removeAllListeners(), this._trainer = e, e;
   }
   async train(t, r, e) {
     const o = this.trainer(e, r);
@@ -179,7 +190,7 @@ 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 u(this._model, this._tokeniser);
     return t.on("start", () => {
       this.status === "ready" && this.setStatus("busy");
     }), t.on("stop", () => {

package/dist/{axis_util-TthehkGs.js → axis_util-BTeTGnZF.js}

@@ -1,4 +1,4 @@
-import { x as c } from "./index-uoQNhva6.js";
+import { x as c } from "./index-BU-PZJ0l.js";
 function i(e, n) {
   for (let t = 0; t < e.length; ++t)
     if (e[e.length - t - 1] !== n - 1 - t)

package/dist/backend.js

@@ -1,9 +1,9 @@
-import { g as o, s as e, r as s } from "./index-uoQNhva6.js";
+import { g as o, s as e, r as s } from "./index-BU-PZJ0l.js";
 async function c(t, a) {
   if (o() !== t) {
     if (t === "webgpu") {
       const { registerWebGPUBackend: i } = await import("./patches/webgpu_base.js");
-      i(a), await import("./index-BF0-PdRD.js"), await import("./ops/webgpu/index.js");
+      i(a), await import("./index-BSjeovee.js"), await import("./ops/webgpu/index.js");
     }
     await e(t), await s(), console.log(`Backend set to ${t}`);
   }