@genai-fi/nanogpt 0.6.1 → 0.6.3

package/dist/Generator.js

@@ -1,15 +1,15 @@
 import { E as u } from "./index-Dwqa6Zy2.js";
-import "./index-CamYe_M8.js";
+import "./index-BAzbokzv.js";
 import "./ops/cpu/attentionMask.js";
 import "./ops/webgl/attentionMask.js";
 import "./ops/grads/attentionMask.js";
 import "./ops/cpu/qkv.js";
 import "./ops/webgl/qkv.js";
 import "./ops/grads/qkv.js";
-import "./random_width-CLMQG5Jn.js";
-import "./register_all_kernels-COt6wLD0.js";
+import "./random_width-DWzaOgrn.js";
+import "./register_all_kernels-BfFCQAqs.js";
 import "./index-Tf7vU29b.js";
-import "./dataset-BFFipD1c.js";
+import "./dataset-pgqp-YfL.js";
 import "./ops/cpu/rope.js";
 import "./ops/webgl/rope.js";
 import "./ops/grads/rope.js";
@@ -35,8 +35,8 @@ import "./ops/cpu/gelu.js";
 import "./ops/webgl/gelu.js";
 import "./ops/grads/gelu.js";
 import "./ops/webgl/log.js";
-import { t as d } from "./tensor2d-jO8JY5Jd.js";
-import { c as g } from "./concat-XOK9ANZu.js";
+import { t as d } from "./tensor2d-CPEkynbH.js";
+import { c as g } from "./concat-5aPGqw3Z.js";
 const k = [
   ...Array.from({ length: 95 }, (a, t) => String.fromCharCode(t + 32)),
   // ASCII

package/dist/NanoGPTModel.js

@@ -1,19 +1,19 @@
 import { defaultConfig as F } from "./config.js";
 import O from "./layers/TransformerBlock.js";
-import { T as _, r as D } from "./TiedEmbedding-C1HBot-5.js";
+import { T as _, r as D } from "./TiedEmbedding-9WeDwvjO.js";
 import K from "./layers/RoPECache.js";
 import N from "./layers/RMSNorm.js";
 import { estimateParameterCount as R } from "./utilities/parameters.js";
 import { createSoftmaxCrossEntropyWithGrad as A } from "./training/sparseCrossEntropy.js";
 import G from "./layers/BaseLayer.js";
-import { E as B, D as V, p as j } from "./random_width-CLMQG5Jn.js";
-import { q as W, w as H, E as J, a6 as Q, t as z, a7 as U, f as v, n as X } from "./index-CamYe_M8.js";
-import { m as Y, t as Z } from "./register_all_kernels-COt6wLD0.js";
-import { r as L } from "./reshape-C45vIIRU.js";
-import { r as tt } from "./range-DqYjKnuG.js";
-import { s as M } from "./softmax-DvMvui-_.js";
-import { t as et } from "./ops-DqtYemmV.js";
-import { g as ot } from "./gather-DKtUaTtA.js";
+import { E as B, D as V, p as j } from "./random_width-DWzaOgrn.js";
+import { o as W, q as H, E as J, a6 as Q, t as z, a7 as U, s as v, k as X } from "./index-BAzbokzv.js";
+import { m as Y, t as Z } from "./register_all_kernels-BfFCQAqs.js";
+import { r as L } from "./reshape-krWGKraP.js";
+import { r as tt } from "./range-DYsrnfiy.js";
+import { s as M } from "./softmax-fsdtf6JC.js";
+import { t as et } from "./ops-C0sQEcPw.js";
+import { g as ot } from "./gather-DjyCjmOD.js";
 /**
  * @license
  * Copyright 2020 Google LLC. All Rights Reserved.

package/dist/{RealDiv-7xu-pkZN.js → RealDiv-BYViZwhN.js}

@@ -1,9 +1,9 @@
-import { ao as T, ac as E, p as O, i as V, aw as B, O as F, M as j, ax as K } from "./index-CamYe_M8.js";
-import { r as $ } from "./Reshape-BYC1oUku.js";
-import { g as A, a as k, b as C, c as N, e as R } from "./axis_util-CCNL7jea.js";
-import { t as U, m as W } from "./shared-ByfrGA97.js";
-import { j as _, f as y } from "./gpgpu_math-B_ycgZ4W.js";
-import { g as G, b as L } from "./kernel_funcs_utils-D5MS0JFg.js";
+import { ao as T, ac as E, p as O, g as V, aw as B, N as F, M as j, ax as K } from "./index-BAzbokzv.js";
+import { r as $ } from "./Reshape-t7Kcikjk.js";
+import { g as A, a as k, b as C, c as N, e as R } from "./axis_util-Bu4h7XWV.js";
+import { t as U, m as W } from "./shared-Ca6iDobD.js";
+import { j as _, f as y } from "./gpgpu_math-CNslybmD.js";
+import { g as G, b as L } from "./kernel_funcs_utils-CUxJCg0g.js";
 /**
  * @license
  * Copyright 2020 Google LLC. All Rights Reserved.

package/dist/{Reshape-BYC1oUku.js → Reshape-t7Kcikjk.js}

@@ -1,5 +1,5 @@
-import { i as c, aa as C, k as f, F as R } from "./index-CamYe_M8.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-B_ycgZ4W.js";
+import { g as c, aa as C, i as f, D as R } from "./index-BAzbokzv.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-CNslybmD.js";
 /**
  * @license
  * Copyright 2018 Google LLC. All Rights Reserved.

package/dist/TeachableLLM.d.ts

@@ -22,12 +22,15 @@ export default class TeachableLLM {
     meta: TeachableLLMMeta;
     constructor(tokeniser?: ITokeniser, model?: NanoGPT);
     get vocab(): string[];
+    /** Model is fully loaded */
     get loaded(): boolean;
     get config(): GPTConfig;
     get model(): NanoGPT;
     get tokeniser(): ITokeniser;
     get status(): TeachableLLMStatus;
+    /** Model is both ready and not busy */
     get ready(): boolean;
+    get busy(): boolean;
     estimateTrainingMemoryUsage(batchSize: number): number;
     private setStatus;
     saveModel(options?: SaveOptions): Promise<Blob>;

package/dist/TeachableLLM.js

@@ -1,17 +1,17 @@
-import { defaultConfig as d } from "./config.js";
-import l from "./NanoGPTModel.js";
-import { saveModel as f } from "./utilities/save.js";
-import { loadModel as u } from "./utilities/load.js";
-import p from "./Generator.js";
-import _ from "./Trainer.js";
-import { E as c } from "./index-Dwqa6Zy2.js";
+import { defaultConfig as _ } from "./config.js";
+import f from "./NanoGPTModel.js";
+import { saveModel as u } from "./utilities/save.js";
+import { loadModel as d } from "./loader/load.js";
+import l from "./Generator.js";
+import p from "./Trainer.js";
+import { E as g } from "./index-Dwqa6Zy2.js";
 import { dummyPassTrainAsync as m } from "./utilities/dummy.js";
-import g from "./tokeniser/CharTokeniser.js";
-import w from "./tokeniser/bpe.js";
+import c from "./tokeniser/CharTokeniser.js";
+import k from "./tokeniser/bpe.js";
 import "./papaparse.min-C8l2Kvo1.js";
 import "./index-Tf7vU29b.js";
 import "./jszip.min-CjP2V1VV.js";
-import "./index-CamYe_M8.js";
+import "./index-BAzbokzv.js";
 import "./ops/cpu/scatterSub.js";
 import "./ops/webgl/scatterSub.js";
 import "./ops/cpu/gatherSub.js";
@@ -22,9 +22,9 @@ import "./ops/grads/attentionMask.js";
 import "./ops/cpu/qkv.js";
 import "./ops/webgl/qkv.js";
 import "./ops/grads/qkv.js";
-import "./random_width-CLMQG5Jn.js";
-import "./register_all_kernels-COt6wLD0.js";
-import "./dataset-BFFipD1c.js";
+import "./random_width-DWzaOgrn.js";
+import "./register_all_kernels-BfFCQAqs.js";
+import "./dataset-pgqp-YfL.js";
 import "./ops/cpu/rope.js";
 import "./ops/webgl/rope.js";
 import "./ops/grads/rope.js";
@@ -43,9 +43,9 @@ import "./ops/cpu/normRMS.js";
 import "./ops/webgl/normRMS.js";
 import "./ops/grads/normRMS.js";
 import "./ops/webgl/log.js";
-import k from "./utilities/profile.js";
+import w from "./utilities/profile.js";
 class a {
-  ee = new c();
+  ee = new g();
   _config;
   _model;
   _tokeniser;
@@ -58,66 +58,71 @@ class a {
   get vocab() {
     return this._tokeniser?.getVocab() || [];
   }
+  /** Model is fully loaded */
   get loaded() {
     return !!this._model && !!this._tokeniser && !!this._config;
   }
   get config() {
     if (!this._config)
-      throw new Error("Model configuration is not initialized.");
+      throw new Error("configuration_not_initialized.");
     return this._config.gpt;
   }
   get model() {
     if (!this._model)
-      throw new Error("Model is not initialized.");
+      throw new Error("model_not_initialized.");
     return this._model;
   }
   get tokeniser() {
     if (!this._tokeniser)
-      throw new Error("Tokeniser is not initialized.");
+      throw new Error("tokeniser_not_initialized.");
     return this._tokeniser;
   }
   get status() {
     return this._status;
   }
+  /** Model is both ready and not busy */
   get ready() {
-    return this._status === "ready" && !!this._model && !!this._tokeniser && this.tokeniser.trained;
+    return this._status === "ready" && !!this._model && !!this._tokeniser;
+  }
+  get busy() {
+    return this._status === "busy" || this._status === "training";
   }
   estimateTrainingMemoryUsage(t) {
-    const e = this._memoryRequirements ?? { perBatch: 0, gradients: 0 }, r = e.perBatch * t, o = e.gradients;
-    return r * 0.66 + o * 4;
+    const e = this._memoryRequirements ?? { perBatch: 0, gradients: 0 }, i = e.perBatch * t, o = e.gradients;
+    return i * 0.66 + o * 4;
   }
   setStatus(t) {
     this._status !== t && (this._status = t, this.ee.emit("status", t));
   }
   saveModel(t) {
     if (!this._model || !this._tokeniser)
-      throw new Error("Model or tokeniser is not initialized.");
-    return f(this._model, this._tokeniser, {
+      throw new Error("model_or_tokeniser_not_initialized.");
+    return u(this._model, this._tokeniser, {
       ...t,
       name: t?.name || this.meta.name
     });
   }
   static loadModel(t) {
     const e = new a();
-    return u(t).then(({ model: r, tokeniser: o, name: s }) => {
-      e._model = r, e._tokeniser = o, e._config = r.config, s && (e.meta.name = s), e.setStatus("warmup"), m(r).then((i) => {
-        e._memoryRequirements = i, e.setStatus("ready"), e.ee.emit("loaded");
-      }).catch((i) => {
-        e.setStatus("error"), e.ee.emit("error", i);
+    return d(t).then(({ model: i, tokeniser: o, name: s }) => {
+      e._model = i, e._tokeniser = o, e._config = i.config, s && (e.meta.name = s), e.setStatus("warmup"), m(i).then((r) => {
+        e._memoryRequirements = r, e.setStatus("ready"), e.ee.emit("loaded");
+      }).catch((r) => {
+        e.setStatus("error"), e.ee.emit("error", r);
       });
-    }).catch((r) => {
-      e.setStatus("error"), e.ee.emit("error", r);
+    }).catch((i) => {
+      e.setStatus("error"), e.ee.emit("error", i);
     }), e;
   }
   static create(t, e = {}) {
-    const r = { ...d, ...e }, o = t === "char" ? new g(r.vocabSize) : new w(r.vocabSize), s = new l(r), i = new a(o, s);
-    return i.setStatus("warmup"), m(s).then((n) => {
-      i._memoryRequirements = n, i.tokeniser.trained ? (i.setStatus("ready"), i.ee.emit("loaded")) : (i.setStatus("awaitingTokens"), i.ee.emit("loaded"), i.tokeniser.once("trainStatus", (h) => {
-        h === "trained" && i.setStatus("ready");
+    const i = { ..._, ...e }, o = t === "char" ? new c(i.vocabSize) : new k(i.vocabSize), s = new f(i), r = new a(o, s);
+    return r.setStatus("warmup"), m(s).then((n) => {
+      r._memoryRequirements = n, r.tokeniser.trained ? (r.setStatus("ready"), r.ee.emit("loaded")) : (r.setStatus("awaitingTokens"), r.ee.emit("loaded"), r.tokeniser.once("trainStatus", (h) => {
+        h === "trained" && r.setStatus("ready");
       }));
     }).catch((n) => {
-      i.setStatus("error"), i.ee.emit("error", n);
-    }), i;
+      r.setStatus("error"), r.ee.emit("error", n);
+    }), r;
   }
   getProfiler() {
     return this._model?.getProfiler();
@@ -128,24 +133,22 @@ class a {
   set enableProfiler(t) {
     if (t) {
       if (!this._config)
-        throw new Error("Model is not initialized.");
-      this._config.layerConfig.profiler || (this._config.layerConfig.profiler = new k());
+        return;
+      this._config.layerConfig.profiler || (this._config.layerConfig.profiler = new w());
     } else
       this._config?.layerConfig.profiler && (this._config.layerConfig.profiler = void 0);
   }
   getNumParams() {
-    if (!this._model)
-      throw new Error("Model is not initialized.");
-    return this._model.getNumParams();
+    return this._model ? this._model.getNumParams() : 0;
   }
   trainer() {
     if (!this._model || !this._tokeniser)
-      throw new Error("Model or tokeniser is not initialized.");
-    const t = new _(this._model, this._tokeniser);
-    return t.on("start", () => this.setStatus("training")), t.on("stop", () => this.setStatus("ready")), t.on("log", async (e, r) => {
+      throw new Error("model_or_tokeniser_not_initialized.");
+    const t = new p(this._model, this._tokeniser);
+    return t.on("start", () => this.setStatus("training")), t.on("stop", () => this.setStatus("ready")), t.on("log", async (e, i) => {
       const o = this.ee.listeners("trainStep");
       for (const s of o)
-        await s(e, r);
+        await s(e, i);
     }), t;
   }
   train(t, e) {
@@ -160,7 +163,7 @@ 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 l(this._model, this._tokeniser);
     return t.on("start", () => {
       this.status === "ready" && this.setStatus("busy");
     }), t.on("stop", () => {

package/dist/{TiedEmbedding-C1HBot-5.js → TiedEmbedding-9WeDwvjO.js}

@@ -1,8 +1,8 @@
-import { R as a, d as s } from "./random_width-CLMQG5Jn.js";
-import "./index-CamYe_M8.js";
+import { R as a, d as s } from "./random_width-DWzaOgrn.js";
+import "./index-BAzbokzv.js";
 import o from "./layers/BaseLayer.js";
-import { v as m } from "./variable-CLVXjN7F.js";
-import { g as d } from "./gather-DKtUaTtA.js";
+import { v as m } from "./variable-wSS22xj5.js";
+import { g as d } from "./gather-DjyCjmOD.js";
 /**
  * @license
  * Copyright 2018 Google LLC

package/dist/{axis_util-CCNL7jea.js → axis_util-Bu4h7XWV.js}

@@ -1,4 +1,4 @@
-import { k as c } from "./index-CamYe_M8.js";
+import { i as c } from "./index-BAzbokzv.js";
 /**
  * @license
  * Copyright 2017 Google LLC. All Rights Reserved.

package/dist/{broadcast_to-CddAF879.js → broadcast_to-DARN-DBD.js}

@@ -1,5 +1,5 @@
-import { q as h, w as f, y as p, I as g, E as u, J as b } from "./index-CamYe_M8.js";
-import { r as T } from "./reshape-C45vIIRU.js";
+import { o as h, q as f, x as p, H as g, E as u, I as b } from "./index-BAzbokzv.js";
+import { r as T } from "./reshape-krWGKraP.js";
 /**
  * @license
  * Copyright 2020 Google LLC. All Rights Reserved.

package/dist/{concat-XOK9ANZu.js → concat-5aPGqw3Z.js}

@@ -1,4 +1,4 @@
-import { q as s, k as a, x as p, I as i, E as l, K as f } from "./index-CamYe_M8.js";
+import { o as s, i as a, w as i, H as p, E as l, J as f } from "./index-BAzbokzv.js";
 /**
  * @license
  * Copyright 2020 Google LLC. All Rights Reserved.
@@ -15,15 +15,15 @@ import { q as s, k as a, x as p, I as i, E as l, K as f } from "./index-CamYe_M8
  * limitations under the License.
  * =============================================================================
  */
-function h(n, e = 0) {
-  a(n.length >= 1, () => "Pass at least one tensor to concat");
-  const t = p(n, "tensors", "concat", "string_or_numeric");
-  if (t[0].dtype === "complex64" && t.forEach((o) => {
-    if (o.dtype !== "complex64")
+function h(o, e = 0) {
+  a(o.length >= 1, () => "Pass at least one tensor to concat");
+  const t = i(o, "tensors", "concat", "string_or_numeric");
+  if (t[0].dtype === "complex64" && t.forEach((n) => {
+    if (n.dtype !== "complex64")
       throw new Error(`Cannot concatenate complex64 tensors with a tensor
-          with dtype ${o.dtype}. `);
+          with dtype ${n.dtype}. `);
   }), t.length === 1)
-    return i(t[0]);
+    return p(t[0]);
   const r = t, c = { axis: e };
   return l.runKernel(f, r, c);
 }

package/dist/{dataset-BFFipD1c.js → dataset-pgqp-YfL.js}

@@ -1,7 +1,7 @@
-import { ab as S, T as h, ac as k, a as v, ad as o, ae as p, af as g, k as N, t as y } from "./index-CamYe_M8.js";
+import { ab as S, T as h, ac as N, d as v, ad as o, ae as p, af as g, i as k, t as y } from "./index-BAzbokzv.js";
 import { s as R } from "./index-C4L8Cm77.js";
-import { s as $ } from "./stack-DgaoDmnF.js";
-import { t as B } from "./tensor-CDz5x1mP.js";
+import { s as $ } from "./stack-dfEEz2OY.js";
+import { t as B } from "./tensor-Xyi595sG.js";
 /**
  * @license
  * Copyright 2018 Google LLC. All Rights Reserved.
@@ -75,7 +75,7 @@ function I(s) {
 }
 function c(s) {
   let t = !1;
-  if (k().get("IS_BROWSER"))
+  if (N().get("IS_BROWSER"))
     t = s instanceof TextDecoder;
   else {
     const { StringDecoder: e } = require("string_decoder");
@@ -930,7 +930,7 @@ class T {
    */
   batch(t, e = !0) {
     const r = this;
-    N(t > 0, () => `batchSize needs to be positive, but it is
+    k(t > 0, () => `batchSize needs to be positive, but it is
       ${t}`);
     let n;
     return this.size === 1 / 0 || this.size == null ? n = this.size : e ? n = Math.ceil(this.size / t) : n = Math.floor(this.size / t), u(async () => (await r.iterator()).columnMajorBatch(t, e, st), n);

package/dist/{dropout-xlKRoJyU.js → dropout-Bciw46HT.js}

@@ -1,4 +1,4 @@
-import { q as l, w as h, E as m, ag as p, y as c, ah as d, ai as g, k as u, T as V, aj as v, a7 as w, b as N } from "./index-CamYe_M8.js";
+import { o as l, q as h, E as m, ag as p, x as c, ah as d, ai as g, i as u, T as V, aj as v, a7 as N, a as w } from "./index-BAzbokzv.js";
 import { s as f } from "./index-C4L8Cm77.js";
 /**
  * @license
@@ -16,11 +16,11 @@ import { s as f } from "./index-C4L8Cm77.js";
  * limitations under the License.
  * =============================================================================
  */
-function b(r) {
+function x(r) {
   const e = { x: h(r, "x", "floor", "float32") };
   return m.runKernel(p, e);
 }
-const x = /* @__PURE__ */ l({ floor_: b });
+const b = /* @__PURE__ */ l({ floor_: x });
 /**
  * @license
  * Copyright 2018 Google LLC. All Rights Reserved.
@@ -69,7 +69,7 @@ class T {
     return t <= this.upper && t >= this.lower;
   }
 }
-class y {
+class $ {
   constructor(t = 0, e = 1, s, n) {
     if (this.canReturnFloat = () => this.dtype == null || this.dtype === "float32", this.min = t, this.range = e - t, this.dtype = s, n == null && (n = Math.random()), typeof n == "number" && (n = n.toString()), !this.canReturnFloat() && this.range <= 1)
       throw new Error(`The difference between ${t} - ${e} <= 1 and dtype is not float`);
@@ -98,7 +98,7 @@ class y {
  * limitations under the License.
  * =============================================================================
  */
-function $(r, t = 0, e = 1, s, n) {
+function y(r, t = 0, e = 1, s, n) {
   if (c(r), s != null && s === "bool")
     throw new Error(`Unsupported data type ${s}`);
   const o = new T(t, e, s, !1, n), a = d(r, s);
@@ -106,7 +106,7 @@ function $(r, t = 0, e = 1, s, n) {
     a.values[i] = o.nextValue();
   return a.toTensor();
 }
-const _ = /* @__PURE__ */ l({ randomNormal_: $ });
+const _ = /* @__PURE__ */ l({ randomNormal_: y });
 /**
  * @license
  * Copyright 2020 Google LLC. All Rights Reserved.
@@ -125,7 +125,7 @@ const _ = /* @__PURE__ */ l({ randomNormal_: $ });
  */
 function M(r, t = 0, e = 1, s = "float32", n) {
   c(r);
-  const o = d(r, s), a = new y(t, e, null, n);
+  const o = d(r, s), a = new $(t, e, null, n);
   for (let i = 0; i < o.values.length; i++)
     o.values[i] = a.nextValue();
   return o.toTensor();
@@ -180,14 +180,14 @@ function R(r, t, e, s) {
   const n = h(r, "x", "dropout");
   if (u(n.dtype === "float32", () => `x has to be a floating point tensor since it's going to be scaled, but got a ${n.dtype} tensor instead.`), u(t >= 0 && t < 1, () => `rate must be a float in the range [0, 1), but got ${t}.`), t === 0)
     return r instanceof V ? n.clone() : n;
-  const o = E(n, e), a = 1 - t, i = v(x(w(D(o, 0, 1, "float32", s), a)), a);
-  return N(n, i);
+  const o = E(n, e), a = 1 - t, i = v(b(N(D(o, 0, 1, "float32", s), a)), a);
+  return w(n, i);
 }
 const q = /* @__PURE__ */ l({ dropout_: R });
 export {
   T as M,
   D as a,
   q as d,
-  x as f,
+  b as f,
   _ as r
 };

package/dist/{gather-DKtUaTtA.js → gather-DjyCjmOD.js}

@@ -1,4 +1,4 @@
-import { q as g, w as t, E as h, G as p } from "./index-CamYe_M8.js";
+import { o as g, q as t, E as h, G as p } from "./index-BAzbokzv.js";
 /**
  * @license
  * Copyright 2018 Google LLC. All Rights Reserved.